JP2017072964A - Information analyzing apparatus and information analyzing method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a technology of presenting desired information to a user.SOLUTION: An information analyzing apparatus includes: an acquisition unit for acquiring multiple pieces of word data generated by user action; a specifying unit which specifies a provision category corresponding to the acquired multiple pieces of word data, from among a plurality of provision categories; a selection unit which determines whether the acquired word data belongs to a query category associated with the specified provision category, on the basis of query relation information including the provision categories, query categories, and a multiple pieces of keyword information data, to select word data to be used for a search keyword from among the acquired word data; and a search control unit which requests for a search using the selected word data, as a search keyword, for the information provided from an information providing destination corresponding to the specified provision category.SELECTED DRAWING: Figure 11

Description

  The present invention relates to an information analysis technique for providing information to a user.

  With the rapid progress of information and communication technology, the problem of digital divide has been pointed out in recent years. This problem is caused not only by unfamiliarity with IT (Information Technology) equipment but also by the huge amount of information that can be obtained. Even those who can use IT equipment to a certain extent find it very difficult to find useful information from a vast amount of information.

  Patent Document 1 listed below describes an information processing apparatus that performs high-accuracy searches for a large number of documents in a short time. This information processing apparatus acquires a document or the like as registration target data, classifies the registration target data based on word data obtained by language analysis of the data, and determines a registration destination. Further, the apparatus compares the relationship between the words included in the acquired query with the relationship between the words included in the document to be searched, and calculates the similarity between the query and the sentence in the document, List the search result list in descending order of match. Patent Document 2 below describes a method for estimating a category synonym from previous search result data. In this method, prior query data including query information and category information related to previous result data is identified, and it is determined whether the query information is a synonym for category information. And when it is judged that it is a synonym, query information and category information are used by a subsequent search request.

  Patent Document 3 listed below describes an information search apparatus that allows a user to obtain desired information smoothly. This information search device specifies a distribution keyword related to the user's comment text data, and requests information from an information providing unit (for example, a site) corresponding to the specified distribution keyword. At this time, the apparatus uses, as a search keyword, at least one word data other than the sorting keyword obtained by decomposing speech text data.

JP 2006-227823 A Special table 2009-516890 JP 2014-110005 A

  In the methods described in Patent Documents 1 and 2 described above, a query including an appropriate word needs to be used for high-accuracy search, and it seems that the degree of dependence on the user's ability is high. In addition, in the technique described in Patent Document 3, it seems that there is still room for ingenuity to make the provided information closer to the user's interest.

  This invention is made | formed in view of such a situation, and implement | achieves the technique which provides a user with desired information.

  Each aspect of the present invention employs the following configurations in order to solve the above-described problems.

  The first aspect relates to an information analysis apparatus. The information analysis apparatus according to the first aspect includes an acquisition unit configured to acquire a plurality of word data generated due to a user's action, and a plurality of acquired destination data from the plurality of provision destination categories. Based on query relation information indicating a relationship between a plurality of destination categories and a plurality of query categories and a relationship between the plurality of query categories and a plurality of keyword information data, a specifying unit for identifying a corresponding destination category, Word data used as a search keyword from the plurality of acquired word data by determining whether or not each acquired word data belongs to a query category associated with the specified provider category Selecting means for selecting the information provided from the information providing destination corresponding to the specified providing destination category; It includes a search control means for requesting a search using the word data as a search keyword, a.

  The second aspect relates to an information analysis method executed by at least one computer. The information analysis method according to the second aspect acquires a plurality of word data generated due to a user's action and corresponds to the acquired at least one word data from a plurality of provision destination categories. Each of the acquired categories is specified based on the query relationship information indicating the relationship between the plurality of destination categories and the plurality of query categories and the relationship between the plurality of query categories and the plurality of keyword information data. Words that determine whether or not the word data belongs to a query category associated with the specified provider category, and a word that is used as a search keyword from the plurality of acquired word data based on the determination result The selected word data for information provided from an information providing destination corresponding to the specified providing destination category by selecting data Requesting a search using as a search keyword includes.

  Another aspect of the present invention is a program that causes at least one computer to execute the method according to the second aspect, or a computer-readable recording medium that records such a program. This recording medium includes a non-transitory tangible medium.

  According to each said aspect, the technique which provides a user with desired information is realizable.

It is a figure which shows notionally the hardware structural example of the information analysis apparatus (analysis apparatus) in 1st embodiment. It is a figure which shows notionally the process structural example of the information analyzer (analyzer) in 1st embodiment. It is a figure which shows the example of the provision destination relation table of a keyword. It is a figure which shows the example of the query category table of a keyword. It is a figure which shows the example of the query word table of a keyword. It is a flowchart which shows the operation example of the information analysis apparatus (analysis apparatus) in 1st embodiment. It is a figure which shows the example of the flow of one operation example of the information analysis apparatus (analysis apparatus) in 1st embodiment, and the data processing example. It is a figure which shows notionally the process structural example of the information analyzer (analyzer) in 2nd embodiment. It is a flowchart which shows the operation example of the information analysis apparatus (analysis apparatus) in 2nd embodiment. It is a figure which shows the flow of one operation example of the information analysis apparatus (analysis apparatus) in 2nd embodiment, and the example of a data processing. It is a figure which shows notionally the process structural example of the information analyzer in 3rd embodiment.

  Embodiments of the present invention will be described below. In addition, each embodiment given below is an illustration, respectively, and this invention is not limited to the structure of the following embodiment.

[First embodiment]
Hereinafter, an information analysis apparatus and an information analysis method in the first embodiment will be described.
〔Device configuration〕
FIG. 1 is a diagram conceptually illustrating a hardware configuration example of an information analysis apparatus (hereinafter sometimes abbreviated as an analysis apparatus) 10 in the first embodiment. The analysis device 10 is communicably connected to the client device 8 and the information providing site 7 used by the user via the communication network 5. The communication network 5 is a public network such as the Internet, a WAN (Wide Area Network), a LAN (Local Area Network), a wireless communication network, or the like. In the present embodiment, the communication mode among the analysis device 10, the information providing site 7, and the client device 8 is not limited.

  The analysis apparatus 10 is a general computer and has hardware elements as shown in FIG. Specifically, the analysis apparatus 10 includes a CPU (Central Processing Unit) 1, a memory 2, an input / output interface (I / F) 3, a communication unit 4, and the like as a hardware configuration. Each of these hardware elements is connected by a bus.

In addition to a general CPU, the CPU 1 includes an application specific integrated circuit (ASIC), a DSP (Digital Signal Processor), a GPU (Graphics Processing Unit), and the like.
The memory 2 is a RAM (Random Access Memory), a ROM (Read Only Memory), or an auxiliary storage device (such as a hard disk).

  The input / output I / F 3 can be connected to a user interface device such as a display device (not shown) or an input device (not shown). The display device is a device that displays a screen corresponding to the drawing data processed by the CPU 1, such as an LCD (Liquid Crystal Display) or a CRT (Cathode Ray Tube) display. The input device is a device that receives an input of a user operation such as a keyboard and a mouse. The display device and the input device may be integrated and realized as a touch panel.

  The communication unit 4 communicates with other computers via the communication network 5 and exchanges signals with other devices. A portable recording medium or the like can be connected to the communication unit 4. The analysis apparatus 10 may include hardware elements not shown in FIG. 1, and the number of hardware elements is not limited to the number shown in FIG. For example, the analysis device 10 includes a plurality of CPUs 1 and a plurality of memories 2. The hardware configuration of the analyzer 10 is not limited.

  The information providing site 7 is a general computer, and is a server device that provides various types of information such as a WEB server and a database server. The present embodiment does not limit the hardware configuration and software configuration of the information providing site 7. Hereinafter, the information providing site 7 may be abbreviated as the site 7.

  The analysis device 10 is connected to one or more sites 7 so as to be communicable. In the present embodiment, the number of sites 7 accessed by the analysis apparatus 10 is not limited. The analysis device 10 picks up information that each user is supposed to want from the large amount of information provided by the site 7 and provides the user (client device 8) with desired information.

  The client device 8 is a general user terminal such as a PC (Personal Computer), a tablet terminal, a smartphone, a mobile phone, or the like. The client device 8 may be a communication robot having a user interface. The hardware configuration and the software configuration of the client device 8 are not limited as long as the client device 8 can output information provided by the analysis device 10 to the user and can receive input from the user. Information can be output by a display device, a printer device, an audio output device, or the like. In addition, an input from a user is an input device (not shown) that accepts an input of a user operation such as a keyboard and a mouse, a microphone (not shown) that acquires a user's speech, and a camera that captures a user's gesture. Etc. can be received. Hereinafter, the client device 8 may be abbreviated as a client 8.

  The client 8 sends the character string data acquired due to the user's operation to the analysis device 10. Specifically, the client 8 acquires character string data input by a user operation on the input device. For example, any character string data such as a search character string input to the browser, a schedule character string input to the calendar application, and a memo can be acquired.

  The client 8 can also record the user's voice collected by the microphone and send the recorded voice data to the analyzer 10. The client 8 may acquire character string data from the voice data using a known voice recognition technique and send the character string data to the analysis device 10.

  In the present embodiment, as long as the character string data or the voice data is caused by the user's action, the acquisition method of the character string data or the voice data by the client 8 is not limited. For example, an application (including a WEB browser) installed in the client 8 acquires the character string data or the voice data using a known technique, and sends the acquired data to the analysis apparatus 10. Further, the client 8 can extract word data by decomposing the acquired character string data into parts of speech, and can transmit the extracted word data to the analysis device 10.

[Processing configuration]
FIG. 2 is a diagram conceptually illustrating a processing configuration example of the analysis apparatus 10 in the first embodiment. The analyzer 10 has software elements as shown in FIG. Specifically, the analysis apparatus 10 includes an acquisition unit 11, a user word DB (DataBase) 12, a keyword DB (DataBase) 13, a specifying unit 14, a selection unit 15, a search control unit 16, an output processing unit 17, and the like. Each of these software elements is realized, for example, by executing a program stored in the memory 2 by the CPU 1. In addition, the program is installed from a portable recording medium such as a CD (Compact Disc) or a memory card or another computer on the network via the input / output I / F 3 or the communication unit 4 and is stored in the memory 2. It may be stored.

  When the acquisition unit 11 receives character string data or voice data from the client 8 or another device, the acquisition unit 11 extracts one or more word data from the received character string data or voice data. Specifically, the acquisition unit 11 extracts one or more word data by performing part-of-speech decomposition (morphological analysis) on the received character string data. Various known methods such as MeCab can be used for morphological analysis. For example, the acquisition unit 11 may acquire only word data of specific parts of speech such as nouns and verbs from words of various parts of speech. Furthermore, the acquisition unit 11 can also acquire only word data of specific nouns such as general nouns, proper nouns, and sagittal connection nouns among nouns, and can also normalize the acquired verbs to basic forms.

  The acquisition unit 11 can acquire character string data in which a user's voice is converted into text by applying a known voice recognition technique to the voice data, and can also decompose the part of speech of the character string data. When the part-of-speech decomposition or speech recognition as described above is executed on the client 8, the acquisition unit 11 may receive the plurality of word data extracted by the client 8 from the client 8.

  The acquisition unit 11 stores the acquired word data in the user word DB 12 in association with the identification information of the transmission source user or the client 8. When the user identification information is used, the acquisition unit 11 receives the user identification information from the client 8 together with the word data or the data that is the basis of the word data. The acquisition unit 11 may further store the acquisition date and time of the word data in the user word DB 12 in association with the word data.

  Furthermore, the acquisition unit 11 acquires the plurality of word data for each user from the user word DB 12 at an arbitrary timing. The arbitrary timing includes random timing and a predetermined cycle. At this time, it is desirable for the acquisition unit 11 to acquire word data that strongly indicates the user's interest or interest from among a plurality of word data accumulated for each user in the user word DB 12. The user's interest and the intensity of interest can be determined by, for example, the occurrence frequency of word data. The acquisition unit 11 may extract word data for all users whose word data is stored in the user word DB 12, or based on the login status of each user, only the logged-in users The plurality of word data may be extracted from the word DB 12.

  The specifying unit 14, the selection unit 15, the search control unit 16, and the output processing unit 17 described later perform processing based on the word data acquired by the acquisition unit 11. On the other hand, as described above, the acquisition unit 11 supports the case of acquiring word data directly from the data sent from the client 8 and the case of acquiring word data spontaneously from the user word DB 12. The former can be expressed as a passive operation because the user's operation is triggered, and the latter can be expressed as a spontaneous or active operation. Therefore, hereinafter, the mode that operates based on the word data directly acquired from the data sent from the client 8 is referred to as a passive operation mode, and the mode that operates based on the word data acquired from the user word DB 12 is active. Indicated as operation mode.

  User word DB12 accumulate | stores the word data produced | generated based on a user's operation | movement for every user. Specifically, the user word DB 12 stores the identification information of the user or client 8 and the word data in association with each other. The user word DB 12 may store a plurality of the same word data for one user, or may store one word data and the number of occurrences for one user by eliminating the duplication. Further, the user word DB 12 may store word data and acquisition date and time of the word data for each user.

  The keyword DB 13 includes a provider relationship table, a query category table, and a query word table.

  The providing destination relationship table stores providing destination relationship information indicating the relationship between the providing destination category and the providing destination keyword. Specifically, the provision destination relation table stores identification information of the provision destination category and keyword data of the provision destination keyword in association with each other. Each provision destination category indicates a category of information provided by each site 7 and is associated with the site 7 that provides information of the corresponding category. The identification information of the provider category is associated with the address information of the site 7 separately. The address information of the site 7 is information for acquiring information provided by the site 7 such as a URL (Uniform Resource Locator). The provision destination keyword is a word having some relationship with the provision destination category. For example, a word having a meaning belonging to the provision destination category is stored as the provision destination keyword. In addition, a word indirectly related to the provision destination category may be stored as the provision destination keyword.

  FIG. 3 is a diagram illustrating an example of the provision destination relation table of the keyword DB 13. In FIG. 3, for the sake of easy understanding, the identification information of the provider category is illustrated by a word (noun) indicating the category. However, the identification information of the provider category stored in the provider relationship table may be a numerical value instead of the word illustrated in FIG. In the example of FIG. 3, “go” is associated with the provision destination category “gourmet” as the provision destination keyword. Since the word “go” means going out, it is reminiscent of “meal when going out”. Thus, although the word “go” does not directly belong to the category “gourmet”, it is related to “gourmet” from an indirect relationship (for example, association of “meal when going out”).

  As described above, since the provision destination category is associated with the site 7, the provision destination relationship table indicates the relationship between the word and the site 7 that provides information directly and indirectly related to the word. it can. Therefore, the providing destination relationship table may store the identification information (may be address information) of the site 7 as the providing category identification information.

  The query category table stores information indicating the relationship between the provider category and the query category. Specifically, the query category table stores the identification information of the provider category and the identification information of the query category in association with each other. The provider category stored in the query category table is the same as the provider category stored in the provider relationship table described above. The query category indicates an information category included in information provided from the site 7 corresponding to the provision destination category. In other words, a query category that is not associated with a certain provider category in the query category table indicates a category that is not used as a search keyword for information provided from the site 7 corresponding to the provider category.

  FIG. 4 is a diagram illustrating an example of a query category table in the keyword DB 13. In FIG. 4, for the sake of easy understanding, each identification information of the provision destination category and the query category is illustrated by a word (noun) indicating the category. However, the identification information of the destination category and the query category stored in the query category table may be numerical values instead of the words illustrated in FIG. In the example of FIG. 4, “dish name” and “place name” are stored as query categories in the provision destination category “gourmet”. Therefore, it is shown that the words of the categories “dishes names” and “place names” are used as search keywords for the information provided from the site 7 corresponding to “gourmet”. On the other hand, the “food name” is not associated with the provision category “gourmet”. Therefore, it is shown that the word of the category of “food name” is not used as a search keyword for information provided from the site 7 associated with “gourmet”.

  The query word table stores information indicating the relationship between the query category and the query keyword. Specifically, the query word table stores query category identification information and query keyword keyword data in association with each other. The query category stored in the query word table is the same as the query category stored in the above-described query category table. The query keyword is a word having a meaning belonging to the query category.

  FIG. 5 is a diagram illustrating an example of a query word table in the keyword DB 13. In FIG. 5, for easy understanding, the identification information of the query category is illustrated by a word (noun) indicating the category. However, the query category identification information stored in the query word table may be numerical values instead of the words illustrated in FIG. In the example of FIG. 5, “Tomorrow”, “Tomorrow”, and “June 8” are associated with the query category “date name” as query keywords.

  As described above, the query category table and the query word table are associated with each other by the query category. Therefore, the query category table and the query word table can also be expressed as query relation information. In addition, the query category table and the query word table can be integrated using the query category. In this case, the integrated table shows the relationship between the provision destination category and the query keyword. By providing the query category table and the query word table separately as in this embodiment, it is not necessary to store duplicate query keywords in the table, leading to a reduction in memory resources. Moreover, the merit that it is easy to manage the data of each table can also be enjoyed.

  The user word DB 12 and the keyword DB 13 may be relational databases, or files written in a predetermined description language such as JSON (JavaScript (registered trademark) Object Notation) or XML (Extensible Markup Language). Also good.

  The specifying unit 14 specifies a provider category corresponding to one or more word data acquired by the acquiring unit 11 by referring to the above-described provider relationship table. For example, the specifying unit 14 determines whether or not the word data acquired by the acquiring unit 11 is stored as a provision destination keyword in the provision destination relation table of the keyword DB 13. The identification unit 14 identifies a provision destination category in which one or more word data is stored as a provision destination keyword. The specifying unit 14 may specify a plurality of provision destination categories. Further, when there are a plurality of provision category categories in which one or more word data are stored as the provision destination keywords, the specifying unit 14 identifies one provision destination category in which the most word data is stored as the provision destination keywords. May be.

  Further, the specifying unit 14 may calculate a similarity between the feature amount of the providing destination keyword and the feature amount of each word data acquired by the acquiring unit 11, and specify the providing destination category using the similarity. it can. Various known methods can be used as a method for expressing the feature amount of word data and a method for calculating similarity between words. The specifying unit 14 converts the provision destination keyword data and each word data acquired by the acquiring unit 11 into feature amount data, and calculates the similarity between the converted feature amount data. The feature amount data may have a vector structure. In the present embodiment, the method for calculating the similarity between words is not limited. However, it is desirable to use a method in which the closeness of meaning and concept is calculated with high accuracy as the similarity.

  The specifying unit 14 can also specify the provision destination category based on the distance of the similarity calculated as described above. As another example, the specifying unit 14 may specify a providing category associated with a providing keyword that is equal to or higher than a predetermined threshold and that shows the highest degree of similarity. Further, the specifying unit 14 may specify a providing destination category having the largest number of providing destination keywords that indicate a degree of similarity equal to or greater than a predetermined threshold. Further, the specifying unit 14 may specify a providing category having the highest average similarity of the providing keywords for each providing category. The specifying unit 14 may specify a providing category whose average similarity is a predetermined threshold or more.

  The specifying unit 14 may hold feature amount data calculated in advance for a large number of words using the above-described known technique. Such feature amount data for each word may be generated by a device other than the analysis device 10. In this case, the specifying unit 14 replaces each word data acquired by the acquisition unit 11 with feature amount data, using a table of feature amount data for each word. In the keyword DB 13, feature amount data corresponding to each of the provision destination keyword and the query keyword may be stored in advance. The provision destination relation table may store average feature amount data of a plurality of provision destination keywords for each provision destination category. In this case, the specifying unit 14 specifies the providing category by calculating the similarity between the feature data of each word data acquired by the acquiring unit 11 and the average feature data for each providing category. As described above, the method of specifying the providing category by the specifying unit 14 is not limited.

  The selection unit 15 selects word data used as a search keyword from one or more word data acquired by the acquisition unit 11. Specifically, the selection unit 15 selects a query in which each word data acquired by the acquisition unit 11 is associated with the provision destination category specified by the specifying unit 14 based on the query category table and the query word table of the keyword DB 13. Whether it belongs to a category is determined. Based on this determination, the selection unit 15 selects word data to be used as a search keyword from one or more word data acquired by the acquisition unit 11. Hereinafter, the query category associated with the provision category specified by the specifying unit 14 may be referred to as “target query category”. When the specifying unit 14 has selected a plurality of supply destination categories, the selection unit 15 selects a search keyword from among the plurality of word data acquired by the acquisition unit 11 for each of the specified plurality of supply destination categories. Each word data to be used is selected. In other words, when different word data is selected for each provider category, when the same word data is selected in common for all provider categories, or when there is a provider category where no word data is selected. There can be.

  For example, the selection unit 15 extracts the target query category from the query category table, and whether or not each word data acquired by the acquisition unit 11 matches the query keyword associated with the target query category in the query word table. Respectively. The selection unit 15 selects word data matching the query keyword associated with the target query category as a word data candidate used as a search keyword, and excludes other word data from the candidate.

  Further, the selection unit 15 calculates the similarity between the query keyword shown in the query word table and the feature amount of each word data acquired by the acquisition unit 11, and uses the calculated similarity to acquire the acquisition unit 11 The above determination may be performed for each word data acquired by the above. The selection unit 15 converts the query keyword data and each word data acquired by the acquisition unit 11 into feature amount data, and calculates the similarity between the converted feature amount data. The notation method of the feature amount of the word data and the similarity calculation method between the words are as described above.

  For example, when a query keyword whose similarity with word data indicates a predetermined threshold or more is associated with the target query category, the selection unit 15 determines that the word data belongs to the query category. When the query word table stores average feature amount data of a plurality of query keywords for each query category, the selection unit 15 selects word data whose similarity with the average feature amount data of the target query category is a predetermined threshold or more. It is determined that it belongs to the query category.

  The search control unit 16 specifies a site 7 corresponding to the provision destination category specified by the specifying unit 14, and uses the word data selected by the selection unit 15 for information provided from the site 7 as a search keyword Request. When there is a providing category for which no word data has been selected, the search control unit 16 does not specify a search keyword for searching for information provided from the site 7 corresponding to the providing category. Also good.

  When the identified site 7 supports in-site search, the search control unit 16 requests the identified site 7 to perform a search using the selected word data as a search keyword, and the search result The information extracted as is received from the site 7. In addition, when the specified site 7 does not support search within the site, a computer other than the site 7 acquires all the information provided by the site 7 from the site 7, and for the acquired information The search may be performed. In this case, the search control unit 16 requests a search to the computer that performs the search. At this time, the search control unit 16 sends the address information of the site 7 and the word data selected as the search keyword to the computer. The computer that performs the search may be the analysis apparatus 10.

  The output processing unit 17 transmits information acquired as a search result by the search control unit 16 to the client 8. As a result, the client 8 outputs the information. The client 8 can output the information provided from the analysis device 10 by various methods such as display, printing, and voice. In the passive operation mode, the client 8 transmits data (character string, word, voice, etc.) generated due to the user's operation to the analysis device 10 and presents the information received from the analysis device 10 to the user. In the active operation mode, the client 8 receives information sent spontaneously from the analysis apparatus 10 regardless of the user's operation, and presents the information to the user.

[Operation example / Information analysis method]
Hereinafter, the information analysis method in the first embodiment will be described with reference to FIG. FIG. 6 is a flowchart showing an operation example of the analyzer 10 in the first embodiment. As shown in FIG. 6, the information analysis method in the first embodiment is executed by at least one computer such as the analysis apparatus 10. Each process shown in FIG. 6 is the same as the processing content of each software element included in the analyzer 10, and therefore details of each process are omitted as appropriate.

  The analysis apparatus 10 acquires a plurality of word data (S61). The word data acquisition method in (S61) can be classified into two methods. One is a method executed in the passive operation mode. Specifically, the analysis apparatus 10 receives character string data or voice data from the client 8, and extracts a plurality of word data from the received character string data or voice data using a known technique. This method of extracting word data is as described in the description of the acquisition unit 11. The analysis device 10 may receive the plurality of word data itself from the client 8. The analysis device 10 stores the acquired word data in the user word DB 12 in association with the identification information of the transmission source user or the client 8. In the passive operation mode, the subsequent steps are executed in response to the reception of data from the client 8 as described above.

  Another method is performed in the active mode of operation. In this case, the analysis apparatus 10 acquires the plurality of word data from the user word DB 12 for each user by referring to the user word DB 12 at an arbitrary timing. At this time, it is desirable for the analysis apparatus 10 to acquire word data that strongly indicates the user's interest or interest from among a plurality of word data accumulated for each user in the user word DB 12. In the active operation mode, the analysis apparatus 10 voluntarily acquires the word data as described above, and the subsequent steps are executed in response to the acquisition.

  The analysis apparatus 10 refers to the provision destination relation table in the keyword DB 13, thereby providing the provision destination category corresponding to the word data acquired in (S61) from among a plurality of provision destination categories stored in the provision destination relation table. Is specified (S62). The method of specifying the providing category is as described in the description of the specifying unit 14.

  The analysis apparatus 10 refers to the query category table and the query word table in the keyword DB 13 to select word data to be used as a search keyword from the plurality of word data acquired in (S61) (S63). Specifically, the analysis device 10 determines whether each word data acquired in (S61) belongs to the query category associated with the provision destination category specified in (S62), thereby Make a selection. This selection method is as described in the description of the selection unit 15.

  The analysis apparatus 10 identifies the site 7 corresponding to the provision destination category identified in (S62), and requests a search using the word data selected in (S63) for the information provided from the site 7 (S63). S64). The analysis device 10 may request a search from the identified site 7 or may request a search from another computer. Further, the analysis device 10 may perform a search by itself.

  The analysis apparatus 10 causes the client 8 to output information extracted as a result of the search (S65). In the passive operation mode, the user of the client 8 can obtain desired information in response to his / her own operation such as an input operation on the client 8. On the other hand, in the active operation mode, the user of the client 8 can obtain desired information at an arbitrary timing.

  Next, a specific example of the information analysis method in the first embodiment will be further described using specific data shown in FIGS. 3, 4, and 5. FIG. 7 is a diagram illustrating a flow of one operation example of the analysis apparatus 10 and a data processing example in the first embodiment. Here, it is assumed that the user inputs a schedule “going to cherry blossom viewing” on the calendar screen displayed on the client 8.

  In this case, the analysis apparatus 10 receives the character string data “Go to Hanami” from the client 8 (S71). The analysis apparatus 10 decomposes the part of speech of the received character string data, and acquires the noun word data “hanami” and the verb word data “go” (S72). Here, the particle word data “ni” is excluded from the processing target.

  The analysis apparatus 10 converts the word data “cherry-blossom viewing” and “go” into feature vectors, respectively (S73). Here, a feature vector is exemplified as data representing the feature amount of word data.

  Here, it is assumed that the average feature vector of the provision destination keyword is stored for each provision destination category in the provision destination relation table of the keyword DB 13. According to the example of FIG. 3, the destination category “event” includes an average of a plurality of destination keywords such as “event”, “fireworks”, “festival”, “disaster prevention training”, “cherry blossom viewing”, “reconstruction”, etc. A feature vector is associated. In addition, the provision destination category “gourmet” is associated with an average feature vector of a plurality of provision destination keywords such as “meal”, “gourmet”, and “go”.

  The analysis apparatus 10 calculates the similarity between each of the “Hanami” and “Go” feature vectors converted in (S73) and each average feature vector stored in the provider relationship table, and exceeds a predetermined threshold value. Each providing category associated with the average feature vector indicating the similarity is identified (S74). Here, since the similarity “0.82” between the feature vector of “Hanami” and the average feature vector of the destination category “Event” is equal to or greater than a predetermined threshold, the destination category “Event” is related to the word data “Hanami”. Identified. Also, since the similarity “0.78” between the feature vector of “go” and the average feature vector of the destination category “gourmet” is equal to or greater than a predetermined threshold, the destination category “gourmet” is specified for the word data “go” Is done.

  The analysis apparatus 10 extracts a query category corresponding to the provision destination category specified in (S74) from the query category table. Specifically, the analysis apparatus 10 extracts the query category “event name” for the provider category “event”, and extracts the query categories “dishes name” and “location name” for the provider category “gourmet”. To do.

  Here, it is assumed that an average feature vector of query keywords is stored in the query word table of the keyword DB 13 for each query category. According to the example of FIG. 5, the query category “event name” is associated with the average feature vectors of the query keywords “fireworks”, “festival”, “cherry blossom viewing”, and “Tanabata”. The query category “dishes name” is associated with the average feature vectors of the query keywords “okonomiyaki”, “sukiyaki”, and “yakiniku”.

  The analysis apparatus 10 uses the average feature vectors associated with the extracted query categories “event name”, “dishes name”, and “place name”, and “cherry-blossom viewing” and “go” converted in (S73). The similarity with the feature vector is calculated. The analysis apparatus 10 selects word data whose calculated similarity is equal to or greater than a predetermined threshold as a search keyword (S75). Here, the word data “cherry-blossom viewing” is selected as a search keyword for the providing category “event” because the similarity between the feature vector and the query category “event name” is equal to or greater than a predetermined threshold. However, the word data “cherry blossom” is excluded from the search keyword for the provision category “gourmet” because the similarity to the feature vector of each query category “dishes name” and “place name” is less than a predetermined threshold. On the other hand, the word data “go” has a similarity to the feature vectors of the query categories “event name”, “dishes name”, and “place name” less than a predetermined threshold value. Is excluded from search keywords for "".

  The analysis apparatus 10 determines an event site and a gourmet site (both sites 7) corresponding to the provision destination categories “event” and “gourmet” specified in (S74), and further determines a query required for each site. (S76). The search keyword “hanami” is determined as the search query for the event site, and no search keyword is specified in the search query for the gourmet site.

[Operation and effect of the first embodiment]
As described above, in the first embodiment, word data generated due to the user's action is acquired, and based on the provision destination relationship table indicating the relationship between the plurality of provision destination categories and the plurality of provision destination keywords, A providing category corresponding to the acquired word data is specified. The plurality of provision destination categories are associated with the information providing site 7 respectively. That is, in the first embodiment, the site 7 related to the word data obtained from the user is specified as the search destination from the sites 7 registered in advance as the search destination. Therefore, according to the first embodiment, since the search can be performed on the site 7 that provides information that is reliable and relates to the user, the information that is highly reliable and relates to the user is provided. be able to.

  In the first embodiment, a query category table indicating the relationship between a plurality of destination categories and a plurality of query categories and a query word table indicating the relationship between the plurality of query categories and a plurality of query keywords are referred to. In these tables, for each site 7 (each provider category), a category that matches the content of information provided from the site 7 is registered as a query category, and for each query category, the words belonging to the query category are registered. Each is registered as a query keyword. Then, based on these tables, it is determined whether each word data belongs to the query category corresponding to the specified provider category, and based on this determination, search word is selected from the acquired word data. The word data to be used is selected. Therefore, according to the first embodiment, it is possible to execute a search using word data that matches the content of the information provided from the site 7 as a search keyword. Can provide accuracy.

  In the first embodiment, the correspondence relationship between the provision destination category and the keyword is stored separately in the provision destination relation table and the combination of the query category table and the query word table. The corresponding relationship is directly stored in the providing destination relationship table, and the corresponding relationship is indirectly stored in the combination of the query category table and the query word table via the query category. Thereby, the set of keywords associated with the same site 7 (providing destination category) can be made different between the providing destination relation table and the combination of the query category table and the query word table. As a result, in the providing destination relationship table for determining the search destination, not only directly related keywords but also indirectly related keywords can be associated with the providing destination category. Thereby, since the information accompanying the word obtained from a user can also be provided, the range of the information to provide can be expanded.

  In the first embodiment, the similarity between the word data obtained from the user and the provision destination keyword or the query keyword may be used in specifying the provision destination category and selecting the word data used for the search keyword. That is, in the first embodiment, the search destination site 7 and the search keyword can be determined based on the similarity between words. Thereby, according to 1st embodiment, based on the word data obtained from a user, the site 7 which provides the information which suits a user preference in a concept level or a semantic level, and a search keyword for extracting such information Can be specified. Therefore, the information to be provided can be brought closer to the user's interest and interest.

  Furthermore, in the first embodiment, triggered by reception of data from the client 8, a search is executed, and a passive operation mode in which information extracted by the search is provided to the client 8, and a spontaneous word from the user word DB 12 In response to data acquisition, an active operation mode that provides information is supported. Thereby, the user can acquire the information he wants when he wants it, or can acquire the information he wants unexpectedly.

[Second Embodiment]
In the first embodiment described above, the feature vector may be used as data indicating the feature amount of the word data. In the providing destination relation table and the query word table, instead of the providing destination keyword and the query keyword, the average feature vector is used. Mentioned that may be stored in advance. The second embodiment automates table setting by learning feature vectors. Hereinafter, the information analysis device and the information analysis method in the second embodiment will be described focusing on the contents different from those in the first embodiment. In the following description, the same contents as those in the first embodiment are omitted as appropriate.

The hardware configuration of the analyzer 10 in the second embodiment may be the same as in the first embodiment.
[Processing configuration]
FIG. 8 is a diagram conceptually illustrating a processing configuration example of the analyzer 10 in the second embodiment. The analyzer 10 has software elements as shown in FIG. Specifically, the analysis apparatus 10 includes an acquisition unit 21, a conversion unit 22, a provision destination DB (DataBase) 23, a specification unit 24, a search control unit 25, an output processing unit 26, an evaluation acquisition unit 27, an update unit 28, and the like. Have. Each of these software elements is realized, for example, by executing a program stored in the memory 2 by the CPU 1. In addition, the program is installed from a portable recording medium such as a CD (Compact Disc) or a memory card or another computer on the network via the input / output I / F 3 or the communication unit 4 and is stored in the memory 2. It may be stored.

  The acquisition unit 21 acquires a plurality of word data generated due to the user's action. The acquisition unit 21 receives user identification information from the client 8 together with word data or data that is the basis of the word data. In this embodiment, since the user word DB 12 in the first embodiment does not exist, the active operation mode is not supported. Except for this point, the processing content of the acquisition unit 21 is the same as that of the acquisition unit 11 in the first embodiment.

  The conversion unit 22 converts the plurality of word data acquired by the acquisition unit 21 into feature vectors. Various known methods can be used for this conversion method. The conversion unit 22 may hold a list of feature vectors calculated in advance for a large number of words using a known method. The feature vector may be generated by a device other than the analysis device 10. In this case, the converting unit 22 converts each word data acquired by the acquiring unit 21 into a feature vector using the retained feature vector list. Hereinafter, the converted feature vector may be referred to as a word feature vector.

  The provision destination DB 23 includes a provision destination relation table indicating the relation between a plurality of information provision destinations and a plurality of feature vectors. The provision destination relation table is provided for each user. Further, the relationship between the user identification information, the plurality of information providing destinations, and the plurality of feature vectors may be stored in the providing destination relationship table. In this embodiment, since the information providing destination is described as the site 7, the providing destination relation table stores the identification information of the site 7 and the feature vector in a one-to-one relationship. The identification information of the site 7 may be the address information of the site 7, or may be identification information of a provision category as in the first embodiment. If the address information of the site 7 can be acquired, the information providing destination identification information stored in the providing destination relation table is not limited.

  Since the feature vector stored in the provider relationship table is updated at any time, the initial value is arbitrary. A randomly generated feature vector may be an initial value, or a feature vector converted from a representative word representing the content of information provided from the corresponding site 7 may be an initial value.

  The specifying unit 24 calculates the degree of similarity between each feature vector stored in the user providing destination relationship table and each word feature vector calculated by the conversion unit 22, thereby obtaining an information providing destination (to be searched) ( The combination of the site 7) and word data is specified. The specifying unit 24 specifies the user's provider relationship table based on the user identification information acquired by the acquiring unit 21. Based on the combination of the word feature vector and the feature vector whose calculated similarity is equal to or greater than a predetermined threshold, the specifying unit 24 combines the word data corresponding to the word feature vector and the site 7 corresponding to the feature vector. Is identified. The predetermined threshold only needs to be held in advance by the specifying unit 24, and the specific value is not limited.

  The search control unit 25 requests a search corresponding to the combination specified by the specifying unit 24. Specifically, the search control unit 25 requests a search using the word data in the combination for the information provided from the site 7 in the combination specified by the specifying unit 24 as a search keyword. In a case where different word data are combined for the same site 7 in the plurality of combinations specified by the specifying unit 24, the search control unit 25 selects the information provided from the site 7. Request multiple searches. For example, when the two word data WD1 and WD2 are combined with the information providing destination ST1, the search control unit 25 performs a search using the search keyword WD1 for the information provided from the information providing destination ST1, and the information providing destination. A search using the search keyword WD2 is requested for the information provided from ST1. The processing content of the search control unit 25 is the same as that of the search control unit 16 in the first embodiment.

  The output processing unit 26 transmits information acquired as a search result by the search control unit 16 to the client 8. When a plurality of searches using different search keywords are performed for the same site 7, the output processing unit 26 sends the acquired information to the client 8 so that the user of the client 8 can distinguish the results of each search. The method for outputting the information acquired as the search result at the client 8 is as described in the first embodiment.

  The evaluation acquisition unit 27 acquires the user evaluation information for the information transmitted by the output processing unit 26. The acquired evaluation information may indicate a numerical value indicating an evaluation score, or may indicate whether or not the user has viewed the information. The numerical value indicating the evaluation point may indicate only good or bad, or may indicate a detailed score such as 5 levels or 10 levels. The evaluation acquisition part 27 can grasp | ascertain the browsing state of the user with respect to information by detecting the user's operation with respect to the output information. The evaluation acquisition unit 27 may cause the client 8 to display a screen for allowing the user to input an evaluation of the information after the information is transmitted by the output processing unit 26. The evaluation acquisition unit 27 acquires evaluation information for each search when the output processing unit 26 distinguishes a plurality of search results and transmits them to the client 8. In the present embodiment, the method for acquiring user evaluation information is not limited.

  Based on the evaluation information acquired by the evaluation acquisition unit 27, the update unit 28 updates the feature vector associated with the information providing destination that is the target of the search in the providing destination relation table. The evaluation information acquired by the evaluation acquisition unit 27 indicates an evaluation for a search in which information provided to the user is extracted. Therefore, the feature vector associated with the information provider to be evaluated is updated so as to approach or separate from the feature vector of the word data used in the search. In the present embodiment, the feature vector update method is not limited.

[Operation example / Information analysis method]
Hereinafter, the information analysis method in the second embodiment will be described with reference to FIG. FIG. 9 is a flowchart showing an operation example of the analyzer 10 in the second embodiment. As shown in FIG. 9, the information analysis method in the second embodiment is executed by at least one computer such as the analysis apparatus 10. Each process shown in FIG. 9 is the same as the processing content of each software element included in the analyzer 10, and therefore details of each process are omitted as appropriate.

  The analyzer 10 acquires a plurality of word data (S91). At this time, the analysis apparatus 10 also acquires user identification information that is the source of the word data. Except for the fact that the active operation mode is not supported, the specific content of the step (S91) is the same as the step (S61) in the first embodiment.

  The analysis apparatus 10 converts the plurality of word data acquired in (S91) into word feature vectors, respectively (S92). This conversion method is as described in the description of the conversion unit 22.

  The analysis device 10 provides information to be searched for by calculating the similarity between each feature vector stored in the user's provider relationship table and each word feature vector obtained by the conversion of (S92). A combination of the destination (site 7) and the word data is specified (S93). The similarity calculation method and the combination specifying method are as described in the description of the specifying unit 24.

  For each combination specified by the specifying unit 24, the analyzer 10 requests an information search corresponding to the combination (S94). The contents of (S94) are as described in the description of the search control unit 25.

  The analysis apparatus 10 transmits information acquired as a result of the search executed in response to the request (S94) to the client 8 (S95). When a plurality of searches using different search keywords are performed for the same site 7, the analysis apparatus 10 sends the acquired information to the client 8 so that the user of the client 8 can distinguish the results of each search. The method for outputting the information acquired as the search result at the client 8 is as described in the first embodiment.

  The analysis apparatus 10 acquires user evaluation information for the information transmitted (output) in (S95) (S96). The evaluation information acquired and the method for acquiring the evaluation information are as described in the description of the evaluation acquisition unit 27.

  Based on the evaluation information acquired in (S96), the analysis apparatus 10 updates the feature vector associated with the information providing destination that is the search target in the providing destination relation table (S97). This update method is as described in the description of the update unit 28.

  Next, a specific example of the information analysis method in the second embodiment will be further described using specific data. FIG. 10 is a diagram illustrating a flow of an operation example of the analysis apparatus 10 and a data processing example in the second embodiment. Here, it is assumed that the user US2 inputs a schedule “going to cherry blossom viewing” on the calendar screen displayed on the client 8.

  The contents of (S101), (S102), and (S103) are the same as the contents of (S71), (S72), and (S73) described with reference to FIG.

  In the present embodiment, a feature vector is stored for each information provider (site 7) in the provider relationship table of the provider DB 23. In the example of FIG. 10, the identification information of the user, the identification information of the information providing destination, and the feature vector are associated and stored in the providing destination relationship table. For example, for the user US2, the information providing destination “event site” and the feature vector VC3 are associated, and the information providing destination “gourmet site” and the feature vector VC4 are associated.

  The analysis apparatus 10 calculates the degree of similarity between the word feature vectors “cherry-blossom viewing” and “go” acquired in the conversion of (S103) and the feature vectors stored in the providing relationship table of the user US2. Then, the combination of the information providing destination and the word data is specified (S104). Here, since the similarity “0.56” between the word feature vector of “Hanami” and the feature vector of the information providing destination “event site” is equal to or greater than the predetermined threshold “0”, the word data “Hanami” and the information providing destination are provided. A combination with the “event site” is specified. Furthermore, since the similarity “0.23” between the feature vector of the word data “go” and the feature vector of the information provider “event site” is equal to or greater than the predetermined threshold “0”, the word data “go” and the information provider A combination with the “event site” is specified. Here, the combination related to the information providing destination “gourmet site” is not specified because the similarity is less than the predetermined threshold.

The analysis apparatus 10 requests two searches corresponding to the two combinations specified in (S104). As a result, the first search using the search keyword “hanami” for information provided from the information provider “event site” and the search keyword “go” for information provided from the same information provider “event site” Each of the used second searches is executed.
The analysis device 10 transmits the information obtained by the two searches to the client 8 in a distinguishable state (S105).

  The analysis apparatus 10 acquires evaluation information indicating the evaluation of the user US2 with respect to the information transmitted to the client 8 in (S105) (S106). Specifically, the analysis apparatus 10 acquires evaluation information of information obtained by the first search and evaluation information of information obtained by the second search. Here, the evaluation information regarding the first search indicates that the provided information has been browsed by the user US2, and the evaluation information regarding the second search indicates that the provided information has not been browsed by the user US2. Show.

  Based on the evaluation information acquired in (S106), the analysis apparatus 10 updates the feature vector VC3 associated with the information providing destination “event site” in the providing destination relation table of the user US2 (S107). In the example of FIG. 10, the feature vector VC3 is updated to VC3 ′ so as to approach the word feature vector of the word data “cherry blossom” and take a value away from the word feature vector of the word data “go”.

[Operation and effect of the second embodiment]
In the second embodiment, a feature vector is associated with each information providing destination, and the combination of the information providing destination and the word data is specified based on the similarity between the feature vector of the word data obtained from the user and the feature vector. Is done. Furthermore, based on the identified combination, a search using a search keyword is performed on information provided from the information providing destination, and information extracted by the search is provided to the user. Then, the user evaluation information related to the provided information is acquired, and the feature vector associated with the information providing destination is updated based on the evaluation information.

  Thereby, when the user's evaluation is high, the feature vector associated with each information providing destination is updated so as to approach the feature amount of the word data used for the search keyword, and when the user's evaluation is low, the word Updated to move away from the data feature. That is, according to the second embodiment, the relationship between the information providing destination and the feature vector is automatically learned so as to suit each user's preference. As a result, according to the second embodiment, setting of the provision destination relation table can be automated. According to the second embodiment, desired information can be provided to the user, and the management effort of the table can be reduced.

[Third embodiment]
Hereinafter, an information analysis apparatus and an information analysis method according to the third embodiment will be described. The third embodiment may be a program that causes at least one computer to execute the information analysis method, or may be a recording medium that can be read by the at least one computer that records such a program. Good.

  FIG. 11 is a diagram conceptually illustrating a processing configuration example of the information analysis apparatus 100 in the third embodiment. As illustrated in FIG. 11, the information analysis apparatus 100 includes an acquisition unit 101, a specification unit 102, a selection unit 103, and a search control unit 104. The information analysis apparatus 100 shown in FIG. 11 has, for example, the same hardware configuration as that of the above-described analysis apparatus 10 shown in FIG. Each software element is realized.

  The acquisition unit 101 acquires a plurality of word data generated due to the user's action. The user's operation includes all operations such as operation of the client 8 (keyboard operation, mouse operation, touch panel operation, moving the terminal of the client 8, etc.), speech, gesture and the like. The acquired word data may be word data obtained indirectly due to the user's action. For example, the acquisition unit 101 can also acquire the plurality of word data from character string data included in information provided from a server device (not shown) by a user browsing operation. The acquisition unit 101 may acquire the plurality of word data from the client 8, or apply predetermined processing (morphological analysis, speech recognition, gesture recognition, etc.) to data obtained from the client 8 or another device. Thus, the plurality of word data may be acquired. The acquisition unit 101 can also acquire word data from a portable recording medium or a device other than the client 8.

  The specifying unit 102 specifies a provider category corresponding to the plurality of word data acquired by the acquiring unit 101 from the plurality of provider categories. The meaning of the provision destination category is as described in the first embodiment. Specific examples of the specifying unit 102 are the specifying unit 14 and the specifying unit 24. That is, the specifying unit 102 may use the provision destination relation table of the keyword DB 13 in the first embodiment or the provision destination relation table of the provision destination DB 23 in the second embodiment. The specifying unit 102 may use matching between words, or may use similarity between words (between feature data).

  As illustrated in FIG. 11, the information analysis apparatus 100 may or may not have the provision destination relation table. The information analysis apparatus 100 may refer to the provision destination relation table possessed by another apparatus.

  The selection unit 103 is configured to obtain each relationship acquired by the acquisition unit 101 based on query relationship information indicating a relationship between a plurality of provision destination categories and a plurality of query categories and a relationship between the plurality of query categories and a plurality of keyword information data. A word used as a search keyword from among a plurality of word data acquired by the acquisition unit 101 by determining whether the word data belongs to a query category associated with the provision category specified by the specifying unit 102 Select data. Specific examples of the query relation information are the query category table and the query word table in the first embodiment. The keyword information data indicated by the query relation information is word data or feature data (including a feature vector) indicating a word feature. The meaning of the query category is as described in the first embodiment. The information analysis apparatus 100 may or may not have query related information. The information analysis apparatus 100 may refer to query relation information possessed by another apparatus. A specific example of the selection unit 103 is the selection unit 15.

  The search control unit 104 requests a search using the word data selected by the selection unit 103 as a search keyword for information provided from an information providing destination corresponding to the providing destination category specified by the specifying unit 102. The information providing destination means a device that provides various types of information. A specific example of the information providing destination is the information providing site 7. The search control unit 104 may request a search from the information providing destination, or may request a search from another device that has collected all the information provided from the information providing destination. In addition, when the information analysis apparatus 100 itself executes a search, the search control unit 104 may request a search from a software element that performs the search. Specific examples of the search control unit 104 are the search control unit 16 and the search control unit 25.

  As illustrated in FIG. 11, the information analysis apparatus 100 may not include the output processing unit 17 and the output processing unit 26. This is because the information obtained by the search may be sent to the client 8 from another device (including the information providing destination).

  The information analysis method in the third embodiment is executed by at least one computer such as the information analysis apparatus 100. The information analysis method in this embodiment includes steps (S111), (S112), (S113), (S114), and (S115). Since these processes are the same as the processing contents of the software elements included in the information analysis apparatus 100, details of the processes are omitted as appropriate.

In step (S111), the computer (CPU 1) acquires a plurality of word data generated due to the user's action.
In step (S112), the computer (CPU 1) specifies a provision destination category corresponding to at least one word data recorded and acquired in (S111) from among a plurality of provision destination categories.

  In the step (S113), the computer (CPU 1), based on the query relationship information indicating the relationship between the plurality of destination categories and the plurality of query categories and the relationship between the plurality of query categories and the plurality of keyword information data ( It is determined whether each word data acquired in (S111) belongs to the query category associated with the providing destination category specified in (S112).

In step (S114), the computer (CPU 1) selects word data to be used as a search keyword from the plurality of word data acquired in (S111) based on the determination result in (S113).
In step (S115), the computer (CPU1) uses the word data selected in (S114) as the search keyword for the information provided from the information provider corresponding to the provider category specified in (S112). Request a search.

  In the third embodiment, one provision destination category may be associated with only one information provision destination, or may be associated with a plurality of information provision destinations. For example, in the case where one provision destination category is associated with only one information provision destination, the above-mentioned “provision destination category” can be replaced with “information provision destination”.

[Operation and effect of the third embodiment]
In the third embodiment, a provision destination category is specified based on a plurality of word data generated due to a user's action, and an information provision destination corresponding to the provision destination category is a target of information search. Therefore, according to the third embodiment, by registering a highly reliable information providing destination, it is possible to perform a search for an information providing destination that provides information that is highly reliable and related to the user. it can. As a result, it is possible to provide the user with high reliability and information related to the user.

  Furthermore, in the third embodiment, it is determined whether or not each of the word data belongs to a query category associated with the specified provider category, and a search keyword is selected from the plurality of word data based on the determination result. The word data to be used is selected. Thereby, in the third embodiment, even if the word data is generated due to the user's action, the word data that does not belong to the query category corresponding to the information providing destination specified as described above is the search keyword. Excluded from. Therefore, according to the third embodiment, since it is possible to execute a search using word data that matches the content of information provided from an information providing destination as a search keyword, information that matches the user's interests and interests can be obtained. It can be provided with high accuracy.

  In the third embodiment, a search using a search keyword for information provided from the information providing destination is requested based on the providing destination category specified as described above and the selected word data. Since this request only needs to be made to a device or software element having an information search function, it does not depend on the presence or absence of the site search function and can target various reliable information providing destinations.

  In addition, in the some flowchart used by the above-mentioned description, although several process (process) is described in order, the execution order of the process performed by each embodiment is not restrict | limited to the order of the description. In each embodiment, the order of the illustrated steps can be changed within a range that does not hinder the contents. Moreover, each above-mentioned embodiment can be combined in the range in which the content does not conflict.

  The above contents can also be specified as follows. However, the above-mentioned content is not limited to the following description.

1. Acquisition means for acquiring a plurality of word data generated due to user's action;
A specifying means for specifying a provider category corresponding to the acquired plurality of word data from a plurality of provider categories;
Each acquired word data is specified based on query relationship information indicating a relationship between the plurality of destination categories and a plurality of query categories and a relationship between the plurality of query categories and a plurality of keyword information data. Selecting means for selecting word data to be used as a search keyword from the plurality of obtained word data by determining whether or not each belongs to a query category associated with a provider category;
Search control means for requesting a search using the selected word data as a search keyword for information provided from an information provider corresponding to the specified provider category;
An information analysis apparatus comprising:
2. The specifying unit specifies the providing destination category by referring to providing destination relation information indicating a relationship between the plurality of providing destination categories and the plurality of keyword information data;
In the provider relationship information and the query relationship information, keyword information data groups associated with at least one same provider category are different.
1. Information analysis device described in 1.
3. The specifying means specifies a plurality of provision destination categories corresponding to the plurality of acquired word data,
The selection means selects word data to be used as a search keyword from the plurality of acquired word data for each of the specified plurality of provision destination categories.
1. Or 2. Information analysis device described in 1.
4). The selection unit calculates a similarity between the keyword information data indicated by the query relation information and the feature amount of each acquired word data, and uses each of the acquired words using the calculated similarity. Respectively determining whether the data belongs to a query category associated with the specified provider category;
1. To 3. An information analysis apparatus according to any one of the above.
5. The specifying unit calculates the similarity between the keyword information data indicated by the supply destination relation information indicating the relationship between the plurality of supply destination categories and the plurality of keyword information data and the feature amount of each acquired word data. And specifying the provider category based on the calculated distance of similarity.
1. To 4. An information analysis apparatus according to any one of the above.
6). When there is a provision category for which no word data has been selected, the search control means requests a search without specifying a search keyword for information provided from the site 7 corresponding to the provision category. To
1. To 5. An information analysis apparatus according to any one of the above.
7). Acquisition means for acquiring a plurality of word data generated due to user's action;
Conversion means for converting each of the obtained plurality of word data into a word feature vector;
By calculating the similarity between each feature vector and each word feature vector associated with a plurality of information providing destinations in the user providing destination relation information, a combination of the information providing destination and word data to be searched is calculated. Identification means to identify;
Search control means for requesting a search using word data in the combination as a search keyword for the information provided from the information providing destination in the specified combination;
Evaluation acquisition means for acquiring the user evaluation information for the search result information requested by the search control means;
Updating means for updating a feature vector associated with the information providing destination to be searched based on the obtained evaluation information in the providing destination relation information;
An information analysis apparatus comprising:
8). The acquisition means extracts the plurality of word data by decomposing part-of-speech of character string data acquired due to the action of the user.
1. To 7. An information analysis apparatus according to any one of the above.
9. The acquisition means acquires the plurality of word data from a plurality of word data accumulated in association with the user.
1. To 6. An information analysis apparatus according to any one of the above.
10. In an information analysis method executed by at least one computer,
Get multiple word data generated due to user actions,
A provider category corresponding to the acquired at least one word data is identified from a plurality of provider categories;
Each acquired word data is specified based on query relationship information indicating a relationship between the plurality of destination categories and a plurality of query categories and a relationship between the plurality of query categories and a plurality of keyword information data. Determine whether each belongs to the query category associated with the provided category,
Based on the result of the determination, select word data to be used as a search keyword from the plurality of acquired word data,
Requesting a search using the selected word data as a search keyword for information provided from an information provider corresponding to the specified provider category;
Information analysis method.
11. The specifying includes referring to provision destination relation information indicating a relation between the plurality of provision destination categories and the plurality of keyword information data;
In the provider relationship information and the query relationship information, keyword information data groups associated with at least one same provider category are different.
10. Information analysis method described in 1.
12 Identifying a plurality of destination categories corresponding to the plurality of acquired word data;
Based on the query relation information, it is determined whether each of the acquired word data belongs to a query category associated with each specified provider category,
For each of the plurality of specified supply destination categories, respectively select word data to be used as a search keyword from the plurality of acquired word data.
Further includes: Or 11. Information analysis method described in 1.
13. Calculating the degree of similarity between the keyword information data indicated by the query relation information and the feature quantity of each acquired word data;
Further including
The determination is performed by using the calculated similarity to determine whether each acquired word data belongs to a query category associated with the specified provider category,
10. To 12. The information analysis method as described in any one of these.
14 Calculating the degree of similarity between the keyword information data indicated by the provision destination relation information indicating the relationship between the plurality of provision destination categories and the plurality of keyword information data and the feature amount of each of the acquired word data;
Further including
The specification specifies the provision destination category based on the calculated distance of similarity.
10. To 13. The information analysis method as described in any one of these.
15. If there is a provision category for which no word data has been selected, a search without designating a search keyword is requested for information provided from the site 7 corresponding to the provision category.
Further includes: To 14. The information analysis method as described in any one of these.
16. In an information analysis method executed by at least one computer,
Get multiple word data generated due to user actions,
Respectively converting the plurality of acquired word data into word feature vectors;
Calculating the similarity between each feature vector and each word feature vector associated with a plurality of information providing destinations in the user providing destination relation information,
Based on the calculated similarity, identify a combination of information providing destination and word data to be searched,
Requesting a search using word data in the combination for the information provided from the information providing destination in the specified combination as a search keyword;
Obtaining the user evaluation information for the requested search result information;
Based on the acquired evaluation information, the feature vector associated with the information providing destination that is the target of the search is updated in the providing destination relation information.
An information analysis method further comprising:
17. Part-of-speech decomposition of character string data acquired due to the user's action;
Further includes: To 16. The information analysis method as described in any one of these.
18. The acquisition acquires the plurality of word data from a plurality of word data accumulated in association with the user.
10. To 15. The information analysis method as described in any one of these.
19. 10. To 18. A program that causes at least one computer to execute the information analysis method according to any one of the above.

1 CPU
2 Memory 7 Information provision site (site)
8 Client device (client)
10,100 Information analyzer (analyzer)
11, 21, 101 Acquisition unit 12 User word DB
13 Keyword DB
14, 24, 102 Identification unit 15, 103 Selection unit 16, 25, 104 Search control unit 17, 26 Output processing unit 22 Conversion unit 23 Destination DB
27 Evaluation acquisition unit 28 Update unit

Claims (11)

Acquisition means for acquiring a plurality of word data generated due to user's action;
A specifying means for specifying a provider category corresponding to the acquired plurality of word data from a plurality of provider categories;
Each acquired word data is specified based on query relationship information indicating a relationship between the plurality of destination categories and a plurality of query categories and a relationship between the plurality of query categories and a plurality of keyword information data. Selecting means for selecting word data to be used as a search keyword from the plurality of obtained word data by determining whether or not each belongs to a query category associated with a provider category;
Search control means for requesting a search using the selected word data as a search keyword for information provided from an information provider corresponding to the specified provider category;
An information analysis apparatus comprising: The specifying unit specifies the providing destination category by referring to providing destination relation information indicating a relationship between the plurality of providing destination categories and the plurality of keyword information data;
In the provider relationship information and the query relationship information, keyword information data groups associated with at least one same provider category are different.
The information analysis apparatus according to claim 1. The specifying means specifies a plurality of provision destination categories corresponding to the plurality of acquired word data,
The selection means selects word data to be used as a search keyword from the plurality of acquired word data for each of the specified plurality of provision destination categories.
The information analysis apparatus according to claim 1 or 2. The selection unit calculates a similarity between the keyword information data indicated by the query relation information and the feature amount of each acquired word data, and uses each of the acquired words using the calculated similarity. Respectively determining whether the data belongs to a query category associated with the specified provider category;
The information analysis apparatus according to any one of claims 1 to 3. The specifying unit calculates the similarity between the keyword information data indicated by the supply destination relation information indicating the relationship between the plurality of supply destination categories and the plurality of keyword information data and the feature amount of each acquired word data. And specifying the provider category based on the calculated distance of similarity.
The information analysis device according to any one of claims 1 to 4. When there is a provision category for which no word data has been selected, the search control means requests a search without specifying a search keyword for information provided from the site 7 corresponding to the provision category. To
The information analysis device according to any one of claims 1 to 5. Acquisition means for acquiring a plurality of word data generated due to user's action;
Conversion means for converting each of the obtained plurality of word data into a word feature vector;
By calculating the similarity between each feature vector and each word feature vector associated with a plurality of information providing destinations in the user providing destination relation information, a combination of the information providing destination and word data to be searched is calculated. Identification means to identify;
Search control means for requesting a search using word data in the combination as a search keyword for the information provided from the information providing destination in the specified combination;
Evaluation acquisition means for acquiring the user evaluation information for the search result information requested by the search control means;
Updating means for updating a feature vector associated with the information providing destination to be searched based on the obtained evaluation information in the providing destination relation information;
An information analysis apparatus comprising: The acquisition means extracts the plurality of word data by decomposing part-of-speech of character string data acquired due to the action of the user.
The information analysis apparatus according to any one of claims 1 to 7. The acquisition means acquires the plurality of word data from a plurality of word data accumulated in association with the user.
The information analysis apparatus according to any one of claims 1 to 6. In an information analysis method executed by at least one computer,
Get multiple word data generated due to user actions,
A provider category corresponding to the acquired at least one word data is identified from a plurality of provider categories;
Each acquired word data is specified based on query relationship information indicating a relationship between the plurality of destination categories and a plurality of query categories and a relationship between the plurality of query categories and a plurality of keyword information data. Determine whether each belongs to the query category associated with the provided category,
Based on the result of the determination, select word data to be used as a search keyword from the plurality of acquired word data,
Requesting a search using the selected word data as a search keyword for information provided from an information provider corresponding to the specified provider category;
Information analysis method.   A program causing at least one computer to execute the information analysis method according to claim 10.

Images