JP6938569B2 - Information processing equipment, information processing methods and information processing programs - Google Patents

Description

The present invention relates to an information processing device, an information processing method, and an information processing program.

In recent years, with the rapid spread of the Internet, for example, techniques related to analysis using various information on the Internet have been provided. For example, a technique has been proposed in which information on needs for a target provided by a predetermined business operator is extracted based on a search query entered by a user.

JP-A-2019-32776

However, it is not always possible to obtain useful information with the above-mentioned prior art. For example, in the above-mentioned prior art, since only the information regarding the needs for the target provided by the predetermined business operator is extracted, it is possible to extract the information regarding the potential needs for the target provided by the predetermined business operator. I can not say.

The present application has been made in view of the above, and an object of the present application is to provide an information processing device, an information processing method, and an information processing program capable of providing useful information.

The information processing apparatus according to the present application has a reception unit that accepts a plurality of first queries indicating similarity determination targets and a plurality of second queries indicating the similarity determination criteria, and each of the second queries. It has a generation unit that generates similar information indicating similarity between the determination target indicated by the first query and the determination criterion indicated by the second query, and an output unit that outputs the similarity information generated by the generation unit. It is characterized by that.

According to one aspect of the embodiment, there is an effect that useful information can be obtained.

FIG. 1 is a diagram showing an example of information processing according to an embodiment. FIG. 2 is a diagram showing a configuration example of an information processing system according to an embodiment. FIG. 3 is a diagram showing a configuration example of the information processing device according to the embodiment. FIG. 4 is a diagram showing an example of the query information storage unit according to the embodiment. FIG. 5 is a diagram showing an example of the vector information storage unit according to the embodiment. FIG. 6 is a diagram showing an example of the similarity information storage unit according to the embodiment. FIG. 7 is a diagram showing an example of a model information storage unit according to the embodiment. FIG. 8 is a diagram showing a configuration example of the terminal device according to the embodiment. FIG. 9 is a flowchart showing an information processing procedure according to the embodiment. FIG. 10 is a diagram showing an example of the generation process of the first model according to the embodiment. FIG. 11 is a diagram showing an example of the generation process of the first model according to the embodiment. FIG. 12 is a diagram showing a configuration example of the generator according to the embodiment. FIG. 13 is a diagram showing an example of the query information storage unit according to the embodiment. FIG. 14 is a diagram showing an example of the vector information storage unit according to the embodiment. FIG. 15 is a diagram showing an example of a model information storage unit according to the embodiment. FIG. 16 is a diagram showing an example of the first model according to the embodiment. FIG. 17 is a flowchart showing a generation processing procedure of the first model according to the embodiment. FIG. 18 is a diagram showing an example of the hardware configuration of the computer that executes the program.

Hereinafter, the information processing apparatus, the information processing method, and the mode for carrying out the information processing program (hereinafter referred to as “the embodiment”) according to the present application will be described in detail with reference to the drawings. The information processing apparatus, information processing method, and information processing program according to the present application are not limited by this embodiment. Further, in each of the following embodiments, the same parts will be designated by the same reference numerals, and duplicate description will be omitted.

[1. An example of information processing]
First, an example of information processing according to the embodiment will be described with reference to FIG. FIG. 1 is a diagram showing an example of information processing according to an embodiment. The information processing according to the embodiment is performed by the information processing device 100 shown in FIG. The information processing device 100 shown in FIG. 1 is a server device that provides a query analysis service to a client (company or the like). Here, the "query" refers to a phrase (character information) used by the user to make an inquiry or request to the database. For example, a "query" includes a search query, which is a phrase used by a user for a search. It should be noted that the "query" in the present invention may include words and phrases such as simple keywords and phrases that have nothing to do with how they are used by the user.

Prior to the description of FIG. 1, the configuration of the information processing system according to the embodiment will be described with reference to FIG. FIG. 2 is a diagram showing a configuration example of an information processing system according to an embodiment. As shown in FIG. 2, the information processing system 1 includes a terminal device 10, a search server 20, a generation device 50, and an information processing device 100. The terminal device 10, the search server 20, the generation device 50, and the information processing device 100 are connected to each other via a predetermined network N so as to be communicable by wire or wirelessly. The information processing system 1 shown in FIG. 2 includes an arbitrary number of terminal devices 10, an arbitrary number of search servers 20, an arbitrary number of generation devices 50, and an arbitrary number of information processing devices 100. May be good.

The terminal device 10 is an information processing device used by a user who is in charge of a client (company or the like). The terminal device 10 is realized by, for example, a smartphone, a tablet terminal, a notebook PC (Personal Computer), a mobile phone, a PDA (Personal Digital Assistant), or the like. In the example shown in FIG. 1, the terminal device 10 is a notebook PC. In the following, the terminal device 10 may be equated with the user. That is, in the following, the user can be read as the terminal device 10.

The terminal device 10 comprises a plurality of first queries indicating the similarity determination target and a plurality of second queries indicating the similarity determination criteria according to the operation of the user U11 who is in charge of the client (company or the like). It is transmitted to the information processing device 100. Further, the terminal device 10 makes it possible to visually recognize the magnitude of the degree of similarity between the determination target indicated by each first query and the determination criterion indicated by the second query for each second query indicating the similarity determination criterion. Information about the information processing device 100 is received from the information processing device 100. The terminal device 10 displays information about the received bar graph on the screen of the terminal device 10.

The search server 20 is a server device that provides a search service. For example, the search service provided by the search server 20 is a comprehensive search service capable of searching for any information. The search server 20 stores information about the search query entered by the user. Specifically, the search server 20 stores information regarding the user's search history. Further, the search server 20 transmits information regarding the search query input by the user to the generation device 50 in response to the request of the generation device 50.

The generation device 50 is a server device that generates the first model M1. The generation device 50 generates the first model M1 by executing a process described later. The first model M1 is a model that outputs a distributed representation of character information (for example, a search query) when character information is input. The distributed representation may be a vector. Here, the distributed representation of the character information output from the first model M1 includes feature information indicating the user's search intention when the character information is input as a search query. That is, the similarity between the distributed representation of the predetermined character information output from the first model M1 and the distributed representation of other character information is the search intention of the user when the predetermined character information is input as a search query. It means that the search intention of the user when other character information is input as a search query is similar. The details of the generation process of the first model by the generation device 50 will be described later.

The information processing device 100 is a server device that provides a client such as a company with a query analysis service that analyzes a general user's search trend regarding a keyword (character information) indicating an analysis target that the client desires for market analysis. Is. In the example shown in FIG. 1, the information processing apparatus 100 receives a plurality of first queries indicating the similarity determination target and a plurality of second queries indicating the similarity determination criteria from the terminal device 10. Further, the information processing apparatus 100 makes it possible to visually recognize the magnitude of the degree of similarity between the determination target indicated by each first query and the determination criterion indicated by the second query for each second query indicating the similarity determination criterion. Generate information about bar charts. Then, the information processing device 100 transmits the information regarding the generated bar graph to the terminal device 10.

Generally, in a query analysis service, a keyword (character information) indicating an analysis target that the client wants to analyze the market is accepted from a client such as a company. Then, the query analysis service extracts information about a query similar to the specified keyword from a huge database of queries, and provides the client with information about the extracted query. For example, the query analysis service converts the character string corresponding to the query and the keyword specified by the client into a distributed expression in order to grasp the similarity between the specified keyword and the query numerically. Then, the query analysis service calculates the similarity between the distributed expression obtained by converting the specified keyword and the distributed expression obtained by converting the character string corresponding to the query, and obtains information about the query similar to the specified keyword. Extract.

Here, since the database owned by the query analysis service has a huge number of queries, the number of distributed expressions obtained by converting the character strings corresponding to the queries is also huge. Also, in general, the distributed representation obtained by converting a character string is generally a high-dimensional vector (for example, a vector having hundreds or thousands of dimensions). That is, if the device that provides the query analysis service simply extracts and provides the information on the analysis result of the query similar to the specified keyword, the client who receives the information on the analysis result obtains useful information. It's difficult. For example, when the information provided to the client is provided with a large number of high-dimensional distributed representations mapped to the distributed representation space, or a huge amount of data showing the similarity between the distributed representations is listed. When provided in a state, the amount of information is large and it is difficult for the client to grasp the analysis result at a glance. Therefore, it is difficult for the client to obtain useful information from the provided information.

Therefore, the information processing apparatus 100 according to the present invention accepts a plurality of first queries indicating the similarity determination target and a plurality of second queries indicating the similarity determination criteria. Further, the information processing apparatus 100 generates similar information indicating the similarity between the determination target indicated by each first query and the determination criterion indicated by the second query for each second query indicating the similarity determination criterion. Then, the information processing device 100 outputs the generated similar information. As a result, the information processing apparatus 100 according to the present invention can provide an analysis result regarding the similarity between a large number of high-dimensional distributed expressions in a state in which it is easy to grasp at a glance. Therefore, the information processing apparatus 100 according to the present invention can obtain useful information.

From here, the flow of information processing will be described with reference to FIG. In FIG. 1, the information processing device 100 transmits the partial content C11 of the content C1 to the terminal device 10 in response to the request of the terminal device 10. Specifically, the information processing device 100 inputs an input field F11 capable of inputting a plurality of first queries, an input field F12 capable of inputting a plurality of second queries, and a query input in the input fields. The partial content C11 including the transmission button B11 to be transmitted to 100 is transmitted to the terminal device 10.

The terminal device 10 receives the partial content C11 of the content C1 from the information processing device 100. When the terminal device 10 receives the partial content C11, the terminal device 10 displays the received partial content C11 on the screen of the terminal device 10.

The user U11 of the terminal device 10 performs an operation of inputting a plurality of first queries indicating a similarity determination target in the input field F11 included in the partial content C11 displayed on the screen of the terminal device 10. In the example shown in FIG. 1, the user U11 performs an operation of inputting nine first queries Q1-1 to Q1-9 in the input field F11. Specifically, the user U11 performs an operation of inputting each character string separated by a delimiter into the input field F11 as one first query. For example, the user U11, who is in charge of the automobile manufacturer # 1, has three first queries "vehicle type T11" (first query Q1-) indicating the names of the three types of automobiles that are the products of the company (automobile manufacturer # 1). 1), the operation of inputting the first query "vehicle type T12" (first query Q1-2) and the first query "vehicle type T13" (first query Q1-3) into the input field F11 is performed. In addition, the user U11 has three first queries "vehicle type T21" (first query Q1-4) and a first query "vehicle type" indicating the names of three types of automobiles that are products of the automobile manufacturer # 2 which is a competitor. The operation of inputting "T22" (first query Q1-5) and the first query "vehicle type T23" (first query Q1-6) into the input field F11 is performed. In addition, the user U11 has three first queries "vehicle type T31" (first query Q1-7) and a first query "vehicle type" indicating the names of three types of automobiles that are products of the automobile manufacturer # 3 which is a competitor. The operation of inputting "T32" (first query Q1-8) and "vehicle type T33" (first query Q1-9) into the input field F11 is performed.

Further, the user U11 of the terminal device 10 performs an operation of inputting a plurality of second queries indicating similarity determination criteria in the input field F12 included in the partial content C11 displayed on the screen of the terminal device 10. The user U11 performs an operation of inputting a keyword to be the axis of analysis when analyzing the first query as the second query. In the example shown in FIG. 1, the user U11 performs an operation of inputting three first queries Q2-1 to Q2-3 into the input field F12. Specifically, the user U11 performs an operation of inputting each character string separated by a delimiter into the input field F12 as one second query. For example, the user U11 inputs a keyword as a second query for grasping in which field of the market the company's product has strengths (or weaknesses) against consumers as compared with the products of competitors. For example, the user U11 has three second queries "camp" (second query Q2-1), second query "SNS # 1" (second query Q2-2), and second query "night view" (second query). Perform the operation of inputting the query Q2-3) into the input field F12.

Subsequently, the user U11 of the terminal device 10 performs an operation of selecting the transmission button B11 included in the partial content C11 displayed on the screen of the terminal device 10. When the transmission button B11 is selected according to the operation of the user U11, the terminal device 10 has nine first queries Q1-1 to Q1-9 input in the input field F11 and three input in the input field F12. The second query Q2-1 to Q2-3 is transmitted to the information processing apparatus 100.

The information processing device 100 receives nine first queries Q1-1 to Q1-9 and three second queries Q2-1 to Q2-3 from the user U11. Specifically, the information processing apparatus 100 receives nine first queries Q1-1 to Q1-9 and three second queries Q2-1 to Q2-3 from the terminal apparatus 10.

When the information processing apparatus 100 receives the first query Q1-1 to Q1-9 and the second query Q2-1 to Q2-3, the information processing apparatus 100 receives the determination target indicated by each first query and the second query for each second query. Calculate the degree of similarity with the judgment criteria shown by. Specifically, when the first query Q1-1 to Q1-9 and the second query Q2-1 to Q2-3 are accepted, each of the first queries Q1-1 to Q1- generated by using the first model M1. The distributed representations QV1-1 to QV1-9 (see FIG. 5) of 9 and the distributed representations QV2-1 to QV2-3 (see FIG. 5) of each of the second queries Q2-1 to Q2-3 are acquired.

Subsequently, when the information processing apparatus 100 acquires the distributed representations QV2-1 to QV1-9 and the distributed representations QV2-1 to QV2-3, the distributed representation of each first query is obtained for each of the distributed representations of the second query. And the degree of similarity with the distributed representation of the second query are calculated. For example, the information processing apparatus 100 calculates the cosine similarity between the distributed representation of each first query and the distributed representation of the second query. The information processing apparatus 100 is not limited to the cosine similarity, and may calculate the similarity between the distributed representations based on any index as long as it is an index applicable as a distance scale between vectors. For example, the information processing apparatus 100 may calculate the value of a predetermined distance function such as the Euclidean distance between distributed expressions, the distance in a non-Euclidean space such as a hyperbolic space, the Manhattan distance, the Mahalanobis distance, and the like.

For example, the information processing apparatus 100 has a distributed expression QV2-1 of the second query Q2-1 "camp" and a distributed expression QV1-1 of each first query Q1-1 "vehicle type T11" to Q1-9 "vehicle type T33". -Similarity with QV1-9 SC1-1 to SC1-9 (see FIG. 6) is calculated.

For example, the information processing apparatus 100 calculates the similarity SC1-1 between the distributed expression QV2-1 of the second query Q2-1 "camp" and the distributed expression QV1-1 of the first query Q1-1 "vehicle type T11". .. Subsequently, the information processing apparatus 100 calculates the similarity SC1-2 between the distributed expression QV2-1 of the second query Q2-1 "camp" and the distributed expression QV1-2 of the first query Q1-2 "vehicle type T12". do. Subsequently, the information processing apparatus 100 calculates the distributed expression QV2-1 of the second query Q2-1 "camp" and the distributed expression of the first query Q1-3 "vehicle type T13" and the similarity SC1-3 of the QV1-3. do. Similarly, the information processing apparatus 100 has a distributed expression QV2-1 of the second query Q2-1 "camp" and a distributed expression QV1 of each first query Q1-4 "vehicle type T21" to Q1-9 "vehicle type T33". Calculate the similarity SC1-4 to SC1-9 with -4 to QV1-9.

Subsequently, the information processing apparatus 100 has a similarity between the distributed representation QV2-1 of the second query Q2-1 and the distributed representation QV1-1 to QV1-9 of each of the first queries Q1-1 to Q1-9. When 1 to SC1-9 is calculated, information about the bar graph G21 that makes the calculated magnitudes of the similarity SC1-1 to SC1-9 visible is generated. Specifically, the information processing apparatus 100 generates the information shown in the display area F21 of the partial content C21 of FIG. More specifically, the information processing apparatus 100 generates information in which "camp", which is a character string indicating the second query and the second query Q2-1, is arranged above the bar graph G21 and displayed. Further, the information processing apparatus 100 generates information regarding the bar graph G21 which indicates the calculated magnitudes of the similarity SC1-1 to SC1-9 by the length of each bar graph.

In addition, the information processing device 100 generates a graph in which regions indicating the magnitude of similarity are color-coded by different colors depending on the automobile manufacturer handling the automobile of the vehicle type indicated by the first query. In FIG. 1, the difference in color is expressed by the difference in the filling pattern. For example, the information processing apparatus 100 displays the area of the bar graph indicating the magnitude of the similarity SC1-1 to SC1-3 corresponding to the first query Q1-1 to Q1-3 indicating the product name of the automobile manufacturer # 1 in red. Generates information about the filled bar graph G21. Further, the information processing apparatus 100 displays the area of the bar graph indicating the size of the similarity SC1-4 to SC1-6 corresponding to the first queries Q1-4 to Q1-6 indicating the product name of the automobile manufacturer # 2 in blue. Generates information about the filled bar graph G21. Further, the information processing apparatus 100 displays the area of the bar graph indicating the size of the similarity SC1-7 to SC1-9 corresponding to the first queries Q1-7 to Q1-9 indicating the product name of the automobile manufacturer # 3 in yellow. Generates information about the filled bar graph G21.

Further, the information processing apparatus 100 has a distributed expression QV2-2 of the second query Q2-2 "SNS # 1" and a distributed expression QV1 of each first query Q1-1 "vehicle type T11" to Q1-9 "vehicle type T33". The degree of similarity with -1 to QV1-9 SC2-1 to SC2-9 (see FIG. 6) is calculated. For example, the information processing apparatus 100 sets the degree of similarity SC2-1 between the distributed expression QV2-2 of the second query Q2-2 "SNS # 1" and the distributed expression QV1-1 of the first query Q1-1 "vehicle type T11". calculate. Subsequently, the information processing apparatus 100 has a similarity SC2-2 between the distributed expression QV2-2 of the second query Q2-2 "SNS # 1" and the distributed expression QV1-2 of the first query Q1-2 "vehicle type T12". Is calculated. Subsequently, the information processing apparatus 100 has a similarity SC2-3 between the distributed expression QV2-2 of the second query Q2-2 "SNS # 1" and the distributed expression QV1-3 of the first query Q1-3 "vehicle type T13". Is calculated. Similarly, the information processing apparatus 100 distributes the distributed expression QV2-2 of the second query Q2-2 "SNS # 1" and the distributed representations of the first queries Q1-4 "vehicle type T21" to Q1-9 "vehicle type T33". The similarity between the expression and QV1-4 to QV1-9 SC2-4 to SC2-9 is calculated.

Subsequently, the information processing apparatus 100 has a similarity between the distributed representation QV2-2 of the second query Q2-2 and the distributed representation QV1-1 to QV1-9 of each of the first queries Q1-1 to Q1-9. When 1 to SC2-9 is calculated, information about the bar graph G22 that makes the calculated magnitudes of the similarity SC2-1 to SC2-9 visible is generated. Specifically, the information processing apparatus 100 generates the information shown in the display area F22 of the partial content C21 of FIG. More specifically, the information processing apparatus 100 generates information in which "SNS # 1", which is a character string indicating the second query and the second query Q2-2, is arranged above the bar graph G22 and displayed. Further, the information processing apparatus 100 generates information regarding the bar graph G22 which indicates the calculated magnitudes of the similarity SC2-1 to SC2-9 by the length of each bar graph.

Further, the information processing apparatus 100 displays the area of the bar graph indicating the size of the similarity SC2-1 to SC2-3 corresponding to the first query Q1-1 to Q1-3 indicating the product name of the automobile manufacturer # 1 in red. Generate information about the filled bar graph G22. Further, the information processing apparatus 100 displays the area of the bar graph indicating the size of the similarity SC2-4 to SC2-6 corresponding to the first queries Q1-4 to Q1-6 indicating the product name of the automobile manufacturer # 2 in blue. Generate information about the filled bar graph G22. Further, the information processing apparatus 100 displays the area of the bar graph indicating the size of the similarity SC2-7 to SC2-9 corresponding to the first queries Q1-7 to Q1-9 indicating the product name of the automobile manufacturer # 3 in yellow. Generate information about the filled bar graph G22.

Further, the information processing apparatus 100 has a distributed expression QV2-3 of the second query Q2-3 "night view" and a distributed expression QV1-1 of each first query Q1-1 "vehicle type T11" to Q1-9 "vehicle type T33". -Similarity with QV1-9 SC3-1 to SC3-9 (see FIG. 6) is calculated. More specifically, the information processing apparatus 100 has a similarity between the distributed expression QV2-3 of the second query Q2-3 "night view" and the distributed expression QV1-1 of the first query Q1-1 "vehicle type T11" SC3-. 1 is calculated. Subsequently, the information processing apparatus 100 calculates the similarity SC3-2 between the distributed expression QV2-3 of the second query Q2-3 "night view" and the distributed expression QV1-2 of the first query Q1-2 "vehicle type T12". do. Subsequently, the information processing apparatus 100 calculates the similarity SC3-3 between the distributed expression QV2-3 of the second query Q2-3 "night view" and the distributed expression QV1-3 of the first query Q1-3 "vehicle type T13". do. Similarly, the information processing apparatus 100 has a distributed expression QV2-3 of the second query Q2-3 "night view" and a distributed expression QV1 of each first query Q1-4 "vehicle type T21" to Q1-9 "vehicle type T33". Calculate the similarity SC3-4 to SC3-9 with -4 to QV1-9.

Subsequently, the information processing apparatus 100 has a degree of similarity between the distributed representation QV2-3 of the second query Q2-3 and the distributed representation QV1-1 to QV1-9 of each of the first queries Q1-1 to Q1-9. When 1 to SC3-9 is calculated, information regarding the bar graph G23 that makes the calculated magnitudes of the similarity SC3-1 to SC3-9 visible is generated. Specifically, the information processing apparatus 100 generates the information shown in the display area F23 of the partial content C21 of FIG. More specifically, the information processing apparatus 100 generates information in which the "night view", which is a character string indicating the second query and the second query Q2-3, is arranged above the bar graph G23 and displayed. Further, the information processing apparatus 100 generates information regarding the bar graph G23 which indicates the calculated magnitudes of the similarity SC3-1 to SC3-9 by the length of each bar graph.

Further, the information processing apparatus 100 displays the area of the bar graph indicating the size of the similarity SC3-1 to SC3-3 corresponding to the first query Q1-1 to Q1-3 indicating the product name of the automobile manufacturer # 1 in red. Generate information about the filled bar graph G23. Further, the information processing apparatus 100 displays the area of the bar graph indicating the size of the similarity SC3-4 to SC3-6 corresponding to the first queries Q1-4 to Q1-6 indicating the product name of the automobile manufacturer # 2 in blue. Generate information about the filled bar graph G23. Further, the information processing apparatus 100 displays the area of the bar graph indicating the size of the similarity SC3-7 to SC3-9 corresponding to the first queries Q1-7 to Q1-9 indicating the product name of the automobile manufacturer # 3 in yellow. Generate information about the filled bar graph G23.

Subsequently, when the information processing apparatus 100 generates information regarding the three bar graphs G21 to G23, the information processing apparatus 100 transmits the information regarding the generated three bar graphs G21 to G23 to the terminal device 10. When the terminal device 10 acquires the information related to the three bar graphs G21 to G23, the display unit 13 displays the information related to the bar graphs G21 to G23 in each of the display areas F21 to F23 included in the partial content C12 of the content C1. Control the display.

As described above, the information processing apparatus 100 receives a plurality of first queries indicating the similarity determination target and a plurality of second queries indicating the similarity determination criteria. Further, the information processing apparatus 100 generates similar information indicating the similarity between the determination target indicated by each first query and the determination criterion indicated by the second query for each second query. Then, the information processing device 100 outputs the generated similar information. As a result, the information processing apparatus 100 can provide an analysis result regarding the similarity between a large number of high-dimensional distributed expressions in a state in which it is easy to grasp at a glance. Therefore, the information processing device 100 can obtain useful information.

[2. Information processing device configuration]
Next, the configuration of the information processing apparatus 100 according to the embodiment will be described with reference to FIG. FIG. 3 is a diagram showing a configuration example of the information processing device 100 according to the embodiment. As shown in FIG. 3, the information processing device 100 includes a communication unit 110, a storage unit 120, and a control unit 130. The information processing device 100 includes an input unit (for example, a keyboard, a mouse, etc.) that receives various operations from the administrator of the information processing device 100, and a display unit (for example, a liquid crystal display, etc.) for displaying various information. You may have.

(Communication unit 110)
The communication unit 110 is realized by, for example, a NIC (Network Interface Card) or the like. Then, the communication unit 110 is connected to the network by wire or wirelessly, and transmits / receives information between the terminal device 10, the search server 20, and the generation device 50, for example.

(Memory unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory (Flash Memory), or a storage device such as a hard disk or an optical disk. As shown in FIG. 3, the storage unit 120 includes a query information storage unit 121, a vector information storage unit 122, a similarity information storage unit 123, and a model information storage unit 124.

(Query information storage unit 121)
The query information storage unit 121 stores various information related to the query received from the user. FIG. 4 shows an example of the query information storage unit according to the embodiment. In the example shown in FIG. 4, the query information storage unit 121 has items such as "user ID", "date and time", "type", "query", and "query ID".

The "user ID" indicates identification information for identifying a user. "Date and time" indicates the date and time when the query was received from the user. "Type" indicates the type of query received from the user. Specifically, the type "1" indicates that the query received from the user is the first query. It also indicates the date and time. "Type" indicates the type of query received from the user. Specifically, the type "2" indicates that the query received from the user is the second query. "Query" indicates a query received from a user. Specifically, the "query ID" indicates identification information for identifying a query received from a user.

In the example shown in the first record of FIG. 4, the query (query Q1-1) identified by the query ID "Q1-1" corresponds to the first query "vehicle type T11" shown in FIG. Further, in the example shown in the 10th record of FIG. 4, the query (query Q2-1) identified by the query ID “Q2-1” corresponds to the second query “camp” shown in FIG.

(Vector information storage unit 122)
The vector information storage unit 122 stores various information related to the vector, which is a distributed representation of the query. FIG. 5 shows an example of the vector information storage unit according to the embodiment. In the example shown in FIG. 5, the vector information storage unit 122 has items such as “vector ID”, “query ID”, and “vector information”.

“Vector ID” indicates identification information for identifying a vector which is a distributed representation of a query. The "query ID" indicates identification information for identifying the query corresponding to the vector. The "vector information" indicates an N-dimensional (for example, 128-dimensional) vector which is a distributed representation of the query.

In the example shown in the first record of FIG. 5, the vector (vector QV1-1) identified by the vector ID “QV1-1” corresponds to the vector QV1-1 which is the query Q1-1 distributed representation shown in FIG. do. Further, the query (query Q1-1) identified by the query ID "Q1-1" indicates that the query corresponding to the vector QV1-1 is the query Q1-1. Further, the vector information "QVDT1-1" indicates an N-dimensional vector which is a distributed representation of the query Q1-1.

(Similarity information storage unit 123)
The similarity information storage unit 123 stores various information regarding the similarity between the distributed representation corresponding to the first query and the distributed representation corresponding to the second query. FIG. 6 shows an example of the similarity information storage unit according to the embodiment. In the example shown in FIG. 6, the similarity information storage unit 123 stores a plurality of data tables for each similarity information generated each time a plurality of first queries and a plurality of second queries are received from the user. Consists of. The similarity information storage unit 123 shown in FIG. 6 is similar to the distributed representation corresponding to the first query Q1-1 to Q1-9 and the distributed representation corresponding to the second query Q2-1 to Q2-3 shown in FIG. It has a data table 123-1 regarding degrees.

The data table 123-1 shows the degree of similarity between the distributed representation corresponding to the first query Q1-1 to Q1-9 and the distributed representation corresponding to the second query Q2-1 to Q2-3 shown in FIG. Store in each cell. “SC1-1” shown in FIG. 6 indicates the degree of similarity between the distributed expression QV1-1 corresponding to the first query Q1-1 shown in FIG. 1 and the distributed expression QV2-1 corresponding to the second query Q2-1. .. In the example shown in FIG. 6, the similarity is represented by a concept such as "SC1-1", but in reality, a numerical value indicating the similarity (for example, "0.888 ..." or "0.5") is used. Numerical value) is stored in each cell of the data table.

(Model information storage unit 124)
The model information storage unit 124 stores various information related to the learning model generated by the generation device 50. FIG. 7 shows an example of the model information storage unit according to the embodiment. In the example shown in FIG. 7, the model information storage unit 124 has items such as "model ID" and "model data".

The "model ID" indicates identification information for identifying the learning model generated by the generation device 50. “Model data” indicates model data of the learning model generated by the generation device 50. For example, "model data" stores data for converting a query into a distributed representation.

In the example shown in the first record of FIG. 7, the learning model identified by the model ID “M1” corresponds to the first model M1 shown in FIG. Further, the model data "MDT1" indicates the model data (model data MDT1) of the first model M1 generated by the generation device 50.

The model data MDT1 includes an input layer into which a query is input, an output layer, a first element which is any layer from the input layer to the output layer and belongs to a layer other than the output layer, and the first element and the first element. Generated to output a distributed representation of the query input to the input layer from the output layer in response to the query input to the input layer, including the second element whose value is calculated based on the weight of the element. The device 50 may be made to function.

Here, it is assumed that the model data MDT1 is realized by the regression model indicated by "y = a1 * x1 + a2 * x2 + ... + ai * xi". In this case, the first element included in the model data MDT1 corresponds to input data (xi) such as x1 and x2. Further, the weight of the first element corresponds to the coefficient ai corresponding to xi. Here, the regression model can be regarded as a simple perceptron having an input layer and an output layer. When each model is regarded as a simple perceptron, the first element corresponds to any node of the input layer, and the second element can be regarded as the node of the output layer.

Further, it is assumed that the model data MDT1 is realized by a neural network having one or a plurality of intermediate layers such as DNN (Deep Neural Network). In this case, the first element included in the model data MDT1 corresponds to either the node of the input layer or the intermediate layer. Further, the second element corresponds to a node in the next stage, which is a node to which a value is transmitted from a node corresponding to the first element. Further, the weight of the first element corresponds to a connection coefficient which is a weight considered for the value transmitted from the node corresponding to the first element to the node corresponding to the second element.

The generation device 50 calculates the distributed representation using a model having an arbitrary structure such as the regression model and the neural network described above. Specifically, the model data MDT1 is set with a coefficient so as to output a distributed representation when a query is input. The generation device 50 calculates the distributed representation using such model data MDT1.

In the above example, the model data MDT1 is a model (hereinafter referred to as model X1) that outputs a distributed representation of the query when a query is input. However, the model data MDT1 according to the embodiment may be a model generated based on the result obtained by repeating the input / output of data to the model X1. For example, the model data MDT1 may be a model (hereinafter, referred to as model Y1) learned by inputting the distributed representation output by the model X1 when the query is input. Alternatively, the model data MDT1 may be a model trained to take a query as an input and output a value of the model Y1 as an output.

Further, when the generation device 50 performs the estimation process using GAN (Generative Adversarial Networks), the model data MDT1 may be a model forming a part of GAN.

(Control unit 130)
Returning to the description of FIG. 3, the control unit 130 is a controller, and is stored in a storage device inside the information processing device 100 by, for example, a CPU (Central Processing Unit) or an MPU (Micro Processing Unit). It is realized by executing various programs (corresponding to an example of an information processing program) using the RAM as a work area. Further, the control unit 130 is a controller, and is realized by, for example, an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

As shown in FIG. 3, the control unit 130 includes a reception unit 131, an acquisition unit 132, a generation unit 133, and an output unit 134, and realizes or executes the information processing operation described below. The internal configuration of the control unit 130 is not limited to the configuration shown in FIG. 3, and may be another configuration as long as it is a configuration for performing information processing described later.

(Reception Department 131)
The reception unit 131 receives a distribution request for the content C1 from the terminal device 10. The reception unit 131 receives a distribution request for the partial content C11 of the content C1 from the terminal device 10. Specifically, the reception unit 131 inputs an input field F11 capable of inputting a plurality of first queries, an input field F12 capable of inputting a plurality of second queries, and an information processing device 100 for queries input in the input fields. Accepts the distribution request of the partial content C11 including the transmission button B11 to be transmitted to.

Subsequently, when the reception unit 131 receives the distribution request for the content C1, the reception unit 131 distributes the content C1 to the terminal device 10. When the reception unit 131 receives the distribution request for the partial content C11 of the content C1, the reception unit 131 distributes the partial content C11 of the content C1 to the terminal device 10. Specifically, the reception unit 131 inputs an input field F11 capable of inputting a plurality of first queries, an input field F12 capable of inputting a plurality of second queries, and an information processing device 100 for queries input in the input fields. The partial content C11 including the transmission button B11 to be transmitted to the terminal device 10 is distributed to the terminal device 10.

Further, the reception unit 131 accepts a plurality of first queries indicating the similarity determination target and a plurality of second queries indicating the similarity determination criteria. Specifically, the reception unit 131 receives a plurality of first queries and a plurality of second queries from the terminal device 10. Subsequently, when the reception unit 131 receives the plurality of first queries and the plurality of second queries, the reception unit 131 stores the received plurality of first queries and the plurality of second queries in the query information storage unit 121. For example, when the reception unit 131 receives the first query, the reception unit 131 stores the received first query in the query information storage unit 121 in association with the type "1" indicating that the query is the first query. Further, when the reception unit 131 receives the second query, the reception unit 131 stores the received second query in the query information storage unit 121 in association with the type "2" indicating that the query is the second query.

In addition, the reception unit 131 receives a plurality of first queries indicating the transaction target. Here, the "transaction target" refers to an article (commodity) subject to a commercial transaction or a service (service) subject to a commercial transaction. In the example shown in FIG. 1, the reception unit 131 has three first queries "vehicle type T11" (first query Q1-1) and first queries "1" indicating the names of three types of automobiles that are products of automobile manufacturer # 1. Accepts the vehicle type T12 (first query Q1-2) and the first query "vehicle type T13" (first query Q1-3). In addition, the reception unit 131 has three first queries "vehicle type T21" (first query Q1-4) and first one indicating the names of three types of automobiles that are products of automobile manufacturer # 2 competing with automobile manufacturer # 1. The query "vehicle type T22" (first query Q1-5) and the first query "vehicle type T23" (first query Q1-6) are accepted. In addition, the reception unit 131 has three first queries "vehicle type T31" (first query Q1-7) and first ones indicating the names of three types of automobiles that are products of automobile manufacturer # 3 competing with automobile manufacturer # 1. The query "vehicle type T32" (first query Q1-8) and "vehicle type T33" (first query Q1-9) are accepted.

In addition, the reception unit 131 accepts a keyword that the user wants to be the axis of analysis when analyzing the first query as the second query. In the example shown in FIG. 1, the reception unit 131 accepts a keyword as a second query for grasping in which field of the market the product handled by the company in charge of the user has strengths (or weaknesses) against consumers. .. For example, the reception unit 131 has three second queries "camp" (second query Q2-1) and second query "SNS # 1" (second query Q2-2), which are keywords that the user wants to use as the axis of analysis. ), "Night view" (second query Q2-3) is accepted.

(Acquisition unit 132)
The acquisition unit 132 acquires various types of information. The acquisition unit 132 acquires various information from an external information processing device. The acquisition unit 132 acquires various information from other information processing devices such as the generation device 50.

Further, the acquisition unit 132 acquires various information from the storage unit 120. The acquisition unit 132 acquires various information from the query information storage unit 121, the vector information storage unit 122, the similarity information storage unit 123, and the model information storage unit 124.

Specifically, the acquisition unit 132 acquires the model. More specifically, when the receiving unit 131 receives a plurality of first queries indicating the similarity determination target and a plurality of second queries indicating the similarity determination criteria, the acquisition unit 132 receives the generation device 50. The first model M1 is acquired from. The acquisition unit 132 acquires the model data MDT1 of the first model M1 from the generation device 50. Subsequently, when the acquisition unit 132 acquires the first model M1 (model data MDT1), the acquisition unit 132 stores the acquired first model M1 (model data MDT1) in the model information storage unit 124.

Further, when the reception unit 131 receives a plurality of first queries indicating the similarity determination target and a plurality of second queries indicating the similarity determination criteria, the acquisition unit 132 refers to the model information storage unit 124. Then, the first model M1 is acquired. Further, when the reception unit 131 receives a plurality of first queries indicating the similarity determination target and a plurality of second queries indicating the similarity determination criteria, the acquisition unit 132 refers to the query information storage unit 121. Then, the plurality of first queries and the plurality of second queries received by the reception unit 131 are acquired. In the example shown in FIG. 1, the acquisition unit 132 acquires the first queries Q1-1 to Q1-9 and the second queries Q2-1 to Q2-3 received by the reception unit 131.

Subsequently, when the acquisition unit 132 acquires a plurality of first queries, it acquires one first query from the plurality of first queries. In the example shown in FIG. 1, when the acquisition unit 132 acquires the first query Q1-1 to Q1-9, it acquires one of the first queries Q1-1 from the first queries Q1-1 to Q1-9. .. Subsequently, the acquisition unit 132 inputs the acquired first query to the first model M1 as the input information of the first model M1. In the example shown in FIG. 1, the acquisition unit 132 inputs the acquired first query Q1-1 to the first model M1 as the input information of the first model M1. Further, the acquisition unit 132 outputs the distributed representation of the first query input to the first model M1 as the output information of the first model M1 from the first model M1. In the example shown in FIG. 1, the acquisition unit 132 outputs the distributed representation QV1-1 of the first query Q1-1 input to the first model M1 as the output information of the first model M1 from the first model M1. In this way, the acquisition unit 132 generates the distributed representation of the first query. Similarly, the acquisition unit 132 generates a distributed representation of each first query for all of the acquired first queries. In the example shown in FIG. 1, the acquisition unit 132 generates the distributed representations QV1-1 to QV1-9 of each of the first queries Q1-1 to Q1-9 for the acquired first queries Q1-1 to Q1-9. .. Subsequently, when the acquisition unit 132 generates the distributed expression of each first query, the acquisition unit 132 stores the generated distributed expression of each first query in association with each first query in the vector information storage unit 122.

Further, when the acquisition unit 132 acquires a plurality of second queries, it acquires one second query from the plurality of second queries. In the example shown in FIG. 1, when the acquisition unit 132 acquires the second query Q2-1 to Q2-3, the acquisition unit 132 acquires one second query Q2-1 from the second queries Q2-1 to Q2-3. .. Subsequently, the acquisition unit 132 inputs the acquired second query to the first model M1 as the input information of the first model M1. In the example shown in FIG. 1, the acquisition unit 132 inputs the acquired second query Q2-1 into the first model M1 as the input information of the first model M1. Further, the acquisition unit 132 outputs the distributed representation of the second query input to the first model M1 as the output information of the first model M1 from the first model M1. In the example shown in FIG. 1, the acquisition unit 132 outputs the distributed representation QV2-1 of the second query Q2-1 input to the first model M1 as the output information of the first model M1 from the first model M1. In this way, the acquisition unit 132 generates the distributed representation of the second query. Similarly, the acquisition unit 132 generates a distributed representation of each second query for all of the acquired second queries. In the example shown in FIG. 1, the acquisition unit 132 generates the distributed representations QV2-1 to QV2-3 of each of the second queries Q2-1 to Q2-3 for the acquired second queries Q2-1 to Q2-3. .. Subsequently, when the acquisition unit 132 generates the distributed expression of each second query, the acquisition unit 132 stores the generated distributed expression of each second query in association with each second query in the vector information storage unit 122.

Further, when the reception unit 131 receives a plurality of first queries indicating the similarity determination target and a plurality of second queries indicating the similarity determination criteria, the acquisition unit 132 uses the first model M1. The distributed representation of each generated first query and the distributed representation of each second query generated using the first model M1 are acquired. For example, the acquisition unit 132 refers to the query information storage unit 121 and the vector information storage unit 122 to acquire the distributed representation of each first query and the distributed representation of each second query received by the reception unit 131. .. In the example shown in FIG. 1, the acquisition unit 132 has the distributed representations QV1-1 to QV1-9 of the first queries Q1-1 to Q1-9 and the distributed representations QV2-1 of the second queries Q2-1 to Q2-3. ~ QV2-3 and are acquired.

(Generator 133)
For each second query, the generation unit 133 generates similar information indicating the similarity between the determination target indicated by each first query and the determination criterion indicated by the second query. Specifically, the generation unit 133 has a search intention when the target information indicating the determination target is input as the first query and a search intention when the reference information indicating the determination criterion is input as the second query. Generate similar information based on scores that indicate similarity. More specifically, the generation unit 133 generates similar information based on the score which is the degree of similarity between the distributed expression corresponding to the character information which is the target information and the distributed expression corresponding to the character information which is the reference information. ..

For example, when the generation unit 133 acquires the distributed representation of each first query and the distributed representation of each second query generated by the acquisition unit 132 using the first model M1, each of the distributed representations of the second query. In addition, the degree of similarity between the distributed representation of each first query and the distributed representation of the second query is calculated. For example, the generation unit 133 calculates the cosine similarity between the distributed representation of each first query and the distributed representation of the second query. The generation unit 133 may calculate the similarity between the distributed representations based on any index as long as it is an index applicable as a distance scale between vectors, not limited to the cosine similarity. For example, the generation unit 133 may calculate the value of a predetermined distance function such as the Euclidean distance between distributed expressions, the distance in a non-Euclidean space such as hyperbolic space, the Manhattan distance, the Mahalanobis distance, and the like.

In the example shown in FIG. 1, the generation unit 133 distributes the distributed expression QV2-1 of the second query Q2-1 “camp” and the dispersion of the first queries Q1-1 “vehicle type T11” to Q1-9 “vehicle type T33”. The similarity SC1-1 to SC1-9 with the expressions QV1-1 to QV1-9 are calculated. Specifically, the generation unit 133 has the distributed expression QV2-1 of the second query Q2-1 "camp" acquired by the acquisition unit 132 and the distributed expression QV1-1 of the first query Q1-1 "vehicle type T11". The similarity SC1-1 of is calculated. Subsequently, the generation unit 133 calculates the similarity SC1-2 between the distributed expression QV2-1 of the second query Q2-1 "camp" and the distributed expression QV1-2 of the first query Q1-2 "vehicle type T12". .. Subsequently, the generation unit 133 calculates the distributed expression QV2-1 of the second query Q2-1 "camp", the distributed expression of the first query Q1-3 "vehicle type T13", and the similarity SC1-3 of the QV1-3. .. Similarly, the generation unit 133 has the distributed expression QV2-1 of the second query Q2-1 "camp" and the distributed expression QV1- of each first query Q1-4 "vehicle type T21" to Q1-9 "vehicle type T33". The similarity SC1-4 to SC1-9 with 4 to QV1-9 is calculated.

In addition, the generation unit 133 has the distributed expression QV2-2 of the second query Q2-2 "SNS # 1" and the distributed expression QV1- of each first query Q1-1 "vehicle type T11" to Q1-9 "vehicle type T33". The degree of similarity with 1 to QV1-9 SC2-1 to SC2-9 is calculated. For example, the generation unit 133 calculates the similarity SC2-1 between the distributed expression QV2-2 of the second query Q2-2 "SNS # 1" and the distributed expression QV1-1 of the first query Q1-1 "vehicle type T11". do. Subsequently, the generation unit 133 determines the degree of similarity SC2-2 between the distributed expression QV2-2 of the second query Q2-2 "SNS # 1" and the distributed expression QV1-2 of the first query Q1-2 "vehicle type T12". calculate. Subsequently, the generation unit 133 determines the degree of similarity SC2-3 between the distributed expression QV2-2 of the second query Q2-2 "SNS # 1" and the distributed expression QV1-3 of the first query Q1-3 "vehicle type T13". calculate. Similarly, the generation unit 133 includes the distributed representation QV2-2 of the second query Q2-2 "SNS # 1" and the distributed representation of the first queries Q1-4 "vehicle type T21" to Q1-9 "vehicle type T33". And QV1-4 to QV1-9 have similarities SC2-4 to SC2-9.

In addition, the generation unit 133 has a distributed expression QV2-3 of the second query Q2-3 "night view" and a distributed expression QV1-1 to Q1-9 "vehicle type T33" of each first query Q1-1 "vehicle type T11" to Q1-9. The degree of similarity with QV1-9 SC3-1 to SC3-9 is calculated. More specifically, the generation unit 133 has a similarity SC3-1 between the distributed expression QV2-3 of the second query Q2-3 "night view" and the distributed expression QV1-1 of the first query Q1-1 "vehicle type T11". Is calculated. Subsequently, the generation unit 133 calculates the similarity SC3-2 between the distributed expression QV2-3 of the second query Q2-3 "night view" and the distributed expression QV1-2 of the first query Q1-2 "vehicle type T12". .. Subsequently, the generation unit 133 calculates the similarity SC3-3 between the distributed expression QV2-3 of the second query Q2-3 "night view" and the distributed expression QV1-3 of the first query Q1-3 "vehicle type T13". .. Similarly, the generation unit 133 has the distributed expression QV2-3 of the second query Q2-3 "night view" and the distributed expression QV1- of each first query Q1-4 "vehicle type T21" to Q1-9 "vehicle type T33". The similarity SC3-4 to SC3-9 with 4 to QV1-9 is calculated.

In addition, the generation unit 133 generates information on the graph that makes the magnitude of the score visible as similar information. Specifically, when the generation unit 133 calculates the similarity between the distributed representation of each first query and the distributed representation of the second query for each distributed representation of the second query, the calculated degree of similarity is calculated. Generate information about the visible graph. For example, the generation unit 133 generates information about the bar graph made visible by indicating the calculated degree of similarity by the length of the bar graph. In addition, the generation unit 133 generates content in which similar information and the second query are displayed in association with each other for each second query. For example, the generation unit 133 generates content in which the generated graph and the second query are visually associated and displayed.

In the example shown in FIG. 1, the generation unit 133 is similar to the distributed representation QV2-1 of the second query Q2-1 and the distributed representation QV1-1 to QV1-9 of each of the first queries Q1-1 to Q1-9. When the degrees SC1-1 to SC1-9 are calculated, information about the bar graph G21 that makes the calculated magnitudes of the similarity SC1-1 to SC1-9 visible is generated. Specifically, the generation unit 133 generates the information shown in the display area F21 of the partial content C21 of FIG. The generation unit 133 generates the partial content C21 in which the generated bar graph G21 and the second query Q2-1 are visually associated and displayed. For example, the generation unit 133 generates information in which "camp", which is a character string indicating the second query and the second query Q2-1, is arranged above the bar graph G21 and displayed. In addition, the generation unit 133 generates information regarding the bar graph G21 which indicates the calculated magnitudes of the similarity SC1-1 to SC1-9 by the length of each bar graph.

Further, the generation unit 133 has a degree of similarity between the distributed representation QV2-2 of the second query Q2-2 and the distributed representation QV1-1 to QV1-9 of each of the first queries Q1-1 to Q1-9. When SC2-9 is calculated, information about the bar graph G22 that makes the calculated magnitudes of similarity SC2-1 to SC2-9 visible is generated. Specifically, the generation unit 133 generates the information shown in the display area F22 of the partial content C21 of FIG. The generation unit 133 generates the partial content C21 in which the generated bar graph G21 and the second query Q2-2 are visually associated and displayed. For example, the generation unit 133 generates information in which "SNS # 1", which is a character string indicating the second query and the second query Q2-2, is arranged above the bar graph G22 and displayed. Further, the generation unit 133 generates information regarding the bar graph G22 which indicates the calculated magnitudes of the similarity SC2-1 to SC2-9 by the length of each bar graph.

Further, the generation unit 133 has a degree of similarity between the distributed representation QV2-3 of the second query Q2-3 and the distributed representation QV1-1 to QV1-9 of each of the first queries Q1-1 to Q1-9. When the SC3-9 is calculated, information about the bar graph G23 that makes the calculated magnitudes of the similarity SC3-1 to SC3-9 visible is generated. Specifically, the generation unit 133 generates the information shown in the display area F23 of the partial content C21 of FIG. The generation unit 133 generates the partial content C21 in which the generated bar graph G23 and the second query Q2-3 are visually associated and displayed. For example, the generation unit 133 generates information in which the “night view”, which is a character string indicating the second query and the second query Q2-3, is arranged above the bar graph G23 and displayed. In addition, the generation unit 133 generates information regarding the bar graph G23 which indicates the calculated magnitudes of the similarity SC3-1 to SC3-9 by the length of each bar graph.

In addition, the generation unit 133 generates information on the graph in which the area indicating the size of the score is color-coded by different colors depending on the business operator handling the transaction target as similar information. For example, the generation unit 133 generates information on a graph in which a region indicating the magnitude of similarity is color-coded by different colors depending on the business operator handling the transaction target indicated by the first query.

In the example shown in FIG. 1, the generation unit 133 generates a graph in which regions indicating the magnitude of similarity are color-coded by different colors depending on the automobile manufacturer handling the automobile of the vehicle type indicated by the first query. For example, the generation unit 133 fills the area of the bar graph indicating the size of the similarity SC1-1 to SC1-3 corresponding to the first query Q1-1 to Q1-3 indicating the product name of the automobile manufacturer # 1 in red. Generates information about the bar graph G21. In addition, the generation unit 133 fills the area of the bar graph indicating the size of the similarity SC1-4 to SC1-6 corresponding to the first queries Q1-4 to Q1-6 indicating the product name of the automobile manufacturer # 2 in blue. Generates information about the bar graph G21. In addition, the generation unit 133 fills the area of the bar graph indicating the size of the similarity SC1-7 to SC1-9 corresponding to the first queries Q1-7 to Q1-9 indicating the product name of the automobile manufacturer # 3 in yellow. Generates information about the bar graph G21.

In addition, the generation unit 133 fills the area of the bar graph indicating the size of the similarity SC2-1 to SC2-3 corresponding to the first query Q1-1 to Q1-3 indicating the product name of the automobile manufacturer # 1 in red. Generates information about the bar graph G22. In addition, the generation unit 133 fills the area of the bar graph indicating the size of the similarity SC2-4 to SC2-6 corresponding to the first queries Q1-4 to Q1-6 indicating the product name of the automobile manufacturer # 2 in blue. Generates information about the bar graph G22. In addition, the generation unit 133 fills the area of the bar graph indicating the size of the similarity SC2-7 to SC2-9 corresponding to the first queries Q1-7 to Q1-9 indicating the product name of the automobile manufacturer # 3 in yellow. Generates information about the bar graph G22.

In addition, the generation unit 133 fills the area of the bar graph indicating the size of the similarity SC3-1 to SC3-3 corresponding to the first query Q1-1 to Q1-3 indicating the product name of the automobile manufacturer # 1 in red. Generates information about the bar graph G23. In addition, the generation unit 133 fills the area of the bar graph indicating the size of the similarity SC3-4 to SC3-6 corresponding to the first queries Q1-4 to Q1-6 indicating the product name of the automobile manufacturer # 2 in blue. Generates information about the bar graph G23. In addition, the generation unit 133 fills the area of the bar graph indicating the size of the similarity SC3-7 to SC3-9 corresponding to the first queries Q1-7 to Q1-9 indicating the product name of the automobile manufacturer # 3 in yellow. Generates information about the bar graph G23.

(Output unit 134)
The output unit 134 outputs similar information generated by the generation unit 133. Specifically, the output unit 134 outputs information about the graph generated by the generation unit 133 for each second query. For example, when the output unit 134 generates information about the graph by the generation unit 133, the output unit 134 transmits the information about the graph to the terminal device 10.

In the example shown in FIG. 1, when the generation unit 133 generates information on the three bar graphs G21 to G23, the output unit 134 transmits the information on the generated three bar graphs G21 to G23 to the terminal device 10.

[3. Terminal device configuration]
Next, the configuration of the terminal device 10 according to the embodiment will be described with reference to FIG. FIG. 8 is a diagram showing a configuration example of the terminal device 10 according to the embodiment. As shown in FIG. 8, the terminal device 10 includes a communication unit 11, an input unit 12, a display unit 13, a storage unit 14, and a control unit 15.

(Communication unit 11)
The communication unit 11 is realized by, for example, a NIC or the like. Then, the communication unit 11 is connected to the network N by wire or wirelessly, and transmits / receives information to / from the information processing device 100.

(Input unit 12, display unit 13)
The input unit 12 is an input device that receives various operations from the user. Various information is input to the input unit 12 via the display unit 13. For example, the input unit 12 is realized by a keyboard, a mouse, operation keys, or the like. The display unit 13 is a display device for displaying various information, that is, a screen. For example, the display unit 13 is realized by a liquid crystal display or the like. The display unit 13 displays the information stored in the storage unit 14. The display unit 13 displays the information received by the reception unit 151. The display unit 13 displays various information according to the control by the display control unit 152. When a touch panel is adopted for the terminal device 10, the input unit 12 and the display unit 13 are integrated. Further, in the following description, the display unit 13 may be described as a screen.

In the example of FIG. 1, the display unit 13 displays the content C1 received by the reception unit 151. The display unit 13 displays the partial content C11 of the content C1 received by the reception unit 151. Specifically, the display unit 13 inputs the input field F11 capable of inputting a plurality of first queries, the input field F12 capable of inputting a plurality of second queries, and the information processing device 100 for the queries input in the input fields. The partial content C11 including the transmission button B11 to be transmitted to is displayed.

Further, the display unit 13 displays the partial content C12 of the content C1 received by the reception unit 151. The display unit 13 displays information about the bar graphs G21 to G23 received by the reception unit 151. Specifically, the display unit 13 displays information about the bar graphs G21 to G23 in each of the display areas F21 to F23 included in the partial content C12 of the content C1 received by the reception unit 151.

(Memory unit 14)
The storage unit 14 is realized by, for example, a semiconductor memory element such as a RAM or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 14 stores various information used for displaying the information. The storage unit 14 stores the information received by the reception unit 151. In the example shown in FIG. 1, the storage unit 14 stores the content C1 received by the reception unit 151. Further, the storage unit 14 stores the partial content C11 of the content C1 received by the reception unit 151. Further, the storage unit 14 stores the partial content C12 of the content C1 received by the reception unit 151. Further, the storage unit 14 stores information regarding the bar graphs G21 to G23 received by the reception unit 151.

(Control unit 15)
In the control unit 15, various programs stored in the storage device inside the terminal device 10 by the CPU, MPU, or the like (for example, corresponding to an example of a display control program for displaying the content C1 or the like on the screen) use the RAM as a work area. It is realized by being executed. For example, these various programs correspond to application programs called web browsers. Further, the control unit 15 is realized by, for example, an integrated circuit such as an ASIC or FPGA.

As shown in FIG. 8, the control unit 15 includes a reception unit 151, a display control unit 152, a reception unit 153, and a transmission unit 154, and realizes or executes an information processing function or operation described below. do. The internal configuration of the control unit 15 is not limited to the configuration shown in FIG. 8, and may be another configuration as long as it is a configuration for performing information processing described later.

(Receiver 151)
The receiving unit 151 receives various information. The receiving unit 151 receives various information from an external information processing device. The receiving unit 151 receives various information from other information processing devices such as the information processing device 100. In the example of FIG. 1, the receiving unit 151 receives the content C1 from the information processing device 100. Further, the receiving unit 151 receives the partial content C11 of the content C1 from the information processing device 100. Further, the receiving unit 151 receives the partial content C12 of the content C1 from the information processing device 100. Further, the receiving unit 151 receives information about the bar graphs G21 to G23 from the information processing device 100.

(Display control unit 152)
The display control unit 152 controls various displays. The display control unit 152 controls the display of the display unit 13. The display control unit 152 controls the display of the display unit 13 in response to the reception by the reception unit 151. The display control unit 152 controls the display of the display unit 13 based on the information received by the reception unit 151. The display control unit 152 controls the display of the display unit 13 based on the information received by the reception unit 153. The display control unit 152 controls the display of the display unit 13 in response to the reception by the reception unit 153. The display control unit 152 controls the display of the display unit 13 so that the content is displayed on the display unit 13.

In the example of FIG. 1, the display control unit 152 controls the display of the display unit 13 so that the content C1 is displayed. Further, the display control unit 152 controls the display of the display unit 13 so that the partial content C11 of the content C1 is displayed. Further, the display control unit 152 controls the display of the display unit 13 so that the partial content C12 of the content C1 is displayed. Further, the display control unit 152 controls the display of the display unit 13 so that the information related to the bar graphs G21 to G23 is displayed in each of the display areas F21 to F23 included in the partial content C12 of the content C1.

(Reception Department 153)
The reception unit 153 receives various information. For example, the reception unit 153 receives an input by the user via the input unit 12. The reception unit 153 accepts operations by the user. The reception unit 153 accepts the user's operation on the information displayed by the display unit 13. The reception unit 153 accepts character input by the user. The reception unit 153 accepts the input of a plurality of first queries by the user. The reception unit 153 accepts the input of the first query by inputting characters into the input field F11 included in the partial content C11 of the content C1. The reception unit 153 accepts the character string input by the user in the input field F11 as the first query. Further, the reception unit 153 accepts each character string separated by a delimiter as each first query.

In addition, the reception unit 153 accepts the input of a plurality of second queries by the user. The reception unit 153 accepts the input of the second query by inputting characters into the input field F12 included in the partial content C11 of the content C1. The reception unit 153 accepts the character string input by the user in the input field F12 as the second query. Further, the reception unit 153 accepts each character string separated by a delimiter as each second query.

In addition, the reception unit 153 accepts the user's selection operation of the transmission button B11. The reception unit 153 accepts the selection operation of the transmission button B11 received by the input unit 12.

In the example of FIG. 1, the reception unit 153 accepts inputs of nine first queries Q1-1 to Q1-9, which are nine character strings separated by delimiters. The reception unit 153 accepts the inputs of the nine first queries Q1-1 to Q1-9 by inputting characters into the input field F11 included in the partial content C11 of the content C1. The reception unit 153 accepts the input of the nine first queries "vehicle type T11" to the character string "vehicle type T33", which are nine character strings input by the user U11 in the input field F11.

Further, the reception unit 153 accepts inputs of three second queries Q2-1 to Q2-3, which are three character strings separated by a delimiter. The reception unit 153 accepts the inputs of the three second queries Q2-1 to Q2-3 by inputting characters into the input field F12 included in the partial content C11 of the content C1. The reception unit 153 accepts the input of the three second queries "camp" to the character string "night view", which are the three character strings input to the input field F12 by the user U11.

In addition, the reception unit 153 accepts the selection operation of the transmission button B11 by the user U11. The reception unit 153 accepts the selection operation of the transmission button B11 received by the input unit 12. The reception unit 153 accepts the selection operation of the transmission button B11 received via the display unit 13.

(Transmission unit 154)
The transmission unit 154 transmits various information to an external information processing device. For example, the transmission unit 154 transmits various information to another information processing device such as the information processing device 100. The transmission unit 154 transmits the information stored in the storage unit 14. Further, the transmission unit 154 transmits various information based on the information from other information processing devices such as the information processing device 100. The transmission unit 154 transmits various types of information based on the information stored in the storage unit 14. The transmission unit 154 transmits the information received by the reception unit 153.

The transmission unit 154 transmits a plurality of first queries and a plurality of second queries received by the reception unit 153 to the information processing device 100. Specifically, when the reception unit 153 accepts the selection operation of the transmission button B11, the transmission unit 154 transmits a plurality of first queries and a plurality of second queries received by the reception unit 153 to the information processing device 100. do.

In the example of FIG. 1, when the reception unit 153 accepts the selection operation of the transmission button B11, the transmission unit 154 processes the nine first queries Q1-1 to Q1-9 received by the reception unit 153 in the information processing device 100. Send to. The transmission unit 154 transmits nine first queries Q1-1 to Q1-9, which are nine character strings received by the reception unit 153, to the information processing device 100.

Further, when the reception unit 153 accepts the selection operation of the transmission button B11, the transmission unit 154 transmits the three second queries Q2-1 to Q2-3 received by the reception unit 153 to the information processing device 100. The transmission unit 154 transmits three second queries Q2-1 to Q2-3, which are three character strings received by the reception unit 153, to the information processing device 100.

[4. Information processing flow]
Next, the procedure of information processing according to the embodiment will be described with reference to FIG. FIG. 9 is a flowchart showing an information processing procedure according to the embodiment. In the example shown in FIG. 9, the information processing apparatus 100 determines whether or not a plurality of first queries indicating the similarity determination target and a plurality of second queries indicating the similarity determination criteria have been received from the terminal device 10. Judgment (step S101). When the information processing apparatus 100 does not accept the plurality of first queries and the plurality of second queries (step S101; No), the information processing apparatus 100 waits until the plurality of first queries and the plurality of second queries are accepted.

Subsequently, when the information processing apparatus 100 receives a plurality of first queries and a plurality of second queries (step S101; Yes), the determination target and the second query indicated by each first query for each second query. Generates similar information indicating similarity to the determination criteria indicated by (step S102).

Subsequently, when the information processing apparatus 100 generates the similar information, the information processing apparatus 100 outputs the generated similar information to the terminal apparatus 10 (step S103).

[5. Modification example]
The information processing system 1 according to the above-described embodiment may be implemented in various different forms other than the above-described embodiment. Therefore, another embodiment of the information processing system 1 will be described below. The same parts as those in the embodiment are designated by the same reference numerals, and the description thereof will be omitted.

[5-1. Color-coded graph according to the attributes of the transaction target]
As similar information, the information processing apparatus 100 may generate information on a graph in which a region indicating the size of the score is color-coded by different colors according to the attributes of the transaction target. Specifically, the generation unit 133 generates information on a graph in which a region indicating the size of the score is color-coded with different colors according to the attributes of the transaction target as similar information. More specifically, when the transaction target indicated by the plurality of first queries received by the reception unit 131 is classified into a plurality of different attributes, the generation unit 133 uses different colors according to the respective attributes. The area showing the magnitude of the score produces information about the color-coded graph. For example, in the generation unit 133, when the attributes of the transaction target indicated by the plurality of first queries received by the reception unit 131 are classified into three different attributes of "food", "clothing", and "pharmaceutical product". , Generates information about a bar graph in which the color of the area indicating the magnitude of the score for the first query corresponding to "food" is filled in red. In addition, the generation unit 133 generates information on a bar graph in which the color of the region indicating the size of the score for the first query corresponding to "clothing" is filled with blue. In addition, the generation unit 133 generates information on a bar graph in which the color of the region indicating the size of the score for the first query corresponding to the “pharmaceutical product” is filled with yellow.

[6. First model generation process]
Next, the flow of the generation process of the first model will be described with reference to FIG. FIG. 10 is a diagram showing an example of the generation process of the first model according to the embodiment. In the example shown in FIG. 10, the generator 50 is a pair consisting of a search query Q11 "Roppongi pasta" and a search query Q12 "Roppongi Italian" continuously input by the same user U1 within a predetermined time. Extract the search query of (step S11).

Subsequently, the generation device 50 inputs the extracted search query Q11 into the first model M1 and outputs a vector BQV11 which is a distributed representation of the search query Q11. Here, the vector BQV11 is a distributed representation of the search query Q11 just output from the output layer of the first model M1, and shows a distributed representation before giving feedback to the first model M1 (before learning). Further, the generation device 50 inputs the extracted search query Q12 into the first model M1 and outputs a vector BQV12 which is a distributed representation of the search query Q12. Here, the vector BQV12 is a distributed representation of the search query Q12 just output from the output layer of the first model M1, and shows a distributed representation before giving feedback to the first model M1 (before learning). In this way, the generation device 50 outputs the vector BQV11 which is the distributed representation of the search query Q11 and the vector BQV12 which is the distributed representation of the search query Q12 (step S12).

Subsequently, the generator 50 is a pair of searches including the search query Q11 (“Roppongi pasta”) and the search query Q12 (“Roppongi Italian”) that are continuously input by the same user U1 within a predetermined time. Since the query is presumed to be a search query input with a predetermined search intention (for example, a search intention of "searching for a restaurant in a certain place"), the search query Q11 is assumed to have similar characteristics to each other. The first model M1 is trained so that the distributed representation (vector QV11) of the above and the distributed representation (vector QV12) of the search query Q12 paired with the search query Q11 are similar in the distributed representation space. For example, let Θ be the magnitude of the angle formed by the vector BQV11 which is the distributed representation of the search query Q11 before giving feedback to the first model M1 (before learning) and the vector BQV12 which is the distributed representation of the search query Q12. Further, let Φ be the size of the angle formed by the vector QV11 which is the distributed expression of the search query Q11 after giving feedback to the first model M1 (after learning) and the vector QV12 which is the distributed expression of the search query Q12. At this time, the generator 50 trains the first model M1 so that Φ is smaller than Θ. For example, the generator 50 calculates the value of the cosine similarity between the vector BQV11 and the vector BQV12. Further, the generation device 50 calculates the value of the cosine similarity between the vector QV11 and the vector QV12. Subsequently, the generator 50 uses the first model so that the cosine similarity values of the vector QV11 and the vector QV12 are larger than the cosine similarity values of the vector BQV11 and the vector BQV12 (so that the values approach 1). Learn M1. In this way, the generation device 50 trains the first model M1 so that the two vectors, which are a pair of distributed representations corresponding to the pair of search queries, are similar in the distributed representation space, so that the distributed representation is expressed from the search query. Is generated (step S13). The generator 50 is not limited to the cosine similarity, and may calculate the similarity between the distributed representations based on any index as long as it is an index applicable as a distance scale between vectors. Further, the generation device 50 may train the first model M1 based on any index as long as it is an index applicable as a distance scale between vectors. For example, the generation device 50 calculates the value of a predetermined distance function such as the Euclidean distance between distributed expressions, the distance in a non-Euclidean space such as hyperbolic space, the Manhattan distance, the Mahalanobis distance, and the like. Subsequently, the generation device 50 may train the first model M1 so that the value of a predetermined distance function between the distributed representations (that is, the distance in the distributed representation space) becomes small.

Next, the flow of the generation process of the first model will be described in more detail with reference to FIG. In the description of FIG. 11, a part that overlaps with the description of FIG. 9 will be omitted as appropriate. FIG. 11 is a diagram showing a generation process of the first model according to the embodiment. In the example shown in FIG. 11, the distributed representation output by the first model M1 generated by the generation device 50 is mapped to the distributed representation space. The generation device 50 trains the first model M1 so that the distributed representation of a predetermined search query and the distributed representation of another search query paired with the predetermined search query are mapped close to each other in the distributed representation space. ..

In the example shown in the upper part of FIG. 11, the generator 50 is a search query Q11 (“Roppongi pasta”), which is four search queries continuously input by the same user U1 within a predetermined time, and a search query. Extract Q12 (“Roppongi Italian”), search query Q13 (“Akasaka pasta”), and search query Q14 (“Azabu pasta”). The generation device 50 extracts four search queries in which the time interval in which each search query is input by the same user U1 is within a predetermined time. The generation device 50 extracts a plurality of search queries in which the time interval in which each search query pair described later is input by the same user U1 is within a predetermined time. When the search queries are arranged in the order in which the search queries are input, the generation device 50 extracts four search queries input in the order of the search query Q11, the search query Q12, the search query Q13, and the search query Q14. When the generation device 50 extracts four search queries, it is a pair of three search queries (search query Q11, search query Q12), with two search queries adjacent in chronological order as a pair of search queries. (Search query Q12, search query Q13) and (search query Q13, search query Q14) are extracted (step S21-1). The generation device 50 may extract a plurality of search queries in which all the search queries are input within a predetermined time by the same user U1. Then, the generation device 50 selects two search queries from the extracted plurality of search queries regardless of whether they are adjacent to each other in chronological order, and uses the two selected search queries as a pair of search queries. It may be extracted.

Subsequently, the generation device 50 inputs the extracted search query Q1k (k = 1, 2, 3, 4) into the first model M1, and distributes the search query Q1k (k = 1, 2, 3, 4). The representation vector BQV1k (k = 1, 2, 3, 4) is output. Here, the vector BQV1k (k = 1, 2, 3, 4) is a distributed representation of the search query Q1k (k = 1, 2, 3, 4) just output from the output layer of the first model M1. , The distributed representation before giving feedback to the first model M1 (before learning) is shown (step S22-1).

Subsequently, in the generator 50, a pair of search queries continuously input by the same user U1 within a predetermined time is subjected to a predetermined search intention (for example, "eating and drinking at a certain place (near Minato-ku, Tokyo)). Since it is presumed that the search query was entered with the search intent of "finding a store"), the distributed representation of the search query Q11 (vector QV11) and the pair with the search query Q11 are assumed to have similar characteristics to each other. The first model M1 is trained so that the distributed representation (vector QV12) of the search query Q12 is similar on the distributed representation space. Further, in the generation device 50, the first distributed representation of the search query Q12 (vector QV12) and the distributed representation of the search query Q13 paired with the search query Q12 (vector QV13) are similar in the distributed representation space. Train model M1. Further, in the generation device 50, the first distributed representation of the search query Q13 (vector QV13) and the distributed representation of the search query Q14 paired with the search query Q13 (vector QV14) are similar in the distributed representation space. Train model M1. In this way, the generation device 50 trains the first model M1 so that the two vectors, which are a pair of distributed representations corresponding to the pair of search queries, are similar in the distributed representation space, so that the distributed representation is expressed from the search query. Is generated (step S23-1).

As a result of the information processing shown in the upper part of FIG. 11, the vector QV1k (k = 1, 2, 3, 4), which is a distributed representation of the search query Q1k (k = 1, 2, 3, 4), is close to the distributed representation space. It is shown that the position is mapped as cluster CL11. For example, the search query Q1k (k = 1, 2, 3, 4) is a search query searched by the user U1 with the search intention of "searching for a restaurant in a certain place (near Minato-ku, Tokyo)". It is presumed to be a set. That is, the search query Q1k (k = 1, 2, 3, 4) is a search query searched with the search intention of "searching for a restaurant in a certain place (near Minato-ku, Tokyo)". , It is presumed that the search query has similar characteristics to each other. Here, when the predetermined search query input with the search intention of "searching for a restaurant in a certain place (near Minato-ku, Tokyo)" is input to the first model, the generator 50 is placed at the position of the cluster CL11. It is possible to output a distributed representation that is mapped. As a result, for example, the generator 50 has a search intention of "searching for a restaurant in a certain place (near Minato-ku, Tokyo)" by extracting a search query corresponding to the distributed representation mapped to the position of the cluster CL11. Search queries can be extracted according to. Therefore, the generation device 50 can appropriately interpret the meaning of the search query.

In the example shown in the lower part of FIG. 11, the generator 50 is a search query Q21 (“refrigerator 400L”), which is three search queries continuously input by the same user U2 within a predetermined time, and a search query. Extract Q22 ("refrigerator medium size") and search query Q23 ("refrigerator medium size recommended"). When the generation device 50 arranges the search queries in the order in which they are input, the generation device 50 extracts three search queries input in the order of the search query Q21, the search query Q22, and the search query Q23. When the generation device 50 extracts three search queries, it is a pair of two search queries (search query Q21, search query Q22), with two search queries adjacent in chronological order as a pair of search queries. (Search query Q22, search query Q23) is extracted (step S21-2).

Subsequently, the generation device 50 inputs the extracted search query Q2m (m = 1, 2, 3) into the first model M1, and a vector that is a distributed representation of the search query Q2m (m = 1, 2, 3). BQV2m (m = 1, 2, 3) is output. Here, the vector BQV2m (m = 1, 2, 3) is a distributed representation of the search query Q2m (m = 1, 2, 3) just output from the output layer of the first model M1, and is the first model. The distributed expression before giving feedback to M1 (before learning) is shown (step S22-2).

Subsequently, the generation device 50 uses the same user U2 to continuously input a pair of search queries within a predetermined time with a predetermined search intention (for example, a search intention of "checking a medium-sized refrigerator"). Since it is presumed to be an input search query, the distributed representation of the search query Q21 (vector QV21) and the distributed representation of the search query Q22 paired with the search query Q21 (vector) are assumed to have similar characteristics to each other. QV22) and the first model M1 are trained so as to be similar in the distributed expression space. Further, in the generation device 50, the first distributed representation of the search query Q22 (vector QV22) and the distributed representation of the search query Q23 paired with the search query Q22 (vector QV23) are similar in the distributed representation space. Train model M1. In this way, the generation device 50 trains the first model M1 so that the two vectors, which are a pair of distributed representations corresponding to the pair of search queries, are similar in the distributed representation space, so that the distributed representation is expressed from the search query. Is generated (step S23-2).

As a result of the information processing shown in the lower part of FIG. 11, the vector QV2m (m = 1, 2, 3), which is a distributed representation of the search query Q2m (m = 1, 2, 3), is located near the distributed representation space of the cluster CL21. It is shown that it is mapped as. For example, the search query Q2m (m = 1, 2, 3) is presumed to be a set of search queries searched by the user U2 with the search intention of "checking a medium-sized refrigerator". That is, Q2m (m = 1, 2, 3) is a search query having characteristics similar to each other in that it is a search query searched with the search intention of "searching for a medium-sized refrigerator". Presumed. Here, the generator 50 outputs a distributed representation that is mapped to the position of the cluster CL21 when a predetermined search query input with the search intention of "checking a medium-sized refrigerator" is input to the first model. can do. As a result, for example, the generator 50 extracts the search query corresponding to the distributed representation mapped to the position of the cluster CL21, thereby extracting the search query according to the search intention of "checking the medium-sized refrigerator". Can be done. Therefore, the generation device 50 can appropriately interpret the meaning of the search query.

Further, the generation device 50 according to the present invention is a search query having different characteristics in that a plurality of randomly extracted search queries are search queries searched under different search intentions. Assuming that, the first model M1 is trained. Specifically, the generation device 50 maps the distributed representation of a predetermined search query and the distributed representation of a search query randomly extracted independently of the predetermined search query far away in the distributed representation space. The first model M1 is trained. In the example shown in FIG. 11, it is assumed that the generation device 50 randomly extracts the search query regardless of the search query Q11, and the search query Q21 is extracted. In this case, in the generation device 50, the distributed representation of the search query Q11 (vector QV11) and the distributed representation of the search query Q21 randomly extracted regardless of the search query Q11 (vector QV21) are far apart in the distributed representation space. The first model M1 is trained so as to be mapped to. As a result, the vector QV1k, which is a distributed expression of the search query Q1k (k = 1, 2, 3, 4) searched with the search intention of "searching for a restaurant in a certain place (near Minato-ku, Tokyo)". It is a distributed representation of the cluster CL11 including (k = 1, 2, 3, 4) and the search query Q2m (m = 1, 2, 3) searched with the search intention of "checking a medium-sized refrigerator". The cluster CL21 containing the vector QV2m (m = 1, 2, 3) is mapped far away on the distributed representation space. That is, the generator 50 according to the present invention trains the first model M1 so that the distributed expressions of a plurality of randomly extracted search queries are different, so that the distributed expressions of the search queries having different search intentions are distributed. It is possible to output to a distant position in space.

As a result of mapping the distributed representation output by the first model M1 generated by the generation device 50 to the distributed representation space, in addition to the cluster CL11 and the cluster CL21 described above, the same user can use the same user within a predetermined time. Cluster CL12 and cluster CL22, which are a set of distributed expressions of a plurality of input search queries, are generated.

As described above, the generator 50 acquires the search query entered by the user. Further, the generation device 50 learns from the acquired search queries that a plurality of search queries input by the same user within a predetermined time have similar characteristics, so that the generated search query can be used as a predetermined search query. Generate a first model that predicts the feature information of the search query. That is, the generation device 50 according to the present invention is similar to each other in that a plurality of search queries continuously input within a predetermined time are search queries searched under a predetermined search intention. The first model is trained by regarding it as a characteristic search query. Specifically, the generation device 50 trains the first model so that the distributed representations of a plurality of search queries input by the same user within a predetermined time are similar to each other, so that the first model is trained from the predetermined search query. Generate the first model that outputs the distributed representation including the feature information of the search query. That is, the generation device 50 according to the present invention trains the first model M1 so that the distributed representations of a plurality of search queries continuously input within a predetermined time are similar, so that the first model M1 is trained under a predetermined search intention. The distributed representation of the search query searched in is able to be output to a close position on the distributed representation space. As a result, the generation device 50 makes it possible to output (interpret) the meaning (search intention) of the search query according to the context of the user who input the search query. Therefore, the generation device 50 can appropriately interpret the meaning of the search query.

Further, the generation device 50 extracts a search query corresponding to the distributed expression mapped in the vicinity of the distributed expression including the feature information of the predetermined search query, so that the predetermined search query corresponds to the searched intent. Search queries can be extracted. That is, the generation device 50 makes it possible to analyze the search trend of the user in consideration of the search intention and context of the user who has input the search query. Therefore, the generation device 50 can improve the analysis accuracy of the user's search trend. Further, the first model M1 generated by the generation device 50 can be made to function as a part of the search system. Alternatively, the generation device 50 is a distributed representation of the search query output by the first model M1 as input information to another system (for example, a search engine) that uses the feature information of the search query predicted by the first model M1. Can also be provided. As a result, the search system can select the content output as the search result based on the feature information of the search query predicted by the first model M1. That is, the search system can select the content output as the search result in consideration of the search intention and context of the user who entered the search query. Further, the search system calculates the similarity between the distributed representation of the character information included in the content output as the search result and the distributed representation of the search query based on the characteristic information of the search query predicted by the first model M1. It will be possible. Then, the search system can determine the display order of the contents output as the search result based on the calculated similarity. That is, the search system can determine the display order of the contents output as the search result in consideration of the search intention and context of the user who input the search query. Therefore, the generation device 50 can improve the usability in the search service.

[7. Generator configuration]
Next, the configuration of the generation device 50 according to the embodiment will be described with reference to FIG. FIG. 12 is a diagram showing a configuration example of the generation device 50 according to the embodiment. As shown in FIG. 12, the generation device 50 includes a communication unit 51, a storage unit 53, and a control unit 52. The generation device 50 has an input unit (for example, a keyboard, a mouse, etc.) that receives various operations from the administrator of the generation device 50, and a display unit (for example, a liquid crystal display, etc.) for displaying various information. You may.

(Communication unit 51)
The communication unit 51 is realized by, for example, a NIC (Network Interface Card) or the like. Then, the communication unit 51 is connected to the network by wire or wirelessly, and for example, information is transmitted / received between the terminal device 10 and the search server 20.

(Memory unit 53)
The storage unit 53 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory (Flash Memory), or a storage device such as a hard disk or an optical disk. As shown in FIG. 12, the storage unit 53 includes a query information storage unit 531, a vector information storage unit 532, and a model information storage unit 533.

(Query information storage unit 531)
The query information storage unit 531 stores various information related to the search query input by the user. FIG. 13 shows an example of the query information storage unit according to the embodiment. In the example shown in FIG. 13, the query information storage unit 531 has items such as "user ID", "date and time", "search query", and "search query ID".

The "user ID" indicates identification information for identifying the user who entered the search query. "Date and time" indicates the date and time when the search server received the search query from the user. The "search query" indicates a search query entered by the user. The "search query ID" indicates identification information for identifying the search query entered by the user.

In the example shown in the first record of FIG. 13, the search query (search query Q11) identified by the search query ID “Q11” corresponds to the search query Q11 shown in FIG. Further, the user ID "U1" indicates that the user who has input the search query Q11 is a user (user U1) identified by the user ID "U1". Further, the date and time "2018/9/1 PM 17:00" indicates that the date and time when the search server receives the search query Q11 from the user U1 is 17:00 pm on September 1, 2018. Further, the search query "Roppongi pasta" indicates the search query Q11 input by the user U1. Specifically, the search query "Roppongi pasta" indicates that the characters "Roppongi" indicating the place name and the characters "pasta" indicating the type of food are separated by a space which is a delimiter.

(Vector information storage unit 532)
The vector information storage unit 532 stores various information related to the vector, which is a distributed representation of the search query. FIG. 14 shows an example of the vector information storage unit according to the embodiment. In the example shown in FIG. 14, the vector information storage unit 532 has items such as "vector ID", "search query ID", and "vector information".

“Vector ID” indicates identification information for identifying a vector which is a distributed representation of a search query. The "search query ID" indicates identification information for identifying the search query corresponding to the vector. "Vector information" indicates an N-dimensional vector which is a distributed representation of a search query. The vector, which is a distributed representation of the search query, is, for example, a 128-dimensional vector.

In the example shown in the first record of FIG. 14, the vector (vector QV11) identified by the vector ID “QV11” corresponds to the vector QV11 which is a distributed representation of the search query Q11 shown in FIG. Further, the search query (search query Q11) identified by the search query ID "Q11" indicates that the search query corresponding to the vector QV11 is the search query Q11. Further, the vector information "QVDT11" indicates an N-dimensional vector which is a distributed representation of the search query Q11.

(Model information storage unit 533)
The model information storage unit 533 stores various information related to the learning model generated by the generation device 50. FIG. 15 shows an example of the model information storage unit according to the embodiment. In the example shown in FIG. 15, the model information storage unit 533 has items such as "model ID" and "model data".

The "model ID" indicates identification information for identifying the learning model generated by the generation device 50. “Model data” indicates model data of the learning model generated by the generation device 50. For example, "model data" stores data for converting a search query into a distributed representation.

In the example shown in the first record of FIG. 15, the learning model identified by the model ID “M1” corresponds to the first model M1 shown in FIG. Further, the model data "MDT1" indicates model data (model data MDT1) of the first model M1 generated by the generation device 50.

The model data MDT1 includes an input layer into which a search query is input, an output layer, a first element which is any layer from the input layer to the output layer and belongs to a layer other than the output layer, and the first element and the first element. The output layer outputs a distributed representation of the search query input to the input layer according to the search query input to the input layer, including the second element whose value is calculated based on the weight of one element. As such, the generator 50 may be made to function.

Here, it is assumed that the model data MDT1 is realized by the regression model indicated by "y = a1 * x1 + a2 * x2 + ... + ai * xi". In this case, the first element included in the model data MDT1 corresponds to input data (xi) such as x1 and x2. Further, the weight of the first element corresponds to the coefficient ai corresponding to xi. Here, the regression model can be regarded as a simple perceptron having an input layer and an output layer. When each model is regarded as a simple perceptron, the first element corresponds to any node of the input layer, and the second element can be regarded as the node of the output layer.

Further, it is assumed that the model data MDT1 is realized by a neural network having one or a plurality of intermediate layers such as DNN (Deep Neural Network). In this case, the first element included in the model data MDT1 corresponds to either the node of the input layer or the intermediate layer. Further, the second element corresponds to a node in the next stage, which is a node to which a value is transmitted from a node corresponding to the first element. Further, the weight of the first element corresponds to a connection coefficient which is a weight considered for the value transmitted from the node corresponding to the first element to the node corresponding to the second element.

The generation device 50 calculates the distributed representation using a model having an arbitrary structure such as the regression model and the neural network described above. Specifically, the model data MDT1 is set with a coefficient so as to output a distributed representation when a search query is input. The generation device 50 calculates the distributed representation using such model data MDT1.

In the above example, the model data MDT1 is a model (hereinafter referred to as model X1) that outputs a distributed representation of the search query when the search query is input. However, the model data MDT1 according to the embodiment may be a model generated based on the result obtained by repeating the input / output of data to the model X1. For example, the model data MDT1 may be a model (hereinafter, referred to as model Y1) learned by inputting the distributed representation output by the model X1 when the search query is input. Alternatively, the model data MDT1 may be a model trained to input a search query and output the output value of the model Y1.

Further, when the generation device 50 performs the estimation process using GAN (Generative Adversarial Networks), the model data MDT1 may be a model forming a part of GAN.

(Control unit 52)
Returning to the description of FIG. 12, the control unit 52 is a controller, and is stored in a storage device inside the generation device 50 by, for example, a CPU (Central Processing Unit) or an MPU (Micro Processing Unit). It is realized by executing various programs (corresponding to an example of a generation program) using the RAM as a work area. Further, the control unit 52 is a controller, and is realized by, for example, an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

Further, the control unit 52 sends the search query input to the input layer to each layer other than the output layer by information processing according to the first model M1 (model data MDT1) stored in the model information storage unit 533. The computer is made to function so as to output a distributed representation from the output layer by performing an operation based on the first element and the weight of the first element with each element to which it belongs as the first element.

Further, the control unit 52 sends the search query input to the input layer to each layer other than the output layer by information processing according to the second model M2 (model data MDT2) stored in the model information storage unit 533. By performing an operation based on the first element and the weight of the first element with each element to which it belongs as the first element, the computer is made to function so that the probability that the search query belongs to each category is output from the output layer.

As shown in FIG. 12, the control unit 52 includes an acquisition unit 521, an extraction unit 522, and a generation unit 523, and realizes or executes the information processing operation described below. The internal configuration of the control unit 52 is not limited to the configuration shown in FIG. 12, and may be another configuration as long as it is a configuration for performing information processing described later.

(Acquisition unit 521)
The acquisition unit 521 acquires various information. Specifically, the acquisition unit 521 acquires the search query input by the user from the search server 20. When the acquisition unit 521 acquires the search query input by the user, the acquisition unit 521 stores the acquired search query in the query information storage unit 531.

In addition, the acquisition unit 521 acquires vector information regarding a vector which is a distributed representation of the search query. When the acquisition unit 521 acquires the vector information, the acquisition unit 521 stores the acquired vector information in the vector information storage unit 532.

In addition, the acquisition unit 521 acquires information about the first model. Specifically, the acquisition unit 521 acquires information about the first model generated by the generation unit 523. When the acquisition unit 521 acquires the information regarding the first model, the acquisition unit 521 stores the acquired information regarding the first model in the model information storage unit 533.

(Extractor 522)
The extraction unit 522 extracts various information. Specifically, the extraction unit 522 extracts a plurality of search queries input by the same user within a predetermined time from the search queries acquired by the acquisition unit 521. For example, the extraction unit 522 extracts a plurality of search queries in which the time interval in which each search query is input by the same user is within a predetermined time. Subsequently, the extraction unit 522 extracts a pair of search queries continuously input by the same user within a predetermined time from among a plurality of search queries input by the same user within a predetermined time. For example, the extraction unit 522 extracts a plurality of search queries in which the time interval in which each search query pair is input by the same user is within a predetermined time. For example, the extraction unit 522 is a search query Q11 (“Roppongi pasta”) which is four search queries continuously input by the same user U1 within a predetermined time among the search queries acquired by the acquisition unit 521. ”), Search query Q12 (“Roppongi Italian”), search query Q13 (“Akasaka pasta”), search query Q14 (“Azabu pasta”). When the search queries are arranged in the order in which they are input, the extraction unit 522 extracts four search queries input in the order of search query Q11, search query Q12, search query Q13, and search query Q14. Subsequently, when the extraction unit 522 extracts four search queries, it is a pair of three search queries (search query Q11, search query), with two search queries adjacent in chronological order as a pair of search queries. Q12), (search query Q12, search query Q13), (search query Q13, search query Q14) are extracted. The extraction unit 522 may extract a plurality of search queries in which all the search queries are input by the same user within a predetermined time. Then, the extraction unit 522 selects two search queries from the plurality of extracted search queries regardless of whether they are adjacent to each other in chronological order, and uses the two selected search queries as a pair of search queries. It may be extracted.

Further, the extraction unit 522 extracts a predetermined search query and other search queries unrelated to the predetermined search query from the search queries acquired by the acquisition unit 521. For example, the extraction unit 522 extracts a predetermined search query from the search queries acquired by the acquisition unit 521. Subsequently, the extraction unit 522 randomly extracts another search query from the search queries acquired by the acquisition unit 521, regardless of the predetermined search query.

(Generation unit 523)
The generation unit 523 generates various information. Specifically, the generation unit 523 learns that among the search queries acquired by the acquisition unit 521, a plurality of search queries input by the same user within a predetermined time have similar characteristics. , Generate a learning model that predicts the feature information of a predetermined search query from a predetermined search query. Specifically, the generation unit 523 trains the learning model so that the distributed expressions of a plurality of search queries input by the same user within a predetermined time are similar, thereby performing a predetermined search from the predetermined search query. Generate a learning model that predicts query feature information. For example, the generation unit 523 generates a learning model by learning so that the distributed expressions of a pair of search queries input consecutively within a predetermined time are similar. For example, the generation unit 523 calculates the value of the similarity of the distributed representation before learning the pair of search queries. In addition, the generation unit 523 calculates the value of the similarity of the distributed representation after learning the pair of search queries. Subsequently, the generation unit 523 trains the learning model so that the value of the similarity of the distributed expression after learning is larger than the value of the similarity of the distributed expression before learning. In this way, the generation unit 523 outputs the distributed expression from the search query by training the learning model so that the two vectors, which are the pair of distributed expressions corresponding to the pair of search queries, are similar in the distributed expression space. Generate a learning model to do. More specifically, the generation unit 523 generates a learning model that outputs a distributed expression from a search query by using the DSSM technology that uses LSTM, which is a kind of RNN, for the distributed expression generation. For example, the generation unit 523 assumes that the pair of search queries input by the same user within a predetermined time have similar characteristics as the correct answer data of the learning model, and the distributed representation of the predetermined search query and the predetermined search query are predetermined. Learn so that the distributed representations of other search queries that are paired with the search query are close together in the distributed representation space. Further, when the first model is generated, the generation unit 523 stores the generated first model (model data MDT1) in the model information storage unit 533 in association with the identification information that identifies the first model.

[8. Example of the first model]
Next, an example of the first model generated by the generation device 50 will be described with reference to FIG. FIG. 16 is a diagram showing an example of the first model according to the embodiment. In the example shown in FIG. 16, the first model M1 generated by the generation device 50 is composed of three layers of LSTM RNNs. In the example shown in FIG. 16, the extraction unit 522 is a pair consisting of a search query Q11 "Roppongi pasta" and a search query Q12 "Roppongi Italian" continuously input by the same user U1 within a predetermined time. Extract search queries for. The generation unit 523 inputs the search query Q11 extracted by the extraction unit 522 to the input layer of the first model M1 (step S41).

Subsequently, the generation unit 523 outputs a 256-dimensional vector BQV11 which is a distributed representation of the search query Q11 from the output layer of the first model M1. Further, the generation unit 523 inputs the search query Q12 extracted by the extraction unit 522 to the input layer of the first model M1. Subsequently, the generation unit 523 outputs a 256-dimensional vector BQV12 which is a distributed representation of the search query Q12 from the output layer of the first model M1 (step S42).

Subsequently, the generation unit 523 generates the first model M1 that outputs the distributed expression from the search query by learning so that the distributed expressions of the two consecutively input search queries are similar (step S43). .. For example, let Θ be the magnitude of the angle formed by the vector BQV11 which is the distributed representation of the search query Q11 before giving feedback to the first model M1 (before learning) and the vector BQV12 which is the distributed representation of the search query Q12. Further, let Φ be the size of the angle formed by the vector QV11 which is the distributed expression of the search query Q11 after giving feedback to the first model M1 (after learning) and the vector QV12 which is the distributed expression of the search query Q12. At this time, the generation unit 523 trains the first model M1 so that Φ is smaller than Θ. For example, the generation unit 523 calculates the value of the cosine similarity between the vector BQV11 and the vector BQV12. Further, the generation unit 523 calculates the value of the cosine similarity between the vector QV11 and the vector QV12. Subsequently, the generation unit 523 prepares the learning model M1 so that the value of the cosine similarity between the vector QV11 and the vector QV12 is larger than the value of the cosine similarity between the vector BQV11 and the vector BQV12 (so that the value approaches 1). To learn. In this way, the generation unit 523 trains the first model M1 so that the two vectors, which are a pair of distributed representations corresponding to the pair of search queries, are similar in the distributed representation space, so that the distributed representation is expressed from the search query. Generates the first model M1 that outputs. The generation unit 523 may calculate the similarity between the distributed representations based on any index as long as it is an index applicable as a distance scale between vectors, not limited to the cosine similarity. Further, the generation unit 523 may train the learning model M1 based on any index as long as it is an index applicable as a distance scale between vectors. For example, the generation unit 523 calculates the value of a predetermined distance function such as the Euclidean distance between distributed expressions, the distance in a non-Euclidean space such as hyperbolic space, the Manhattan distance, and the Mahalanobis distance. Subsequently, the generation unit 523 may train the learning model M1 so that the value of a predetermined distance function between the distributed representations (that is, the distance in the distributed representation space) becomes small.

Further, the generation unit 523 learns that, as a plurality of search queries input by the same user within a predetermined time, a plurality of search queries including character information separated by a predetermined delimiter have similar characteristics. By doing so, the first model is generated. For example, the generation unit 523 includes a search query "Roppongi pasta" in which the characters "Roppongi" indicating the place name and the characters "pasta" indicating the type of food are separated by a space, and "Roppongi" indicating the place name. The first model is generated by learning that the search query "Roppongi Italian", which is separated by a space delimiter from the character "Italian" indicating the type of food, has similar characteristics.

Further, the generation unit 523 generates the first model by learning that a plurality of randomly extracted search queries among the search queries acquired by the acquisition unit 521 have different characteristics. Specifically, the generation unit 523 generates the first model by learning so that the distributed representations of a pair of randomly extracted search queries among the search queries acquired by the acquisition unit 521 are different. .. For example, in the generation unit 523, the distributed representation of the predetermined search query extracted by the extraction unit 522 and the distributed representation of the search query randomly extracted regardless of the predetermined search query are far apart in the distributed representation space. The first model M1 is trained so as to be mapped.

[9. Flow of generation processing of the first model]
Next, the procedure of the generation process of the first model according to the embodiment will be described with reference to FIG. FIG. 17 is a flowchart showing a generation processing procedure of the first model according to the embodiment.

In the example shown in FIG. 17, the generation device 50 acquires the search query input by the user (step S1001).

Subsequently, the generation device 50 extracts a plurality of search queries input by the same user within a predetermined time (step S1002).

Subsequently, the generation device 50 generates a first model that predicts the characteristic information of a predetermined search query from the predetermined search query by learning that the plurality of extracted search queries have similar characteristics (step). S1003).

[10. effect〕
As described above, the information processing apparatus 100 according to the embodiment includes a reception unit 131, a generation unit 133, and an output unit 134. The reception unit 131 accepts a plurality of first queries indicating the similarity determination target and a plurality of second queries indicating the similarity determination criteria. For each second query, the generation unit 133 generates similar information indicating the similarity between the determination target indicated by each first query and the determination criterion indicated by the second query. The output unit 134 outputs similar information generated by the generation unit 133.

As a result, the information processing apparatus 100 can provide an analysis result regarding the similarity between a large number of high-dimensional distributed expressions in a state in which it is easy to grasp at a glance. Therefore, the information processing device 100 can obtain useful information.

Further, the generation unit 133 determines the similarity between the search intention when the target information indicating the determination target is input as the first query and the search intention when the reference information indicating the determination criterion is input as the second query. Generate similar information based on the score shown.

As a result, the information processing apparatus 100 can provide an analysis result regarding the similarity of the search intention between the first query and the second query.

Further, the generation unit 133 generates similar information based on the score which is the degree of similarity between the distributed expression corresponding to the character information which is the target information and the distributed expression corresponding to the character information which is the reference information.

As a result, the information processing apparatus 100 can provide the analysis result regarding the similarity of the search intention between the first query and the second query in a state where it can be objectively grasped numerically.

In addition, the generation unit 133 generates information on the graph that makes the magnitude of the score visible as similar information. The output unit 134 outputs information about the graph generated by the generation unit 133 for each second query.

As a result, the information processing apparatus 100 can provide an analysis result regarding the similarity between a large number of high-dimensional distributed expressions in a state in which it is easy to grasp at a glance.

In addition, the reception unit 131 receives a plurality of first queries indicating the transaction target. As similar information, the generation unit 133 generates information on a graph in which the area indicating the size of the score is color-coded by different colors according to the attributes of the transaction target.

As a result, the information processing apparatus 100 makes it possible to provide the analysis results between the attributes of the transaction target in a state where they can be easily compared at a glance.

In addition, the reception unit 131 receives a plurality of first queries indicating the transaction target. As similar information, the generation unit 133 generates information on a graph in which a region indicating the size of the score is color-coded with different colors depending on the business operator handling the transaction target.

As a result, the information processing apparatus 100 makes it possible to provide the analysis results in a state in which it is easy to compare at a glance among the business operators handling the transaction target.

In addition, the generation unit 133 generates content in which similar information and the second query are displayed in association with each other for each second query.

As a result, the information processing apparatus 100 can provide the analysis results of the plurality of first queries for each of the different analysis axes in a state in which it is easy to grasp at a glance.

[11. Hardware configuration]
Further, the information processing device 100 or the generation device 50 or the terminal device 10 according to the above-described embodiment is realized by, for example, a computer 1000 having a configuration as shown in FIG. FIG. 18 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device 100, the generation device 50, or the terminal device 10. The computer 1000 includes a CPU 1100, a RAM 1200, a ROM 1300, an HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

The CPU 1100 operates based on a program stored in the ROM 1300 or the HDD 1400, and controls each part. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started, a program depending on the hardware of the computer 1000, and the like.

The HDD 1400 stores a program executed by the CPU 1100, data used by such a program, and the like. The communication interface 1500 receives data from another device via a predetermined communication network and sends it to the CPU 1100, and transmits the data generated by the CPU 1100 to the other device via the predetermined communication network.

The CPU 1100 controls an output device such as a display or a printer, and an input device such as a keyboard or a mouse via the input / output interface 1600. The CPU 1100 acquires data from the input device via the input / output interface 1600. Further, the CPU 1100 outputs the generated data to the output device via the input / output interface 1600.

The media interface 1700 reads a program or data stored in the recording medium 1800 and provides the program or data to the CPU 1100 via the RAM 1200. The CPU 1100 loads the program from the recording medium 1800 onto the RAM 1200 via the media interface 1700, and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or PD (Phase change rewritable disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. And so on.

For example, when the computer 1000 functions as the information processing device 100, the generation device 50, or the terminal device 10, the CPU 1100 of the computer 1000 controls the control unit 130 or the control unit 52 or the control unit 52 by executing the program loaded on the RAM 1200. The function of the part 15 is realized. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, these programs may be acquired from another device via a predetermined communication network.

Although some of the embodiments of the present application have been described in detail with reference to the drawings, these are examples, and various modifications are made based on the knowledge of those skilled in the art, including the embodiments described in the disclosure column of the invention. It is possible to practice the present invention in other improved forms.

[12. others〕
Further, among the processes described in the above-described embodiments and modifications, all or part of the processes described as being automatically performed can be manually performed, or are described as being manually performed. It is also possible to automatically perform all or part of the processed processing by a known method. In addition, the processing procedure, specific name, and information including various data and parameters shown in the above document and drawings can be arbitrarily changed unless otherwise specified. For example, the various information shown in each figure is not limited to the illustrated information.

Further, each component of each of the illustrated devices is a functional concept, and does not necessarily have to be physically configured as shown in the figure. That is, the specific form of distribution / integration of each device is not limited to the one shown in the figure, and all or part of the device is functionally or physically dispersed / physically distributed in any unit according to various loads and usage conditions. Can be integrated and configured.

Further, the above-described embodiments and modifications can be appropriately combined as long as the processing contents do not contradict each other.

Further, the above-mentioned "section, module, unit" can be read as "means" or "circuit". For example, the generation unit can be read as a generation means or a generation circuit.

1 Information processing system 10 Terminal device 20 Search server 50 Generation device 100 Information processing device 110 Communication unit 120 Storage unit 121 Query information storage unit 122 Vector information storage unit 123 Similarity information storage unit 124 Model information storage unit 130 Control unit 131 Reception unit 132 Acquisition unit 133 Generation unit 134 Output unit

Claims (8)

A reception unit that accepts a plurality of first queries indicating similarity determination targets and a plurality of second queries indicating the similarity determination criteria.
For each of the second queries, the search intention when the target information indicating the determination target indicated by each first query is input as the first query and the reference information indicating the determination criteria indicated by the second query are the second. A generation unit that generates similar information indicating the similarity between the determination target and the determination criterion based on the score indicating the similarity with the search intention when input as a query.
An output unit that outputs similar information generated by the generation unit,
Equipped with a,
The reception department
Accepts multiple first queries that indicate the transaction target,
The generator
As the similar information, the information processing apparatus is characterized in that it generates information on a graph in which a region indicating the size of the score is color-coded with different colors depending on the information on the transaction target. The generator
A claim characterized in that the similar information is generated based on the score, which is the degree of similarity between the distributed expression corresponding to the character information which is the target information and the distributed expression corresponding to the character information which is the reference information. The information processing apparatus according to 1. The generator
As the similar information, the output unit that generates information about a graph that makes the magnitude of the score visible is
The information processing apparatus according to claim 1 or 2 , wherein information about a graph generated by the generation unit is output for each of the second queries. The reception department
Accepts multiple first queries that indicate the transaction target,
The generator
As the similar information, any one of claims 1 to 3 , wherein the region indicating the size of the score generates information regarding the color-coded graph by different colors according to the attribute of the transaction target. The information processing device described in. The reception department
Accepts multiple first queries that indicate the transaction target,
The generator
Any of claims 1 to 4 , wherein as the similar information, information on a graph in which a region indicating the size of the score is color-coded by a different color depending on the business operator handling the transaction target is generated. The information processing device described in one. The generator
The information processing apparatus according to any one of claims 1 to 5 , wherein for each of the second queries, a content displayed in which the similar information and the second query are associated with each other is generated. It is an information processing method executed by a computer.
A reception process that accepts a plurality of first queries indicating similarity determination targets and a plurality of second queries indicating the similarity determination criteria.
For each of the second queries, the search intention when the target information indicating the determination target indicated by each first query is input as the first query and the reference information indicating the determination criteria indicated by the second query are the second. A generation step of generating similar information indicating the similarity between the judgment target and the judgment criterion based on the score showing the similarity with the search intention when input as a query.
An output process that outputs similar information generated by the generation process, and an output process that outputs similar information.
Only including,
The reception process is
Accepts multiple first queries that indicate the transaction target,
The production step is
As the similar information, an information processing method for generating information on a graph in which a region indicating the size of the score is color-coded with different colors depending on the information on the transaction target. A reception procedure for accepting a plurality of first queries indicating similarity determination targets and a plurality of second queries indicating the similarity determination criteria.
For each of the second queries, the search intention when the target information indicating the determination target indicated by each first query is input as the first query and the reference information indicating the determination criteria indicated by the second query are the second. A generation procedure for generating similar information indicating the similarity between the judgment target and the judgment criterion based on the score showing the similarity with the search intention when input as a query, and
An output procedure that outputs similar information generated by the above generation procedure,
Let the computer run
The reception procedure is
Accepts multiple first queries that indicate the transaction target,
The generation procedure is
An information processing program characterized in that, as the similar information, information on a graph in which a region indicating the size of the score is color-coded by different colors depending on the information on the transaction target is generated.

Images