WO2014000280A1

WO2014000280A1 - Method and apparatus for providing task-based service recommendations

Info

Publication number: WO2014000280A1
Application number: PCT/CN2012/077937
Authority: WO
Inventors: Jiaqi ZOU; Jilei Tian
Original assignee: Nokia Corporation
Priority date: 2012-06-29
Filing date: 2012-06-29
Publication date: 2014-01-03
Also published as: CN104412262B; CN104412262A; EP2867800A4; EP2867800A1

Abstract

An approach for providing task-based service recommendations based on semantics is described. A task-based service recommendation platform determines an input for specifying at least one term of at least one task-based query. The task-based service recommendation platform determines one or more word groupings based, at least in part, on the at least one term. The task-based service recommendation platform determines one or more responses to the at least one task-based query based, at least in part, on a correlation of the one or more responses to the one or more word groupings.

Description

METHOD AND APPARATUS FOR PROVIDING TASK-BASED SERVICE

RECOMMENDATIONS

BACKGROUND

[0001] Service providers and device manufacturers (e.g., wireless, cellular, etc.) are continually challenged to deliver value and convenience to consumers by, for example, providing compelling network services and applications. As a result, consumers now have access to a vast library of services and applications for accomplishing any number of tasks. However, in many cases, the available services and applications often work in isolation, so that tasks that may depend on using multiple services and/or applications in combination can require that the user discover and invoke each service or application independently. This burden can potentially discourage users from these services or from finding new services or applications to complete particular tasks (e.g., planning a trip which may require accessing multiple travel services, location-based applications, etc. to complete). As a result, service providers and device manufacturers face significant technical challenges to facilitating user discovery and use of services and applications for completing user tasks.

SOME EXAMPLE EMBODIMENTS

[0002] Therefore, there is a need for an approach for providing task-based service/application recommendations in a way that minimizes user input burdens by leveraging, for instance, semantic relationships between the user input and related tasks to query for recommended services and/or applications.

[0003] According to one embodiment, a method comprises determining an input for specifying at least one term of at least one task-based query. The method also comprises determining one or more word groupings based, at least in part, on the at least one term. The method further comprises determining one or more responses to the at least one task-based query based, at least in part, on a correlation of the one or more responses to the one or more word groupings. [0004] According to another embodiment, an apparatus comprises at least one processor, and at least one memory including computer program code for one or more computer programs, the at least one memory and the computer program code configured to, with the at least one processor, cause, at least in part, the apparatus to determine an input for specifying at least one term of at least one task-based query. The apparatus is also caused to determine one or more word groupings based, at least in part, on the at least one term. The apparatus is further caused to determine one or more responses to the at least one task-based query based, at least in part, on a correlation of the one or more responses to the one or more word groupings.

[0005] According to another embodiment, a computer-readable storage medium carries one or more sequences of one or more instructions which, when executed by one or more processors, cause, at least in part, an apparatus to determine an input for specifying at least one term of at least one task-based query. The apparatus is also caused to determine one or more word groupings based, at least in part, on the at least one term. The apparatus is further caused to determine one or more responses to the at least one task-based query based, at least in part, on a correlation of the one or more responses to the one or more word groupings.

[0006] According to another embodiment, an apparatus comprises means for determining an input for specifying at least one term of at least one task-based query. The apparatus also comprises means for detennining one or more word groupings based, at least in part, on the at least one term. The apparatus further comprises means for determining one or more responses to the at least one task-based query based, at least in part, on a correlation of the one or more responses to the one or more word groupings.

[0007] In addition, for various example embodiments of the invention, the following is applicable: a method comprising facilitating a processing of and/or processing (1) data and/or (2) information and/or (3) at least one signal, the (1) data and/or (2) information and/or (3) at least one signal based, at least in part, on (or derived at least in part from) any one or any combination of methods (or processes) disclosed in this application as relevant to any embodiment of the invention.

[0008] For various example embodiments of the invention, the following is also applicable: a method comprising facilitating access to at least one interface configured to allow access to at least one service, the at least one service configured to perform any one or any combination of network or service provider methods (or processes) disclosed in this application.

[0009] For various example embodiments of the invention, the following is also applicable: a method comprising facilitating creating and/or facilitating modifying (1) at least one device user interface element and/or (2) at least one device user interface functionality, the (1) at least one device user interface element and/or (2) at least one device user interface functionality based, at least in part, on data and/or information resulting from one or any combination of methods or processes disclosed in this application as relevant to any embodiment of the invention, and/or at least one signal resulting from one or any combination of methods (or processes) disclosed in this application as relevant to any embodiment of the invention.

[0010] For various example embodiments of the invention, the following is also applicable: a method comprising creating and/or modifying (1) at least one device user interface element and/or (2) at least one device user interface functionality, the (1) at least one device user interface element and/or (2) at least one device user interface functionality based at least in part on data and/or information resulting from one or any combination of methods (or processes) disclosed in this application as relevant to any embodiment of the invention, and or at least one signal resulting from one or any combination of methods (or processes) disclosed in this application as relevant to any embodiment of the invention.

[0011] In various example embodiments, the methods (or processes) can be accomplished on the service provider side or on the mobile device side or in any shared way between service provider and mobile device with actions being performed on both sides. For various example embodiments, the following is applicable: An apparatus comprising means for performing the method of any of originally filed claims 1-28 and 46-49.

[0012] Still other aspects, features, and advantages of the invention are readily apparent from the following detailed description, simply by illustrating a number of particular embodiments and implementations, including the best mode contemplated for carrying out the invention. The invention is also capable of other and different embodiments, and its several details can be modified in various obvious respects, all without departing from the spirit and scope of the invention. Accordingly, the drawings and description are to be regarded as illustrative in nature, and not as restrictive. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The embodiments of the invention are illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings:

[0014] FIG. 1 is a diagram of a system capable of providing task-based service recommendations based on semantics, according to one embodiment;

[0015] FIG. 2 is a diagram of the components of a task-based service recommendation platform, according to one embodiment;

[0016] FIG. 3 is a diagram of a semantic model, according to one embodiment;

[0017] FIG. 4 is a flowchart of a process for providing task-based service recommendations based on semantics, according to one embodiment;

[0018] FIG. 5 is a flowchart of a process for creating a semantic model for task-based service recommendations, according to one embodiment;

[0019] FIG. 6 is a flowchart of a process for constructing a task-based query based on semantic models, according to one embodiment;

[0020] FIG. 7 is a flowchart of a process for determining service recommendations for results of task-based queries, according to one embodiment;

[0021] FIGs. 8A and 8B are diagrams of user interfaces utilized in the processes of FIGs. 1-7, according to various embodiments;

[0022] FIG. 9 is a diagram of a user interface for presenting service recommendations parsed from a task solution, according to one embodiment;

[0023] FIG. 10 is a diagram of hardware that can be used to implement an embodiment of the invention;

[0024] FIG. 11 is a diagram of a chip set that can be used to implement an embodiment of the invention; and

[0025] FIG. 12 is a diagram of a mobile terminal (e.g., handset) that can be used to implement an embodiment of the invention. DESCRIPTION OF SOME EMBODIMENTS

[0026] Examples of a method, apparatus, and computer program for providing task-based service recommendations based on semantics are disclosed. In the following description, for the purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the invention. It is apparent, however, to one skilled in the art that the embodiments of the invention may be practiced without these specific details or with an equivalent arrangement. In other instances, well-known structures and devices are shown in block diagram form in order to avoid unnecessarily obscuring the embodiments of the invention.

[0027] FIG. 1 is a diagram of a system capable of providing task-based service recommendations based on semantics, according to one embodiment. As previously discussed, users often need services to help them in solving problems or performing tasks in their daily lives. By way of example, there can be hundreds of thousands of applications in various applications stores that cover a variety of available services. Many of these services and/or applications can serve as good tools for users. However, in many cases, users may have to manually choose or discover these services among hundreds of thousands of available applications and services to solve the problems or to perform the tasks.

[0028] Moreover, users often want to know how to handle a task or solve a problem. The instructions for handling a task or solving a problem can be a sequence of things or steps, while most existing services are designed to fulfill one need. Accordingly, a single application or service may be not sufficient to meet the user's specific needs because certain problems or tasks may require several services or applications in combination. In addition, when interacting with a device to specify a task, the semantics or goal of a user is not normally well described, leading to unsatisfactory performance (e.g., irrelevant service recommendations).

[0029] As another problem, services like search engines may provide information about how to solve a problem, but may not provide tools (e.g., applications or services) to solve the problem. For example, searching a knowledge base (e.g., eHow.com) can provide a listing of instructions for completing a queried task, but the result of the query does not provide or link to tools (e.g., services and/or applications) for performing the steps of the instructions. Consequently, users may have to take farther steps to find the right tools for their specific needs. This way of searching for and discovering services and/or applications can be inefficient.

[0030] To address these problems, a system 100 of FIG. 1 introduces the capability to provide task-based service recommendations based on semantics derived from terms or inputs queried by a user. In one embodiment, the system 100 provides a query auto- completion process using a semantic model built from, for instance, a knowledge-oriented database or corpus. By way of example, the system 100 determines terms or parameters (e.g., words or word groupings) of a tasked-based from a user input in a query request field. In one example, the word groupings or input are short inputs (e.g., two-three words) that can be processed by the system 100 to create or complete a more complete query for task-based services or recommendations .

[0031] In one embodiment, word groupings (e.g., noun-verb pairs) may be matched against previously determined word groupings or pairs that have been modeled from knowledge bases using rich semantics. For example, a query of user intention may be represented by "verb + noun" form with additional semantics. It is noted that although various embodiments are discussed with respect to verb-noun pairings, it is contemplated that the various embodiments described herein are also applicable to word groupings of any other parts of speech (e.g., modifiers, prepositions, etc.) and of any number of terms (e.g., three or more as opposed to just pairings). In one embodiment, the system 100 models the verb-noun relationship by using dependency parsing of available knowledge bases. In other words, the verb-noun pairings are based on which verbs and nouns (or other terms) most often appear or occur with each other in the knowledge bases. For example, a parsing of available knowledge bases (e.g., an eHow.com database) may indicate that the verb "plan" is most often paired with the noun "travel". Accordingly, if a user inputs the noun "travel" in a query field, the system 100 may determine that the noun is most often paired with the verb "plan" and automatically completes the query as "plan travel" from the initial input of "travel". In one embodiment, the responses (e.g., instructions and services) to the query maybe determined based on previously determined correlations between the responses and the word groupings (e.g., the verb-noun pairing). [0032] In one embodiment, the system 100 may determine the word groupings based, at least in part, on the situation or context of the user or the mobile device of the user. In other words, the system 100 may determine the user's context (e.g., location, time, activity, history, etc.) and find the appropriate word grouping to auto-complete the user's task-based query based on the user's situation. For example, one verb-noun pairing may apply when the user is in a home context versus a work context. In this way, the user's intentions with respect to the task-based query may be decided by query semantics and user situations, and the user situations may be automatically determined by sensors of user devices. In addition, the query semantics/goal of the user is understood by the system 100 and supported by the context information and semantic model.

[0033] In one embodiment, the system 100 performs the task-based query generated as described in the various embodiments above. The query, for instance, enables the system 100 to offer the user both the instructions (e.g., based on knowledge bases) and the services/applications to solve a problem or complete a task associated with the task-based query. As previously discussed, the instructions or other responses determined from the task-based query can be a sequence of things to steps to complete the steps of the instructions. For example, the instructions are provided by knowledge bases (e.g., eHow.com) and the services or applications are provided by application stores and/or commonly used web services (e.g., hotel booking, travel agency, taxi, restaurant, shopping, dating, job hunting services, etc.)

[0034] In one embodiment, the system 100 enables to the user select a combination of services to complete the task or solve a problem from a recommended set of services. In another embodiment, the system 100 enables the user to recommend his or her own service or application for completing the task. This recommendation can then be used for determining subsequent recommendations. In one embodiment, the option to recommend his or her own service can be presented to the user if there are no available recommendations for a particular service or when there are less than a threshold number of service recommendations.

[0035] In one embodiment, the system 100 enables the user to input a keyword about a task and recommend the user one or more other words to make the task description semantically complete (e.g., verb-noun pairing) by utilizing a dependency network. Based on the task description, the system 100 can recommend a solution that precisely matches what the user is looking for by utilizing knowledge base (e.g., wikiHow, eHow, etc.) as well as the situation or context of the user (e.g., what knowledge the user use to select under the similar situation). Based on the solution, all necessary services can be offered to the user for selection by utilizing the situation or context of the user (e.g., services user used to select and quality and credibility of services user learned in the past).

[0036] As shown in FIG. 1, the system 100 comprises one or more user equipment (UEs) lOla-lOln (also collectively referred to as UEs 101) having connectivity to a task-based service recommendation platform 103 via a communication network 105. In one embodiment, the task-based service recommendation platform 103 provides task-based service recommendations based on the semantics of word groupings (e.g., verb-noun pairs) determined from query inputs or parameters as discussed with respect to the various embodiments described herein. In one embodiment, the word groupings or verb-noun pairs are determined and stored in the semantic models database 107. In one embodiment, the semantic models in the database 107 are based on a dependency network of terms or words parsed from one or more knowledge bases 109a- 109m (also collectively referred to as knowledge bases 109). By way of example, the one or knowledge bases 109 include information related to completing specific tasks or solving problems. This knowledge information can be contributed through crowdsourcing, service providers, content providers, and the like. In one embodiment, the knowledge bases 109 can respond to task-based queries by provide a set of instructions or steps associated with the task or problem.

[0037] In one embodiment, the word groupings and resulting task-based query of the knowledge bases 109 can be based, at least in part, on contextual information (e.g., collected by the UEs 101 from respective sensors l l la-l l ln (also collectively known as sensors 111)). In addition, the task-based service recommendation platform 103 can also determine service recommendations based, at least in part, on the contextual information. The sensors 111 include, for instance, sensors for measuring any contextual parameter including, for instance, location sensors (e.g., GPS), light sensors, accelerometers, position sensors, environmental sensors, etc. In yet another embodiment, the word groupings, queries, service recommendations, etc. can also be based on user profile information (e.g., stored in the user profile database 111). The user profile database 113 can store, for instance, characteristics, preferences, and the like associated with the user. This profile information can be used to determine the service recommendations for the user. In one embodiment, the system 100 selects from the available services 115a- 115k (also collectively referred to as services 115). The services 115, for instance, may be any web accessible service available over the communication network 105. In one embodiment, the services 115 can be accessed by or work in tandem with applications 117a-117n (also collectively referred to as applications 117) to provide services or perform tasks for the UEs 101. In some embodiments, the applications 117 are available for download to the UEs 101 via one or more application stores 119a- 11 j

(0038] In one embodiment, the system 100 determines the service recommendations based, at least in part, on the responses received to the task-based query. For example, in one example use case, the task-based query may specify or be automatically completed to specify a word grouping (e.g., a verb-noun pairing) such as "plan travel" based on semantic modeling or a semantic dependency network of related terms or words. The system 100 can then search knowledge bases 109 for articles related to planning travel. These articles can, for instance, contain instructions or steps for completing the articles. In one embodiment, the system 100 parses word groupings (e.g., verb-noun pairs) in the instructions or steps to determine which services 11 1 to recommend for completing each instruction or step.

[0039] In one embodiment, the UEs 101 include respective task clients 121 a- 12 In (also collectively referred to as task clients 121) for performing functions associated with task-based queries and service determination at the UE 101. By way of example, when operating in an online configuration, the task client 121 may determine query inputs and pass them to the task- based service recommendation platform 103 for processing. In an embodiment where the task client 121 is operating in an offline mode, the task client 121 may be configured with semantic models from the database 107 and/or user profile information from the database 113 so that all or a portion of the functionality described with respect to the various embodiments of the task- based service recommendation platform 103 can be performed by task client 121.

[0040] By way of example, the communication network 105 of system 100 includes one or more networks such as a data network, a wireless network, a telephony network, or any combination thereof. It is contemplated that the data network may be any local area network (LAN), metropolitan area network (MAN), wide area network (WAN), a public data network (e.g., the Internet), short range wireless network, or any other suitable packet-switched network, such as a commercially owned, proprietary packet-switched network, e.g., a proprietary cable or fiber-optic network, and the like, or any combination thereof. In addition, the wireless network may be, for example, a cellular network and may employ various technologies including enhanced data rates for global evolution (EDGE), general packet radio service (GPRS), global system for mobile communications (GSM), Internet protocol multimedia subsystem (IMS), universal mobile telecommunications system (UMTS), etc., as well as any other suitable wireless medium, e.g., worldwide interoperability for microwave access (WiMAX), Long Term Evolution (LTE) networks, code division multiple access (CDMA), wideband code division multiple access (WCDMA), wireless fidelity (WiFi), wireless LAN (WLAN), Bluetooth®, Internet Protocol (IP) data casting, satellite, mobile ad-hoc network (MANET), and the like, or any combination thereof.

[0041] The UE 101 is any type of mobile terminal, fixed terminal, or portable terminal including a mobile handset, station, unit, device, multimedia computer, multimedia tablet, Internet node, communicator, desktop computer, laptop computer, notebook computer, netbook computer, tablet computer, personal communication system (PCS) device, personal navigation device, personal digital assistants (PDAs), audio/video player, digital camera/camcorder, positioning device, television receiver, radio broadcast receiver, electronic book device, game device, or any combination thereof, including the accessories and peripherals of these devices, or any combination thereof. It is also contemplated that the UE 101 can support any type of interface to the user (such as "wearable" circuitry, etc.).

[0042] By way of example, the UE 101, the task-based service recommendation platform 103, task clients 121, services 115, and application stores 119 communicate with each other and other components of the communication network 105 using well known, new or still developing protocols. In this context, a protocol includes a set of rules defining how the network nodes within the communication network 105 interact with each other based on information sent over the communication links. The protocols are effective at different layers of operation within each node, from generating and receiving physical signals of various types, to selecting a link for transferring those signals, to the format of information indicated by those signals, to identifying which software application executing on a computer system sends or receives the information. The conceptually different layers of protocols for exchanging information over a network are described in the Open Systems Interconnection (OSI) Reference Model.

[0043] Communications between the network nodes are typically effected by exchanging discrete packets of data. Each packet typically comprises (1) header information associated with a particular protocol, and (2) payload information that follows the header information and contains information that may be processed independently of that particular protocol. In some protocols, the packet includes (3) trailer information following the payload and indicating the end of the payload information. The header includes information such as the source of the packet, its destination, the length of the payload, and other properties used by the protocol. Often, the data in the payload for the particular protocol includes a header and payload for a different protocol associated with a different, higher layer of the OSI Reference Model. The header for a particular protocol typically indicates a type for the next protocol contained in its payload. The higher layer protocol is said to be encapsulated in the lower layer protocol. The headers included in a packet traversing multiple heterogeneous networks, such as the Internet, typically include a physical (layer 1) header, a data-link (layer 2) header, an internetwork (layer 3) header and a transport (layer 4) header, and various application (layer 5, layer 6 and layer 7) headers as defined by the OSI Reference Model.

[0044] In one embodiment, the task-based service recommendation platform 103 and the task clients 121 interact according to a client-server model. It is noted that the client-server model of computer process interaction is widely known and used. According to the client-server model, a client process sends a message including a request to a server process, and the server process responds by providing a service. The server process may also return a message with a response to the client process. Often the client process and server process execute on different computer devices, called hosts, and communicate via a network using one or more protocols for network communications. The term "server" is conventionally used to refer to the process that provides the service, or the host computer on which the process operates. Similarly, the term "client" is conventionally used to refer to the process that makes the request, or the host computer on which the process operates. As used herein, the terms "client" and "server" refer to the processes, rather than the host computers, unless otherwise clear from the context. In addition, the process performed by a server can be broken up to run as multiple processes on multiple hosts (sometimes called tiers) for reasons that include reliability, scalability, and redundancy, among others.

[0045] FIG. 2 is a diagram of the components of the task-based service recommendation platform 103, according to one embodiment. By way of example, the task-based service recommendation platform 103 includes one or more components for providing task-based service recommendations based on semantics. It is contemplated that the functions of these components may be combined in one or more components or performed by other components of equivalent functionality. In this embodiment, the task-based service recommendation platform includes a control logic 201, a semantic model construction module 203, an input determination module 205, a task-based query module 207, a service recommendation module 209, and a user interface module 211.

[0046] In one embodiment, the control logic 201 executes one or more algorithms for providing task-based service recommendations based on semantics. The control logic 201, for instance, interacts with a semantic model construction module 203 to generate or train semantic models based, at least in part, on word groupings (e.g., verb-noun pairings) that appear in processed knowledge bases 109. In one embodiment, the semantic model construction module 203 performs a dependency parsing on one or more articles of the knowledge base 109. The articles include, for instance, a title or metadata as well as a sequence of actions to be executed for completing a task. In an example use case, the title and/or metadata addresses or identifies the problem to be solved or tasked to be completed in the article; and the sequence of actions are the steps or instructions on how to execute the task. In cases, where the article has no title or metadata, or where the title or metadata do not adequately describe the problem solved or task to be completed, the semantic model construction module 203 can perform a dependency parsing of the contents of the article in whole or in part.

[0047] In one embodiment, dependency parsing determines verb-noun dependencies or the dependencies or one or more terms found to be associated above a predetermined confidence level. The parts or speech (e.g., verbs, nouns, prepositions, etc.) used in the word groupings can be dependent on, for instance, the language of the words used and/or the grammar associated with the language. For example, in the English language, verb-noun dependencies are used to model the semantics of knowledge bases 109. In one embodiment, the strength of the verb- noun pairing or grouping can be used to rank potential matches. Examples of a semantic model are described in more detail below.

[0048] After construction of the semantic models, the input determination module 205 accepts user input of one or more terms (e.g., words) as an initial task-based query. For example, a user can input one or just a few words for processing for auto-completion or determination of additional terms or p rameters to use in constructing the entire task-based query. In one embodiment, the input determination module 205 interacts with the task-based query module 207 to determine or recommend relevant words given the initial query. For example, in the case where the word grouping in the generated semantic models is a verb-noun pair, the task- based query module 207 matches the initial input term (e.g., a noun or a verb) with the other term in the pairing to construct the verb-noun pairing for initiating a task-based query. In this way, the task-based query module 207 enriches an understanding of the initial query input based on the semantic models. In one embodiment, the task-based query module 207 can also enrich the query or determine the appropriate semantic models based, at least in part, on context or situational information associated with the user.

[0049] In one embodiment, the task-based query module 207 can then execute or perform the determined task-based query against one or more knowledge bases 109 to determine a sequence of steps or actions to complete the task or solve a problem associated with the task-based query. For example, the task-based query module 207 can determine one or more responses (e.g., instructions for completing a task) to the task-based query from the knowledge bases 109 based on whether the responses correlate to the semantic word grouping (e.g., verb-noun pair) determined as part of the verb-noun pairing or word grouping in the task-based query.

[0050] In one embodiment, the task-based query module 207 interacts with the service recommendation module 209 to recommend services 115 for completing the sequence of actions or steps in the responses returned by the task-based query module 207. In this way, the task- based service recommendation platform 103 can offer the user both the instructions and the services for performing a task or solving a problem. In one embodiment, the instructions are provided by the knowledge bases 109 (e.g., eHow.com). Similarly, the applications 117 supporting the services 115 are provided by the application stores 119. Moreover, the services 115 may include one or more web services (e.g., hotel booking, travel agency, etc.) depending on the task to be performed. In one embodiment, the user interface module 211 generates one or more user interfaces for presenting the instructions along with the service recommendations. Examples of such interfaces are discussed further below.

[0051] FIG. 3 is a diagram of a semantic model, according to one embodiment. In the example of FIG. 3, the semantic model is based on a word grouping consisting primarily of verb- noun pairings. In various embodiments, the system 100 (e.g., via the task-based service recommendation platform 103 of the semantic model construction module 203 of the platform 103) processes articles in knowledge bases 109 to create semantic models evaluating task-based query inputs. For example, the title of an article in the knowledge bases 109 (e.g., eHow.com) is generally task-oriented and are provided in syntax grammar and semantics. Accordingly, in one embodiment, the system 100 evaluates the title of each article to perform a dependency parsing to construct the semantic model 300. However, it is noted that in addition or alternatively, the system 100 can perform a dependency parsing of the entire article to generate the semantic model 300.

[0052] By way of example, as part of the dependency parsing, the task-based service recommendation platform 103 extracts all verb-noun pairs and/or dependencies in the articles of the knowledge bases 109. In some embodiments, the platform 103 may also calculate the relation strength of the verb-noun pairs to build the semantic model 300 or dependency network of the semantic model 300. In yet another embodiment, the platform 103 may also tag other parts of speech or terms (e.g., prepositions) to determine additional semantic meaning for the verb-noun pair or word grouping.

[0053] As shown in FIG. 3, the semantic model 300 includes a dependency network that contains four kinds of nodes: verb nodes 301a-301d (also collectively referred to as verb nodes 301), noun nodes 303a-303b (also collectively referred to as noun nodes 303), preposition nodes 305a-305b (also collectively referred to as preposition nodes 305), and domain nodes 307a-307e (also collectively referred to as domain nodes 307). By way of example, a verb node 301 represents a term or word that is a verb, like "repair". In one embodiment, the verb nodes 301 are connected to noun nodes 303. Similarly, a noun node 303 represents a term or word that is a noun, like "vehicle". The noun nodes 303 are typically connected to verb nodes 301 to make a verb-noun pair such as "repair vehicle".

[0054] In one embodiment, preposition nodes 305 may represent prepositions that connect a verb and a noun. For example, the preposition "off may connect the verb "pay" and the noun "ticket" to result in a verb-preposition-noun grouping of "pay off ticket". In one embodiment, the proposition node 305 is optional because a preposition word may not exist for dependency between a transitive verb and a noun.

[0055] In one embodiment, the domain nodes 307 indicate the dependency relationship of a particular word grouping or verb-noun pair that falls in predefined domains in the knowledge bases 109. By way of example, predefined domains are categories of that can be used to group the knowledge based articles. In one embodiment, the domains may represent particular subject areas such as cars, home goods, etc. For example, if the dependency relation between "buy" and "car" occurs only in a "car" domain in the knowledge bases 109, then the platform 103 can add a domain node 307 for the relation to represent the car domain.

[0056] In one embodiment, the domain node 307 is optional and is intended to categorize verb-noun pairs or word groupings that may be unique to one or only a few domains. For example, only when a dependency relation appears in just one or two domains will the platform 103 add the domain node 307 to describe the verb noun pair. Otherwise (e.g., for domains >=3), the platform 103 introduces no domain node 307, for instance, to avoid cluttering the semantic model 300. It is contemplated that the threshold number of domains can be set to any number or not enforced altogether. In the case of no domain threshold, the platform 103 can record all domains applicable for a particular verb-noun pairing or word grouping.

[0057] In one example use case, the articles or a knowledge base 109 (e.g., eHow.com) are crawled to identify article titles and/or article content. Based on the identification of the articles, the platform 103 divides the articles into predetermined domains representing any number of categories such as cars, pets & animals, home repair, etc. In this example, each article contains a title and a sequence of actions to be executed for task completion. Typically, the title addresses clearly the problem solved or task performed in that article. As noted earlier, the sequence of actions are steps on how to execute the task described in the article. As part of the crawling, the platform 103 performs a dependency parsing of the articles to extract and model the verb-noun pairs or other word groupings most representative of the articles as well as the tasks or actions in the articles. This dependency parsing then forms the basis of the semantic model 300 use in the various embodiments described herein.

[0058] FIG. 4 is a flowchart is summary of a process for providing task-based service recommendations based on semantics, according to one embodiment. In one embodiment, the task-based service recommendation platform 103 performs the process 400 and is implemented in, for instance, a chip set including a processor and a memory as shown in FIG. 11. In addition or alternatively, the task client 121 may perform all or a portion of the process 400.

[0059] In step 401, the platform 103 receives an input specifying a task-based query from a user. This input, for instance, includes at least one term related to a task-based query. Typically the term or word is part of a word grouping (e.g., a verb-noun pair) for a task-based query that can be automatically completed based on semantics. In this example, the platform uses semantic models of word dependency networks to fill in relevant terms of the task-based query given the user input (step 403). For example, if the platform 103 expects a task-based query to include at least a verb-noun pair and the user inputs just one of the terms in the pair, the platform 103 can process the term against the semantic models to determine which other terms the inputted term is most likely to be associated with. Based on this query auto-completion process, the platform 103 can construct a complete task-based query with minimal input from the user.

[0060] In step 405, the platform 103 executes the constructed task-based queries against one or more knowledge bases 109 to determine query responses that provide possible solutions for the task in the query. In one embodiment, the solutions are received from one or more solution sources such as the knowledge bases 109 (step 407). In some embodiments, the platform may determine a user's situation or context to propose a possible solution to a requested task (step 309). By way of example, the solution may be presented as an article determined or otherwise derived from the knowledge bases 109 for review by the user (step 411).

[0061] In one embodiment, the platform 103 may enable the user to edit the presented solution (step 413). For example, if the user finds alternative solutions/actions or sees errors in the solutions, the user can edit the article. The user edits and revised solutions can be fed back to the knowledge bases 109 for updating of the knowledge bases 109.

[0062] After determining the solution, the platform 103 processes the solution to detennine the individual actions or steps that comprise the solutions and to recommend appropriate services/applications for completing the actions or steps (step 415). In one embodiment, the platform 103 retrieves application or service information on or more applications sources such services 115 and/or application stores 119 (step 417). In step 419, the platform 103 processes the application or service information as the actions or steps of the solutions to provide service recommendations. In one embodiment, the processing of the application or service information may include, for instance, determining which verb-noun pairs or word groupings best match or describe a particular application or service. Then by comparing the verb-noun pairs of the applications/services against the verb-noun pairs of the task-based query, the platform 103 can determine one or more service recommendations for presentation to the user.

[0063] In step 421, the platform 103 enables to the user to suggest or recommend services to associate with particular actions or steps in the solution. For example, if no service is identified for a particular action, the user may specify a service or application that can perform the action. In addition, if the user prefers another service or application other than the one recommended by the platform 103, the user may also specify the service or application as well. Information regarding user recommended services can then be provided to the application sources (e.g., services 115, application stores 119) to refine subsequent recommendations to the user or other similar users.

[0064] FIG. 5 is a flowchart of a process for creating a semantic model for task-based service recommendations, according to one embodiment. In one embodiment, the task-based service recommendation platform 103 performs the process 500 and is implemented in, for instance, a chip set including a processor and a memory as shown in FIG. 11. In addition or alternatively, the task client 121 may perform all or a portion of the process 500.

[0065] In step 501, the platform 103 causes, at least in part, a parsing of one or more knowledge databases 109 to determine the one or more semantic models, at least one dependency network, or a combination thereof. Based on the parsing (e.g., a dependency parsing), the platform 103 causes, at least in part, a construction of the one or more semantic models based, at least in part, on the at least one dependency network.

[0066] In one embodiment, the platform 103 determines the at least one dependency network based, at least in part, on one or more grammatical relationships among the at least one term, the one or more other terms, or a combination thereof. The grammatical relationship can be based on the language used in the articles. For example, for English, a verb-noun relationship can be determined among the various terms extracted from the articles. In other words, the dependency network models the relationships among the terms or words found in word groupings such as verb-noun pairs. For example, the relationships among the terms may be identified based on the frequency that the words occur together in articles of the knowledge bases 109. Because the words as associated based on a syntax grammar, semantic meaning can be derived from the association. As previously discussed, other terms or words (e.g., prepositions) may be used to characterize the verb-noun relationship or word grouping based on the syntax and grammar of corresponding language. [0067] In step 505, the platform 103 can determine strength of the dependency relationships provided in the semantic models. For example, for each relation between verb and noun or among other terms in a semantic mode, the platform 103 can calculate a score that characterizes the relationship and stands for the importance of the relation. In one embodiment, for a relation C from a verb A to a noun B, the relation strength of C represents the importance of the noun B to the verb A. Accordingly, in one embodiment, the relation strength is calculated based on a ration of the number of occurrences of A and B in the knowledge based 109 to the number of occurrences of A with respect to any noun N. In this case, the platform 103 will infer that a high ration with respect to a particular A-B pairing indicates a higher level of importance between A and B. [0068] In one embodiment, the strength of the relationship is used to determine which verb- noun pairs or word groupings are most likely given only one or a subset of terms or words in the pair or grouping. In some embodiments, the strength of the dependency relationships can be dependent on the context of a user so that the platform 103 can take into account the user's situation in determining task-based service recommendations for the user.

[0069] In step 507, the platform 107 determines whether there are one or more updates to the knowledge bases 109 (e.g., whether new or updated articles have been added to the knowledge bases 109). On detecting an update, the platform 103 returns to step 601 to cause, at least in part, an updating of the one or more semantic models, the at least one dependency network, or a combination thereof based, at least in part, on the one or more updates.

[0070] FIG. 6 is a flowchart of a process for constructing a task-based query based on semantic models, according to one embodiment. In one embodiment, the task-based service recommendation platform 103 performs the process 600 and is implemented in, for instance, a chip set including a processor and a memory as shown in FIG. 11. In addition or alternatively, the task client 121 may perform all or a portion of the process 600.

[0071] In step 601, the platform 103 determines an input for specifying at least one term of at least one task-based query. In one embodiment, the input can be one term or word of a word grouping or verb-noun pair. The platform 103 then determines one or more word groupings based, at least in part, on the at least one term. In one embodiment, the term or word includes, at least in part, a verb, a noun, a proposition, a domain, or a combination thereof. The terms or words can then combined into one or more word groupings that can include, at least in part, one or more verb-noun pairs For example, the platform 103 can match the input term against word groupings modeled from the knowledge bases 109 using, for instance, the dependency network of the semantic models described previously. The platform 103 can then present or recommend one or more possible verb-noun pairs or word groupings for the user to select. After the user selects at least one verb-noun pair, the platform 103 will construct a task-based query based on the selected verb -noun pair.

[0072] In step 603, the platform 103 determines one or more responses to the at least one task-based query based, at least in part, on a correlation of the one or more responses to the one or more word groupings. In one embodiment, the one or more responses represent solutions or instructions for completing a requested task. While conducting dependency parsing of the knowledge bases 109, the platform 103 can, for instance, process the articles to determine which verb-nouns pairs can characterize a particular solution described in the respective article. The query verb-noun pair can then be matched with the verb-noun pairs associated with the solutions to determine the solutions to present or recommend to a user. In other words, the platform 103 causes, at least in part, a parsing of at least a portion of the one or more responses to detennine occurrence information of the one or more word groupings or verb-noun pairs (e.g., frequency or number of times the word groupings appear in the responses). The correlation of the responses to the word groupings and the selection of the potential solutions can be based on the occurrence information.

[0073] In one embodiment, this correlation reflects a similarity of the responses or search results to the semantics or word groupings of the query. For example, given M search results, for each solution i(l<=i<-M), the platform 103 can find N users who have the most similarity with the current user and have used or ranked the solution proposed for the current user. The platform 103 can then calculate the rank of the this solution as:

Each of the responses or solutions can then be ranked or presented to the user according to the calculated score.

{0074] In one embodiment, the platform 103 also determines contextual information associated with the input, a device associated with the input, a user associated with the device, or a combination thereof. This contextual information can be used to determine the user's situation or context (e.g., home, work, pleasure, etc.) that can affect what types of solutions or service recommendations to present to the user. For example, different word groupings (e.g., verb-noun pairs), responses to the task-based queries, correlation between the word groupings and the solutions, and the like can depend on the contextual information.

[0075] FIG. 7 is a flowchart of a process for determining service recommendations for results of task-based queries, according to one embodiment. In one embodiment, the task-based 12 077937

service recommendation platform 103 performs the process 700 and is implemented in, for instance, a chip set including a processor and a memory as shown in FIG. 11. In addition or alternatively, the task client 121 may perform all or a portion of the process 700. The process 700 assumes that the platform 103 has already completed the process 600 to determine one or more responses or solutions to a user's task-based query based on semantics.

[0076] In step 701, the platform 103 determines one or more instructions for completing at least one task associated with the at least one task-based query, wherein the one or more responses include, at least in part, the one or more instructions. For example, the instructions, solutions, actions, etc. for completing a particular task can be parsed from the one or more responses (e.g., a knowledge base article responsive to the query).

10077] In step 703, the platform 103 then determines one or more services for performing the one or more instructions. By way of example, the one or more responses may include, at least in part, the one or more services or links to the one or more services. In one embodiment, the platform 103 may determine the recommended services for completing the tasks or instructions according to a process similar to that described with recommending a solution in step 603 of the process 600. For example, the platform 103 can match the verb-noun pairs or word groupings associated with the task-based query with the word groupings describing a potential service or application. Given M matched services for each instruction or step of a proposed solution, the platform 103 finds N users who have the most similarity with the current user and have used or ranked the respective service. For example, for each service i(l<=i<=M), the platform 103 generates a ranking score as follows:

The service recommendations can then be presented to the user based on the ranking score.

[0078] In one embodiment, the recommended services are provided from application sources such as the application stores 1 19 and/or the services 115. By way of example, applications within these application sources can be searched according to their descriptions. In one embodiment, the service or application description can be describe using standard formats such as a Web Services Description Language (WSDL) or an Extensible Markup Language (XML). [0079] Accordingly, in step 705, the platform causes, a presentation of the one or more responses, the one or more instructions, or a combination thereof in association with one or more links to the one or more services determined above. In one embodiment, the platform 103 can determine feedback information or manual input for specifying any of the word groupings, the responses, the instructions, the correlation between the query and responses, the instructions, the services, or a combination thereof. For example, the platform 103 enables the user to view the service recommendations, modify the service recommendations, define what recommendations should be presented, make recommendations to others, and the like. In other words, once a user identifies a desired solution or service recommendation, the user can rank, edit, comment, and/or rate the solution or recommendation. In addition, the user can add other applications or solutions that the user thinks are valuable. If a user adds an application or service, the platform 103 can extend the current query (e.g., word grouping or verb-noun pair) as one of the application's or solution's tags. In this way, the platform 103 can use feedback information to improve future recommendations.

[0080] In yet another embodiment, the platform 103 enables the user to save recommended solutions and services as plan. The plan is then accessible to the user for reference during completion of task, steps of the task, etc.

[0081] FIGs. 8A and 8B are diagrams of user interfaces utilized in the processes of FIGs. 1-7, according to various embodiments. More specifically, FIGs. 8A and 8B present a use case in which a user is planning to travel to a destination (e.g., New York) using the various embodiments of task-based service recommendation processes described herein. As shown in user interface (UI) 801 of FIG. 8 A, the user can simply type a query input term 803 of "travel", and the system 100 can complete the user's intended query by presenting a list 805 of matching verb-noun pairs determined from the query input. For example, the verb-noun pairs are determined using the dependency network of the semantic model described above.

[0082] In this example, the user selects the "plan travel" verb-noun pair to initiate a query for a corresponding solution from the solution source 807 (e.g., a knowledge base 109). In one embodiment, the platform 103 queries for the solution by matching the verb -noun pair against equivalent verb-noun pairs tagged to the solution (e.g., a knowledge article). In addition, the platform 103 can use contextual information 809 about the user to refine the solutions search or provide ranking and/or sorting of potential solutions to recommend to the user.

[0083] The determined solutions are presented in the UI 811. As shown, the solutions are ranked according to the best match against the query verb-noun pair. In this example, the user selects the top recommended solution of "How to plan a travel to New York". Based on this selection, the platform 103 can take into account the user's current situation (e.g., location in Washington DC, 30-year male IT professional) to determine what composite services or applications will need to perform the task (e.g., plan a travel to New York) in the solution. For example, the platform 103 can search an application source 813 (e.g., application stores 119 and/or services 115) to identify or recommend services and/or applications for completing individual steps of the task.

[0084] Referring now to FIG. 8B, the UI 821 presents a list of actions or instructions for planning travel to New York. In this case, the solution includes four steps: (1) book your flight ticket, (2) reserve a hotel; (3) rent a car; and (4) find restaurants. The UE 821 also provides an option 823 to see the services recommended for performing each of the steps of the solution. On selecting the option 823, the platform 103 presents a list recommended services that the user may need to perform the actions of the solution. By way of example, the UI 825 may present icons that link to the applications for download or for execution if the applications are already downloaded. The UI 825 also includes an option 827 for the user add a service if the service is not already recommended. The UI 825 also provides an option 829 to save the solutions and linked applications/services as a plan for later reference. The UI 831 depicts a screen presenting the save plan which includes a summary of the instructions and accompanying links to the services/applications for completing the task in the plan.

[0085] FIG. 9 is a diagram of a user interface for presenting service recommendations parsed from a task solution, according to one embodiment. As shown in FIG. 9, the platform 103 has determined a solution 901 that presents a list of six instructions or actions for completing a task of "how to plan travel arrangements". To determine or recommend services for each step, the platform parses each of the six instructions to determine the occurrence of word groupings (e.g., verb-noun pairs, verb-preposition-noun groups, etc.) that provide semantic meaning for determining related services. For example, in the step 1 of the solution 901, the platform 103 has identified the word groupings "post office" and "apply for passport". Based on these word groupings, a task-based query identifies a passport or post office service as the best service for completing step 1. Similarly, for each of the remaining steps, the platform 103 identifies the appropriate word groupings and corresponding service. The listing of the actions and the services for completing those actions constitute the service recommendation for a user initiating a task-based query for planning travel arrangements.

[0086] The processes described herein for providing task-based service recommendations based on semantics may be advantageously implemented via software, hardware, firmware or a combination of software and/or firmware and or hardware. For example, the processes described herein, may be advantageously implemented via processors), Digital Signal Processing (DSP) chip, an Application Specific Integrated Circuit (ASIC), Field Programmable Gate Arrays (FPGAs), etc. Such exemplary hardware for performing the described functions is detailed below.

[0087] FIG. 10 illustrates a computer system 1000 upon which an embodiment of the invention may be implemented. Although computer system 1000 is depicted with respect to a particular device or equipment, it is contemplated that other devices or equipment (e.g., network elements, servers, etc.) within FIG. 10 can deploy the illustrated hardware and components of system 1000. Computer system 1000 is programmed (e.g., via computer program code or instructions) to provide task-based service recommendations based on semantics as described herein and includes a communication mechanism such as a bus 1010 for passing information between other internal and external components of the computer system 1000. Information (also called data) is represented as a physical expression of a measurable phenomenon, typically electric voltages, but including, in other embodiments, such phenomena as magnetic, electromagnetic, pressure, chemical, biological, molecular, atomic, sub-atomic and quantum interactions. For example, north and south magnetic fields, or a zero and non-zero electric voltage, represent two states (0, 1) of a binary digit (bit). Other phenomena can represent digits of a higher base. A superposition of multiple simultaneous quantum states before measurement represents a quantum bit (qubit). A sequence of one or more digits constitutes digital data that is used to represent a number or code for a character. In some embodiments, information called analog data is represented by a near continuum of measurable values within a particular range. Computer system 1000, or a portion thereof, constitutes a means for performing one or more steps of providing task-based service recommendations based on semantics.

[0088] A bus 1010 includes one or more parallel conductors of information so that information is transferred quickly among devices coupled to the bus 1010. One or more processors 1002 for processing information are coupled with the bus 1010.

[0089] A processor (or multiple processors) 1002 performs a set of operations on information as specified by computer program code related to provide task-based service recommendations based on semantics. The computer program code is a set of instructions or statements providing instructions for the operation of the processor and/or the computer system to perform specified functions. The code, for example, may be written in a computer programming language that is compiled into a native instruction set of the processor. The code may also be written directly using the native instruction set (e.g., machine language). The set of operations include bringing information in from the bus 1010 and placing information on the bus 1010. The set of operations also typically include comparing two or more units of information, shifting positions of units of information, and combining two or more units of information, such as by addition or multiplication or logical operations like OR, exclusive OR (XOR), and AND. Each operation of the set of operations that can be performed by the processor is represented to the processor by information called instructions, such as an operation code of one or more digits. A sequence of operations to be executed by the processor 1002, such as a sequence of operation codes, constitute processor instructions, also called computer system instructions or, simply, computer instructions. Processors may be implemented as mechanical, electrical, magnetic, optical, chemical or quantum components, among others, alone or in combination.

[0090] Computer system 1000 also includes a memory 1004 coupled to bus 1010. The memory 1004, such as a random access memory (RAM) or any other dynamic storage device, stores information including processor instructions for providing task-based service recommendations based on semantics. Dynamic memory allows information stored therein to be changed by the computer system 1000. RAM allows a unit of information stored at a location called a memory address to be stored and retrieved independently of information at P T/CN2012/077937

neighboring addresses. The memory 1004 is also used by the processor 1002 to store temporary values during execution of processor instructions. The computer system 1000 also includes a read only memory (ROM) 1006 or any other static storage device coupled to the bus 1010 for storing static information, including instructions, that is not changed by the computer system 1000. Some memory is composed of volatile storage that loses the information stored thereon when power is lost. Also coupled to bus 1010 is a non- volatile (persistent) storage device 1008, such as a magnetic disk, optical disk or flash card, for storing information, including instructions, that persists even when the computer system 1000 is turned off or otherwise loses power.

[0091] Information, including instructions for providing task-based service recommendations based on semantics, is provided to the bus 1010 for use by the processor from an external input device 1012, such as a keyboard containing alphanumeric keys operated by a human user, a microphone, an Infrared (IR) remote control, a joystick, a game pad, a stylus pen, a touch screen, or a sensor. A sensor detects conditions in its vicinity and transforms those detections into physical expression compatible with the measurable phenomenon used to represent information in computer system 1000. Other external devices coupled to bus 1010, used primarily for interacting with humans, include a display device 1014, such as a cathode ray tube (CRT), a liquid crystal display (LCD), a light emitting diode (LED) display, an organic LED (OLED) display, a plasma screen, or a printer for presenting text or images, and a pointing device 1016, such as a mouse, a trackball, cursor direction keys, or a motion sensor, for controlling a position of a small cursor image presented on the display 1014 and issuing commands associated with graphical elements presented on the display 1014. In some embodiments, for example, in embodiments in which the computer system 1000 performs all functions automatically without human input, one or more of external input device 1012, display device 1014 and pointing device 1016 is omitted.

[0092] In the illustrated embodiment, special purpose hardware, such as an application specific integrated circuit (ASIC) 1020, is coupled to bus 1010. The special purpose hardware is configured to perform operations not performed by processor 1002 quickly enough for special purposes. Examples of ASICs include graphics accelerator cards for generating images for display 1014, cryptographic boards for encrypting and decrypting messages sent over a network, speech recognition, and interfaces to special external devices, such as robotic arms and medical scanning equipment that repeatedly perform some complex sequence of operations that are more efficiently implemented in hardware.

[0093] Computer system 1000 also includes one or more instances of a communications interface 1070 coupled to bus 1010. Communication interface 1070 provides a one-way or two-way communication coupling to a variety of external devices that operate with their own processors, such as printers, scanners and external disks. In general the coupling is with a network link 1078 that is connected to a local network 1080 to which a variety of external devices with their own processors are connected. For example, communication interface 1070 may be a parallel port or a serial port or a universal serial bus (USB) port on a personal computer. In some embodiments, communications interface 1070 is an integrated services digital network (ISDN) card or a digital subscriber line (DSL) card or a telephone modem that provides an information communication connection to a corresponding type of telephone line. In some embodiments, a communication interface 1070 is a cable modem that converts signals on bus 1010 into signals for a communication connection over a coaxial cable or into optical signals for a communication connection over a fiber optic cable. As another example, communications interface 1070 may be a local area network (LAN) card to provide a data communication connection to a compatible LAN, such as Ethernet. Wireless links may also be implemented. For wireless links, the communications interface 1070 sends or receives or both sends and receives electrical, acoustic or electromagnetic signals, including infrared and optical signals, that carry information streams, such as digital data. For example, in wireless handheld devices, such as mobile telephones like cell phones, the communications interface 1070 includes a radio band electromagnetic transmitter and receiver called a radio transceiver. In certain embodiments, the communications interface 1070 enables connection to the communication network 105 for providing task-based service recommendations based on semantics to the UE 101.

[0094] The term "computer-readable medium" as used herein refers to any medium that participates in providing information to processor 1002, including instructions for execution. Such a medium may take many forms, including, but not limited to computer-readable storage medium (e.g., non-volatile media, volatile media), and transmission media. Non-transitory media, such as non-volatile media, include, for example, optical or magnetic disks, such as storage device 1008. Volatile media include, for example, dynamic memory 1004, Transmission media include, for example, twisted pair cables, coaxial cables, copper wire, fiber optic cables, and carrier waves that travel through space without wires or cables, such as acoustic waves and electromagnetic waves, including radio, optical and infrared waves. Signals include man-made transient variations in amplitude, frequency, phase, polarization or other physical properties transmitted through the transmission media. Common forms of computer-readable media include, for example, a floppy disk, a flexible disk, hard disk, magnetic tape, any other magnetic medium, a CD-ROM, CDRW, DVD, any other optical medium, punch cards, paper tape, optical mark sheets, any other physical medium with patterns of holes or other optically recognizable indicia, a RAM, a PROM, an EPROM, a FLASH-EPROM, an EEPROM, a flash memory, any other memory chip or cartridge, a carrier wave, or any other medium from which a computer can read. The term computer-readable storage medium is used herein to refer to any computer-readable medium except transmission media.

[0095] Logic encoded in one or more tangible media includes one or both of processor instructions on a computer-readable storage media and special purpose hardware, such as ASIC 1020.

[0096] Network link 1078 typically provides information communication using transmission media through one or more networks to other devices that use or process the information. For example, network link 1078 may provide a connection through local network 1080 to a host computer 1082 or to equipment 1084 operated by an Internet Service Provider (ISP). ISP equipment 1084 in turn provides data communication services through the public, world-wide packet-switching communication network of networks now commonly referred to as the Internet 1090.

[0097] A computer called a server host 1092 connected to the Internet hosts a process that provides a service in response to information received over the Internet. For example, server host 1092 hosts a process that provides information representing video data for presentation at display 1014. It is contemplated that the components of system 1000 can be deployed in various configurations within other computer systems, e.g., host 1082 and server 1092. [0098] At least some embodiments of the invention are related to the use of computer system 1000 for implementing some or all of the techniques described herein. According to one embodiment of the invention, those techniques are performed by computer system 1000 in response to processor 1002 executing one or more sequences of one or more processor instructions contained in memory 1004. Such instructions, also called computer instructions, software and program code, may be read into memory 1004 from another computer-readable medium such as storage device 1008 or network link 1078. Execution of the sequences of instructions contained in memory 1004 causes processor 1002 to perform one or more of the method steps described herein. In alternative embodiments, hardware, such as ASIC 1020, may be used in place of or in combination with software to implement the invention. Thus, embodiments of the invention are not limited to any specific combination of hardware and software, unless otherwise explicitly stated herein.

[0099] The signals transmitted over network link 1078 and other networks through communications interface 1070, carry information to and from computer system 1000. Computer system 1000 can send and receive information, including program code, through the networks 1080, 1090 among others, through network link 1078 and communications interface 1070. In an example using the Internet 1090, a server host 1092 transmits program code for a particular application, requested by a message sent from computer 1000, through Internet 1090, ISP equipment 1084, local network 1080 and communications interface 1070. The received code may be executed by processor 1002 as it is received, or may be stored in memory 1004 or in storage device 1008 or any other non- volatile storage for later execution, or both. In this manner, computer system 1000 may obtain application program code in the form of signals on a carrier wave.

[0100] Various forms of computer readable media may be involved in carrying one or more sequence of instructions or data or both to processor 1002 for execution. For example, instructions and data may initially be carried on a magnetic disk of a remote computer such as host 1082. The remote computer loads the instructions and data into its dynamic memory and sends the instructions and data over a telephone line using a modem. A modem local to the computer system 1000 receives the instructions and data on a telephone line and uses an infra- red transmitter to convert the instructions and data to a signal on an infra-red carrier wave 77937

serving as the network link 1078. An infrared detector serving as communications interface 1070 receives the instructions and data carried in the infrared signal and places information representing the instructions and data onto bus 1010. Bus 1010 carries the information to memory 1004 from which processor 1002 retrieves and executes the instructions using some of the data sent with the instructions. The instructions and data received in memory 1004 may optionally be stored on storage device 1008, either before or after execution by the processor 1002.

[0101] FIG. 11 illustrates a chip set or chip 1100 upon which an embodiment of the invention may be implemented. Chip set 1100 is programmed to provide task-based service recommendations based on semantics as described herein and includes, for instance, the processor and memory components described with respect to FIG. 10 incorporated in one or more physical packages (e.g., chips). By way of example, a physical package includes an arrangement of one or more materials, components, and/or wires on a structural assembly (e.g., a baseboard) to provide one or more characteristics such as physical strength, conservation of size, and/or limitation of electrical interaction. It is contemplated that in certain embodiments the chip set 1100 can be implemented in a single chip. It is further contemplated that in certain embodiments the chip set or chip 1100 can be implemented as a single "system on a chip." It is further contemplated that in certain embodiments a separate ASIC would not be used, for example, and that all relevant functions as disclosed herein would be performed by a processor or processors. Chip set or chip 1100, or a portion thereof, constitutes a means for performing one or more steps of providing user interface navigation information associated with the availability of functions. Chip set or chip 1100, or a portion thereof, constitutes a means for performing one or more steps of providing task-based service recommendations based on semantics.

[0102] In one embodiment, the chip set or chip 1100 includes a communication mechanism such as a bus 1 101 for passing information among the components of the chip set 1100. A processor 1103 has connectivity to the bus 1101 to execute instructions and process information stored in, for example, a memory 1105. The processor 1103 may include one or more processing cores with each core configured to perform independently. A multi-core processor enables multiprocessing within a single physical package. Examples of a multi-core processor include two, four, eight, or greater numbers of processing cores. Alternatively or in addition, the processor 1103 may include one or more microprocessors configured in tandem via the bus 1101 to enable independent execution of instructions, pipelining, and multithreading. The processor 1103 may also be accompanied with one or more specialized components to perform certain processing functions and tasks such as one or more digital signal processors (DSP) 1107, or one or more application-specific integrated circuits (ASIC) 1109. A DSP 1107 typically is configured to process real-world signals (e.g., sound) in real time independently of the processor 1103. Similarly, an ASIC 1109 can be configured to performed specialized functions not easily performed by a more general purpose processor. Other specialized components to aid in performing the inventive functions described herein may include one or more field programmable gate arrays (FPGA), one or more controllers, or one or more other special- purpose computer chips.

[0103] In one embodiment, the chip set or chip 1100 includes merely one or more processors and some software and/or firmware supporting and/or relating to and/or for the one or more processors.

[0104] The processor 1103 and accompanying components have connectivity to the memory 1105 via the bus 1101. The memory 1105 includes both dynamic memory (e.g., RAM, magnetic disk, writable optical disk, etc.) and static memory (e.g., ROM, CD-ROM, etc.) for storing executable instructions that when executed perform the inventive steps described herein to provide task-based service recommendations based on semantics. The memory 1105 also stores the data associated with or generated by the execution of the inventive steps.

[0105] FIG. 12 is a diagram of exemplary components of a mobile terminal (e.g., handset) for communications, which is capable of operating in the system of FIG. 1, according to one embodiment. In some embodiments, mobile terminal 1201, or a portion thereof, constitutes a means for performing one or more steps of providing task-based service recommendations based on semantics. Generally, a radio receiver is often defined in terms of front-end and back-end characteristics. The front-end of the receiver encompasses all of the Radio Frequency (RF) circuitry whereas the back-end encompasses all of the base-band processing circuitry. As used in this application, the term "circuitry" refers to both: (1) hardware-only implementations (such as implementations in only analog and/or digital circuitry), and (2) to combinations of circuitry and software (and/or firmware) (such as, if applicable to the particular context, to a combination of processor(s), including digital signal processors), software, and memory(ies) that work together to cause an apparatus, such as a mobile phone or server, to perform various functions). This definition of "circuitry" applies to all uses of this term in this application, including in any claims. As a further example, as used in this application and if applicable to the particular context, the term "circuitry" would also cover an implementation of merely a processor (or multiple processors) and its (or their) accompanying software/or firmware. The term "circuitry" would also cover if applicable to the particular context, for example, a baseband integrated circuit or applications processor integrated circuit in a mobile phone or a similar integrated circuit in a cellular network device or other network devices.

[0106] Pertinent internal components of the telephone include a Main Control Unit (MCU) 1203, a Digital Signal Processor (DSP) 1205, and a receiver/transmitter unit including a microphone gain control unit and a speaker gain control unit. A main display unit 1207 provides a display to the user in support of various applications and mobile terminal functions that perform or support the steps of providing task-based service recommendations based on semantics. The display 1207 includes display circuitry configured to display at least a portion of a user interface of the mobile terminal (e.g., mobile telephone). Additionally, the display 1207 and display circuitry are configured to facilitate user control of at least some functions of the mobile terminal. An audio function circuitry 1209 includes a microphone 1211 and microphone amplifier that amplifies the speech signal output from the microphone 1211. The amplified speech signal output from the microphone 1211 is fed to a coder/decoder (CODEC) 1213.

[0107] A radio section 1215 amplifies power and converts frequency in order to communicate with a base station, which is included in a mobile communication system, via antenna 1217. The power amplifier (PA) 1219 and the transmitter/modulation circuitry are operationally responsive to the MCU 1203, with an output from the PA 1219 coupled to the duplexer 1221 or circulator or antenna switch, as known in the art. The PA 1219 also couples to a battery interface and power control unit 1220. [0108] In use, a user of mobile terminal 1201 speaks into the microphone 1211 and his or her voice along with any detected background noise is converted into an analog voltage. The analog voltage is then converted into a digital signal through the Analog to Digital Converter (ADC) 1223. The control unit 1203 routes the digital signal into the DSP 1205 for processing therein, such as speech encoding, channel encoding, encrypting, and interleaving. In one embodiment, the processed voice signals are encoded, by units not separately shown, using a cellular transmission protocol such as enhanced data rates for global evolution (EDGE), general packet radio service (GPRS), global system for mobile communications (GSM), Internet protocol multimedia subsystem (IMS), universal mobile telecommunications system (UMTS), etc., as well as any other suitable wireless medium, e.g., microwave access (WiMAX), Long Term Evolution (LTE) networks, code division multiple access (CDMA), wideband code division multiple access (WCDMA), wireless fidelity (WiFi), satellite, and the like, or any combination thereof.

[0109] The encoded signals are then routed to an equalizer 1225 for compensation of any frequency-dependent impairments that occur during transmission though the air such as phase and amplitude distortion. After equalizing the bit stream, the modulator 1227 combines the signal with a RF signal generated in the RF interface 1229. The modulator 1227 generates a sine wave by way of frequency or phase modulation. In order to prepare the signal for transmission, an up-converter 1231 combines the sine wave output from the modulator 1227 with another sine wave generated by a synthesizer 1233 to achieve the desired frequency of transmission. The signal is then sent through a PA 1219 to increase the signal to an appropriate power level. In practical systems, the PA 1219 acts as a variable gain amplifier whose gain is controlled by the DSP 1205 from information received from a network base station. The signal is then filtered within the duplexer 1221 and optionally sent to an antenna coupler 1235 to match impedances to provide maximum power transfer. Finally, the signal is transmitted via antenna 1217 to a local base station. An automatic gain control (AGC) can be supplied to control the gain of the fi al stages of the receiver. The signals may be forwarded from there to a remote telephone which may be another cellular telephone, any other mobile phone or a land-line connected to a Public Switched Telephone Network (PSTN), or other telephony networks. [0110] Voice signals transmitted to the mobile terminal 1201 are received via antenna 1217 and immediately amplified by a low noise amplifier (LNA) 1237. A down-converter 1239 lowers the carrier frequency while the demodulator 1241 strips away the RF leaving only a digital bit stream. The signal then goes through the equalizer 1225 and is processed by the DSP 1205. A Digital to Analog Converter (DAC) 1243 converts the signal and the resulting output is transmitted to the user through the speaker 1245, all under control of a Main Control Unit (MCU) 1203 which can be implemented as a Central Processing Unit (CPU).

[0111] The MCU 1203 receives various signals including input signals from the keyboard 1247. The keyboard 1247 and/or the MCU 1203 in combination with other user input components (e.g., the microphone 1211) comprise a user interface circuitry for managing user input. The MCU 1203 runs a user interface software to facilitate user control of at least some functions of the mobile terminal 1201 to provide task-based service recommendations based on semantics. The MCU 1203 also delivers a display command and a switch command to the display 1207 and to the speech output switching controller, respectively. Further, the MCU 1203 exchanges information with the DSP 1205 and can access an optionally incorporated SIM card 1249 and a memory 1251. In addition, the MCU 1203 executes various control functions required of the terminal. The DSP 1205 may, depending upon the implementation, perform any of a variety of conventional digital processing functions on the voice signals. Additionally, DSP 1205 determines the background noise level of the local environment from the signals detected by microphone 1211 and sets the gain of microphone 1211 to a level selected to compensate for the natural tendency of the user of the mobile terminal 1201.

[0112] The CODEC 1213 includes the ADC 1223 and DAC 1243. The memory 1251 stores various data including call incoming tone data and is capable of storing other data including music data received via, e.g., the global Internet. The software module could reside in RAM memory, flash memory, registers, or any other form of writable storage medium known in the art. The memory device 12 1 may be, but not limited to, a single memory, CD, DVD, ROM, RAM, EEPROM, optical storage, magnetic disk storage, flash memory storage, or any other non- olatile storage medium capable of storing digital data. [0113] An optionally incorporated SIM card 1249 carries, for instance, important information, such as the cellular phone number, the carrier supplying service, subscription details, and security information. The SIM card 1249 serves primarily to identify the mobile terminal 1201 on a radio network. The card 1249 also contains a memory for storing a personal telephone number registry, text messages, and user specific mobile terminal settings,

[0114] While the invention has been described in connection with a number of embodiments and implementations, the invention is not so limited but covers various obvious modifications and equivalent arrangements, which fall within the purview of the appended claims. Although features of the invention are expressed in certain combinations among the claims, it is contemplated that these features can be arranged in any combination and order.

Claims

What is claimed is:

1. A method comprising facilitating a processing of and/or processing (1) data and/or (2) information and/or (3) at least one signal, the (1) data and/or (2) information and/or (3) at least one signal based, at least in part, on the following:

at least one determination of an input for specifying at least one term of at least one task- based query;

at least one determination of one or more word groupings based, at least in part, on the at least one term; and

at least one determination of one or more responses to the at least one task-based query based, at least in part, on a correlation of the one or more responses to the one or more word groupings.

2. A method of claim 1, wherein the (1) data and/or (2) information and/or (3) at least one signal are further based, at least in part, on the following:

at least one determination of one or more instructions for completing at least one task

associated with the at least one task-based query,

wherein the one or more responses include, at least in part, the one or more instructions.

3. A method of claim 2, wherein the (1) data and/or (2) information and/or (3) at least one signal are further based, at least in part, on the following:

at least one determination of one or more services for performing the one or more

instructions,

wherein the one or more responses include, at least in part, the one or more services.

4. A method of claim 3, wherein the (1) data and/or (2) information and/or (3) at least one signal are further based, at least in part, on the following:

a presentation of the one or more responses, the one or more instructions, or a combination thereof in association with one or more links to the one or more services.

5. A method according to any of claims 3 and 4, wherein the (1) data and/or (2) information and/or (3) at least one signal are further based, at least in part, on the following:

at least one determination of the one or more word groupings, the one or more responses, the correlation, the one or more instructions, the one or more services, or a combination thereof based, at least in part, on one or more user inputs, user feedback information, or a combination thereof.

6. A method according to any of claims 1-5, wherein the (1) data and/or (2) information and/or (3) at least one signal are further based, at least in part, on the following:

a parsing of at least a portion of the one or more responses to determine occurrence

information of the one or more word groupings,

wherein the correlation is based, at least in part, on the occurrence information.

7. A method according to any of claims 1-6, wherein the (1) data and/or (2) information and/or (3) at least one signal are further based, at least in part, on the following:

at least one determination of the one or more word groupings based, at least in part, on one or more semantic models.

8. A method of claim 7, wherein the (1) data and/or (2) information and/or (3) at least one signal are further based, at least in part, on the following:

a construction of the one or more semantic models based, at least in part, on at least one dependency network of the at least one term, one or more other terms, or a combination thereof.

9. A method of claim 8, wherein the (1) data and/or (2) information and/or (3) at least one signal are further based, at least in part, on the following:

at least one determination of the at least one dependency network based, at least in part, on one or more grammatical relationships among the at least one term, the one or more other terms, or a combination thereof.

10. A method of claim 9, wherein the (1) data and/or (2) information and/or (3) at least one signal are further based, at least in part, on the following:

at least one determination of strength information associated with the one or more

grammatical relationships,

wherein the at least one dependency network is based, at least in part, on the strength

information.

11. A method according to any of claims 8-10, wherein the ( 1 ) data and/or (2) information and/or (3) at least one signal are further based, at least in part, on the following:

a parsing of one or more knowledge databases to determine the one or more semantic models, the at least one dependency network, or a combination thereof.

12. A method of claim 11, wherein the (1) data and/or (2) information and/or (3) at least one signal are further based, at least in part, on the following:

at least one determination of one or more updates to the one or more knowledge databases; and

an updating of the one or more semantic models, the at least one dependency network, or a combination thereof based, at least in part, on the one or more updates.

13. A method according to any of claims 1-12, wherein the (1) data and/or (2) information and/or (3) at least one signal are further based, at least in part, on the following:

at least one determination of contextual information associated with the input, a device

associated with the input, a user associated with the device, or a combination thereof, wherein the one or more word groupings, the one or more responses, the correlation, or a combination are based, at least in part, on the contextual information.

14. A method according to any of claims 1-13, wherein the at least one term includes, at least in part, a verb, a noun, a proposition, a domain, or a combination thereof, and wherein the one or more word groupings include, at least in part, one or more verb-noun pairs.

15. A method comprising :

determining an input for specifying at least one term of at least one task-based query;

determining one or more word groupings based, at least in part, on the at least one term; and determining one or more responses to the at least one task-based query based, at least in part, on a correlation of the one or more responses to the one or more word groupings.

16. A method of claim 15, further comprising:

deteraiining one or more instructions for completing at least one task associated with the at least one task-based query,

17. A method of claim 16, further comprising:

determining one or more services for performing the one or more instructions,

18. A method of claim 17, further comprising:

causing, at least in part, a presentation of the one or more responses, the one or more

instructions, or a combination thereof in association with one or more links to the one or more services.

19. A method according to any of claims 17 and 18, further comprising:

determining the one or more word groupings, the one or more responses, the correlation, the one or more instructions, the one or more services, or a combination thereof based, at least in part, on one or more user inputs, user feedback information, or a combination thereof.

20. A method according to any of claims 15-19, further comprising:

causing, at least in part, a parsing of at least a portion of the one or more responses to

determine occurrence information of the one or more word groupings,

21. A method according to any of claims 15-20, further comprising:

determining the one or more word groupings based, at least in part, on one or more semantic models.

22. A method of claim 21 , further comprising:

causing, at least in part, a construction of the one or more semantic models based, at least in part, on at least one dependency network of the at least one term, one or more other terms, or a combination thereof.

23. A method of claim 22, further comprising:

determining the at least one dependency network based, at least in part, on one or more

grammatical relationships among the at least one term, the one or more other terms, or a combination thereof.

24. A method of claim 23, further comprising:

determining strength information associated with the one or more grammatical relationships, wherein the at least one dependency network is based, at least in part, on the strength

information.

25. A method according to any of claims 22-24, further comprising:

causing, at least in part, a parsing of one or more knowledge databases to determine the one or more semantic models, the at least one dependency network, or a combination thereof.

26. A method of claim 15, further comprising:

determining one or more updates to the one or more knowledge databases; and

causing, at least in part, an updating of the one or more semantic models, the at least one

dependency network, or a combination thereof based, at least in part, on the one or more updates.

27. A method according to any of claims 15-26, further comprising:

determining contextual information associated with the input, a device associated with the input, a user associated with the device, or a combination thereof,

wherein the one or more word groupings, the one or more responses, the correlation, or a combination are based, at least in part, on the contextual information.

28. A method according to any of claims 15-27, wherein the at least one term includes, at least in part, a verb, a noun, a proposition, a domain, or a combination thereof, and wherein the one or more word groupings include, at least in part, one or more verb-noun pairs.

29. An apparatus comprising:

at least one processor; and

at least one memory including computer program code for one or more programs, the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus to perform at least the following,

determine an input for specifying at least one term of at least one task-based query; determine one or more word groupings based, at least in part, on the at least one term; and

determine one or more responses to the at least one task-based query based, at least in part, on a correlation of the one or more responses to the one or more word groupings.

30. An apparatus of claim 29, wherein the apparatus is further caused to:

determine one or more instructions for completing at least one task associated with the at least one task-based query,

31. An apparatus of claim 30, wherein the apparatus is further caused to:

determine one or more services for performing the one or more instructions,

32. An apparatus of claim 31 , wherein the apparatus is further caused to:

cause, at least in part, a presentation of the one or more responses, the one or more

33. An apparatus according to any of claims 31 and 32, wherein the apparatus is further caused to:

determme the one or more word groupings, the one or more responses, the correlation, the one or more instructions, the one or more services, or a combination thereof based, at least in part, on one or more user inputs, user feedback information, or a combination thereof.

34. An apparatus according to any of claims 29-33, wherein the apparatus is further caused to:

cause, at least in part, a parsing of at least a portion of the one or more responses to

determine occurrence information of the one or more word groupings,

35. An apparatus according to any of claims 29-34, wherein the apparatus is further caused to:

determine the one or more word groupings based, at least in part, on one or more semantic models.

36. An apparatus of claim 35, wherein the apparatus is further caused to:

cause, at least in part, a construction of the one or more semantic models based, at least in part, on at least one dependency network of the at least one term, one or more other terms, or a combination thereof.

An apparatus of claim 36, wherein the apparatus is further caused to: determine the at least one dependency network based, at least in part, on one or more grammatical relationships among the at least one term, the one or more other terms, or a combination thereof.

38. An apparatus of claim 37, wherein the apparatus is further caused to:

determine strength information associated with the one or more grammatical relationships, wherein the at least one dependency network is based, at least in part, on the strength

information.

39. An apparatus according to any of claims 36-38, wherein the apparatus is further caused to:

cause, at least in part, a arsing of one or more knowledge databases to determine the one or more semantic models, the at least one dependency network, or a combination thereof.

40. An apparatus of claim 29, wherein the apparatus is further caused to:

determine one or more updates to the one or more knowledge databases; and

cause, at least in part, an updating of the one or more semantic models, the at least one

41. An apparatus according to any of claims 29-40, wherein the apparatus is further caused to:

determine contextual information associated with the input, a device associated with the input, a user associated with the device, or a combination thereof,

42. An apparatus according to any of claims 29-41 , wherein the at least one term includes, at least in part, a verb, a noun, a proposition, a domain, or a combination thereof, and wherein the one or more word groupings include, at least in part, one or more verb-noun pairs.

43. A computer-readable storage medium carrying one or more sequences of one or more instructions which, when executed by one or more processors, cause an apparatus to at least perform at least a method of any of claims 1-28.

44. An apparatus comprising means for performing at least a method of any of claims 1 -28.

45. A computer program product including one or more sequences of one or more instructions which, when executed by one or more processors, cause an apparatus to at least perform the steps of a method of any of claims 1-28.

46. A method comprising facilitating access to at least one interface configured to allow access to at least one service, the at least one service configured to perform a method of any of claims 1-28.

47. A method comprising facilitating a processing of and/or processing (1) data and/or (2) information and/or (3) at least one signal, the (1) data and/or (2) information and/or (3) at least one signal based, at least in part, on a method of any of claims 1-28.

48. A method comprising facilitating creating and/or facilitating modifying (1) at least one device user interface element and/or (2) at least one device user interface functionality, the (1) at least one device user interface element and/or (2) at least one device user interface functionality based, at least in part, on a method of any of claims 1-28.

49. A method comprising creating and/or modifying (1) at least one device user interface element and/or (2) at least one device user interface functionality, the (1) at least one device user interface element and/or (2) at least one device user interface functionality based, at least in part, on a method of any of claims 1-28.