WO2006046390A1 - 情報検索装置 - Google Patents
情報検索装置 Download PDFInfo
- Publication number
- WO2006046390A1 WO2006046390A1 PCT/JP2005/018461 JP2005018461W WO2006046390A1 WO 2006046390 A1 WO2006046390 A1 WO 2006046390A1 JP 2005018461 W JP2005018461 W JP 2005018461W WO 2006046390 A1 WO2006046390 A1 WO 2006046390A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- information
- search
- preference
- related word
- search condition
- Prior art date
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
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3325—Reformulation based on results of preceding query
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/3332—Query translation
- G06F16/3338—Query expansion
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y10—TECHNICAL SUBJECTS COVERED BY FORMER USPC
- Y10S—TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y10S707/00—Data processing: database and file management or data structures
- Y10S707/99931—Database or file accessing
- Y10S707/99933—Query processing, i.e. searching
- Y10S707/99934—Query formulation, input preparation, or translation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y10—TECHNICAL SUBJECTS COVERED BY FORMER USPC
- Y10S—TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y10S707/00—Data processing: database and file management or data structures
- Y10S707/99931—Database or file accessing
- Y10S707/99933—Query processing, i.e. searching
- Y10S707/99935—Query augmenting and refining, e.g. inexact access
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y10—TECHNICAL SUBJECTS COVERED BY FORMER USPC
- Y10S—TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y10S707/00—Data processing: database and file management or data structures
- Y10S707/99931—Database or file accessing
- Y10S707/99933—Query processing, i.e. searching
- Y10S707/99936—Pattern matching access
Definitions
- the present invention relates to an information retrieval apparatus that performs information retrieval using an associative dictionary that stores associations between words included in information stored in a database.
- an associative dictionary created in this way for example, when an information search device searches for information using a search keyword and there is no corresponding information, a search is performed using an associative dictionary. A keyword related to the keyword is extracted, and information is searched again by the extracted related keyword.
- an information search device as an input aid for search keywords, a plurality of associative dictionaries in which related words are stored are prepared, and a plurality of associative dictionaries are selected by the user when searching.
- a document processing apparatus that can acquire and display related words related to a keyword input by a user from a selected associative dictionary is disclosed (for example, see Patent Document 1).
- an associative dictionary for each person is constructed, and after entering a search keyword, the search keyword is searched for the associative dictionary for each individual, and the search keyword does not exist in the individual associative dictionary.
- an associative dictionary creation device that acquires related words related to the integrated associative dictionary power search keyword in which all keywords are stored and presents it to the user is disclosed (for example, see Patent Document 2).
- Patent Document 1 JP-A-10-134075
- Patent Document 2 Japanese Patent Laid-Open No. 2000-348042
- a general associative dictionary constructed by calculating the degree of association between performer names existing in program information such as an electronic program guide that is superimposed on a broadcast wave and then broadcast on a TV program!
- program information such as an electronic program guide that is superimposed on a broadcast wave and then broadcast on a TV program.
- the preference association dictionary changes when the user's preference changes. Because the stored performer names are added or deleted, the user cannot know the performer names stored in the preference association dictionary.
- the preference association dictionary is first referred to, and there is an associated performer name that matches the user's preference in the preference association dictionary. After understanding that there is no such thing, the load increases for users who refer to the general associative dictionary and are powerful.
- the associative dictionary creation device that can be separated using the conventional associative dictionary and all keywords stored in the conventional associative dictionary, if the search keyword exists in the individual associative dictionary, Since the personal associative dictionary is always used, the ability to properly use and separate the personal associative dictionary and the integrated associative dictionary according to the scene in consideration of the search context, display content, and search scene. I got it.
- a general associative dictionary storing relations between words existing in program information such as an electronic program guide superimposed on a broadcast wave for an entire TV program, and a user's favorite genre
- a preference association dictionary that stores relationships between words that exist in the program information of other programs
- related words related to words that exist in program information outside the user's favorite genre are displayed.
- the user's favorite genre differs from the target program genre, so an appropriate related word must be obtained. It was difficult.
- the present invention has been made in view of the above circumstances, a preference association dictionary in which words included in accordance with user preferences are dynamically changed, and all key words included in a database. It is an object of the present invention to provide an information retrieval apparatus that can be used by appropriately switching between a general associative dictionary that stores the relationship of the above.
- an information search device is an information search device that searches information that matches a search request from a database in which information to be searched is stored, and stores the information in the database.
- General association dictionary storage means for storing a relationship between a plurality of words included in the recorded information
- a preference association dictionary storage for storing a relationship between a plurality of words reflecting a user's preference for the information stored in the database
- a degree of fitness for calculating the degree of matching between the means and the preference association dictionary feature information indicating the characteristics of the word stored in the preference association dictionary storage means and the input information which is the information input by the user
- at least one of the general associative dictionary storage means and the preference association dictionary storage means based on the fitness, and the selected general association dictionary Search condition generation means for acquiring a related word that is a word related to the input information from at least one of the storage means and the preference association dictionary storage means, and generating a search condition using the acquired related word;
- a search unit that searches the database for information
- the preference association dictionary when acquiring related terms using the preference association dictionary and the general association dictionary in order to expand the search condition for the input information, By calculating the degree of matching between the preference association dictionary feature information indicating the characteristics of the preference association dictionary and the input information, and determining the scene in which the preference association dictionary is used based on the degree of adaptation, the preference association dictionary can be made more appropriate. It can be used in search conditions, search context, display content, and search situations.
- FIG. 1 is a block diagram showing a configuration of an information search apparatus according to Embodiment 1 of the present invention.
- FIG. 2 is a diagram showing an example of a profile used in the information search device according to Embodiment 1 of the present invention.
- FIG. 3 is a diagram showing an example of a general associative dictionary used in the information search apparatus according to Embodiment 1 of the present invention.
- FIG. 4 is a diagram showing an example of a preference association dictionary used in the information search apparatus according to Embodiment 1 of the present invention.
- FIG. 5 is a flowchart showing an operation flow of the information search apparatus according to Embodiment 1 of the present invention.
- FIG. 6 is a diagram showing an example of a profile storing situation keywords and emotion keywords used in the information search device according to Embodiment 1 of the present invention.
- FIG. 7 is a diagram showing an example of information displayed on the display unit of the information search device according to Embodiment 1 of the present invention.
- FIG. 8 is a diagram showing an example of a preference association dictionary in which related values used in the information search apparatus according to Embodiment 1 of the present invention are stored! /.
- FIG. 9 is a diagram showing an example of a table storing the relationship between the degree of matching used in the information search device according to Embodiment 1 of the present invention and the number of acquired related words corresponding thereto.
- FIG. 10 is a diagram showing an example of a general associative dictionary in which related values used in the information search device according to Embodiment 1 of the present invention are stored.
- FIG. 11 is a diagram showing an example of a table storing the relationship between the degree of matching used in the information search device according to Embodiment 1 of the present invention and the number of acquired related words corresponding thereto.
- FIG. 12 is a block diagram showing a configuration of an information search apparatus according to Embodiment 2 of the present invention.
- FIG. 13 is a diagram showing an example of a preference association dictionary used in the information search device according to Embodiment 2 of the present invention.
- FIG. 14 is a diagram showing an example of a general associative dictionary used in the information search device according to Embodiment 2 of the present invention.
- FIG. 15 is a flowchart showing a flow of operation of the information search device according to Embodiment 2 of the present invention.
- FIG. 16 is a diagram showing an example of the contents of an acquired word storage unit used in the information search device according to Embodiment 2 of the present invention.
- FIG. 17 is a diagram showing an example of the contents of an acquired word storage unit used in the information search device according to Embodiment 2 of the present invention.
- An information search apparatus is an information search apparatus that searches information that matches a search request from a database in which information to be searched is stored, and is stored in the database.
- a general associative dictionary storage unit that stores a relationship between a plurality of words included in information
- a preference association dictionary storage unit that stores a relationship between a plurality of words that reflects a user's preference with respect to information stored in the database
- a related word that is a word related to the input information based on the degree of matching calculated by the degree of matching calculating means from at least one of the degree of calculating means, the general association dictionary storing means, and the preference association dictionary storing means
- Search condition generation means for generating a search condition using the acquired related word
- search means for searching for information that matches the search condition generated by the search condition generated by the search condition
- the goodness-of-fit calculation means may use a profile that is information relating to user preferences as the preference association dictionary feature information.
- the preference association dictionary that reflects the user's preferences has the same characteristics as the profile, which is information about the user's preferences, and therefore, the fitness is easily calculated based on the profile. can do.
- the goodness-of-fit calculation means may use a word that is stored in the preference association dictionary storage means as the preference association dictionary feature information.
- the general association dictionary and the preference association dictionary according to input information. And can be used by switching more appropriately.
- the goodness-of-fit calculation means may use information searched in advance by the search means as the input information.
- the general associative dictionary is considered in consideration of the search result displayed last time. It is possible to switch the preference association dictionary appropriately and use it, and if the search result matches the preference association dictionary, it is possible to obtain a related term adapted to the user as a related term.
- the search condition generation unit selects the general association dictionary storage unit or the preference association dictionary storage unit based on the magnitude of the fitness value, and the selected general association dictionary storage unit or Even if the related word is acquired from the preference association dictionary storage means Good.
- the search condition generation means may acquire a quantity of the related words according to the magnitude of the fitness value.
- the search condition generation unit may acquire a quantity of the related words corresponding to the magnitude of the fitness value from the preference association dictionary storage unit and the general association dictionary storage unit, respectively. Yo ⁇ .
- the information search device is an information search device that searches information that matches a search request from a database in which information to be searched is stored, and stores the information in the database.
- a general associative dictionary storage means for storing a relationship between a plurality of words included in the recorded information, and a relationship indicating a degree of relevance between the relationships between the plurality of words reflecting the user's preference for the information stored in the database
- a preference association dictionary storage unit that stores the value together with a value, and a related word that is a word related to the input information that is information input by the user.
- the association value is predetermined for the input information from the preference association dictionary storage unit.
- the predetermined threshold value is set to a predetermined value.
- a search condition is generated using the unacquired related word, and the unacquired related word is determined. If a related word is acquired and determined to be, the search condition generating means for generating a search condition using the related word acquired by the general related word acquiring means, and the database from the database Generated by search condition generation means It is characterized in further comprising a retrieval means for retrieving information that matches the search criteria.
- the general associative dictionary storage unit stores a relationship between a plurality of words included in the information stored in the database together with a related value indicating a degree of association
- the general related word acquisition unit includes the A word having a related value greater than or equal to a predetermined threshold for the input information is acquired as a related word from the general associative dictionary storage means, and the related word is acquired for the second time or more for the same input information. In some cases, lower the predetermined threshold by a predetermined value.
- the program information search device is a program information search device for searching program information that matches a database power search request in which program information to be searched is stored,
- General associative dictionary storage means for storing a relationship between a plurality of words included in program information stored in a database, and a relationship between a plurality of words reflecting a user's preference with respect to program information stored in the database
- a preference association dictionary storage means that stores the preference association dictionary feature information indicating the characteristics of the words that are stored in the preference association dictionary storage means and the input information that is input by the user. Is calculated by the fitness calculation means from at least one of the fitness calculation means for calculating the standard association dictionary storage means and the preference association dictionary storage means.
- a search condition generation unit that acquires a related word that is a word related to the input information based on the degree of matching, and generates a search condition using the acquired related word, and a search condition generation unit that generates the search condition from the database. And a search means for searching for program information that matches the generated search conditions.
- the present invention can be realized as an information search method that can be realized as such an information search device, and has a characteristic means included in an information search device such as NAGKO as a step. It can also be realized as a program that causes a computer to execute steps. Needless to say, such a program can be distributed via a recording medium such as a CD-ROM or a transmission medium such as the Internet.
- FIG. 1 is a block diagram showing a configuration of an information search device according to Embodiment 1 of the present invention.
- This information search device is a device for searching information that matches a search request from a database in which information to be searched is stored using a related word.
- the information search device includes an input unit 101 and a profile storage unit 102.
- the input unit 101 includes input devices such as a keyboard, a mouse, and a remote controller, and a user inputs search conditions and input data including a search keyword.
- the profile storage unit 102 stores, for each user, a profile that is information relating to user preferences.
- the profile includes, for example, the genre to which the user's favorite content belongs, favorite performer, viewing time, etc., and indicates the degree of preference associated with each data (genre, performer, viewing time, etc.) Stores weight values and so on.
- FIG. 2 is a diagram illustrating an example of a profile stored in the profile storage unit 102.
- a label indicating the type of data, data, and a weight value indicating the user's preference for the data are stored in association with each other.
- FIG. Label, Data, Weight
- the content storage unit 105 stores, for example, information related to a television broadcast program, information related to content stored in a node disc recorder, and the like.
- the general associative dictionary storage unit 103 stores a general associative dictionary that is included in the information stored in the content storage unit 105 and indicates the relationship between a plurality of words.
- the general associative dictionary for example, related words, which are a plurality of related words, are stored in pairs.
- FIG. 3 is a diagram illustrating an example of a general associative dictionary stored in the general associative dictionary storage unit 103.
- the general association dictionary as shown in Fig.
- the preference association dictionary storage unit 104 includes a preference association dictionary that indicates a relationship between words that reflects user preferences for a plurality of words included in the information stored in the content storage unit 105. I remember it.
- the preference association dictionary for example, words such as a genre, a person name, a broadcast time, etc. extracted from information about a TV broadcast program viewed by a user included in a profile are stored in the content storage unit 105. The related words in the information are stored in pairs.
- the words included in the profile are extracted from the information related to the TV broadcast program viewed by the user, but the favorite genre, personal name, and broadcast time directly input by the user may be included in the profile. .
- the preference association dictionary 4 is a diagram showing an example of a preference association dictionary stored in the preference association dictionary storage unit 104.
- the preference association dictionary stores (Drama, Taro Matsushita, Hanako Matsushita) and (Taro Matsushita, Ichiro Matsushita) as pairs of preference association dictionary related words as shown in FIG.
- the goodness-of-fit calculation unit 106 calculates the goodness of fit between the search condition input from the input unit 101 and the preference association dictionary stored in the preference association dictionary storage unit 104.
- the search keyword included in the search condition is used as input information
- the preference association dictionary is created based on the profile stored in the profile storage unit 102
- the profile is a word stored in the preference association dictionary.
- This is used as the feature association dictionary feature information indicating the features of the. Therefore, the fitness level calculation unit 106 calculates the fitness level between the search keyword included in the search condition and the profile stored in the profile storage unit 102. That is, the fitness calculation unit 106 searches for a profile using a search keyword included in the input search condition, and adds a weight value added to the search keyword and added to the search keyword. Calculated as fitness.
- a search keyword included in the search condition input from the input unit 101 is used, and as an example, this input includes designation, for example.
- the search condition generation unit 107 based on the fitness calculated by the fitness calculation unit 106, stores a general association dictionary or preference association dictionary stored in the general association dictionary storage unit 103.
- the preference association dictionary stored in the unit 104 is selected, and related terms related to the search keyword are acquired from the selected general association dictionary or preference association dictionary, and a search condition is generated.
- the search condition generation unit 107 acquires a related word from the general association dictionary when the goodness degree calculated by the goodness degree calculation unit 106 is smaller than a predetermined threshold value, and the goodness degree is higher than the predetermined threshold value. If it is too big, get related words from the preference association dictionary.
- the search unit 108 acquires information matching the search condition generated by the search condition generation unit 107 from the content storage unit 105, and outputs it as a search result.
- FIG. 5 is a flowchart showing an operation flow of the information search apparatus.
- the fitness level calculation unit 106 accepts this search condition (step S101).
- this search condition “I want to see Taro Matsushita's drama” from the input section 101 and when I input “I saw Taro Matsushita's variety”.
- the goodness-of-fit calculation unit 106 calculates the goodness-of-fit between the received search condition and the profile stored in the profile storage unit 102 (step S102). That is, the suitability calculation unit 106 also extracts the search keyword from the search condition power input from the input unit 101, and if the search keyword exists in the profile stored in the profile storage unit 102, the weight for the search keyword By adding the values, the degree of fitness between the search condition and the profile is calculated.
- the search condition in the above example is “Taro Matsushita's Drama”
- the fitness calculation unit 106 extracts the search keyword “Taro Matsushita, Drama” and stores it in the profile.
- the weight value “80” of “Taro Matsushita” and the weight value “80” of “Drama” are added to calculate “160” as the fitness.
- the fitness calculation unit 106 extracts the search keyword “Taro Matsushita, Variety”, and stores it in the profile. Based on the weight value “80” of “Taro Matsushita”, “80” is calculated as the fitness.
- the search condition generation unit 107 determines whether the fitness level calculated by the fitness level calculation unit 106 is greater than a predetermined threshold value (step S103).
- the search condition generation unit 107 stores the general associative dictionary storage unit 103.
- a general associative dictionary to be stored is selected, related words related to the search keyword included in the search condition are acquired from the selected general associative dictionary (step S104), and a search condition is generated (step S106).
- the search condition generation unit 107 selects the preference association dictionary stored in the preference association dictionary storage unit 104 and selects the selected preference association.
- a related term related to the search keyword included in the search condition is acquired from the dictionary (step S105), and a search condition is generated (step S106).
- the search condition in the above example is “I want to see the variety of Taro Matsushita”
- the relevance for the search keyword “Taro Matsushita, Variety” calculated by the relevance calculation unit 106 is “80”.
- the search condition generation unit 107 determines that it is equal to or less than a predetermined threshold value (here, as an example, the predetermined threshold value is “100”).
- the search condition generation unit 107 uses the general association dictionary power stored in the general association dictionary storage unit 103 as well as related words “drama, Hanako Matsushita, Goro Matsushita, Jiro Matsushita, Manji” of the search keyword “Taro Matsushita, Variety”. Acquired and the acquired related terms and search keywords are output as search conditions.
- the search condition in the above example is “I want to watch Taro Matsushita's drama”
- the fitness for the search keyword “Taro Matsushita, Drama” calculated by the fitness calculation unit 106 is “160 Therefore, the search condition generation unit 107 determines that the value is larger than the predetermined threshold “100”.
- the search condition generation unit 107 acquires the related words “Matsushita Hanako, Ichiro Matsushita” of the search keyword “Taro Matsushita, Drama” and the related words acquired in the preference association dictionary power stored in the preference association dictionary storage unit 104. And the search keyword are output as search conditions.
- the search unit 108 acquires information that matches the search condition generated by the search condition generation unit 107 from the content storage unit 105 and sets it as a search result (step S107).
- the search condition in the above example is “I want to see the variety of Taro Matsushita”
- the search unit 108 generates the search conditions “Taro Matsushita, Drama, Hanako Matsushita, Goro Matsushita, Information including any of the keywords “Noraeti, Jiro Matsushita, Manzai” is acquired from the content storage unit 105 and used as a search result.
- the search unit 108 searches for any keyword of the search conditions “Taro Matsushita, Drama, Hanako Matsushita, Ichiro Matsushita”. Is acquired from the content storage unit 105 and used as a search result.
- the fitness level calculation unit 106 calculates the fitness level between the search condition input from the input unit 101 and the profile stored in the profile storage unit 102. Instead, it may be stored in the preference association dictionary storage unit 104, and the fitness may be calculated using the preference association dictionary.
- the search keyword “Goro Matsushita, historical drama” is extracted from the search condition, and the preference association dictionary storage unit If more than a predetermined number of related terms of the search keyword “Matsushita Goro, historical drama” are obtained from the preference association dictionary stored in 104, the acquired related terms and search keywords are output to the search unit 108 as search conditions. If the number of related words is less than or equal to the predetermined number, the related words are acquired from the general associative dictionary stored in the general associative dictionary storage unit 103, and the acquired related words and search keywords are output to the search unit 108 as search conditions. .
- the number of related words of the search keyword “Matsushita Goro, historical drama” that also acquires the preference association dictionary power is “0”. For example, if the predetermined number is 4, the general association dictionary will be less than the predetermined number. Also related to the search keyword "Goro Matsushita, historical drama"
- “Drama, Taro Matsushita, Hanako Matsushita, Ichiro Matsushita” is acquired, and the acquired related terms and search keyword are output to the search unit 108 as search conditions.
- the general association dictionary and preference association dictionary can be more automatically automatically matched to the search conditions even on devices that do not have profiles, such as devices that allow users to manually edit and create preference association dictionaries. It can be switched for use.
- the fitness level calculation unit 106 calculates the fitness level between the search keyword included in the search condition input from the input unit 101 and the profile stored in the profile storage unit 102.
- the user status and emotion keywords can be input from the input unit 101. You may make it calculate the compatibility with the profile and emotional keyword etc. which the user input.
- FIG. 6 is a diagram showing an example of a profile storing situation keywords and emotion keywords.
- a situation keyword, an emotion keyword, a label indicating the type of data, data, and a weight value indicating the degree of user preference for the data are stored in association with each other. ing.
- the fitness calculation unit 106 selects the emotion keyword “fun” and the search keyword from the search condition.
- the general association dictionary and preference association dictionary can be automatically switched and used in a more appropriate situation according to the user's situation and emotion, and related words that match the user's situation and emotion can be acquired. can do.
- the fitness level calculation unit 106 calculates the fitness level between the search condition input from the input unit 101 and the profile stored in the profile storage unit 102.
- the information search device Further, a display unit 301 may be provided, and when content is displayed on the display unit 301, the degree of matching between the content and the profile may be calculated.
- FIG. 7 is a diagram illustrating an example of information displayed on the display unit.
- the user selects “Other Taro Matsushita's program as a search condition from the input unit 101.
- the goodness-of-fit calculation unit 106 extracts the search keyword “Taro Matsushita” from the search conditions, and then displays it on the display unit 301 to indicate the content feature in the information.
- the goodness-of-fit calculation unit 106 calculates the goodness of fit “160” between the extracted word “Taro Matsushita, Drama” and the profile shown in FIG. 3, and the calculated goodness of fit “160” and the search keyword “Taro Matsushita To the search condition generation unit 107.
- the general associative dictionary and the preference association are considered in consideration of the previously displayed search results. It is possible to automatically switch between dictionaries and use them, and when the displayed content matches the preference association dictionary, it is possible to acquire related words adapted to the user as related words.
- the search condition generation unit 107 also has a general association dictionary stored in the general association dictionary storage unit 103 or a preference association dictionary stored in the preference association dictionary storage unit 104. Function related to the search keyword included in the search condition entered from the input unit 101 If all the collocations are acquired, but the general association dictionary and the preference association dictionary define the degree of association between related terms in the respective dictionaries, the related value is calculated from the related terms related to the search keyword. Let's get only related words.
- FIG. 8 is a diagram illustrating an example of a preference association dictionary in which related values are stored.
- the goodness of fit “160” and the search keyword “Taro Matsushita, Drama” are input from the goodness of fit calculation unit 106, the goodness of fit “160” is set to a predetermined threshold value. It is determined that the value is larger than “100”, and a predetermined number of related words are stored in the preference association dictionary stored in the preference association dictionary storage unit 104 shown in FIG. (It is also possible to use related terms with a predetermined weight value or more.) Acquire “Ichiro Matsushita, Jiro Matsushita, Saburo Matsushita” and output the acquired related terms and search keywords as search conditions. By doing so, it is possible to improve the accuracy with respect to the degree of association of the acquired related words.
- the search condition generation unit 107 relates to the search keyword included in the search condition input from the input unit 101 from the preference association dictionary stored in the preference association dictionary storage unit 104.
- the related degree of the related words in the preference association dictionary is defined as a related value, it is calculated by the fitness level calculation unit 106. It is possible to obtain a number of related terms that are proportional to the degree of goodness from the preference association dictionary in descending order of relevance.
- the search condition generator 107 sets the suitability “160” to a predetermined threshold. If it is determined that the degree of matching with the preference association dictionary is higher than the value “100” and the degree of matching is high, a predetermined number of related words are retrieved from the preference association dictionary shown in FIG. 8 stored in the preference association dictionary storage unit 104. (Here, as an example, refer to a table that stores the degree of goodness and the number of related words obtained from the preference association dictionary as shown in Fig. 9 (in this example, from the one with the largest weight value). ) Or a related term that is more than the weight value inversely proportional to the goodness of fit.) Acquire “Ichiro Matsushita, Jiro Matsushita, Saburo Matsushita”.
- the search condition generation unit 107 has a fitness level 110 greater than a predetermined threshold 100! ⁇ is judged to have a low relevance to the preference association dictionary, and the relevance is low! .
- the preference association dictionary power shown in Fig. 8 Predetermined number of related words (Here, as an example, a table storing the number of related words obtained from the general association dictionary corresponding to the goodness as shown in Fig. 9 is shown. Get “Ichiro Matsushita” by referring (here, one from the largest weight value) or as a related term that is more than the weight value inversely proportional to the fitness.
- the search condition generation unit 107 stores the general association dictionary stored in the general association dictionary storage unit 103 or the preference association dictionary stored in the preference association dictionary storage unit 104.
- the related word related to the search keyword included in the search condition entered from the input unit 101 was acquired, but the fitness calculated by the fitness level calculation unit 106 from both the general association dictionary and the preference association dictionary You may make it acquire the related word of the quantity according to a degree.
- the search condition generator 107 determines that the fitness for the preference association dictionary is high. If the fitness level is high, the preference association dictionary power shown in Fig. 8 is stored in the preference association dictionary storage unit 104 and a predetermined number of related words (here, the fitness level shown in Fig.
- the search condition generation unit 107 has a general association dictionary capability stored in the general association dictionary storage unit 103 as shown in FIG. And the number of related words acquired from the corresponding general associative dictionary (refer to here one from the one with the largest weight value) or acquired by the search condition generation unit 107 The total number of related words is determined in advance, and the total power can be any number excluding the total number of related words acquired from the preference association dictionary.
- the search condition generation unit 107 determines that the fitness level for the preference association dictionary is low. If the degree of goodness is low, the preference association dictionary power shown in Fig. 8 has a predetermined number of related words (in this example, the degree of goodness as shown in Fig. 9 and the number of related words obtained from the preference association dictionary corresponding to it) Get “Ichiro Matsushita” by referring to the table to be stored (one from the largest weight value) or more than the weight value inversely proportional to the fitness.
- the search condition generation unit 107 also has a general association dictionary power as shown in FIG. 10 and a predetermined number of related words (in this example, the related words acquired from the matching degree shown in FIG. 11 and the corresponding general association dictionary as an example.
- a predetermined number of related words in this example, the related words acquired from the matching degree shown in FIG. 11 and the corresponding general association dictionary as an example.
- the search condition generation unit 107 determines the total number of related words (This number may be the number obtained by removing the total number of related words acquired by the association dictionary.) Acquire “Rokuro Matsushita, Goro Matsushita”.
- the content stored in content storage section 105 is content stored in a node disc recorder or the like regarding information relating to a television broadcast program, but is not limited to this. It may also include information on WEB pages and contents on the Internet.
- the fitness level calculation unit 106 adds the weight value included in the profile when calculating the fitness level between the search condition and the profile stored in the profile storage unit 102.
- the weight value for the search keyword included in the search condition is obtained as a vector, and the inner product value with the vector obtained from the profile Any method can be used that can calculate the distance between the search condition and the profile that can be used as the goodness of fit.
- the distance is used as the matching degree between the search condition and the profile, the smaller the matching degree is, the more the search condition and the profile are matched.
- the fitness is less than a predetermined threshold, the related word is acquired from the preference association dictionary, and when the fitness is greater than the predetermined threshold, the general association dictionary power related word is acquired.
- the search condition generation unit 107 acquires a related word and generates a search condition.
- the information search apparatus further includes a display unit, and the search condition generation unit 107 acquires the related function. You may make it display a collocation word on a display part, make a user select a related word, and produce
- the preference association dictionary and the general association dictionary are used to expand the search condition for the search keyword
- the feature of the preference association dictionary is expressed.
- the preference association dictionary is calculated by calculating the degree of fit between the preference association dictionary feature information and the features of the search conditions, display content, and information about the scene of the search, and determining the scene to use the preference association dictionary based on this suitability. It can be used in more appropriate search conditions, search contexts, display contents, and search situations.
- FIG. 12 is a block diagram showing the configuration of the information search apparatus according to Embodiment 2 of the present invention. Note that portions similar to those in Embodiment 1 are denoted by the same reference numerals, and detailed description thereof is omitted.
- the information search apparatus is an apparatus for searching for information that matches a database force search request in which information to be searched is stored using related terms.
- the preference association dictionary storage unit 201 includes a preference association dictionary indicating a relationship between words that reflects user preferences for a plurality of words included in the information stored in the content storage unit 105. I remember it.
- a related word pair (related word 1, related word 2) that is a pair of related words and a related value that represents the degree of related word pair are stored in association with each other.
- FIG. 13 is a diagram showing an example of a preference association dictionary stored in the preference association dictionary storage unit 201. As shown in FIG.
- the preference association dictionary contains ( ((Jiro Matsushita, Taro Matsushita), 80), ((Drama, Hanako Matsushita), 70), ((Taro Matsushita, Hanako Matsushita), 50) are stored as collocation pairs and related values.
- the higher the relation value the higher the degree of relation.
- the acquired word storage unit 202 stores related words acquired by the unacquired related word determination unit 205.
- the general associative dictionary storage unit 203 stores a general associative dictionary that is included in the information stored in the content storage unit 105 and indicates the relationship between a plurality of words.
- a related word pair (related word 1 and related word 2) in which related words are paired and a related value indicating the degree of related word pair are stored in association with each other.
- FIG. 14 is a diagram illustrating an example of a general association dictionary stored in the general association dictionary storage unit 203.
- FIG. 14 ((Taro Matsushita, Ichiro Matsushita), 80), ((Variety, Ichiro Matsushita), 70), ( (Variety, comics), 90), ... are stored.
- the preference related word acquisition unit 204 selects a related word associated with a search keyword included in the search condition and a related value equal to or greater than a predetermined threshold value as a preference association dictionary. Obtained from the preference association dictionary stored in the storage unit 201. In addition, when a search condition expansion command is input from the input unit 101, the preference related word acquisition unit 204 lowers a predetermined threshold value and associates the search keyword included in the search condition with a related value equal to or higher than the reduced threshold value. The obtained related words are acquired from the preference association dictionary stored in the preference association dictionary storage unit 201.
- the unacquired related word determination unit 205 When the search condition is input from the input unit 101, the unacquired related word determination unit 205 initializes the acquired word storage unit 202 and acquires the related word acquired by the preference related word acquisition unit 204. The related words are stored in the word storage unit 202 and further output to the search unit 207. The unacquired related word determination unit 205 also stores the related word acquired by the preference related word acquisition unit 204 in the acquired word storage unit 202 when the search condition extension command is input from the input unit 101. Judge the force that is. When the related word is not stored, the acquired related word determination unit 205 additionally stores the related word in the acquired word storage unit 202 and further outputs the related word to the search unit 2007. If stored, the general related word acquisition unit 206 has an input unit 1 The search keyword included in the search condition input from 01 is output.
- the general related word acquisition unit 206 receives the general associative dictionary power search keyword stored in the general associative dictionary storage unit 203 and the association with a predetermined threshold or more.
- the related word associated with the value is acquired, and the acquired related word is output to the search unit 207.
- the general related word acquisition unit 206 lowers the predetermined threshold to reduce the search keyword included in the search condition when the search keyword to which the unacquired related word determination unit 205 is also input is the second time or more.
- a related word associated with a related value greater than or equal to the threshold is acquired from the general associative dictionary stored in the general associative dictionary storage unit 203.
- the search unit 207 When a related word is input from the unacquired related word determining unit 205 or the general related word acquiring unit 206, the search unit 207 generates a search condition from the input related word, and the generated search condition The matched information is acquired from the content storage unit 105 and used as a search result.
- FIG. 15 is a flowchart showing an operation flow of the information search apparatus.
- the preference related word acquisition unit 204 receives the search condition or the search condition expansion command (step S201).
- the preference-related word acquisition unit 204 determines whether the received search condition or search condition extension command is a force search condition extension command that is a search condition (step S202). If the result of this determination is a search condition (YES in step S202), the preference related word acquisition unit 204 associates the search keyword included in the search condition with a related value that is equal to or greater than a predetermined threshold for the preference association dictionary.
- the related words are acquired from the preference association dictionary stored in the preference association dictionary storage unit 201 (step S203). As a specific example, a case where the user inputs the search condition “Taro Matsushita” from the input unit 101 will be described.
- the preference-related word acquisition unit 204 and the search keyword “Taro Matsushita” included in the search condition “Taro Matsushita” input from the input unit 101 and a predetermined threshold (in this example, a predetermined threshold is used as an example).
- the related word “Jiro Matsushita” associated with the above related values is acquired from the preference association dictionary stored in the preference association dictionary storage unit 201.
- the unacquired related word determination unit 205 initializes the acquired word storage unit 202 (step S 204), the related word acquired by the preference related word acquisition unit 204 is stored in the acquired word storage unit 202 (step S205), and the related word is output to the search unit 207.
- the unacquired related word determination unit 205 initializes the acquired word storage unit 202, stores the related word “Jiro Matsushita” acquired by the preference related word acquisition unit 204 in the acquired word storage unit 202, Further, the related word is output to the search unit 207.
- FIG. 16 is a diagram illustrating the contents of the acquired word storage unit 202 when the related word “Jiro Matsushita” is stored.
- the search unit 207 when a related word is input from the unacquired related word determination unit 205, the search unit 207 generates a search condition from the input related word, and stores information that matches the generated search condition as content. Obtained from the storage unit 105 and used as a search result (step S213).
- the search unit 20 7 when the related word “Jiro Matsushita” is input from the unacquired related word determination unit 205, the search unit 20 7 generates the search condition “Jiro Matsushita” from the input related word “Jiro Matsushita”.
- Information including the keyword of the search condition “Jiro Matsushita” is acquired from the content storage unit 105 and used as a search result.
- the preference related word acquisition unit 204 lowers a predetermined threshold for the preference association dictionary (step S 2 06). . Then, the preference related word acquisition unit 204 acquires a related word associated with the search keyword included in the search condition with a related value equal to or higher than the lowered threshold from the preference association dictionary stored in the preference association dictionary storage unit 201 (step S207).
- a search condition extension command is input after the search condition “Taro Matsushita” is input from the input unit 101 by the user.
- the preference related word acquisition unit 204 lowers the threshold “60” to the threshold “50” (here, as an example, the threshold decrease range is “10”).
- the preference association dictionary power stored in the preference association dictionary storage unit 201 is also related to the search keyword “Taro Matsushita” included in the search condition “Taro Matsushita” and the related word “Jiro Matsushita” , Hanako Matsushita ". Also, here, related words above the threshold are acquired, but the number of related words to be acquired may be increased in descending order of related values.
- the unacquired related word determination unit 205 determines whether the related word acquired by the preference related word acquisition unit 204 is already stored in the acquired word storage unit 202 (step S 208). If the result of this determination is not stored, that is, if an unacquired related word can be acquired In step S208 (YES), the unacquired related word determination unit 205 additionally stores this related word in the acquired word storage unit 202 (step S209), and further outputs this related word to the search unit 207.
- the unacquired related word determination unit 205 stores the related word “Hanako Matsushita” in the acquired word storage unit 202 among the related words “Jiro Matsushita and Hanako Matsushita” acquired by the preference related word acquisition unit 204.
- the related word “Hanako Matsushita” is additionally stored in the acquired word storage unit 202, and the related word “Hanako Matsushita” is further output to the search unit 207.
- FIG. 17 is a diagram showing the contents of the acquired word storage unit 202 when the related word “Hanako Matsushita” is stored.
- the search unit 207 when a related word is input from the unacquired related word determination unit 205, the search unit 207 generates a search condition from the input related word, and stores information that matches the generated search condition as content. Obtained from the storage unit 105 and used as a search result (step S213).
- the search unit 20 7 when the related word “Hanako Matsushita” is input from the unacquired related word determination unit 205, the search unit 20 7 generates the search condition “Hanako Matsushita” from the input related word “Hanako Matsushita”. Then, information including the keyword of the search condition “Hanako Matsushita” is obtained from the content storage unit 105 and used as a search result.
- the detection input from the input unit 101 is performed.
- the search keyword included in the search condition is output to the general related word acquisition unit 206.
- the general related word acquisition unit 206 determines whether the search keyword is input from the unacquired related word determination unit 205 for the first time. (Step S210).
- the general associated word acquisition unit 206 searches the general associative dictionary stored in the general associative dictionary storage unit 203 for a search keyword and a predetermined threshold value for the general associative dictionary.
- the related word associated with the related value is acquired (step S212), and the acquired related word is output to the search unit 207. If it is not the first time (NO in step S210), the general related word acquiring unit 206 decreases the predetermined threshold for the general associative dictionary (step S211).
- the general related word acquisition unit 206 also acquires the general association dictionary power stored in the general association dictionary storage unit 203 for the related terms associated with the search keyword included in the search condition and the related value equal to or higher than the lowered threshold ( In step S212), the acquired related terms are output to the search unit 207.
- search unit 207 is input.
- a search condition is generated from the related terms, and information that matches the generated search condition is acquired from the content storage unit 105 and used as a search result (step S213).
- the search condition “Taro Matsushita” is input from the input unit 101 by the user and then the second search condition expansion instruction is input.
- the search condition expansion command is input from the input unit 101
- the preference related word acquisition unit 204 lowers the threshold value 50 to the threshold value 40, and searches the search condition “Taro Matsushita from the preference association dictionary stored in the preference association dictionary storage unit 201.
- the unacquired related word determination unit 205 determines that the related words “Jiro Matsushita and Hanako Matsushita” acquired by the preference related word acquisition unit 204 are already stored in the acquired word storage unit 202, and inputs The search keyword “Taro Matsushita” included in the search condition “Taro Matsushita” input from the section 101 is output to the general related word acquisition section 206.
- the general related word acquisition unit 206 searches from the general association dictionary stored in the general association dictionary storage unit 203.
- the related word “Ichiro Matsushita” associated with the keyword “Taro Matsushita” and a related value greater than or equal to a predetermined threshold (in this example, the predetermined threshold is 80) is acquired, and the acquired related word “Ichiro Matsushita” is acquired.
- a predetermined threshold in this example, the predetermined threshold is 80
- the search unit 207 When the related word “Ichiro Matsushita” is human-powered from the general related word acquisition unit 206, the search unit 207 generates the search condition “Ichiro Matsushita” from the related word “Matsushita Ichiro” and the search condition “Ichiro Matsushita” The information including the keyword “is acquired from the content storage unit 105 and used as a search result.
- the general related word acquisition unit 206 acquires the related words related to the search keyword for which the unacquired related word determination unit 205 is also input from the general associative dictionary storage unit 203.
- the related words stored in the acquired word storage unit 202 are excluded from the related words acquired from the general associative dictionary storage unit 203, and only the remaining related words are searched. You may make it output to 207. By doing this, it is not necessary to search for related terms that have already been searched, and it is not necessary to present the user with duplicate search results searched with the same related terms.
- the content stored in content storage section 105 is a television set.
- Information related to broadcast programs is assumed to be content stored in a node disc recorder or the like. However, it is not limited to this, and information on WEB pages and content on the Internet may be included.
- the search unit 207 acquires related words and generates search conditions.
- the information search apparatus further includes a display unit, and the search unit 207 displays the acquired related words in the display unit. The user may be prompted to select a related word and generate a search condition using the related word selected by the user. In this way, the user can search for information by specifying related terms.
- the general association dictionary is used. Related words can be acquired using.
- the general association dictionary storage unit 103 is a general association dictionary storage unit
- the preference association dictionary storage unit 104 is a preference association dictionary storage unit.
- 106 corresponds to the fitness calculation means
- the search condition generation unit 107 corresponds to the search condition generation means
- the search unit 108 corresponds to the search means.
- the preference association dictionary storage unit 201 is a preference association dictionary storage unit
- the general association dictionary storage unit 203 is a general association dictionary storage unit
- a preference related word acquisition unit 204 is As a preference related word acquisition means
- an unacquired related word determination unit 205 is an unacquired related word determination means
- a general related word acquisition unit 206 is a general related word acquisition means
- a search unit 207 is a search condition generation means and a search means, Each corresponds.
- the information retrieval apparatus can use the preference association dictionary in more appropriate search conditions, search contexts, display contents, and search scenes. It is useful as a terminal that can access hard disk recorders, DVD recorders, TVs, audio components, and the Internet to search for information.
Abstract
Description
Claims
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2006542316A JP4008954B2 (ja) | 2004-10-29 | 2005-10-05 | 情報検索装置 |
US11/385,751 US7725486B2 (en) | 2004-10-29 | 2006-03-22 | Information retrieval apparatus |
US11/434,761 US7483921B2 (en) | 2004-10-29 | 2006-05-17 | Information retrieval apparatus |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2004315483 | 2004-10-29 | ||
JP2004-315483 | 2004-10-29 |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US11/385,751 Continuation US7725486B2 (en) | 2004-10-29 | 2006-03-22 | Information retrieval apparatus |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2006046390A1 true WO2006046390A1 (ja) | 2006-05-04 |
Family
ID=36227634
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2005/018461 WO2006046390A1 (ja) | 2004-10-29 | 2005-10-05 | 情報検索装置 |
Country Status (4)
Country | Link |
---|---|
US (2) | US7725486B2 (ja) |
JP (1) | JP4008954B2 (ja) |
CN (1) | CN100550014C (ja) |
WO (1) | WO2006046390A1 (ja) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2008071198A (ja) * | 2006-09-14 | 2008-03-27 | Ricoh Co Ltd | 文書検索装置、文書検索方法、文書検索プログラムおよび記録媒体 |
JP2009140306A (ja) * | 2007-12-07 | 2009-06-25 | Toshiba Corp | 情報提供サーバおよび情報提供方法 |
WO2009104387A1 (ja) * | 2008-02-20 | 2009-08-27 | パナソニック株式会社 | 対話型番組検索装置 |
JP4464463B2 (ja) * | 2007-08-03 | 2010-05-19 | パナソニック株式会社 | 関連語提示装置 |
CN102231147A (zh) * | 2010-11-08 | 2011-11-02 | 百度在线网络技术(北京)有限公司 | 一种用于实时展现联想词的方法、设备及系统 |
WO2017061037A1 (ja) * | 2015-10-09 | 2017-04-13 | 楽天株式会社 | 情報処理装置、情報処理方法及び情報処理プログラム |
Families Citing this family (30)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN100454303C (zh) * | 2005-01-07 | 2009-01-21 | 松下电器产业株式会社 | 联想辞典制作装置 |
US7788266B2 (en) | 2005-08-26 | 2010-08-31 | Veveo, Inc. | Method and system for processing ambiguous, multi-term search queries |
US7774341B2 (en) | 2006-03-06 | 2010-08-10 | Veveo, Inc. | Methods and systems for selecting and presenting content based on dynamically identifying microgenres associated with the content |
US8510453B2 (en) * | 2007-03-21 | 2013-08-13 | Samsung Electronics Co., Ltd. | Framework for correlating content on a local network with information on an external network |
US8843467B2 (en) * | 2007-05-15 | 2014-09-23 | Samsung Electronics Co., Ltd. | Method and system for providing relevant information to a user of a device in a local network |
EP4209927A1 (en) | 2006-04-20 | 2023-07-12 | Veveo, Inc. | User interface methods and systems for selecting and presenting content based on user navigation and selection actions associated with the content |
JP4767754B2 (ja) * | 2006-05-18 | 2011-09-07 | 富士通株式会社 | 音声認識装置および音声認識プログラム |
US8032545B2 (en) * | 2006-06-14 | 2011-10-04 | General Electric Company | Systems and methods for refining identification of clinical study candidates |
US8078884B2 (en) * | 2006-11-13 | 2011-12-13 | Veveo, Inc. | Method of and system for selecting and presenting content based on user identification |
US8935269B2 (en) * | 2006-12-04 | 2015-01-13 | Samsung Electronics Co., Ltd. | Method and apparatus for contextual search and query refinement on consumer electronics devices |
JP2008242836A (ja) * | 2007-03-27 | 2008-10-09 | Toshiba Corp | 辞書更新装置およびプログラム |
US8176068B2 (en) * | 2007-10-31 | 2012-05-08 | Samsung Electronics Co., Ltd. | Method and system for suggesting search queries on electronic devices |
US7814108B2 (en) * | 2007-12-21 | 2010-10-12 | Microsoft Corporation | Search engine platform |
EP2263212A1 (en) * | 2008-03-09 | 2010-12-22 | Avaworks Incorporated | Photo realistic talking head creation, content creation, and distribution system and method |
JP4388137B2 (ja) * | 2008-03-10 | 2009-12-24 | パナソニック株式会社 | コンテンツ検索装置及びコンテンツ検索方法 |
US8938465B2 (en) * | 2008-09-10 | 2015-01-20 | Samsung Electronics Co., Ltd. | Method and system for utilizing packaged content sources to identify and provide information based on contextual information |
US9166714B2 (en) | 2009-09-11 | 2015-10-20 | Veveo, Inc. | Method of and system for presenting enriched video viewing analytics |
CN102088635B (zh) * | 2009-12-04 | 2013-04-17 | 深圳Tcl新技术有限公司 | 网络电视机记录历史搜索关键字的方法 |
US20110191332A1 (en) | 2010-02-04 | 2011-08-04 | Veveo, Inc. | Method of and System for Updating Locally Cached Content Descriptor Information |
CN102193936B (zh) * | 2010-03-09 | 2013-09-18 | 阿里巴巴集团控股有限公司 | 一种数据分类的方法及装置 |
US8738377B2 (en) | 2010-06-07 | 2014-05-27 | Google Inc. | Predicting and learning carrier phrases for speech input |
US8683348B1 (en) * | 2010-07-14 | 2014-03-25 | Intuit Inc. | Modifying software based on a user's emotional state |
CN102411583B (zh) * | 2010-09-20 | 2013-09-18 | 阿里巴巴集团控股有限公司 | 一种文本匹配方法及装置 |
CN102436513B (zh) * | 2012-01-18 | 2014-11-05 | 中国电子科技集团公司第十五研究所 | 分布式检索方法和系统 |
US9235565B2 (en) * | 2012-02-14 | 2016-01-12 | Facebook, Inc. | Blending customized user dictionaries |
CN105989016B (zh) * | 2015-01-28 | 2021-08-10 | 日本冲信息株式会社 | 信息处理装置 |
JP6433928B2 (ja) * | 2016-02-15 | 2018-12-05 | 株式会社東芝 | 検索装置、検索方法および検索システム |
US11108708B2 (en) * | 2016-06-06 | 2021-08-31 | Global Tel*Link Corporation | Personalized chatbots for inmates |
CN106547917A (zh) * | 2016-11-29 | 2017-03-29 | 国网信息通信产业集团有限公司 | 一种信息处理方法及电子设备 |
US10404804B2 (en) | 2017-01-30 | 2019-09-03 | Global Tel*Link Corporation | System and method for personalized virtual reality experience in a controlled environment |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH09190451A (ja) * | 1996-01-09 | 1997-07-22 | Oki Electric Ind Co Ltd | 情報検索装置 |
JPH10143521A (ja) * | 1996-11-11 | 1998-05-29 | Oki Electric Ind Co Ltd | 情報検索方法及び情報検索装置 |
JP2001188802A (ja) * | 1999-11-22 | 2001-07-10 | Nec Corp | 情報検索装置及び情報検索方法 |
JP2003271631A (ja) * | 2002-03-13 | 2003-09-26 | Ntt Data Technology Corp | 特許文献検索方法及び装置 |
Family Cites Families (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2839839B2 (ja) | 1994-07-13 | 1998-12-16 | 株式会社エイ・ティ・アール通信システム研究所 | 情報検索装置 |
US6070160A (en) * | 1995-05-19 | 2000-05-30 | Artnet Worldwide Corporation | Non-linear database set searching apparatus and method |
JP3429612B2 (ja) | 1995-09-28 | 2003-07-22 | 沖電気工業株式会社 | 辞書登録装置及び機械翻訳装置 |
JPH09231264A (ja) * | 1996-02-23 | 1997-09-05 | Hitachi Ltd | オンラインショッピング支援方法およびシステム |
JP3099756B2 (ja) | 1996-10-31 | 2000-10-16 | 富士ゼロックス株式会社 | 文書処理装置、単語抽出装置及び単語抽出方法 |
US6266649B1 (en) * | 1998-09-18 | 2001-07-24 | Amazon.Com, Inc. | Collaborative recommendations using item-to-item similarity mappings |
US6317722B1 (en) * | 1998-09-18 | 2001-11-13 | Amazon.Com, Inc. | Use of electronic shopping carts to generate personal recommendations |
JP2000348042A (ja) | 1999-06-03 | 2000-12-15 | Fujitsu Ltd | 統合シソーラス作成装置、修正シソーラス作成装置、情報収集型シソーラス作成装置、統合シソーラス作成プログラム記憶媒体、修正シソーラス作成プログラム記憶媒体、および情報収集型シソーラス作成プログラム記憶媒体 |
US6701310B1 (en) * | 1999-11-22 | 2004-03-02 | Nec Corporation | Information search device and information search method using topic-centric query routing |
US6687696B2 (en) * | 2000-07-26 | 2004-02-03 | Recommind Inc. | System and method for personalized search, information filtering, and for generating recommendations utilizing statistical latent class models |
US6615208B1 (en) * | 2000-09-01 | 2003-09-02 | Telcordia Technologies, Inc. | Automatic recommendation of products using latent semantic indexing of content |
US8676830B2 (en) * | 2004-03-04 | 2014-03-18 | Yahoo! Inc. | Keyword recommendation for internet search engines |
-
2005
- 2005-10-05 CN CNB2005800050103A patent/CN100550014C/zh not_active Expired - Fee Related
- 2005-10-05 JP JP2006542316A patent/JP4008954B2/ja not_active Expired - Fee Related
- 2005-10-05 WO PCT/JP2005/018461 patent/WO2006046390A1/ja active Application Filing
-
2006
- 2006-03-22 US US11/385,751 patent/US7725486B2/en not_active Expired - Fee Related
- 2006-05-17 US US11/434,761 patent/US7483921B2/en not_active Expired - Fee Related
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH09190451A (ja) * | 1996-01-09 | 1997-07-22 | Oki Electric Ind Co Ltd | 情報検索装置 |
JPH10143521A (ja) * | 1996-11-11 | 1998-05-29 | Oki Electric Ind Co Ltd | 情報検索方法及び情報検索装置 |
JP2001188802A (ja) * | 1999-11-22 | 2001-07-10 | Nec Corp | 情報検索装置及び情報検索方法 |
JP2003271631A (ja) * | 2002-03-13 | 2003-09-26 | Ntt Data Technology Corp | 特許文献検索方法及び装置 |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2008071198A (ja) * | 2006-09-14 | 2008-03-27 | Ricoh Co Ltd | 文書検索装置、文書検索方法、文書検索プログラムおよび記録媒体 |
JP4464463B2 (ja) * | 2007-08-03 | 2010-05-19 | パナソニック株式会社 | 関連語提示装置 |
JPWO2009019830A1 (ja) * | 2007-08-03 | 2010-10-28 | パナソニック株式会社 | 関連語提示装置 |
US8504357B2 (en) | 2007-08-03 | 2013-08-06 | Panasonic Corporation | Related word presentation device |
JP2009140306A (ja) * | 2007-12-07 | 2009-06-25 | Toshiba Corp | 情報提供サーバおよび情報提供方法 |
WO2009104387A1 (ja) * | 2008-02-20 | 2009-08-27 | パナソニック株式会社 | 対話型番組検索装置 |
JPWO2009104387A1 (ja) * | 2008-02-20 | 2011-06-16 | パナソニック株式会社 | 対話型番組検索装置 |
US8161043B2 (en) | 2008-02-20 | 2012-04-17 | Panasonic Corporation | Interactive program search apparatus |
CN102231147A (zh) * | 2010-11-08 | 2011-11-02 | 百度在线网络技术(北京)有限公司 | 一种用于实时展现联想词的方法、设备及系统 |
WO2017061037A1 (ja) * | 2015-10-09 | 2017-04-13 | 楽天株式会社 | 情報処理装置、情報処理方法及び情報処理プログラム |
JPWO2017061037A1 (ja) * | 2015-10-09 | 2018-04-05 | 楽天株式会社 | 情報処理装置、情報処理方法及び情報処理プログラム |
Also Published As
Publication number | Publication date |
---|---|
CN1918571A (zh) | 2007-02-21 |
JPWO2006046390A1 (ja) | 2008-05-22 |
CN100550014C (zh) | 2009-10-14 |
JP4008954B2 (ja) | 2007-11-14 |
US20060167918A1 (en) | 2006-07-27 |
US20060206471A1 (en) | 2006-09-14 |
US7483921B2 (en) | 2009-01-27 |
US7725486B2 (en) | 2010-05-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP4008954B2 (ja) | 情報検索装置 | |
US8280720B2 (en) | Association dictionary creation apparatus | |
JP4331257B2 (ja) | 情報検索装置 | |
JP4436894B2 (ja) | コンテンツ検索装置 | |
EP1154358A2 (en) | Automatic text classification system | |
JP2004030526A (ja) | 検索結果ランキング変更処理プログラム、検索結果ランキング変更処理プログラム記録媒体、およびコンテンツ検索処理方法 | |
US20100229120A1 (en) | Operation assisting apparatus and operation assisting method | |
US20020099730A1 (en) | Automatic text classification system | |
US9973815B2 (en) | Apparatus, method, and program for processing information | |
JP4399514B2 (ja) | 対話型番組検索装置 | |
US10360260B2 (en) | System and method for semantic analysis of song lyrics in a media content environment | |
JP2006202159A (ja) | 情報提供システム、情報提供方法及びそのプログラム | |
CN1518710A (zh) | 自动视频检索器精灵 | |
JP4659755B2 (ja) | コンテンツデータ検索装置 | |
JP4734048B2 (ja) | 情報検索装置、情報検索方法および情報検索プログラム | |
JP2006186426A (ja) | 情報検索表示装置、情報検索表示方法および情報検索表示プログラム | |
JP4592719B2 (ja) | ダイジェストコンテンツ表示装置及びそのプログラム | |
JP2005346347A (ja) | 情報検索装置、情報検索方法、情報検索プログラムおよび記録媒体 | |
JP2010044733A (ja) | 嗜好分析プログラム及び嗜好分析装置 | |
KR20070061887A (ko) | 컴플라이언스 정보 제공 방법 | |
JP2008225584A (ja) | 物品推薦装置、物品推薦システム、物品推薦方法及び物品推薦プログラム | |
JP2009134484A (ja) | コンテンツ選択支援装置、コンテンツ選択支援方法及びそのプログラム | |
JP2007183765A (ja) | 関連語取得装置 | |
KR101544603B1 (ko) | 개인화된 웹 정보 제공 장치 및 방법 | |
JP2002132823A (ja) | マルチメディア情報処理装置、マルチメディア情報処理方法およびそのプログラムが記録されたコンピュータ読み取り可能な記録媒体 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
WWE | Wipo information: entry into national phase |
Ref document number: 2006542316 Country of ref document: JP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 11385751 Country of ref document: US |
|
AK | Designated states |
Kind code of ref document: A1 Designated state(s): AE AG AL AM AT AU AZ BA BB BG BW BY BZ CA CH CN CO CR CU CZ DK DM DZ EC EE EG ES FI GB GD GH GM HR HU ID IL IN IS JP KE KG KP KR KZ LC LK LR LS LT LU LV LY MD MG MK MN MW MX MZ NA NG NO NZ OM PG PH PL PT RO RU SC SD SG SK SL SM SY TJ TM TN TR TT TZ UG US UZ VC VN YU ZA ZM |
|
AL | Designated countries for regional patents |
Kind code of ref document: A1 Designated state(s): BW GH GM KE LS MW MZ NA SD SZ TZ UG ZM ZW AM AZ BY KG MD RU TJ TM AT BE BG CH CY DE DK EE ES FI FR GB GR HU IE IS IT LU LV MC NL PL PT RO SE SI SK TR BF BJ CF CG CI CM GA GN GQ GW MR NE SN TD TG |
|
WWP | Wipo information: published in national office |
Ref document number: 11385751 Country of ref document: US |
|
WWE | Wipo information: entry into national phase |
Ref document number: 200580005010.3 Country of ref document: CN |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application | ||
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 05790426 Country of ref document: EP Kind code of ref document: A1 |