JP6664599B2 - Ambiguity evaluation device, ambiguity evaluation method, and ambiguity evaluation program - Google Patents

Description

  The present invention relates to an ambiguity evaluation device, an ambiguity evaluation method, and an ambiguity evaluation program for evaluating ambiguity for a keyword used at the time of a search.

  2. Description of the Related Art Conventionally, there is a service that discloses a Web site or the like on a communication network such as the Internet and presents information desired by a terminal user to a terminal accessing the Web site. For example, in a service form such as online shopping, a database in which merchandise information is registered in advance by a predetermined keyword (for example, a search query or the like) specified by the user from a terminal is searched, and the extracted merchandise is used by the user. If the product is present, the user can be provided with the product by performing a purchase procedure or the like.

  Conventionally, when a user enters a search keyword and clicks a "search" button, the user not only jumps to the search result page, but also displays other search keywords related to the search keyword entered by the user. (See, for example, Patent Document 1).

  In Patent Literature 1, a search keyword set received by a user is received, and a plurality of predetermined words corresponding to intentions not clearly defined are compared with the search keyword set, so that the search keyword set is clearly defined by the user. It is determined whether or not the keyword indicates the intention specified in (1), and if it is determined that the search keyword set indicates the intention clearly specified, a process for acquiring a further recommended search keyword is executed.

JP 2014-501422 A

  In the above-described method, it is indispensable to accurately estimate the ambiguity of the intention in order to appropriately switch the processing for displaying the search keyword. Simply, even though we can quantify ambiguity based on the click distribution of each query, there is actually a difference in the degree of relevance between clicks, and in order to estimate more realistically, Further use of information is required.

  The present invention has been made in view of the above problems, and has as its object to present an appropriate search result to a user by quantifying the ambiguity of the user's intention.

Ambiguity evaluation apparatus according to an embodiment of the present invention, and keywords used during search as a search history information in association with a plurality of categories corresponding to the search results retrieved from the search data by using the keywords storage means for Ru was stored, the search history information that will be stored in the storage means, calculating a similarity between the plurality of categories for the keywords, ambiguity evaluation for evaluating the ambiguity of the keyword from the calculated degree of similarity Means.

  According to the embodiment of the present invention, it is possible to quantify the ambiguity of the user's intention and to present an appropriate search result to the user.

It is a figure showing an example of the whole composition of an information presentation system. FIG. 3 is a diagram illustrating an example of a hardware configuration of the ambiguity evaluation device. It is a flowchart which shows an example of information presentation processing. It is a figure for explaining the ambiguity of a query. It is a figure for explaining the relation of similarity and ambiguity with respect to a category. It is a figure showing an example of a calculation result of similarity. It is a figure showing an example of the contents of a search using ambiguity data.

  Hereinafter, each embodiment of the present invention will be described in detail with reference to the accompanying drawings.

<Overall configuration of information presentation system>
FIG. 1 is a diagram illustrating an example of the overall configuration of the information presentation system. In the example of FIG. 1, the information presentation system 10 includes an ambiguity evaluation device 11, which is an example of an information presentation device, and one or a plurality of terminals 12-1 to 12-n (hereinafter, “terminal 12” as necessary). ). The ambiguity evaluation device 11 and the terminal 12 are connected to a communication network 13 typified by a LAN (Local Access Area) or the Internet so that data can be transmitted and received.

  The ambiguity evaluation device 11 publishes Web sites such as shopping sites, news sites, Q & A sites, e-commerce sites, search sites, and the like. The ambiguity evaluation device 11 receives an input of a predetermined keyword (for example, a search query) or the like from the terminal 12 accessed via the communication network 13, and stores search target data (for example, product data) or the like stored in advance. , The corresponding product information (title, category, etc.), search results of words, sentences, etc. are extracted and provided to the terminal 12 from which the keyword has been input. In addition, the ambiguity evaluation device 11 associates a search query from each terminal 12 with a category for a search result searched from product data using the search query, and stores the search query, for example, as a search log (search history information). .

  Here, the category is an individual division when a thing is classified based on a certain standard, and is divided into, for example, a classification, a field, a division, a type, a section, and a genre. For example, when the search query is “table”, the categories are “row table”, “center table”, “side table”, etc., but are not limited thereto. In the present embodiment, the ambiguity evaluation device 11 may acquire the above-described product data and search log information from an external device that provides another Web site.

  Further, the ambiguity evaluation device 11 calculates the similarity between categories using the above-described product data and the search log, and evaluates the ambiguity related to the keyword (query) based on the calculated similarity. For example, the ambiguity evaluation device 11 generates a vector expression for each category from the product data, extracts a category distribution for each query from the click result of the search log, and obtains the vector expression and the category distribution described above. The ambiguity of each query is evaluated based on the similarity between the categories. When the ambiguity evaluation device 11 has data (category tree) of a tree structure between categories having high reliability in advance, the ambiguity evaluation device 11 may calculate the similarity based on the category tree. In this case, for example, with respect to a keyword (for example, a table) used at the time of a search, the similarity is calculated from a relationship between a category (for example, a row table, etc.) of a lower concept of a category corresponding to the keyword by referring to a tree structure. can do.

  In addition, when a search query from the terminal 12 is received, the ambiguity evaluation device 11 refers to an ambiguity evaluation result (ambiguity data) and performs other information (for example, The search query is supplemented by another search query, etc., and a search is performed using the supplemented content. Further, the ambiguity evaluation device 11 presents the search result to the terminal 12.

  The ambiguity evaluation device 11 may be, for example, a general-purpose PC (Personal Computer) or a server, or may be a cloud server configured by cloud computing having at least one information processing device, but is not limited thereto. .

  The terminal 12 is a device for each user to receive a service from the ambiguity evaluation device 11 or the like. The user accesses the ambiguity evaluation device 11 from the terminal 12 via the communication network 13 and searches for desired information (product information) using a search screen or the like published on the Web site. When performing a search, by performing user registration or the like, history information for each user can be obtained, and an appropriate search result can be presented for each user. The terminal 12 may be a PC or a communication terminal such as a tablet terminal, a smartphone, or a mobile phone, but is not limited thereto.

  The communication network 13 is a LAN or the Internet as described above. The communication network 13 may be wired, wireless, or a combination thereof.

<Functional configuration of ambiguity evaluation device 11>
Next, an example of a functional configuration of the ambiguity evaluation device 11 described above will be specifically described. As shown in FIG. 1, the ambiguity evaluation device 11 includes an input unit 21, an output unit 22, a storage unit 23, an ambiguity evaluation unit 24, a search unit 25, an information presentation unit 26, and a communication unit 27. And control means 28.

  The input unit 21 receives inputs such as an ambiguity evaluation process in the present embodiment, start / end of an information presentation process, and various settings. The input unit 21 is a pointing device such as a keyboard and a mouse if the ambiguity evaluation device 11 is a general-purpose computer such as a PC. Further, the input means 21 may be a touch panel or the like. Further, the input unit 21 may be a voice input device such as a microphone capable of performing the above-described input by voice or the like, for example.

  The output unit 22 outputs the content input by the input unit 21 and the content executed based on the input content. The output unit 22 is, for example, a display or a speaker. The output unit 22 may be a touch panel integrated with the input unit 21. Further, the output unit 22 may be a printing device such as a printer that prints a processing result or the like on a printing medium such as paper.

  The storage unit 23 stores various information required in the present embodiment. Specifically, the storage unit 23 stores product data 31 for extracting product information corresponding to the input search query, a search query, and a search log storing the search query in association with a category corresponding to a search result by the search query. 32, ambiguity data 33 storing the ambiguity for each search query, and information presentation data 34 storing supplementary information, presentation information, and the like corresponding to the ambiguity. The product data 31 is an example of search target data, and is not limited to product data.

  The information stored in the storage unit 23 is not limited to these. For example, a category associated with a keyword used at the time of a search is stored as tree-structured data (category tree) between preset categories. May be. Further, the storage unit 23 may store, for example, address information for communicating with the terminal 12, user information for identifying the user, terminal information for identifying the terminal 12, and abnormal information when an error occurs. Good.

  The ambiguity evaluation means 24 evaluates the ambiguity of each search query based on the similarity between categories obtained as a result of the search by the search query. For example, when calculating the similarity between the categories, the ambiguity evaluation unit 24 replaces each category with a vector in a linguistic space.

  For example, the ambiguity evaluation unit 24 generates a vector expression for each category from the product data 31. Note that, for generating the vector expression, for example, a technique such as a latent semantic index (LSI) can be used, but the present invention is not limited to this. Further, the ambiguity evaluation unit 24 extracts a category distribution (click rate) for each query from the number for each category associated with each search query included in the search log 32. The ambiguity evaluation means 24 calculates the similarity by combining the vector expression and the category distribution, and evaluates the ambiguity for each query based on the calculated similarity.

  Note that the search log 32 may be a collection of logs of each terminal 12, a log for each terminal 12 (for each user), and may be classified according to predetermined conditions (for example, a period, a time zone, a region) and the like. May be. The search log 32 may store a group of categories that the user has clicked (browsing instruction) among the categories corresponding to the search results. In this case, the ambiguity evaluation unit 24 extracts a category distribution (click ratio) for each query from the number of clicks (the number of browsing instructions) for each category included in the search log 32, and combines the vector expression and the category distribution to obtain a similarity. Calculate the degree. As described above, by reducing the information amount of the search log 32, the processing can be speeded up. Also, what the user instructed to browse is highly likely to be the information desired by the user, so by calculating the similarity using only the useful information, the ambiguity of each query is appropriately evaluated, The evaluation result can be used for the next search or the like.

  In calculating the similarity, the ambiguity evaluation unit 24 compares metadata such as words, genres, attribute information, and detailed descriptions associated with each category, and determines the number and type of matching data. May be used to calculate the similarity.

  In the case where a preset category tree is stored in, for example, the storage unit 23, the ambiguity evaluation unit 24 may calculate the similarity based on the category tree. The category tree is such that a relationship between categories is formed in a tree structure such as “table> center table> glass table” and “table> center table> wooden table”. For example, if there is a tree structure such as “table> row table”, “table> center table”, “table> side table”, etc., “row table”, “center table”, “center table”, The similarity between the "side tables" is calculated as being high.

  The category tree preferably has a highly reliable (sufficiently reliable) tree structure. The editing of the tree structure is usually performed manually, and the category “digital camera” is manually changed by another person such as “PC-related equipment> digital camera” or “camera> digital camera”. In such a case, the reliability is low. The similarity can be calculated with high accuracy by using not a category tree with low reliability but a category tree with high reliability that is mechanically formed based on a predetermined condition.

  The ambiguity evaluation unit 24 stores the ambiguity evaluation result for each query obtained based on the similarity between the categories in the storage unit 23 as the ambiguity data 33.

  The search means 25 refers to the ambiguity data 33 corresponding to the search query when the input of the search query from the terminal 12 is received. If the search query is not ambiguous, the search means 25 executes the product data with the search query as it is. A search to 31 is performed. Further, when the search query is ambiguous, the search unit 25 performs a process of supplementing the search query, and performs a search using the supplemented content.

  Here, the replenishment process means that the search range is expanded by adding another search query set in advance corresponding to the input search query, or user preference information registered in advance (for example, sports enthusiasts). , Gardening, fashion enthusiasts, etc.), or the input query is changed to narrow down the search range, but the processing is not limited to this. Note that the other search queries and user preference information described above can be acquired with reference to the information presentation data 34, for example. The search unit 25 stores the search query in the search log 32 in association with the category or the like corresponding to the search result.

  The information presenting unit 26 presents the result searched by the searching unit 25 to the terminal 12. When presenting the search result, if the user preference information or the like has been registered in advance, the information presenting unit 26 may sort and display the search result in an order corresponding to the user preference. In addition, when there is a browsing instruction such as a click on the category of the search result from the presented terminal 12, the information presenting unit 26 may store the information in the search log 32.

  The communication unit 27 transmits and receives data to and from each terminal 12 via the communication network 13. Note that the communication unit 27 may perform a user authentication process when accessing from the terminal 12. In the user authentication process, for example, it is determined whether or not authentication information such as a user ID and a password input from the terminal 12 matches a user ID and a password included in the user information stored in the storage unit 23 in advance. If they match, the access from the terminal 12 is permitted. If they do not match, the user is notified of the fact, and the user is not allowed to use it unless the user newly registers. It is not something to be done.

  The control unit 28 controls the entire components of the ambiguity evaluation device 11. For example, the control unit 28 performs control such as evaluation of ambiguity for each search query by the ambiguity evaluation unit 24, search by the search unit 25, and information presentation by the information presentation unit 26, but is not limited thereto. . For example, the control unit 28 may perform control such as start and end of various processes in this embodiment, control when an error occurs, and the like.

<Hardware configuration of ambiguity evaluation device 11>
Here, in the present embodiment, an execution program (ambiguity evaluation program) for causing a computer to execute each function of the ambiguity evaluation device 11 described above is generated and installed in, for example, a general-purpose PC, server, or the like. It is possible to realize information presentation processing in the form.

  FIG. 2 is a diagram illustrating an example of a hardware configuration of the ambiguity evaluation device. The computer body of the ambiguity evaluation device 11 shown in FIG. 2 includes an input device 41, an output device 42, a drive device 43, an auxiliary storage device 44, a memory device 45, and a CPU (Central Processing Unit) for performing various controls. ) 46 and a network connection device 47, which are interconnected by a system bus B.

  The input device 41 has a keyboard and a pointing device such as a mouse operated by a user or the like, has a voice input device or the like such as a microphone, and inputs various operation signals such as execution of a program from the user or the like.

  The output device 42 has a display for displaying various windows, data, and the like necessary for operating the computer main body that performs each process in the present embodiment, and displays the execution progress, results, and the like by a control program of the CPU 46.

  Here, the execution program installed in the computer main body in the present embodiment is provided by a portable recording medium 48 such as a USB (Universal Serial Bus) memory or a CD-ROM. The recording medium 48 can be set in the drive device 43, and an execution program included in the recording medium 48 is installed in the auxiliary storage device 44 from the recording medium 48 via the drive device 43.

  The auxiliary storage device 44 is a storage unit such as a hard disk, and stores the execution program according to the present embodiment, a control program provided in a computer, and the like, and can perform input / output as needed.

  The memory device 45 stores an execution program and the like read from the auxiliary storage device 44 by the CPU 46. The memory device 45 is a ROM (Read Only Memory), a RAM (Random Access Memory), or the like. Note that the auxiliary storage device 44 and the memory device 45 described above may be integrally configured as one storage device.

  The CPU 46 controls processes of the entire computer, such as various calculations and input / output of data with each hardware component, based on a control program such as an OS (Operating System) and an execution program stored in the memory device 45. Thus, the information presentation process according to the present embodiment is realized. Various information and the like necessary during execution of the program may be obtained from the auxiliary storage device 44 and the execution result or the like may be stored.

  The network connection device 47 obtains an execution program from another device connected to the communication network by connecting to a communication network represented by the Internet, a LAN, or the like. Further, the network connection device 47 can provide an execution result obtained by executing the program or the execution program itself in the present embodiment to another device or the like.

  The recording medium 48 is a computer-readable recording medium that stores an execution program and the like as described above. The recording medium 48 may be, for example, a semiconductor memory such as a flash memory. In addition, the recording medium 48 may be a portable recording medium such as a USB memory, but is not limited to this.

  In the present embodiment, by installing an execution program (for example, an ambiguity evaluation program or the like) on the above-described hardware configuration of the computer main body, hardware resources and software cooperate to implement the ambiguity evaluation processing in the present embodiment. Etc. can be realized. Further, the ambiguity evaluation program corresponding to the above-described ambiguity evaluation processing may be, for example, in a state of being resident on the device, or may be activated by an activation instruction. The hardware configuration described above may be applied to the terminal 12, for example.

<Information presentation processing in the present embodiment>
Next, information presentation processing including ambiguity evaluation processing in the present embodiment will be described using a flowchart. FIG. 3 is a flowchart illustrating an example of the information presentation process. In the following description, a state is shown in which the ambiguity evaluation device 11 has already performed a search or the like by each terminal 12 or the like and has a search log.

  In the example of FIG. 3, the ambiguity evaluation unit 24 generates a vector expression for each category from the commodity data 31 stored as an example of the search target data stored in advance (S01). Next, the ambiguity evaluation unit 24 extracts a category distribution for each query from the click result of the search log 32 (S02). In the process of S02, the category distribution may be extracted using the search result category instead of the click result for the search result category included in the search log 32.

  Next, the ambiguity evaluation means 24 calculates the similarity between the categories for each query by combining the vector expression and the category distribution (S03), and evaluates the ambiguity for each query from the calculated similarity. The data 33 is stored in the storage unit 23 (S04). Note that the processes of S01 to S04 need only be performed before the processes of S05 and thereafter, and need not be performed continuously.

  Next, the search unit 25 receives an input of a search query from the terminal 12 (S05), refers to the ambiguity data for the received search query, and acquires a corresponding ambiguity (S06). Next, the search unit 25 determines whether or not the obtained ambiguity is equal to or greater than a preset threshold (S07). If the obtained ambiguity is equal to or greater than the threshold (YES in S07), other information (for example, The search is performed by supplementing additional keywords (S08). In addition, in the processing of S07, when the value is not equal to or larger than the threshold value (NO in S07), the search unit 25 performs a search using a search query without performing replenishment (S09).

  After the processing of S08 or S09, the information presenting means 26 presents information of the search result (S10). Further, the information presenting unit 26 acquires information such as a click result from the terminal 12 for the presented search result, and stores the information in the search log 32 together with the search query, the search result, and the like (S11).

  Here, the search unit 25 determines whether or not an input of another search query has been received (S12), and if an input of another search query has been received (YES in S12), the process returns to S06. When the input of another search query is not received (NO in S12), for example, after a predetermined time has elapsed, or when there is a process such as closing the screen of the Web site from the terminal 12, the control unit 28 Then, the information presenting process in the present embodiment ends.

<Query ambiguity>
Here, the ambiguity of the query in the present embodiment will be described with reference to the drawings. FIG. 4 is a diagram for explaining the ambiguity of a query.

  For example, in the example shown in FIG. 4A, when the category clicked by the user among the search results for the search query “table” is “row table”, “center table”, “side table”, etc., these are Since they belong to the genre (attribute) of the same product “desk”, the similarity is high. Therefore, when the similarity of each category is high (for example, equal to or more than a preset threshold), it is determined that the ambiguity of the query is low, and the search is performed without performing the supplementary processing for the query of “table”. Is done.

  Further, in the example shown in FIG. 4B, it is assumed that the category clicked by the user among the search results for the search query “balloon” is “balloon bowl”, “balloon skirt”, and “balloon telegram”. In such a case, although each has the character "balloon", the genre of the product is not the same. Therefore, in such a case, the similarity between the categories is low, and the query “balloon” performs the above-described supplement processing as a keyword with high ambiguity. For example, when there is preference information such as “I like gardening” as user information, the search query is searched using a compound word such as “balloon × gardening”. Thereby, an appropriate search result can be presented to the user.

<Vagueness evaluation method>
Next, an example of the ambiguity evaluation method in the present embodiment will be specifically described. For example, the ambiguity evaluation unit 24 includes information on a product category and a product title obtained from the product data 31, a search query included in the search log 32, and a click of each user on each category of the search result by the search query. The ambiguity of the search query is determined by counting the number (the number of browsing instructions).

  For example, the association between a category and a product is usually performed based on human judgment or the like, and thus has incompleteness. Further, the categories are not necessarily independent, and some categories have high similarity to other categories. Therefore, in the present embodiment, each category is mapped to a low-dimensional vector space using an LSI or the like. The LSI is usually applied to an association matrix between terms (words) and sentences (documents). In the present embodiment, the LSI is applied to an association matrix between queries and categories.

  For example, in the present embodiment, an association matrix between a query and a category is configured using a score based on TF (Term Frequency) -IDF (Inverse Document Frequency) as shown in the following equation (1).

ここで、上述した式（１）において、ｔは単語（ターム）を示し、ｃはカテゴリを示し、ｄはドキュメントを示し、商品データにおけるタイトルに相当する。また、ｄｏｃｓ（ｃ）はカテゴリｃに含まれているドキュメント（商品）の集合を示す。また、ｔｅｒｍｓ（ｄ）はドキュメントの中に含まれている単語の集合を示す。また、ｎ_ｔ，ｄは、単語ｔが文章（商品）ｄの中で何回使用されているかを示す。また、Ｄはドキュメント全体の集合を示し、｜Ｄ｜は、ドキュメント全体の数（全商品数）を示す。なお、（１）式を用いた計算において、カテゴリ数は少ないため、通常のターム（単語）と文章（ドキュメント）とを用いたスコア計算よりも迅速に計算することができる。

Here, in the above-described equation (1), t indicates a word (term), c indicates a category, d indicates a document, and corresponds to a title in product data. Docs (c) indicates a set of documents (products) included in the category c. Further, terms (d) indicates a set of words included in the document. Also, n _{t, d} indicates how many times the word t is used in the sentence (product) d. D indicates a set of the entire document, and | D | indicates the number of the entire document (the total number of products). In addition, in the calculation using the expression (1), since the number of categories is small, the calculation can be performed more quickly than the score calculation using a normal term (word) and a sentence (document).

  In the present embodiment, the ambiguity for the query is quantified by aggregating the category vectors c based on the “direction” of the vector. FIG. 5 is a diagram for explaining a relationship between similarity and ambiguity with respect to a category. For example, FIGS. 5A and 5B show linguistic space vectors, and c1 to c3 respectively indicate categories extracted by a search query and clicked by the user.

  When this category is dropped into the space shown in FIGS. 5A and 5B, the direction of each category is discrete in the example of FIG. Become. Therefore, in the case of FIG. 5A, it is evaluated that the similarity between the categories is low and the ambiguity of the query is high. Further, in the example of FIG. 5B, the direction of each category is close, and the aggregation result of each vector is a large vector amount. Therefore, in the case shown in FIG. 5B, it is evaluated that the similarity between the categories is high and the ambiguity of the query is low.

  In this embodiment, in order to evaluate the uniformity of the direction of the vector, first, the center (center of gravity) of the direction for each vector is obtained. In the present embodiment, for example, the center of the category direction can be calculated by the following equation (2).

ここで、上述した式（２）において、Ｃ_ｌｅａｆは、階層構造を有するカテゴリｃの葉（末端）の部分である。なお、本実施形態では、末端カテゴリＣ_ｌｅａｆに限定した例を用いて説明するが、これに限定されるものではなく、例えば全カテゴリＣを用いてもよい。また、ｐ（ｃ｜ｑ）は、クエリｑが与えられたときに、カテゴリｃが出てくる確率を示しており、ｃ∈Ｃ_ｌｅａｆの関係を有する。また、末端カテゴリＣ_ｌｅａｆに限定しない場合には、ｃ∈Ｃの関係を有する。

Here, in the above equation (2), C _leaf is a leaf (end) portion of category c having a hierarchical structure. In the present embodiment, an example in which the category is limited to the terminal category C _leaf will be described. However, the present invention is not limited to this. For example, all categories C may be used. Further, p (c | q), when the query q is given, indicates the probability that comes out category c, has a relationship c∈C _leaf. When it is not limited to terminal category _{C leaf} has a relationship C∈C.

  Next, the distance of each category vector based on the acquired center is calculated using cosine similarity or the like, whereby the similarity of each category can be calculated. Note that, for the calculation of the similarity, for example, the following equation (3) can be used.

ここで、上述した式（３）において、クエリｑの類似度ｓｉｍ（ｑ）は、０から１の範囲で与えられ、類似性が高いほど、値が１に近くなり、類似性が低いほど値が０に近くなる。

Here, in equation (3) above, the similarity sim (q) of the query q is given in the range of 0 to 1, and the higher the similarity, the closer the value is to 1; Becomes closer to 0.

<Example of similarity calculation result>
Here, an example of the calculation result of the similarity will be described with reference to the drawings. FIG. 6 is a diagram illustrating an example of the calculation result of the similarity. In the example of FIG. 6, the similarity is calculated from a search query (keyword), a search result (the number of clicks), and the like used on an actual website such as a commercial transaction site.

  In the example of FIG. 6, for two examples of “table” and “balloon” as queries, each category acquired from the search log 32 and a click (browsing instruction) ratio ( 6 shows the calculation results (sim) of the above-described formula (3) for each query.In the example of FIG. 6, in the case of the query "table", the click ratio is calculated for all 265 categories. The maximum of (probability) is 0.094, and the other five top categories are shown. Almost all of the categories including the top five categories are included in the same genre and attribute of the table (Table), and the similarity (sim) according to the above equation (3) is a high value of 0.883. Was.

  On the other hand, in the example of FIG. 6, in the case of the query “balloon”, the maximum click rate is 0.094 for all 152 categories, and the other five top categories are shown. The top five categories include different genres and attributes such as gardening, toys, and fashion, and the similarity (sim) according to the above equation (3) is also 0. It was a low value of 376.

  In the present embodiment, the ambiguity is quantified using the similarity described above, and is stored as the ambiguity data 33. Thereby, for the subsequent search request, the ambiguity with respect to the input search query is determined from the ambiguity data 33, and when the similarity is low (the ambiguity is high), the expansion of the search keyword and the use of the user information are performed. , A search process is performed, and the result is presented.

<Search contents using ambiguity data>
Next, search contents using ambiguity data in the present embodiment will be described with reference to the drawings. FIG. 7 is a diagram illustrating an example of a search content using ambiguity data. Note that the example of FIG. 7 shows generation of ambiguity data and search contents using the generated ambiguity data.

  In the example of FIG. 7, as described above, the degree of ambiguity with respect to the query is evaluated using the product data 31 and the search log 32. In the present embodiment, as shown in FIG. 7A, a vector expression for each category is generated from a category, a title (product name), and the like included in the product data 31. For the vector expression, for example, an LSI or the like can be used, and the direction and amount of each category vector can be calculated using the above-described equation (1) and the like.

  In the present embodiment, as shown in (2) of FIG. 7, the distribution (click rate) of each category clicked (browsed) on a query (for example, a table) is extracted using the search log 32.

  Next, similarity between categories is calculated using each category vector based on the distribution of the extracted categories, and the degree of ambiguity is evaluated from the calculated result. In the example of FIG. 7, the similarity is calculated by the above-described equations (2) and (3) using the category vectors corresponding to the “row table”, “center table”, and “side table”, and the calculation result is calculated. The ambiguity evaluation result is stored in the ambiguity data 33. In the example of (3) in FIG. 7, the similarity “0.88” obtained by Expression (3) is stored in association with the query (table) as an ambiguity evaluation result. The data stored in the ambiguity data 33 is not limited to the above-described calculation result of the similarity. For example, as “ambiguity = 1−similarity”, a value calculated using the similarity ( For example, ambiguity = 1-0.88 = 0.12) may be stored in the ambiguity data 33.

  By using the ambiguity data 33, for example, as shown in (4) of FIG. 7, when a search query of “table” is input in a search site provided by the ambiguity evaluation device 11, the ambiguity data 33 , And since the ambiguity of the table is low, the search is performed with the query as it is. Further, in the case of another search query “balloon”, since the similarity is as low as 0.376 (high ambiguity) according to the example of FIG. 6, another search keyword is added or user information is used. The search is performed by supplementing a keyword corresponding to the preference information, and the search result is presented.

<Summary>
As described above, according to the present embodiment, the ambiguity of the user's intention can be quantified. As a result, the present embodiment can present an appropriate search result to the user. In the above-described embodiment, the query to be evaluated for ambiguity is one word. However, even in the case of a compound word including a plurality of words, the compound word is regarded as one search query, and Similarity can be calculated, and ambiguity can be evaluated based on the calculated similarity. Further, regarding the calculation of the similarity between the categories described above, the similarity may be calculated by replacing the vector with a vector in a linguistic space, or the similarity may be calculated using a tree structure of a preset category. And these may be combined.

  As described above, the preferred embodiments of the present invention have been described in detail, but the present invention is not limited to the specific embodiments, and various modifications may be made within the scope of the present invention described in the appended claims. , Changes are possible.

  The order of the flowcharts described in the above embodiments may be changed as long as there is no inconsistency. In addition, all or some of the embodiments described above can be combined. In addition, all or a part of each embodiment described above can be implemented by a program. This program can be stored in a storage medium.

  Note that the present invention is not limited to the configuration shown here, such as a combination of the configuration described in the above embodiment with other elements. These points can be changed without departing from the spirit of the present invention, and can be appropriately determined according to the application form.

DESCRIPTION OF SYMBOLS 10 Information presentation system 11 Ambiguity evaluation device 12 Terminal 13 Communication network 21 Input means 22 Output means 23 Storage means 24 Ambiguity evaluation means 25 Search means 26 Information presentation means 27 Communication means 28 Control means 31 Product data 32 Search log 33 Ambiguity Data 34 Information presentation data 41 Input device 42 Output device 43 Drive device 44 Auxiliary storage device 45 Memory device 46 CPU
47 network connection device 48 recording medium

Claims (10)

And keywords used when searching a storage unit that Ru is stored as a plurality of search log information in association with the category corresponding to the retrieved search result from the search data by using the keywords,
From the search history information that will be stored in the storage means, calculating a similarity between the plurality of categories for the keywords, the ambiguity evaluating means from the calculated similarity evaluating the ambiguity of the keyword,
An ambiguity evaluation device comprising: The ambiguity evaluation means,
Generate a spatial vector representation for each of the plurality of categories included in the search target data,
Extract the category distribution of the keywords based on the number of each of the plurality of categories obtained from the search history information,
The ambiguity evaluation device according to claim 1, wherein the similarity is calculated based on the vector expression and the category distribution. The ambiguity evaluation means,
The ambiguity evaluation device according to claim 1, wherein ambiguity data corresponding to the similarity of the keyword is stored in the storage unit. To the keywords entered in order to perform a new search, the acquired ambiguity of the ambiguity data for the keyword, and having a search means for searching made to correspond to the ambiguity obtained The ambiguity evaluation device according to claim 3. The search means,
The ambiguity is compared with a preset threshold. If the ambiguity is equal to or greater than the threshold, the keyword is supplemented with other information, and a search is performed using the supplemented content. The ambiguity evaluation device according to claim 4, wherein a search is performed using the keyword when the above is not the case. The storage means,
6. The search history information according to claim 1, wherein, among the categories corresponding to the search results searched from the search target data, a category designated by a user to be browsed is stored as search history information in association with the keyword. The ambiguity evaluation device described in the above. The ambiguity evaluation means,
The ambiguity evaluation device according to any one of claims 1 to 6, wherein the similarity is calculated based on preset tree structure data between the plurality of categories. A plurality of categories associated with the keyword used in the search time, a storage unit Ru is stored as data of a tree structure between a preset category,
Based on the data of the tree structure between the plurality of categories stored in the storage means, fuzzy wherein calculating a similarity between the plurality of categories for the keyword, to evaluate the ambiguity of the keyword from the calculated degree of similarity Sex evaluation means;
An ambiguity evaluation device comprising: And keywords used when searching, a storing step of search target data retrieved Results in in association with a plurality of categories corresponding Ru stored in the storage means as a retrieval history information using the keywords,
From the search history information that will be stored in the storage means, calculating a similarity between the plurality of categories for the keywords, the ambiguity evaluation step from calculated similarity evaluating the ambiguity of the keyword,
Ambiguity evaluation method that causes a computer to execute Computer
And keywords used when searching a plurality of categories and storing means Ru is stored as the retrieval history information in association with corresponding to search results retrieved from the search data by using the keywords and,
Wherein the search history information that will be stored in the storage means, calculating a similarity between the plurality of categories for the keywords, ambiguity evaluating means for evaluating the ambiguity of the keyword from the calculated degree of similarity,
Ambiguity evaluation program to function as a.

Images