CN104881446A - Searching method and searching device - Google Patents
Searching method and searching device Download PDFInfo
- Publication number
- CN104881446A CN104881446A CN201510245979.3A CN201510245979A CN104881446A CN 104881446 A CN104881446 A CN 104881446A CN 201510245979 A CN201510245979 A CN 201510245979A CN 104881446 A CN104881446 A CN 104881446A
- Authority
- CN
- China
- Prior art keywords
- viewpoint
- candidate
- aggregation
- answer
- tendentiousness
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
Abstract
The invention provides a searching method and a searching device. According to the searching method and the searching device, a candidate aggregation problem matched with an acquired search keyword is obtained as a target aggregation problem, and then viewpoint data corresponding to the candidate aggregation problem can be obtained and also can be output; as resources in an original resource base are not single contents independent of each other any more, but contain aggregated viewpoint problems and the viewpoint data corresponding to the problems, and consequently, each search result is not single content and is capable of basically satisfying the real search intention of a user; as a result, the problem of increase of data interaction between an application and a search engine due to repeated searching of the user by use of the application in the prior art can be avoided, and therefore, the processing burden of the search engine can be reduced.
Description
[technical field]
The present invention relates to search technique, particularly relate to a kind of searching method and device.
[background technology]
Search engine refers to according to certain strategy, uses specific computer program to gather information from internet, and after organizing information and processing, for user provides search service, the information display of user search being correlated with is to the system of user.How utilizing search service to meet consumers' demand to greatest extent, for Internet enterprises, is an important problem.In the search box of user in the application of search engine correspondence, inputted search keyword, will search for keyword by application, send to search engine.Search engine then according to search keyword, is searched in a database, to obtain and to search for the resource of Keywords matching such as, webpage or document etc., using as several Search Results, and returns to application and exports.
But, if user wants to obtain the rich content with structures by search keyword, due to the single content that the resource in original resources bank is all separate, make each Search Results also be single content, possibly cannot meet the real search intention of user, make user need repeatedly to be searched for by application, required content can be obtained, like this, the data interaction between application and search engine can be increased, thus result in the increase of the processing load of search engine.
[summary of the invention]
Many aspects of the present invention provide a kind of searching method and device, in order to reduce the processing load of search engine.
An aspect of of the present present invention, provides a kind of searching method, comprising:
Obtain search keyword;
Obtain and candidate's aggregation problem of described search Keywords matching, using as target polymerization problem;
Obtain the viewpoint data corresponding to described target polymerization problem;
Export the described viewpoint data corresponding to described target polymerization problem.
Aspect as above and arbitrary possible implementation, provide a kind of implementation further, and described viewpoint data comprise at least one item in the statistics of each viewpoint at least one viewpoint and at least one viewpoint described.
Aspect as above and arbitrary possible implementation, provide a kind of implementation further, and at least one viewpoint described comprises the first tendentiousness viewpoint and the second tendentiousness viewpoint.
Aspect as above and arbitrary possible implementation, provide a kind of implementation further, and the statistics of described each viewpoint comprises at least one item in following data:
The attribute information of each viewpoint;
The appearance situation of each viewpoint in the answer of the viewpoint class problem corresponding to described target polymerization problem; And
The appearance situation statistical graph of each viewpoint in the answer of the viewpoint class problem corresponding to described target polymerization problem.
Aspect as above and arbitrary possible implementation, provide a kind of implementation further, candidate's aggregation problem of described acquisition and described search Keywords matching, using before target polymerization problem, also comprises:
Problem in resources bank is identified, to obtain viewpoint class problem;
Polymerization process based on semanteme is carried out to described viewpoint class problem, to obtain at least one candidate's aggregation problem;
According to the answer of the viewpoint class problem at least one candidate's aggregation problem described corresponding to each candidate's aggregation problem, obtain the viewpoint data corresponding to described each candidate's aggregation problem.
Aspect as above and arbitrary possible implementation, a kind of implementation is provided further, according to the answer of the viewpoint class problem at least one candidate's aggregation problem described corresponding to each candidate's aggregation problem, obtain the viewpoint data corresponding to described each candidate's aggregation problem, comprising:
According to the answer of the viewpoint class problem at least one candidate's aggregation problem described corresponding to each candidate's aggregation problem, obtain at least one candidate's tendentiousness vocabulary or the phrase corresponding to described each candidate's aggregation problem;
Identifying processing is carried out at least one candidate's tendentiousness vocabulary described or phrase, to obtain viewpoint included in described viewpoint data.
Aspect as above and arbitrary possible implementation, provide a kind of implementation further, and the described viewpoint data corresponding to described output described target polymerization problem, comprising:
With structured form, export the described viewpoint data corresponding to described target polymerization problem.
Another aspect of the present invention, provides a kind of searcher, comprising:
Acquiring unit, for obtaining search keyword;
Matching unit, for obtaining the candidate's aggregation problem with described search Keywords matching, using as target polymerization problem;
Described matching unit, also for obtaining the viewpoint data corresponding to described target polymerization problem;
Output unit, for exporting the described viewpoint data corresponding to described target polymerization problem.
Aspect as above and arbitrary possible implementation, provide a kind of implementation further, and described viewpoint data comprise at least one item in the statistics of each viewpoint at least one viewpoint and at least one viewpoint described.
Aspect as above and arbitrary possible implementation, provide a kind of implementation further, and at least one viewpoint described comprises the first tendentiousness viewpoint and the second tendentiousness viewpoint.
Aspect as above and arbitrary possible implementation, provide a kind of implementation further, and the statistics of described each viewpoint comprises at least one item in following data:
The attribute information of each viewpoint;
The appearance situation of each viewpoint in the answer of the viewpoint class problem corresponding to described target polymerization problem; And
The appearance situation statistical graph of each viewpoint in the answer of the viewpoint class problem corresponding to described target polymerization problem.
Aspect as above and arbitrary possible implementation, provide a kind of implementation further, described device also comprises excavation unit, for
Problem in resources bank is identified, to obtain viewpoint class problem;
Polymerization process based on semanteme is carried out to described viewpoint class problem, to obtain at least one candidate's aggregation problem; And
According to the answer of the viewpoint class problem at least one candidate's aggregation problem described corresponding to each candidate's aggregation problem, obtain the viewpoint data corresponding to described each candidate's aggregation problem.
Aspect as above and arbitrary possible implementation, provide a kind of implementation further, described excavation unit, specifically for
According to the answer of the viewpoint class problem at least one candidate's aggregation problem described corresponding to each candidate's aggregation problem, obtain at least one candidate's tendentiousness vocabulary or the phrase corresponding to described each candidate's aggregation problem; And
Identifying processing is carried out at least one candidate's tendentiousness vocabulary described or phrase, to obtain viewpoint included in described viewpoint data.
Aspect as above and arbitrary possible implementation, provide a kind of implementation, described output unit further, specifically for
With structured form, export the described viewpoint data corresponding to described target polymerization problem.
Aspect as above and arbitrary possible implementation, provide a kind of implementation further, and at least one viewpoint described comprises the first tendentiousness viewpoint and the second tendentiousness viewpoint.
As shown from the above technical solution, the embodiment of the present invention is by obtaining the candidate's aggregation problem with the search Keywords matching obtained, using as target polymerization problem, and then the viewpoint data obtained corresponding to described target polymerization problem, make it possible to the described viewpoint data exported corresponding to described target polymerization problem, due to the single content that the resource in original resources bank is no longer all separate, but the viewpoint class problem contained through polymerization and the viewpoint data corresponding to these problems, each Search Results is made to be no longer single content, substantially the real search intention of user can be met, therefore, the problem of the data interaction in prior art because user carries out searching for by application repeatedly between the increase application that causes and search engine can be avoided, thus reduce the processing load of search engine.
In addition, adopt technical scheme provided by the invention, due to the single content that the resource in original resources bank is no longer all separate, but the viewpoint class problem contained through polymerization and the viewpoint data corresponding to these problems, each Search Results is made to be no longer single content, substantially the real search intention of user can be met, therefore, it is possible to effectively improve the validity of Search Results.
In addition, adopt technical scheme provided by the invention, due to the single content that the resource in original resources bank is no longer all separate, but the viewpoint class problem contained through polymerization and the viewpoint data corresponding to these problems, each Search Results is made to be no longer single content, substantially the real search intention of user can be met, therefore, it is possible to effectively improve the efficiency of search.
In addition, adopt technical scheme provided by the invention, by with structured form, export Search Results and the described viewpoint data corresponding to described target polymerization problem, the effect that represents of Search Results can be made to have and give prominence to the key points and content feature clearly, thus effectively improve Consumer's Experience.
[accompanying drawing explanation]
In order to be illustrated more clearly in the technical scheme in the embodiment of the present invention, be briefly described to the accompanying drawing used required in embodiment or description of the prior art below, apparently, accompanying drawing in the following describes is some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.
The schematic flow sheet of the searching method that Fig. 1 provides for one embodiment of the invention;
Fig. 2 be in the embodiment that Fig. 1 is corresponding Search Results represent schematic diagram;
The structural representation of the searcher that Fig. 3 provides for another embodiment of the present invention;
The structural representation of the searcher that Fig. 4 provides for another embodiment of the present invention.
[embodiment]
For making the object of the embodiment of the present invention, technical scheme and advantage clearly, below in conjunction with the accompanying drawing in the embodiment of the present invention, technical scheme in the embodiment of the present invention is clearly and completely described, obviously, described embodiment is the present invention's part embodiment, instead of whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art, not making other embodiments whole obtained under creative work prerequisite, belong to the scope of protection of the invention.
It should be noted that, terminal involved in the embodiment of the present invention can include but not limited to mobile phone, personal digital assistant (Personal Digital Assistant, PDA), radio hand-held equipment, panel computer (Tablet Computer), PC (Personal Computer, PC), MP3 player, MP4 player, wearable device (such as, intelligent glasses, intelligent watch, Intelligent bracelet etc.) etc.
In addition, term "and/or" herein, being only a kind of incidence relation describing affiliated partner, can there are three kinds of relations in expression, and such as, A and/or B, can represent: individualism A, exists A and B simultaneously, these three kinds of situations of individualism B.In addition, character "/" herein, general expression forward-backward correlation is to the relation liking a kind of "or".
The schematic flow sheet of the searching method that Fig. 1 provides for one embodiment of the invention, as shown in Figure 1.
101, search keyword is obtained.
102, to obtain and candidate's aggregation problem of described search Keywords matching, using as target polymerization problem.
103, the viewpoint data corresponding to described target polymerization problem are obtained.
104, the described viewpoint data corresponding to described target polymerization problem are exported.
It should be noted that, the executive agent of 101 ~ 104 partly or entirely can for being positioned at the application of local terminal, or can also for being arranged on plug-in unit or SDK (Software Development Kit) (the Software Development Kit of the application being arranged in local terminal, the functional unit such as SDK), or can also for being arranged in the search engine of network side server, or can also for being positioned at the distributed system of network side, the present embodiment is not particularly limited this.
Be understandable that, described application can be mounted in the local program (nativeApp) in terminal, or can also be a web page program (webApp) of browser in terminal, and the present embodiment does not limit this.
Like this, by obtaining the candidate's aggregation problem with the search Keywords matching obtained, using as target polymerization problem, and then the viewpoint data obtained corresponding to described target polymerization problem, make it possible to the described viewpoint data exported corresponding to described target polymerization problem, due to the single content that the resource in original resources bank is no longer all separate, but the viewpoint class problem contained through polymerization and the viewpoint data corresponding to these problems, each Search Results is made to be no longer single content, substantially the real search intention of user can be met, therefore, the problem of the data interaction in prior art because user carries out searching for by application repeatedly between the increase application that causes and search engine can be avoided, thus reduce the processing load of search engine.
Alternatively, in one of the present embodiment possible implementation, in 101, specifically can gather the described search keyword that user provides, the search command that can be triggered by user is realized.Specifically can adopt the order of following two kinds of mode triggering searches:
Mode one:
On the page that user can represent in current application input described search keyword, then, by clicking the search button on this page, such as, the search answer button etc. that vertical search system provides such as to be known at by the button using Baidu.com that the common large search system such as Baidu provides or Baidu, with triggering searches order, in this search command, comprise described search keyword.Wherein, the quantity that user inputs described search keyword can be one, or can also be several, and its order can be random order, and the present embodiment is not particularly limited this.Like this, after receiving this search command, then can parse wherein comprised described search keyword.
Mode two:
Adopt Asynchronous loading technology such as, Ajax Asynchronous loading or Jsonp Asynchronous loading etc., the input content that the page that user in real represents in current application inputs, in order to distinguish with search keyword, input content now can be called it is input keyword.Wherein, the quantity that user inputs described search keyword can be one, or can also be several, and its order can be random order, and the present embodiment is not particularly limited this.Like this, after receiving this search command, then can parse wherein comprised described search keyword.Particularly, the interface such as Ajax interface or Jsonp interface specifically can be provided, these interfaces can use Java, supertext pre-service (HypertextPreprocessor, PHP) language such as language is write, what it was concrete calls and can use Jquery, or the language such as primary JavaScript is write.
Alternatively, in one of the present embodiment possible implementation, in 102, specifically can utilize the matching way based on semanteme, obtain the candidate's aggregation problem with described search Keywords matching, using as target polymerization problem.
In a concrete implementation procedure, specifically can calculate the semantic distance between the candidate's aggregation problem in search keyword and resources bank, then, then according to semantic distance, the semantic similarity of both acquisitions.Describe in detail and specifically see the related content of the semantic similarity between prior art Chinese version, can repeat no more herein.If the semantic similarity obtained meets the similarity condition pre-set, such as, be more than or equal to similarity threshold etc., then can using this candidate's aggregation problem as target polymerization problem.
Alternatively, in one of the present embodiment possible implementation, in 103, the described viewpoint data obtained can include but not limited at least one item in the statistics of each viewpoint at least one viewpoint and at least one viewpoint described, and the present embodiment is not particularly limited this.
Like this, due to the single content that the resource in original resources bank is no longer all separate, but the viewpoint class problem contained through polymerization and several viewpoints corresponding to these problems, and statistics, make each Search Results be no longer single content, substantially can meet the real search intention of user.
Particularly, the statistics of the described each viewpoint obtained, can include but not limited at least one item in following data:
The attribute information of each viewpoint;
The appearance situation of each viewpoint in the answer of the viewpoint class problem corresponding to described target polymerization problem; And
The appearance situation statistical graph of each viewpoint in the answer of the viewpoint class problem corresponding to described target polymerization problem.
In a concrete implementation procedure, the attribute information of each viewpoint, may be used for the tendentiousness type describing each viewpoint.Such as, positive type or passive type etc.
In the implementation procedure that another is concrete, the appearance situation of each viewpoint in the answer of the viewpoint class problem corresponding to described target polymerization problem, may be used for describing the appearance situation that each viewpoint occurs in the answer of its correspondence.Wherein, so-calledly occur situation, can for there is ratio, or can also be occurrence number, the present embodiment be particularly limited this.
It should be noted that, the statistics of the appearance situation of each viewpoint in same answer can be arranged as required flexibly, can this viewpoint often occur once, statistics is once, as long as or can also this viewpoint occur once, no matter this viewpoint have also appeared several times, and all add up as once, the present embodiment is not particularly limited this.
In the implementation procedure that another is concrete, the appearance situation statistical graph of each viewpoint in the answer of the viewpoint class problem corresponding to described target polymerization problem, may be used for describing the appearance situation statistical graph that each viewpoint occurs in the answer of its correspondence.Wherein, so-calledly occur situation, can for there is ratio, or can also be occurrence number, the present embodiment be particularly limited this.
It should be noted that, the statistics of the appearance situation of each viewpoint in same answer can be arranged as required flexibly, can this viewpoint often occur once, statistics is once, as long as or can also this viewpoint occur once, no matter this viewpoint have also appeared several times, and all add up as once, the present embodiment is not particularly limited this.
Alternatively, in one of the present embodiment possible implementation, before 103, can further include dredge operation.Particularly, specifically can identify problem in resources bank, to obtain viewpoint class problem, and then, the polymerization process based on semanteme is carried out to described viewpoint class problem, to obtain at least one candidate's aggregation problem.Then, then according to the answer of the viewpoint class problem at least one candidate's aggregation problem described corresponding to each candidate's aggregation problem, the viewpoint data corresponding to described each candidate's aggregation problem can be obtained.
Particularly, specifically can in many ways, problem in resources bank be identified, to obtain viewpoint class problem.So-called resources bank, wherein comprised resource, can be in advance in internet, utilizes spiders technology, and several webpages gathered or question and answer are to (i.e. problem-answer resource to).
In a concrete implementation procedure, specifically can Utilizing question template, problem in resources bank is identified, to obtain viewpoint class problem.
So-called problem masterplate, refers to the sentence structure comprising keyword and syntactic structure and defines.Wherein said keyword has strong query tendency usually.
For this question template below: " NP+ be+", wherein, NP, representation noun phrase, key word such containing " being+" in this problem masterplate problem of representation, comprised noun phrase before simultaneously " being+", when the problem that meets the problems referred to above template occurs, this problem is just identified as viewpoint class problem.
Such as, " Emperor Qin is the son of Lv Buwei " such problem, owing to meeting the problems referred to above masterplate, this problem is just identified as viewpoint class problem.Except noun phrase, can also be limited the part in problem masterplate except key word by the syntactic structure such as phrase or verb phrase in sentence, repeat no longer especially at this.
Keyword in problem masterplate has very strong query tendency, this is because the keyword extraction of problem masterplate obtains after the problem of puing question to the high-quality in database carries out statistical study, such as, can extract by the enquirement obtaining in database answering compared with multi-user or in the enquirement of puing question to generation to obtain user's answer rear within a short period of time, add up after these problems of puing question to are carried out participle, by the number of times that each word occurs separately in a problem, the number of times jointly occurred with other words, probability and each word that each word occurs separately in a problem and the probability that other words jointly occur in a problem can be calculated, independent probability of occurrence is high or common probability of occurrence is high word so just can be selected as the keyword of problem masterplate.By comprising to said extracted the analysis that crucial word problem carries out syntactic structure, complete problem masterplate namely can be obtained.
In the implementation procedure that another is concrete, specifically can utilize sorter, problem in resources bank is identified, to obtain viewpoint class problem.Such as, what the characteristic parameter of described sorter can include but not limited in following parameter is one or more:
Whether type belonging to the word that the word that problem comprises, problem comprise and part of speech thereof, question length, problem, problem comprise the attribute the word whether entity word of specified type and problem comprise specified type.
Particularly, specifically can adopt preassigned training sample set, train, to build sorter, in order to identify viewpoint class problem.
It should be noted that, training sample concentrates comprised training sample, can, for the known sample through mark, like this, can directly utilize these known sample to train, to build sorter, or can also a part be the known sample of passing through mark, another part is not through the unknown sample of mark, so, then can known sample be first utilized to train, to build preliminary classification device, then, recycling preliminary classification device is evaluated and tested unknown sample, to obtain classification results, and then then can according to the classification results of unknown sample, unknown sample is marked, to form known sample, as the known sample newly increased, utilize the known sample newly increased, and original known sample re-starts training, to build new sorter, until constructed sorter or known sample meet the cut-off condition of sorter, the quantity being more than or equal to accuracy rate threshold value or the known sample pre-set as classification accuracy is more than or equal to the amount threshold etc. pre-set, the present embodiment is not particularly limited this.
In the implementation procedure that another is concrete, specifically can Utilizing question template and sorter, problem in resources bank is identified, to obtain viewpoint class problem.Such as, problem masterplate specifically can include but not limited to the question template of the types such as WHERE (place class) question template, HOW (method class) question template, WHY (reason class) question template, TIME (time class) question template, SCOPE (scope class) question template, CODE (number class) question template, ADV (commercial paper) question template, PRICE (price class) question template and TERM (without clear and definite query demand class) question template.Specifically can first Utilizing question template, problem in resources bank is filtered, so that the other problems not being obviously viewpoint class problem is filtered out, such as, problem etc. corresponding to WHY question template can be filtered out, remaining may be some problems of viewpoint class problem.Then, recycling sorter, to remaining may be that some problems of viewpoint class problem identify, to obtain viewpoint class problem.Like this, owing to having filtered out the problem corresponding to most of question template, the problem only corresponding to remaining fraction question template, therefore, can alleviate the collection difficulty that training sample that training classifier uses concentrates sample.
Particularly, carrying out, in the process based on the polymerization process of semanteme, specifically can calculating the semantic distance between two between viewpoint class problem to described viewpoint class problem, then, then according to semantic distance, the semantic similarity of both acquisitions.Describe in detail and specifically see the related content of the semantic similarity between prior art Chinese version, can repeat no more herein.If the semantic similarity obtained meets the similarity condition pre-set, such as, be more than or equal to similarity threshold etc., then corresponding two viewpoint class problems can be polymerized to a grouping.If the semantic similarity obtained does not meet the similarity condition pre-set, such as, be less than similarity threshold etc., then no longer corresponding two viewpoint class problems be polymerized to a grouping.Then, then according to viewpoint class problems all in each grouping, obtain and represent the unified problem of of this grouping, be i.e. candidate's aggregation problem.Such as, any one viewpoint class problem in this grouping can specifically be selected, as the candidate's aggregation problem corresponding to this grouping.
It should be noted that, problem can comprise title and content, and the title of some problem is identical with content, and the title of some problem is different with content, and this depends on the enquirement custom of the user of input problem.Herein, the problem participating in carrying out Semantic Similarity Measurement is " viewpoint class problem ", and can be the title of problem, or can also be title and the content of problem, or can also be the content of problem, the present embodiment be particularly limited this.So, i.e. " candidate's aggregation problem ", can be the title of problem, or can also be title and the content of problem, or can also be the content of problem, the present embodiment be particularly limited this unified problem of of the representative that obtains grouping.
Particularly, after obtaining the candidate's aggregation problem corresponding to each grouping, specifically according to the answer of the viewpoint class problem at least one candidate's aggregation problem described corresponding to each candidate's aggregation problem, at least one candidate's tendentiousness vocabulary or the phrase corresponding to described each candidate's aggregation problem can be obtained.Then, then identifying processing is carried out at least one candidate's tendentiousness vocabulary described or phrase, to obtain viewpoint included in described viewpoint data.
In a concrete implementation procedure, specifically can utilize and preassignedly specifically can utilize preassigned dictionary data, identifying processing is carried out to the answer of the viewpoint class problem corresponding to each candidate's aggregation problem, to obtain at least one candidate's tendentiousness vocabulary or the phrase corresponding to described each candidate's aggregation problem.
Particularly, described dictionary data can be the data of appraise dictionary, or can also be the data of strong tendentiousness dictionary, or can also be the data of adjective dictionary, or can also be the data of adversative dictionary, and the present embodiment is not particularly limited this.
Such as, the data of described appraise dictionary, specifically can extract net (HowNet) from knowing, such as, sad soldier most certainly fails, be approximately 2600 vocabulary or phrase.
Or, more such as, the data of described strong tendentiousness dictionary, specifically can be arranged by developer, such as, can not wait, about 180 vocabulary or phrase.
Or, more such as, the data of described adjective dictionary, are mainly used for analyzing in answer not in described appraise dictionary and strong tendentiousness dictionary, and can represent vocabulary or the phrase of certain tendentiousness implication, such as, neat, clear or clearly demarcated etc.
Or, more such as, described adversative dictionary, is mainly used for analyzing in answer not in described appraise dictionary and strong tendentiousness dictionary, and can represents vocabulary or the phrase of certain turnover, such as, but etc.
In the implementation procedure that another is concrete, specifically can utilize preassigned ad hoc structure data, such as, double acknowledge structured data, double denial structured data, negative be structured data or affirmative Negative Structure data etc. certainly, identifying processing is carried out to adjacent candidate's tendentiousness vocabulary or phrase, to obtain new candidate's tendentiousness vocabulary or phrase.Such as, to "no" and " can not " these two adjacent candidate's tendentiousness vocabulary or phrase, obtain " energy " this new candidate's tendentiousness vocabulary or phrase.
In the implementation procedure that another is concrete, specifically can utilize N-Gram algorithm, such as, utilize Uni-Gram vocabulary or the phrase of tendentiousness vocabulary or phrase and the unitary obtained based on dictionary data or ad hoc structure data, associate out the vocabulary or phrase that are adjacent, such as, at least one item in the Bi-Gram vocabulary (as can not process) of the binary be adjacent or phrase and the Tri-Gram vocabulary of ternary be adjacent or phrase, using as new candidate's tendentiousness vocabulary or phrase.
In the implementation procedure that another is concrete, specifically can utilize preassigned Q-A key vocabularies or phrase data, identifying processing is carried out to the answer of the viewpoint class problem corresponding to each candidate's aggregation problem, to obtain at least one candidate's tendentiousness vocabulary or the phrase corresponding to described each candidate's aggregation problem.
Particularly, described Q-A key vocabularies or phrase data, be mainly used for analyzing in answer not in described appraise dictionary and strong tendentiousness dictionary, and can represent vocabulary or the phrase of certain tendentiousness implication under specific linguistic context.
Such as: Q: accountant certificate is good
examine? A: pretty good
examine~ ~! I has attacked suddenly and has just examined out for two months Wherein, verb " is examined ", represents the vocabulary of certain tendentiousness implication exactly under this linguistic context.
Or, more such as, Q: ectopic pregnancy
seriously? A: certainly
seriouslychild is large can rise brokenly by fallopian tubal will not do a good job and can cause deaths by massive haemorrhage; Wherein, adjective " seriously ", represents the vocabulary of certain tendentiousness implication exactly under this linguistic context.
In the implementation procedure that another is concrete, after at least one the candidate's tendentiousness vocabulary obtained corresponding to described each candidate's aggregation problem or phrase, specifically can according to the position in place subordinate sentence in these candidate's tendentiousness vocabulary or the answer of phrase place, utilize classifying rules, these candidate's tendentiousness vocabulary or phrase are identified, to obtain the tendentious viewpoint corresponding to these candidate's tendentiousness vocabulary or phrase.Such as, to the position in place subordinate sentence in candidate's tendentiousness vocabulary or the answer of phrase place, carry out the weighted calculation of log type, to obtain weights, and then according to weights, obtain the tendentious viewpoint corresponding to these candidate's tendentiousness vocabulary or phrase.
In the implementation procedure that another is concrete, after at least one the candidate's tendentiousness vocabulary obtained corresponding to described each candidate's aggregation problem or phrase, specifically sorter can be utilized, these candidate's tendentiousness vocabulary or phrase are identified, to obtain the tendentious viewpoint corresponding to these candidate's tendentiousness vocabulary or phrase.
Particularly, specifically can adopt preassigned training sample set, train, to build sorter, in order to identify the tendentious viewpoint corresponding to candidate's tendentiousness vocabulary or phrase.
It should be noted that, training sample concentrates comprised training sample, can, for the known sample through mark, like this, can directly utilize these known sample to train, to build sorter, or can also a part be the known sample of passing through mark, another part is not through the unknown sample of mark, so, then can known sample be first utilized to train, to build preliminary classification device, then, recycling preliminary classification device is evaluated and tested unknown sample, to obtain classification results, and then then can according to the classification results of unknown sample, unknown sample is marked, to form known sample, as the known sample newly increased, utilize the known sample newly increased, and original known sample re-starts training, to build new sorter, until constructed sorter or known sample meet the cut-off condition of sorter, the quantity being more than or equal to accuracy rate threshold value or the known sample pre-set as classification accuracy is more than or equal to the amount threshold etc. pre-set, the present embodiment is not particularly limited this.
In the present embodiment, the source of training sample can be divided into two kinds, a kind of training sample being pm and marking, have about 1000, for this partially short text, training sample scale is a bit very few, for this situation, utilize many modes of throwing in of surveying to mark, the training sample intercepting annotation results consistance 100% supplements, and finally utilizes 10000 training samples.
Alternatively, in one of the present embodiment possible implementation, in 103, at least one viewpoint described obtained can comprise the first tendentiousness viewpoint and the second tendentiousness viewpoint.Such as, be and be not; Or, more such as, can with cannot; Or, more such as, difficult or be not difficult.
Alternatively, in one of the present embodiment possible implementation, in 104, specifically with structured form, the described viewpoint data corresponding to described target polymerization problem can be exported, to realize representing of Search Results.
As shown in Figure 2, be that search keyword is " son that Emperor Qin is Lu's not Wei ", adopts the Search Results that technical scheme provided by the present invention exports shown in Fig. 2.Wherein,
Representing in region 21, what export is the target polymerization problem with search Keywords matching;
Representing in region 22, two viewpoints corresponding to this target polymerization problem exported, are namely and are not; And
Representing in region 23, the statistics for each viewpoint exported.
Like this, by with structured form, export Search Results and the described viewpoint data corresponding to described target polymerization problem, the effect that represents of Search Results can be made to have and give prominence to the key points and content feature clearly, thus effectively improve Consumer's Experience.
Be understandable that, in general, due to Search Results specified in the page to represent region limited, cannot the whole Search Results of complete display within a screen, then can by a part of content in described Search Results, carry out foldingly representing process, or further a scroll bar can also be set in the described page, to make user drag scroll bar, represent region carry out roll display to coordinate, the present embodiment is not particularly limited this.
Alternatively, in the process of dredge operation, after obtaining at least one viewpoint, can also sort to these viewpoint place answers further, to obtain the answer comprising these viewpoints through sequence.And then, in 103, then can obtain the answer comprising these viewpoints further, and in 104, further output packet is containing the answer of these viewpoints.
Particularly, specifically can utilize at least one item in following information, as ranking factor, the answer at these viewpoint places be sorted:
The mass parameter of viewpoint place answer;
The tendentiousness parameter of viewpoint place answer; And
The semantic dependency of viewpoint place answer.
Wherein,
The mass parameter of described viewpoint place answer, for describing the quality of viewpoint place answer, specifically can according to the quality score of the text of answer, and at least one item in user's score of user corresponding to answer, obtain.
The tendentiousness parameter of described viewpoint place answer, for describing the tendentiousness intensity of viewpoint place answer, specifically can judge whether to comprise in score, answer in turnover vocabulary or phrase and answer according to tendentiousness at least one item whether comprised in obvious strong tendentious vocabulary or phrase, obtain.
The semantic dependency of described viewpoint place answer, for describing the semantic degree of correlation between viewpoint and this viewpoint place answer.Specifically can adopt the computing method of existing text semantic correlativity, detailed description see related content of the prior art, can repeat no more herein.
Particularly, specifically can according to ordering requirements, ordering strategy corresponding to selection, and the ranking factor required for this ordering strategy, or the weights reentried further corresponding to ranking factor, and then, then can utilize selected ranking factor and weights thereof, these viewpoint place answers are sorted.
In the present embodiment, by obtaining the candidate's aggregation problem with the search Keywords matching obtained, using as target polymerization problem, and then the viewpoint data obtained corresponding to described target polymerization problem, make it possible to the described viewpoint data exported corresponding to described target polymerization problem, due to the single content that the resource in original resources bank is no longer all separate, but the viewpoint class problem contained through polymerization and the viewpoint data corresponding to these problems, each Search Results is made to be no longer single content, substantially the real search intention of user can be met, therefore, the problem of the data interaction in prior art because user carries out searching for by application repeatedly between the increase application that causes and search engine can be avoided, thus reduce the processing load of search engine.
In addition, adopt technical scheme provided by the invention, due to the single content that the resource in original resources bank is no longer all separate, but the viewpoint class problem contained through polymerization and the viewpoint data corresponding to these problems, each Search Results is made to be no longer single content, substantially the real search intention of user can be met, therefore, it is possible to effectively improve the validity of Search Results.
In addition, adopt technical scheme provided by the invention, due to the single content that the resource in original resources bank is no longer all separate, but the viewpoint class problem contained through polymerization and the viewpoint data corresponding to these problems, each Search Results is made to be no longer single content, substantially the real search intention of user can be met, therefore, it is possible to effectively improve the efficiency of search.
In addition, adopt technical scheme provided by the invention, by with structured form, export Search Results and the described viewpoint data corresponding to described target polymerization problem, the effect that represents of Search Results can be made to have and give prominence to the key points and content feature clearly, thus effectively improve Consumer's Experience.
It should be noted that, for aforesaid each embodiment of the method, in order to simple description, therefore it is all expressed as a series of combination of actions, but those skilled in the art should know, the present invention is not by the restriction of described sequence of movement, because according to the present invention, some step can adopt other orders or carry out simultaneously.Secondly, those skilled in the art also should know, the embodiment described in instructions all belongs to preferred embodiment, and involved action and module might not be that the present invention is necessary.
In the above-described embodiments, the description of each embodiment is all emphasized particularly on different fields, in certain embodiment, there is no the part described in detail, can see the associated description of other embodiments.
The structural representation of the searcher that Fig. 3 provides for another embodiment of the present invention, as shown in Figure 3.The searcher of the present embodiment can comprise acquiring unit 31, matching unit 32 and output unit 33.Wherein, acquiring unit 31, for obtaining search keyword; Matching unit 32, for obtaining the candidate's aggregation problem with described search Keywords matching, using as target polymerization problem; Described matching unit 32, also for obtaining the viewpoint data corresponding to described target polymerization problem; Output unit 33, for exporting the described viewpoint data corresponding to described target polymerization problem.
It should be noted that, the searcher that the present embodiment provides partly or entirely can for being positioned at the application of local terminal, or can also for being arranged on plug-in unit or SDK (Software Development Kit) (the Software Development Kit of the application being arranged in local terminal, the functional unit such as SDK), or can also for being arranged in the search engine of network side server, or can also for being positioned at the distributed system of network side, the present embodiment is not particularly limited this.
Be understandable that, described application can be mounted in the local program (nativeApp) in terminal, or can also be a web page program (webApp) of browser in terminal, and the present embodiment does not limit this.
Alternatively, in one of the present embodiment possible implementation, described matching unit 32, the described viewpoint data obtained can include but not limited at least one item in the statistics of each viewpoint at least one viewpoint and at least one viewpoint described, and the present embodiment is not particularly limited this.
In a concrete implementation procedure, the statistics of described each viewpoint that described matching unit 32 obtains, can include but not limited at least one item in following data:
The attribute information of each viewpoint;
The appearance situation of each viewpoint in the answer of the viewpoint class problem corresponding to described target polymerization problem; And
The appearance situation statistical graph of each viewpoint in the answer of the viewpoint class problem corresponding to described target polymerization problem.
Alternatively, in one of the present embodiment possible implementation, as shown in Figure 4, the searcher that the present embodiment provides can further include and excavates unit 41, for identifying problem in resources bank, to obtain viewpoint class problem; Polymerization process based on semanteme is carried out to described viewpoint class problem, to obtain at least one candidate's aggregation problem; And according to the answer of the viewpoint class problem at least one candidate's aggregation problem described corresponding to each candidate's aggregation problem, obtain the viewpoint data corresponding to described each candidate's aggregation problem.
In a concrete implementation procedure, described excavation unit 41, specifically may be used for the answer according to the viewpoint class problem at least one candidate's aggregation problem described corresponding to each candidate's aggregation problem, obtain at least one candidate's tendentiousness vocabulary or phrase corresponding to described each candidate's aggregation problem; And identifying processing is carried out at least one candidate's tendentiousness vocabulary described or phrase, to obtain viewpoint included in described viewpoint data.
Alternatively, in one of the present embodiment possible implementation, at least one viewpoint described that described matching unit 32 obtains can include but not limited to the first tendentiousness viewpoint and the second tendentiousness viewpoint, and the present embodiment is not particularly limited this.
Alternatively, in one of the present embodiment possible implementation, described output unit 33, specifically may be used for structured form, exports the described viewpoint data corresponding to described target polymerization problem.
It should be noted that, method in the embodiment that Fig. 1 is corresponding, the searcher that can be provided by the present embodiment realizes.Detailed description see the related content in embodiment corresponding to Fig. 1, can repeat no more herein.
In the present embodiment, candidate's aggregation problem of the search Keywords matching obtained with acquiring unit is obtained by matching unit, using as target polymerization problem, and then the viewpoint data obtained corresponding to described target polymerization problem, make output unit can export described viewpoint data corresponding to described target polymerization problem, due to the single content that the resource in original resources bank is no longer all separate, but the viewpoint class problem contained through polymerization and the viewpoint data corresponding to these problems, each Search Results is made to be no longer single content, substantially the real search intention of user can be met, therefore, the problem of the data interaction in prior art because user carries out searching for by application repeatedly between the increase application that causes and search engine can be avoided, thus reduce the processing load of search engine.
In addition, adopt technical scheme provided by the invention, due to the single content that the resource in original resources bank is no longer all separate, but the viewpoint class problem contained through polymerization and the viewpoint data corresponding to these problems, each Search Results is made to be no longer single content, substantially the real search intention of user can be met, therefore, it is possible to effectively improve the validity of Search Results.
In addition, adopt technical scheme provided by the invention, due to the single content that the resource in original resources bank is no longer all separate, but the viewpoint class problem contained through polymerization and the viewpoint data corresponding to these problems, each Search Results is made to be no longer single content, substantially the real search intention of user can be met, therefore, it is possible to effectively improve the efficiency of search.
In addition, adopt technical scheme provided by the invention, by with structured form, export Search Results and the described viewpoint data corresponding to described target polymerization problem, the effect that represents of Search Results can be made to have and give prominence to the key points and content feature clearly, thus effectively improve Consumer's Experience.
Those skilled in the art can be well understood to, and for convenience and simplicity of description, the system of foregoing description, the specific works process of device and unit, with reference to the corresponding process in preceding method embodiment, can not repeat them here.
In several embodiment provided by the present invention, should be understood that, disclosed system, apparatus and method, can realize by another way.Such as, device embodiment described above is only schematic, such as, the division of described unit, be only a kind of logic function to divide, actual can have other dividing mode when realizing, such as multiple unit or assembly can in conjunction with or another system can be integrated into, or some features can be ignored, or do not perform.Another point, shown or discussed coupling each other or direct-coupling or communication connection can be by some interfaces, and the indirect coupling of device or unit or communication connection can be electrical, machinery or other form.
The described unit illustrated as separating component or can may not be and physically separates, and the parts as unit display can be or may not be physical location, namely can be positioned at a place, or also can be distributed in multiple network element.Some or all of unit wherein can be selected according to the actual needs to realize the object of the present embodiment scheme.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, also can be that the independent physics of unit exists, also can two or more unit in a unit integrated.Above-mentioned integrated unit both can adopt the form of hardware to realize, and the form that hardware also can be adopted to add SFU software functional unit realizes.
The above-mentioned integrated unit realized with the form of SFU software functional unit, can be stored in a computer read/write memory medium.Above-mentioned SFU software functional unit is stored in a storage medium, comprising some instructions in order to make a computer equipment (can be personal computer, server, or the network equipment etc.) or processor (processor) perform the part steps of method described in each embodiment of the present invention.And aforesaid storage medium comprises: USB flash disk, portable hard drive, ROM (read-only memory) (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disc or CD etc. various can be program code stored medium.
Last it is noted that above embodiment is only in order to illustrate technical scheme of the present invention, be not intended to limit; Although with reference to previous embodiment to invention has been detailed description, those of ordinary skill in the art is to be understood that: it still can be modified to the technical scheme described in foregoing embodiments, or carries out equivalent replacement to wherein portion of techniques feature; And these amendments or replacement, do not make the essence of appropriate technical solution depart from the spirit and scope of various embodiments of the present invention technical scheme.
Claims (14)
1. a searching method, is characterized in that, comprising:
Obtain search keyword;
Obtain and candidate's aggregation problem of described search Keywords matching, using as target polymerization problem;
Obtain the viewpoint data corresponding to described target polymerization problem;
Export the described viewpoint data corresponding to described target polymerization problem.
2. method according to claim 1, is characterized in that, described viewpoint data comprise at least one item in the statistics of each viewpoint at least one viewpoint and at least one viewpoint described.
3. method according to claim 2, is characterized in that, at least one viewpoint described comprises the first tendentiousness viewpoint and the second tendentiousness viewpoint.
4. method according to claim 2, is characterized in that, the statistics of described each viewpoint, comprises at least one item in following data:
The attribute information of each viewpoint;
The appearance situation of each viewpoint in the answer of the viewpoint class problem corresponding to described target polymerization problem; And
The appearance situation statistical graph of each viewpoint in the answer of the viewpoint class problem corresponding to described target polymerization problem.
5. method according to claim 1, is characterized in that, candidate's aggregation problem of described acquisition and described search Keywords matching, using before target polymerization problem, also comprises:
Problem in resources bank is identified, to obtain viewpoint class problem;
Polymerization process based on semanteme is carried out to described viewpoint class problem, to obtain at least one candidate's aggregation problem;
According to the answer of the viewpoint class problem at least one candidate's aggregation problem described corresponding to each candidate's aggregation problem, obtain the viewpoint data corresponding to described each candidate's aggregation problem.
6. method according to claim 5, is characterized in that, according to the answer of the viewpoint class problem at least one candidate's aggregation problem described corresponding to each candidate's aggregation problem, obtains the viewpoint data corresponding to described each candidate's aggregation problem, comprising:
According to the answer of the viewpoint class problem at least one candidate's aggregation problem described corresponding to each candidate's aggregation problem, obtain at least one candidate's tendentiousness vocabulary or the phrase corresponding to described each candidate's aggregation problem;
Identifying processing is carried out at least one candidate's tendentiousness vocabulary described or phrase, to obtain viewpoint included in described viewpoint data.
7. the method according to the arbitrary claim of claim 1 ~ 6, is characterized in that, the described viewpoint data corresponding to described output described target polymerization problem, comprising:
With structured form, export the described viewpoint data corresponding to described target polymerization problem.
8. a searcher, is characterized in that, comprising:
Acquiring unit, for obtaining search keyword;
Matching unit, for obtaining the candidate's aggregation problem with described search Keywords matching, using as target polymerization problem;
Described matching unit, also for obtaining the viewpoint data corresponding to described target polymerization problem;
Output unit, for exporting the described viewpoint data corresponding to described target polymerization problem.
9. device according to claim 8, is characterized in that, described viewpoint data comprise at least one item in the statistics of each viewpoint at least one viewpoint and at least one viewpoint described.
10. device according to claim 9, is characterized in that, at least one viewpoint described comprises the first tendentiousness viewpoint and the second tendentiousness viewpoint.
11. devices according to claim 9, is characterized in that, the statistics of described each viewpoint, comprise at least one item in following data:
The attribute information of each viewpoint;
The appearance situation of each viewpoint in the answer of the viewpoint class problem corresponding to described target polymerization problem; And
The appearance situation statistical graph of each viewpoint in the answer of the viewpoint class problem corresponding to described target polymerization problem.
12. devices according to claim 8, is characterized in that, described device also comprises excavation unit, for
Problem in resources bank is identified, to obtain viewpoint class problem;
Polymerization process based on semanteme is carried out to described viewpoint class problem, to obtain at least one candidate's aggregation problem; And
According to the answer of the viewpoint class problem at least one candidate's aggregation problem described corresponding to each candidate's aggregation problem, obtain the viewpoint data corresponding to described each candidate's aggregation problem.
13. devices according to claim 12, is characterized in that, described excavation unit, specifically for
According to the answer of the viewpoint class problem at least one candidate's aggregation problem described corresponding to each candidate's aggregation problem, obtain at least one candidate's tendentiousness vocabulary or the phrase corresponding to described each candidate's aggregation problem; And
Identifying processing is carried out at least one candidate's tendentiousness vocabulary described or phrase, to obtain viewpoint included in described viewpoint data.
Device described in 14. according to Claim 8 ~ 13 arbitrary claims, is characterized in that, described output unit, specifically for
With structured form, export the described viewpoint data corresponding to described target polymerization problem.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510245979.3A CN104881446A (en) | 2015-05-14 | 2015-05-14 | Searching method and searching device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510245979.3A CN104881446A (en) | 2015-05-14 | 2015-05-14 | Searching method and searching device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104881446A true CN104881446A (en) | 2015-09-02 |
Family
ID=53948940
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510245979.3A Pending CN104881446A (en) | 2015-05-14 | 2015-05-14 | Searching method and searching device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104881446A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106354036A (en) * | 2016-08-30 | 2017-01-25 | 广东美的制冷设备有限公司 | Household appliance control method and device |
| CN106777236A (en) * | 2016-12-27 | 2017-05-31 | 北京百度网讯科技有限公司 | The exhibiting method and device of the Query Result based on depth question and answer |
| CN107807933A (en) * | 2016-09-09 | 2018-03-16 | 阿里巴巴集团控股有限公司 | A kind of answering method and device for puing question to |
| WO2021129515A1 (en) * | 2019-12-23 | 2021-07-01 | 中兴通讯股份有限公司 | Knowledge graph query method, electronic device, and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040243568A1 (en) * | 2000-08-24 | 2004-12-02 | Hai-Feng Wang | Search engine with natural language-based robust parsing of user query and relevance feedback learning |
| CN103810218A (en) * | 2012-11-14 | 2014-05-21 | 北京百度网讯科技有限公司 | Problem cluster-based automatic asking and answering method and device |
| CN103914543A (en) * | 2014-04-03 | 2014-07-09 | 北京百度网讯科技有限公司 | Search result displaying method and device |
| CN103927381A (en) * | 2014-04-29 | 2014-07-16 | 北京百度网讯科技有限公司 | Right-and-wrong problem processing method and device |
| CN104063497A (en) * | 2014-07-04 | 2014-09-24 | 百度在线网络技术（北京）有限公司 | Viewpoint processing method and device and searching method and device |
| CN104573028A (en) * | 2015-01-14 | 2015-04-29 | 百度在线网络技术（北京）有限公司 | Intelligent question-answer implementing method and system |
-
2015
- 2015-05-14 CN CN201510245979.3A patent/CN104881446A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040243568A1 (en) * | 2000-08-24 | 2004-12-02 | Hai-Feng Wang | Search engine with natural language-based robust parsing of user query and relevance feedback learning |
| CN103810218A (en) * | 2012-11-14 | 2014-05-21 | 北京百度网讯科技有限公司 | Problem cluster-based automatic asking and answering method and device |
| CN103914543A (en) * | 2014-04-03 | 2014-07-09 | 北京百度网讯科技有限公司 | Search result displaying method and device |
| CN103927381A (en) * | 2014-04-29 | 2014-07-16 | 北京百度网讯科技有限公司 | Right-and-wrong problem processing method and device |
| CN104063497A (en) * | 2014-07-04 | 2014-09-24 | 百度在线网络技术（北京）有限公司 | Viewpoint processing method and device and searching method and device |
| CN104573028A (en) * | 2015-01-14 | 2015-04-29 | 百度在线网络技术（北京）有限公司 | Intelligent question-answer implementing method and system |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106354036A (en) * | 2016-08-30 | 2017-01-25 | 广东美的制冷设备有限公司 | Household appliance control method and device |
| CN106354036B (en) * | 2016-08-30 | 2019-04-30 | 广东美的制冷设备有限公司 | Household electric appliance control method and device |
| CN107807933A (en) * | 2016-09-09 | 2018-03-16 | 阿里巴巴集团控股有限公司 | A kind of answering method and device for puing question to |
| CN106777236A (en) * | 2016-12-27 | 2017-05-31 | 北京百度网讯科技有限公司 | The exhibiting method and device of the Query Result based on depth question and answer |
| WO2021129515A1 (en) * | 2019-12-23 | 2021-07-01 | 中兴通讯股份有限公司 | Knowledge graph query method, electronic device, and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109189942B (en) | Construction method and device of patent data knowledge graph | |
| US10095689B2 (en) | Automated ontology building | |
| CN101593200B (en) | Method for classifying Chinese webpages based on keyword frequency analysis | |
| Ding et al. | Entity discovery and assignment for opinion mining applications | |
| CN104376406B (en) | A kind of enterprise innovation resource management and analysis method based on big data | |
| CN113822067A (en) | Key information extraction method and device, computer equipment and storage medium | |
| CN104899322A (en) | Search engine and implementation method thereof | |
| CN107102993B (en) | User appeal analysis method and device | |
| Chawla et al. | Product opinion mining using sentiment analysis on smartphone reviews | |
| CN103136228A (en) | Image search method and image search device | |
| CN103324665A (en) | Hot spot information extraction method and device based on micro-blog | |
| CN104978332B (en) | User-generated content label data generation method, device and correlation technique and device | |
| CN103838756A (en) | Method and device for determining pushed information | |
| CN105843796A (en) | Microblog emotional tendency analysis method and device | |
| CN104881446A (en) | Searching method and searching device | |
| CN110688540B (en) | Cheating account screening method, device, equipment and medium | |
| WO2015084757A1 (en) | Systems and methods for processing data stored in a database | |
| CN114330329A (en) | Service content searching method and device, electronic equipment and storage medium | |
| CN111400436A (en) | Search method and device based on user intention recognition | |
| CN104881447A (en) | Searching method and device | |
| CN111737607B (en) | Data processing method, device, electronic equipment and storage medium | |
| CN114116997A (en) | Knowledge question answering method, knowledge question answering device, electronic equipment and storage medium | |
| US11468236B2 (en) | Method and apparatus for performing word segmentation on text, device, and medium | |
| Wei et al. | Online education recommendation model based on user behavior data analysis | |
| CN113821588A (en) | Text processing method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| EXSB | Decision made by sipo to initiate substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150902 |