Information processing apparatus, information processing method, information processing program

Abstract

To provide: an information processing device capable of providing a user with more appropriate information; an information processing method; and an information processing program.SOLUTION: An information processing device 10 comprises: a first acquisition unit which acquires a search query entered by a user on a terminal device T; a learning unit which generates a learning model for converting the search query; and a conversion unit which converts the search query using the learning model. The learning unit learns a relationship between the search query entered by a user and search results selected by the user, from search results corresponding to the search query, and generates a learning model.SELECTED DRAWING: Figure 2

Description

Technical Field

[0001] The present invention relates to an information processing apparatus, an information processing method, and an information processing program.

Background Art

[0002] Information processing technologies for providing various information to users are known. A user inputs a search query regarding the information they seek into an information processing apparatus, and the information processing apparatus searches for the information the user seeks based on the input search query.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, depending on the search query input by the user, it may not be possible to search for the information the user seeks.

[0005] In view of the above problems, an object of the present invention is to provide appropriate information to the user.

Means for Solving the Problems

[0006] In order to solve the above-described problems and achieve the object, an information processing apparatus according to the present disclosure includes a first acquisition unit that acquires a search query input by a user, a learning unit that generates a learning model for converting the search query, and a conversion unit that converts the search query using the learning model.

Effects of the Invention

[0007] According to one aspect of the embodiment, it is possible to provide appropriate information to the user.

Brief Description of the Drawings

[0008]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

[0009] Hereinafter, embodiments for implementing the information processing apparatus, information processing method, and information processing program according to the present application (hereinafter referred to as "embodiments") will be described in detail with reference to the drawings. Note that the information processing apparatus, information processing method, and information processing program according to the present application are not limited by this embodiment. In the following embodiments, the same parts are denoted by the same reference numerals, and redundant descriptions are omitted.

[0010] [First Embodiment] [1-1. About an Example of an Information Processing Apparatus] First, an information processing apparatus 10, which is an example of the information processing apparatus according to the embodiment, will be described with reference to FIG. 1.

[0011] FIG. 1 is a diagram showing an example of an information processing apparatus according to the first embodiment. The information processing apparatus 10 shown in FIG. 1 is an information processing apparatus that performs information processing, and is realized by, for example, a server apparatus, a cloud system, or the like. For example, the information processing apparatus 10 communicates with terminal devices used by each user via the network N. The network N is various wireless communication networks such as 4G (Generation), 5G, LTE (Long Term Evolution), Wifi (registered trademark), or wireless LAN (Local Area Network), or various wired communication networks.

[0012] The terminal device QT1 (hereinafter, may be collectively referred to as "terminal device T") is a smart device such as a PC (Personal Computer), a server device, a smart television, a smartphone, a smart speaker, or a tablet. The terminal device T can communicate with the information processing apparatus 10 via the network N.

[0013] Further, the terminal device QT1 may have a screen such as a liquid crystal display and has a screen having a touch panel function, and has a function capable of receiving various operations on the content distributed from the information processing apparatus 10, such as a tap operation, a slide operation, and a scroll operation, by a finger or a stylus from the user. In the example shown in FIG. 1, it is assumed that the terminal device QT1 is a terminal device used by the questioner Q1.

[0014] The information processing device 10 is a host computer for a server that provides various services to client terminals. The information processing device 10 distributes content to the terminal device QT1. For example, the information processing device 10 distributes content in which information related to a portal site, a game information distribution site, a news site, an auction site, a weather forecast site, a shopping site, a finance (stock price) site, a route search site, a map providing site, a travel site, a restaurant introduction site, a bulletin board site, a web blog, etc. is arranged in a tile-like manner to the terminal device T. The information processing device 10 of the present embodiment provides an information sharing service in which users can ask questions and give answers to each other.

[0015] Also, the information processing device 10 is a host computer for a server that provides various services to client terminals. For example, the information processing device 10 may be a server that provides information transmission services (hereinafter referred to as information services) such as an information search service, an SNS (Social Networking Service), a news distribution service, an information summarization service, an Internet encyclopedia service, an Internet dictionary service, a blog service, etc.

[0016] The information processing apparatus 10 shown in FIG. 1, the information processing apparatus 10A, the information processing apparatus 10B, and the information processing apparatus 10C are connected via the network N so as to be able to transmit and receive information to and from each other. The information processing apparatus 10A is a server that provides a service Y1 (for example, a question-and-answer service), which is one of the information services. Further, the information processing apparatus 10B is a server that provides a service Y2 (for example, an Internet encyclopedia service), which is one of the information services. Further, the information processing apparatus 10C is a server that provides a service Y3 (for example, an information search service), which is one of the information services. In the example shown in FIG. 1, four information processing apparatuses, namely, the information processing apparatus 10, the information processing apparatus 10A, the information processing apparatus 10B, and the information processing apparatus 10C, provide different information services, but the number of information processing apparatuses is not limited to four, and any other arbitrary number of information processing apparatuses may be used. That is, there may be one information processing apparatus 10, or one information processing apparatus 10 may provide different information services in any combination.

[0017] For example, in the example shown in FIG. 1, the information processing apparatus 10 causes a learning model to learn the relationship between a search query and a selected search result (step S1). The information processing apparatus 10 receives an input of a search query from a user (step S2). The information processing apparatus 10 converts the input search query (step S3). The information processing apparatus 10 acquires related information based on the converted search query (step S4). The information processing apparatus 10 causes the acquired related information to be displayed on the user terminal (step S5).

[0018] [1-2. Regarding the processing of the information processing apparatus] Here, depending on the form of the search query input by the user, the information sought by the user may not be retrievable. Therefore, it is required to convert the search query input by the user into a search query that can retrieve the information sought by the user.

[0019] Therefore, the information processing apparatus 10 generates a learning model for converting a search query and uses the generated learning model to convert the search query input by the user.

[0020] For example, the process when a user inputs a search query A "What is the difference in performance between the tennis rackets of Manufacturer A and Manufacturer B" as a search query will be described. In this case, the information processing apparatus 10 converts the search query into a keyword search query. That is, the information processing apparatus 10 converts the search query A into a keyword search query of "Manufacturer A", "Manufacturer B", "tennis racket", and "performance". When the search query A is converted into a keyword search query, the information processing apparatus 10 acquires related information from a plurality of information services based on the keyword search query. When the information processing apparatus 10 acquires the related information, it causes the acquired related information to be displayed on the user's terminal device.

[0021] As a result, it is possible to convert the search query input by the user into a search query that can acquire information in line with the user's search intention. Therefore, it is possible to provide the user with the information that the user wants to obtain by inputting the search query.

[0022] [1-3. Learning Process Using the First Search Query Database] Here, when converting the search query input by the user, if it is possible to convert the search query using a learning model that has learned the relationship between the search query and the search result selected by the user from among the search results retrieved based on the search query, it is considered that a search query that can acquire a search result in line with the user's search intention can be obtained.

[0023] Therefore, the information processing apparatus 10 learns the relationship between the search query input by the user and the search result selected by the user from among the search results corresponding to the search query, and generates a learning model.

[0024] For example, the information processing apparatus 10 includes a first search query database 31, which will be described later, that associates and registers a search query input by a user with a selected search result, which means a search result selected by the user from among the search results corresponding to the search query. The information processing apparatus 10 uses the data registered in the first search query database 31 to learn the relationship between the search query input by the user and the search result selected by the user from among the search results corresponding to the search query, and generates a learning model. The information processing apparatus 10 acquires the search query input by the user, inputs the acquired search query into the learning model, and obtains the output of the converted search query. When the information processing apparatus 10 acquires the output of the converted search query, it uses the converted search query to acquire relevant information from a plurality of information services. When the information processing apparatus 10 acquires the relevant information, it causes the acquired relevant information to be displayed on the user's terminal device.

[0025] Thereby, the search query input by the user can be converted into a search query that can acquire information along with the user's search intention. Therefore, it is possible to provide the user with the information that the user thought to obtain by inputting the search query.

[0026] 〔1-4. Learning Process Using the Second Search Query Database〕 Here, when converting the search query input by the user, if it is possible to convert the search query using a learning model that has learned the relevant information selected by the user from among the relevant information acquired from a plurality of information services based on the search query and the search query, it is considered that a search query that can acquire relevant information along with the user's search intention can be obtained from a plurality of information services.

[0027] Therefore, the information processing apparatus 10 learns the relationship between the search query input by the user and the relevant information selected by the user from among the relevant information acquired from a plurality of information services based on the search query, and generates a learning model.

[0028] For example, the information processing apparatus 10 includes a second search query database 32 described below, which associates and registers a search query input by a user with selected related information selected by the user from among related information obtained from a plurality of information services based on the search query. The information processing apparatus 10 uses the data registered in the second search query database 32 to learn the relationship between the search query input by the user and the related information selected by the user from among the related information obtained from a plurality of information services based on the search query, and generates a learning model. The information processing apparatus 10 acquires the search query input by the user, inputs the acquired search query into the learning model, and obtains an output of the converted search query. When the information processing apparatus 10 acquires the output of the converted search query, it uses the converted search query to acquire related information from a plurality of information services. When the information processing apparatus 10 acquires the related information, it causes the acquired related information to be displayed on the user's terminal device.

[0029] As a result, the search query input by the user can be converted into a search query that can acquire related information in line with the user's search intention. Therefore, it is possible to provide the user with the information that the user wants to obtain by inputting the search query.

[0030] [1-5. Learning Process Using the Third Search Query Database] Here, when converting the search query input by the user, if a learning model that has learned the relationship between the search query and the selected question sentence from among the related question sentences obtained from the question-and-answer service based on the search query can be used to convert the search query, it is considered that a search query that can acquire related question sentences in line with the user's search intention from the question-and-answer service can be obtained.

[0031] Therefore, the information processing apparatus 10 learns the relationship between the search query input by the user and the selected question sentence from among the related question sentences obtained from the question-and-answer service based on the search query, and generates a learning model.

[0032] For example, the information processing apparatus 10 includes a third search query database 33, which will be described later, that associates and registers a search query input by a user with a selected question sentence that means the question sentence selected by the user from among related question sentences obtained from a question-and-answer service based on the search query. Further, the information processing apparatus 10 includes a Q&A database 34, which will be described later, that associates and registers a question sentence input by a user with a set of answer sentences input by other users for the question sentence. The information processing apparatus 10 uses the data registered in the third search query database 33 to learn the relationship between the search query input by the user and the question sentence selected by the user from among the related question sentences obtained from the question-and-answer service based on the search query, and generates a learning model. The information processing apparatus 10 acquires the search query input by the user, inputs the acquired search query into the learning model, and obtains the output of the converted search query. When the information processing apparatus 10 acquires the output of the converted search query, it uses the converted search query to acquire related question sentences from the question-and-answer service. When the information processing apparatus 10 acquires the related question sentences, it causes the related question sentences to be displayed on the terminal device of the user. Note that the information processing apparatus 10 adds a link to access the set of answer sentences input by other users to the related question sentence and causes the related question sentence to be displayed on the terminal device of the user.

[0033] As a result, the search query input by the user can be converted into a search query capable of obtaining a question sentence that conforms to the user's search intention. Therefore, it is possible to provide the user with the information that the user wants to obtain by inputting the search query.

[0034] [1-6. Conversion Process] Here, the information processing apparatus 10 uses a learning model for converting a search query to convert a natural language search query into a keyword search query.

[0035] For example, the processing when a user inputs a search query A, "What is the difference in performance between the tennis rackets of Manufacturer A and Manufacturer B," will be described. In this case, the information processing apparatus 10 converts the search query A into search queries with keywords of "Manufacturer A," "Manufacturer B," "tennis racket," and "performance." The information processing apparatus 10 acquires relevant information from a plurality of information services based on the converted search queries with keywords. After the information processing apparatus 10 acquires the relevant information, it causes the acquired relevant information to be displayed on the user's terminal device.

[0036] Thereby, the search query in natural language input by the user can be converted into a search query with keywords that can acquire information in line with the user's search intention. Therefore, it is possible to provide the user with the information that the user wanted to obtain by inputting the search query in natural language.

[0037] [Regarding the display of relevant information from 1-7.] Here, when the user inputs a search query, in addition to the search results of the normal search, if relevant information can be acquired based on the search query from a plurality of information services and displayed on the user's terminal device, it is considered that the use of the plurality of information services can be activated.

[0038] Therefore, the information processing apparatus 10 acquires relevant information from among the plurality of information services based on the converted search query.

[0039] For example, the process when a user inputs a search query A "What is the difference in performance between the tennis rackets of Manufacturer A and Manufacturer B" will be described. In this case, the information processing apparatus 10 converts the search query A into search queries with keywords "Manufacturer A", "Manufacturer B", "tennis racket", and "performance". Based on the converted search queries with keywords, the information processing apparatus 10 acquires relevant information from a plurality of information services. The information processing apparatus 10, for example, acquires information regarding "Manufacturer A" and "Manufacturer B" and "tennis racket" from a shopping site as relevant information. Also, the information processing apparatus 10, for example, acquires information regarding "Manufacturer A" and "Manufacturer B" and "tennis racket" from an auction site as relevant information. Further, the information processing apparatus 10, for example, acquires information regarding "Manufacturer A", "Manufacturer B", "tennis racket", and "performance" from a bulletin board site as relevant information. After the information processing apparatus 10 acquires the relevant information, it causes the acquired relevant information to be displayed on the user's terminal device together with other search results.

[0040] Thereby, the search query input by the user can be converted, relevant information can be acquired from a plurality of information services based on the converted search query, and the acquired relevant information can be displayed on the user's terminal device. Therefore, the information required by the user can be appropriately provided. Also, the use of a plurality of information services can be activated.

[0041] [Regarding the display of question texts 1-8] Here, when a user inputs a search query, in addition to the search results of a normal search, if relevant question texts can be acquired from a question-and-answer service based on the search query and displayed on the user's terminal device, it is considered that the information required by the user can be provided. As a result, the use of the question-and-answer service registered on the portal site can be activated.

[0042] Therefore, the information processing apparatus 10 acquires relevant question texts from among the question-and-answer services based on the search query after conversion.

[0043] For example, the processing when a user inputs a search query A "What is the difference in performance between the tennis rackets of manufacturer A and manufacturer B" will be described. In this case, the information processing device 10 converts the search query A into keyword search queries B "manufacturer A", "manufacturer B", "tennis racket", and "performance". Based on the converted keyword search query B, the information processing device 10 obtains relevant question texts from the question-and-answer service. For example, assume that a question text A "What is the difference in performance between the tennis rackets of manufacturer A and manufacturer B" that contains all the keyword search queries B from the user is posted to the question-and-answer service, and an answer text has been posted by another user in response to the question text A. In this case, the information processing device 10 obtains the question text A from the question-and-answer service. After obtaining the question text A, the information processing device 10 causes the obtained question text A to be displayed on the user's terminal device together with other search results.

[0044] In this way, the search query input by the user can be converted, relevant question texts can be obtained from the question-and-answer service based on the converted search query, and the obtained question texts can be displayed on the user's terminal device. Therefore, the information required by the user can be provided appropriately.

[0045] [1-9. Obtaining Similar Question Texts Using Clusters of Distributed Representations of Question Texts] Here, when searching for question texts, it is considered that the user can obtain information in line with the search intention of the input search query by referring to relevant question texts if not only question texts that contain all the keywords of the search query but also question texts that do not contain all the keywords of the search query but have a similar meaning are displayed.

[0046] Therefore, the information processing device 10 clusters the distributed representations corresponding to the character information of the question texts based on the similarity, calculates the similarity between the distributed representation of the character information of the search query after conversion and the distributed representation corresponding to the character information of the question texts, selects a cluster of question texts related to the search query based on the calculated similarity, and obtains the question texts included in the selected cluster.

[0047] For example, in a question-and-answer service, assume that the user inputs question sentence B "What is the difference in performance between the tennis rackets of manufacturer C and manufacturer D", question sentence C "How much are the prices of the tennis rackets of manufacturer A and manufacturer B", and question sentence D "What are the manufacturers of tennis rackets". And assume that answer sentences have been input from other users for question sentence B, question sentence C, and question sentence D. In this case, the information processing device 10 calculates distributed representations for question sentence B, question sentence C, and question sentence D. Here, since question sentence B, question sentence C, and question sentence D have similar meanings, the distributed representations are also calculated to be close values. When the distributed representations of question sentence B, question sentence C, and question sentence D are calculated, the information processing device 10 classifies question sentence B, question sentence C, and question sentence D into the same cluster A. Here, assume that the information processing device 10 has obtained the same search query A as the aforementioned question sentence A from the user. When the information processing device 10 obtains the search query A, it calculates the distributed representation of the obtained search query A. Since question sentence A has a similar meaning to question sentence B, question sentence C, and question sentence D, the distributed representation of search query A, which is the same as question sentence A, is calculated to be a value close to the distributed representations of question sentence B, question sentence C, and question sentence D. When the distributed representation of search query A is calculated, the information processing device 10 obtains, for example, question sentence B from among the question sentences classified into cluster A. Note that the number of question sentences obtained from cluster A is not limited to one, and any other number of question sentences may be obtained. When the information processing device 10 obtains question sentence B from cluster A, it causes the user's terminal device to display question sentence B together with other search results.

[0048] Thereby, it is possible to provide the user with information along with the search intention of the search query when the user inputs the search query. Therefore, it is possible to appropriately provide the information required by the user.

[0049] [2. Configuration of Information Processing Device] Hereinafter, an example of the functional configuration of the above-described information processing apparatus 10 will be described. In the following description, an example of the functional configuration of the information processing apparatus 10 that executes information processing at the information service site is shown. FIG. 2 is a diagram showing a configuration example of the information processing apparatus according to the first embodiment. As shown in FIG. 2, the information processing apparatus 10 includes a communication unit 20, a storage unit 30, and a control unit 40.

[0050] The communication unit 20 is realized by, for example, a NIC (Network Interface Card) or the like. Then, the communication unit 20 is connected to the network N by wire or wirelessly, and transmits and receives information to and from the terminal device T.

[0051] The storage unit 30 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk.

[0052] Further, the storage unit 30 stores a first search query database 31, a second search query database 32, a third search query database 33, a Q&A database 34, a learning model 35, and a distributed representation database 36.

[0053] In the first search query database 31, the search query input by the user and the information of the search result selected by the user for the search result searched based on the search query are registered. For example, FIG. 3 is a diagram showing an example of the information registered in the first search query database 31 according to the embodiment. As shown in FIG. 3, in the first search query database 31, information having items such as "user ID", "search query", and "selected search result" is registered.

[0054] Here, the "user ID" is an identifier for identifying a user. Also, the "search query" is information indicating the search query input by the user. Further, the "selected search result" is information indicating the search result selected by the user from the search results retrieved based on the search query input by the user. Note that, without specifying a user, a search query may be obtained uniformly from all users, and a selected search result indicating the search result selected by the user from the search results retrieved based on the obtained search query may be obtained, and the obtained search query and non-selected search query may be registered in the first search query database 31.

[0055] For example, in the example shown in FIG. 3, information such as the user ID "U1", the search query "search query #U1-1", and the selected search result "selected search result #U1-1" is registered in the first search query database 31. Such information indicates that the search query indicated by the search query "search query #U1-1" was input by the user indicated by the user ID "U1", and the information indicated by the selected search result "selected search result #U1-1" was selected.

[0056] Note that, in the example shown in FIG. 3, the information registered in the first search query database 31 is described using conceptual expressions such as search query #U1 and selected search result #U1-1. However, in actuality, the character information that becomes the search query input by the user and the character information of the selected search result indicating the search result selected by the user from the search results retrieved based on the search query will be registered. Also, in addition to the information shown in FIG. 3, any other arbitrary information related to the search query may be registered in the first search query database 31.

[0057] In the second search query database 32, there are registered the search query input by the user, the related information selected by the user from among the related information obtained from a plurality of information services based on the search query, and the name of the information service from which the related information was obtained. For example, FIG. 4 is a diagram showing an example of information registered in the second search query database 32 according to the first embodiment. As shown in FIG. 4, information having items such as "user ID", "search query", "selected related information", and "information service name" is registered in the second search query database 32.

[0058] For example, in the example shown in FIG. 4, information such as the user ID "U1", the search query "search query #U1-1", and the information service name "information service A" are registered in association with each other. Such information indicates that the user indicated by the user ID "U1" entered the search query indicated by the search query "search query #U1-1", selected the related information indicated by the unselected related information "unselected related information #U1-1", and the selected related information was obtained from the information service indicated by the information service name "information service A".

[0059] Note that in the example shown in FIG. 4, conceptual expressions such as "search query #U1-1" and "information service A" are described, but actually, the character information that is the search query input by the user, the character information of the related information selected by the user from among the related information obtained from a plurality of information services based on the search query, and the character information of the name of the information service from which the related information selected by the user was obtained are registered. Also, in addition to the information shown in FIG. 4, any other information related to the search query may be registered in the second search query database 32.

[0060] In the third search query database 33, there are registered the search queries input by the user and the question texts selected by the user from among the question texts obtained from the question-and-answer service based on the search queries. For example, FIG. 5 is a diagram showing an example of the information registered in the third search query database 33 according to the first embodiment. As shown in FIG. 5, information having items such as "user ID", "search query", and "selected question text" is registered in the third search query database 33.

[0061] For example, in the example shown in FIG. 5, information such as user ID "U1", search query "search query #U1-1", and selected question text "selected question text #U1-1" is registered in association. Such information indicates that the user indicated by the user ID "U1" input the search query indicated by the search query "search query #U1-1" and selected the question text indicated by the non-selected question text "non-selected question text #U1-1".

[0062] Note that in the example shown in FIG. 5, conceptual expressions such as "search query #U1-1" and "selected question text #U1-1" are described, but in reality, the character information that is the search query input by the user and the character information of the question text selected by the user from among the related question texts obtained from the question-and-answer service based on the search query will be registered. Also, in addition to the information shown in FIG. 5, any other arbitrary information related to the search query may be registered in the third search query database 33.

[0063] In the Q&A database 34, there is registered information regarding the question text input by the user, the set of answer texts input by other users for the question text, and the answer text selected as the best answer by the user who input the question from among the set of answer texts input by other users. For example, FIG. 6 is a diagram showing an example of the information registered in the Q&A database according to the first embodiment. As shown in FIG. 6, in the Q&A database 34, information having items such as "Question ID", "Question Text", "Answer Text Set", and "Selection Information" is registered. Note that the answer text set is information that combines into one the answer texts input from one or more other users for the question text input by the user.

[0064] In the example shown in FIG. 6, information such as question ID "Q1", question text "Question Text #1", answer text set "Answer Text Set #1", and selection information "Answer Text #1-1" is registered in association. Such information indicates that the question ID "Q1" is assigned to the question text input by the user, the question text input by the user is registered as the question text "Question Text #1", the answer texts shown in the answer text set "Answer Text Set #1" are input from other users for the question text input by the user, and the answer text shown by the selection information "Answer Text #1-1" is selected as the best answer by the user who input the question text.

[0065] Note that in the example shown in FIG. 6, conceptual expressions such as "Question Text #1", "Answer Text Set #1", and "Answer Text #1-1" are described, but actually, the character information of the question text input by the user, the character information of the set of answer texts input from other users for the question text input by the user, and the character information of the answer text selected by the user who input the question text will be registered. Also, in addition to the information shown in FIG. 6, for example, in the Q&A database 34, various arbitrary information regarding the question texts and answer texts, such as the user ID of the user who input the question text and the user ID of the user who input the answer text for the input question text, may be registered.

[0066] The learning model 35 stores an unlearned learning model and a learned learning model. As the learned learning model, a learning model generated by the learning unit 42, which will be described later, executing learning processing is stored. When the learning unit 42, which will be described later, executes learning processing, the learning processing is executed using the unlearned learning model stored in the learning model 35.

[0067] In the distributed representation database 36, the question sentence input by the user, the distributed representation of the question sentence, and the cluster classified into the question sentence are registered in association with each other.

[0068] The control unit 40 is, for example, a controller, and is realized by various programs stored in the storage device of the information processing apparatus 10 being executed with the RAM as a work area by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like. Further, the control unit 40 may be a controller and may be realized by an integrated circuit such as an ASIC (Application Specific Circuit) or an FPGA (Field Programmable Gate Array).

[0069] As shown in FIG. 2, the control unit 40 includes an acquisition unit 41, a learning unit 42, a conversion unit 43, a calculation unit 44, a classification unit 45, a reception unit 46, and a provision unit 47.

[0070] The acquisition unit 41 includes a first acquisition unit 411, a second acquisition unit 412, and a third acquisition unit 413. The first acquisition unit 411 acquires the search query input by the user. For example, if the user inputs the search query A "What is the performance difference between the tennis rackets of manufacturer A and manufacturer B" as a search query to the terminal device T, the first acquisition unit 411 acquires the search query input to the terminal device T via the network N and the communication unit 20.

[0071] The second acquisition unit 412 acquires relevant information from a plurality of information services based on the search query converted by a conversion unit 43 described later from the search query input by the user. For example, assume that the user inputs, as a search query to the terminal device T, a search query A "What is the difference in performance between the tennis rackets of manufacturer A and manufacturer B". In this case, the first acquisition unit 411 acquires the search query A input by the user, and the conversion unit 43 described later converts the acquired search query A into keyword search queries B "manufacturer A", "manufacturer B", "tennis racket", and "performance". The second acquisition unit 412 acquires relevant information from a plurality of information services based on the search query B converted by the conversion unit 43. For example, the second acquisition unit 412 acquires, as relevant information, sales information regarding "tennis rackets" of "manufacturer A" and "manufacturer B" from a shopping site.

[0072] The third acquisition unit 413 selects a cluster of question sentences and acquires the question sentences included in the selected cluster based on the calculation result of the distributed representation of the search query input by the user. That is, when the calculation unit 44 described later calculates the distributed representation of the search query input by the user, the third acquisition unit 413 calculates the similarity between the distributed representation of the search query input by the user and the distributed representation of the cluster of question sentences, and selects the cluster of question sentences with a high similarity. When a cluster of question sentences with a high similarity is selected, the third acquisition unit 413 acquires the question sentences included in the selected cluster.

[0073] The learning unit 42 generates a learning model for converting a search query. For example, the learning unit 42 learns the relationship between the search queries registered in the first search query database 31 and the selected search results, and generates a learning model for converting the search query. In this case, for example, when inputting the natural language included in the character information of the selected search results, a learning model that outputs the search query input by the user may be generated. Further, for example, the learning unit 42 learns the relationship between the search queries registered in the second search query database 32 and the selected related information, and generates a learning model for converting the search query. In this case, for example, when inputting the natural language included in the character information of the selected related information, a learning model that outputs the search query input by the user may be generated. Further, for example, the learning unit 42 learns the relationship between the search queries registered in the third search query database 33 and the selected question sentence, and generates a learning model for converting the search query. In this case, for example, when inputting the natural language included in the character information of the selected question sentence, a learning model that outputs the search query input by the user may be generated. That is, the learning model converts the search query according to the behavior after the user inputs the search query. In other words, the learning model is trained to convert the search query according to the search intention inferred from the behavior after the user inputs the search query.

[0074] The learning unit 42 generates a learning model that has been learned by end-to-end deep learning. End-to-end deep learning replaces a machine learning system that requires multiple stages of processing from when input data is given until a result is output with a single large neural network having a plurality of layers / modules that perform various processes, and then performs learning. That is, end-to-end deep learning directly learns the correspondence between input and output. By using end-to-end deep learning, it is not necessary to prepare an intermediate structure specialized for a specific function, and it is not necessary to consider the problem in the upstream process that occurs in natural language processing being postponed to the downstream process.

[0075] The conversion unit 43 converts a search query using a learning model. For example, the conversion unit 43 inputs the search query input by the user into the learning model generated by the learning unit 42 learning the relationship between the search query registered in the first search query database 31 and the selected search result, thereby obtaining the output of the converted search query. Also, for example, the conversion unit 43 inputs the search query input by the user into the learning model generated by the learning unit 42 learning the relationship between the search query registered in the second search query database 32 and the selected related information, thereby obtaining the output of the converted search query. Also, for example, the conversion unit 43 inputs the search query input by the user into the learning model generated by the learning unit 42 learning the relationship between the search query registered in the third search query database 33 and the selected question sentence, thereby obtaining the output of the converted search query.

[0076] The calculation unit 44 calculates a distributed representation corresponding to the character information. For example, the calculation unit 44 performs morphological analysis on the question sentence, segments it into morphemes, and converts the segmented morphemes into a distributed representation. For example, word2vec can be used to convert a word into a distributed representation. After converting all the words constituting the question sentence into a distributed representation, for example, the distributed representation of the question sentence can be obtained by calculating the average value of the distributed representations of all the words constituting the question sentence. After the calculation unit 44 calculates the distributed representation of the question sentence, it registers the distributed representation of the question sentence in association with the question sentence in the distributed representation database 36. When the search query is a natural sentence, the distributed representation of the natural sentence search query can be obtained by performing the same processing.

[0077] The classification unit 45 clusters the distributed representations corresponding to the character information of the question sentences based on the similarity. For example, the classification unit 45 calculates the cosine similarity between the distributed representation corresponding to the character information of the question sentence and the distributed representations corresponding to the character information of other question sentences. Note that the classification unit 45 is not limited to the cosine similarity, and any index applicable as a distance measure between vectors can be used to calculate the similarity between the distributed representations. For example, the classification unit 45 may calculate the values of predetermined distance functions such as the Euclidean distance between the distributed representations, the distance in a non-Euclidean space such as a hyperbolic space, the Manhattan distance, and the Mahalanobis distance.

[0078] When the similarity of the distributed representation corresponding to the character information of the question sentence is calculated, the classification unit 45 clusters the distributed representations of the question sentences based on the similarity of the distributed representations. After clustering the distributed representations of the question sentences, the classification unit 45 registers the question sentences and the clusters of the distributed representations of the question sentences in association with the distributed representations of the question sentences in the distributed representation database 36. For example, K-means clustering can be used for clustering the distributed representations of the question sentences. K-means clustering classifies data into a given number of clusters (K) using the average values of the clusters.

[0079] The reception unit 46 receives registrations of questions and answers from the user. For example, when the reception unit 46 receives a sentence serving as a question from the user's terminal device, the received sentence is registered as a question sentence in the Q&A database 34. Also, when the reception unit 46 receives a sentence serving as an answer from the terminal device used by the answerer, the received sentence is registered in the Q&A database 34 in association with the question ID of the corresponding question sentence. Thereby, it is possible to receive submissions of new question sentences and answer sentences from the user and update the Q&A database 34.

[0080] The providing unit 47 provides either the related information acquired by at least the second acquisition unit 412 or the question sentence acquired by the third acquisition unit 413 to the user who input the search query. That is, the providing unit 47 may display the related information acquired by the second acquisition unit 412, or may display the question sentence acquired by the third acquisition unit 413. Further, the providing unit 47 may display both the related information acquired by the second acquisition unit 412 and the question sentence acquired by the third acquisition unit 413 on the user's terminal device.

[0081] 〔3. Processing procedure〕 Next, with reference to FIG. 7, the information processing procedure by the information processing apparatus 10 according to the first embodiment will be described. FIG. 7 is a flowchart showing an example of the flow of information processing according to the first embodiment. For example, the information processing apparatus 10 acquires the search query input by the user (step S101). Then, the information processing apparatus 10 converts the acquired search query (step S102). Then, the information processing apparatus 10 acquires related information from a plurality of information services (step S103). Then, the information processing apparatus 10 displays the acquired related information on the terminal device of the user who input the search query (step S104).

[0082] 〔4. Hardware configuration〕 Further, the information processing apparatus 10 according to the above-described embodiment is realized by, for example, a computer 1000 having a configuration as shown in FIG. 8. FIG. 8 is a diagram showing an example of the hardware configuration. The computer 1000 is connected to an output device 1010 and an input device 1020, and has a form in which an arithmetic device 1030, a primary storage device 1040, a secondary storage device 1050, an output IF (Interface) 1060, an input IF 1070, and a network IF 1080 are connected by a bus 1090.

[0083] The arithmetic unit 1030 operates based on programs stored in the primary storage device 1040 and the secondary storage device 1050, and programs read from the input device 1020, etc., and executes various processes. The primary storage device 1040 is a memory device that primarily stores data used by the arithmetic unit 1030 for various calculations, such as a RAM. Further, the secondary storage device 1050 is a storage device in which data used by the arithmetic unit 1030 for various calculations and various databases are registered, and is realized by a ROM (Read Only Memory), an HDD (Hard Disk Drive), a flash memory, etc.

[0084] The output IF 1060 is an interface for transmitting information to be output to the output device 1010 that outputs various information such as a monitor and a printer, and is realized by a connector of a standard such as USB (Universal Serial Bus), DVI (Digital Visual Interface), HDMI (registered trademark) (High Definition Multimedia Interface). Further, the input IF 1070 is an interface for receiving information from various input devices 1020 such as a mouse, a keyboard, and a scanner, and is realized by, for example, USB or the like.

[0085] Note that the input device 1020 may be a device that reads information from an optical recording medium such as a CD (Compact Disc), a DVD (Digital Versatile Disc), a 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. Further, the input device 1020 may be an external storage medium such as a USB memory.

[0086] The network IF 1080 receives data from other devices via the network N and sends it to the arithmetic unit 1030, and also transmits data generated by the arithmetic unit 1030 via the network N to other devices.

[0087] The arithmetic unit 1030 controls the output device 1010 and the input device 1020 via the output IF 1060 and the input IF 1070. For example, the arithmetic unit 1030 loads a program from the input device 1020 or the secondary storage device 1050 onto the primary storage device 1040 and executes the loaded program.

[0088] For example, when the computer 1000 functions as the information processing apparatus 10, the arithmetic unit 1030 of the computer 1000 realizes the function of the control unit 40 by executing the program loaded onto the primary storage device 1040.

[0089] [5. Effects] The information processing apparatus 10 according to the present disclosure includes a first acquisition unit 411 that acquires a search query input by a user, a learning unit 42 that generates a learning model for converting the search query, and a conversion unit 43 that converts the search query using the learning model.

[0090] According to this configuration, since the search query input by the user is converted using the learning model, it is possible to provide appropriate information to the user.

[0091] Further, the learning unit 42 learns the relationship between the search query input by the user and the search result selected by the user from among the search results corresponding to the search query, and generates a learning model.

[0092] According to this configuration, it is possible to generate a learning model that can convert the search query input by the user into a search query capable of obtaining a search result along with the user's search intention. Therefore, it is possible to provide appropriate information to the user.

[0093] Further, the learning unit 42 learns the relationship between the search query input by the user and the relevant information selected by the user from among the relevant information acquired from a plurality of information services based on the search query, and generates a learning model.

[0094] According to this configuration, it is possible to generate a learning model that can convert a search query input by a user into a search query capable of obtaining relevant information in line with the user's search intention. Therefore, it is possible to provide appropriate information to the user.

[0095] In addition, the learning unit 42 learns the relationship between the search query input by the user and the question sentence selected by the user from among the related question sentences obtained from the question-and-answer service based on the search query, and generates a learning model.

[0096] According to this configuration, it is possible to generate a learning model that can convert a search query input by a user into a search query capable of obtaining a question sentence in line with the user's search intention. Therefore, it is possible to provide appropriate information to the user.

[0097] In addition, the conversion unit 43 uses the learning model to convert a natural language search query into a keyword search query.

[0098] According to this configuration, the natural language search query input by the user can be converted into a keyword search query. Therefore, it is possible to provide appropriate information to the user.

[0099] In addition, the information processing apparatus 10 according to the present disclosure includes a second acquisition unit 412 that acquires relevant information from among a plurality of information services based on the search query after being converted by the conversion unit 43.

[0100] According to this configuration, the search query input by the user can be converted into a search query capable of searching for relevant information in line with the user's search intention, and relevant information can be obtained from among a plurality of information services. Therefore, it is possible to provide appropriate information to the user.

[0101] In addition, the second acquisition unit 412 acquires a question sentence as relevant information from among question-and-answer services as information services based on the search query after being converted by the conversion unit 43.

[0102] According to this configuration, the search query input by the user can be converted into a search query that can search for a question sentence along the user's search intention, and the question sentence can be obtained as relevant information from among the question-and-answer services as an information service. Therefore, appropriate information can be provided to the user.

[0103] Further, the information processing apparatus 10 according to the present disclosure includes a calculation unit 44 that calculates a distributed representation corresponding to character information, a classification unit 45 that clusters question sentences based on the similarity of the distributed representations corresponding to the question sentences, and a third acquisition unit 413 that selects a cluster of question sentences based on the calculation result of the distributed representation of the search query input by the user and acquires the question sentences included in the selected cluster.

[0104] According to this configuration, based on the calculation result of the distributed representation of the search query input by the user, a cluster of question sentences can be selected, and the question sentences included in the selected cluster can be acquired. Therefore, appropriate information can be provided to the user.

[0105] The information processing method according to the present disclosure includes steps of acquiring a search query input by a user, converting the search query, acquiring relevant information from a plurality of information services based on the converted search query, and displaying the acquired relevant information.

[0106] According to this configuration, the search query input by the user can be converted into a search query that can search for information along the user's search intention, and relevant information can be acquired from among a plurality of information services. Therefore, appropriate information can be provided to the user.

[0107] The information processing program according to the present disclosure causes a computer to execute steps of acquiring a search query input by a user, converting the search query, acquiring relevant information from a plurality of information services based on the converted search query, and displaying the acquired relevant information.

[0108] As described above, the embodiments of the present application have been described in detail with reference to the drawings. However, this is merely an example, and the present invention can be implemented in other forms with various modifications and improvements based on the knowledge of those skilled in the art, including the aspects described in the column of the disclosure of the invention.

[0109] Also, the "section (section, module, unit)" described above can be read as "means" or "circuit", etc. For example, the acquisition unit can be read as an acquisition means or an acquisition circuit.

Description of Reference Numerals

[0110] 10 Information processing apparatus 20 Communication unit 30 Storage unit 31 First search query database 32 Second search query database 33 Third search query database 34 Q&A database 35 Learning model 36 Distributed representation database 40 Control unit 41 Acquisition unit 411 First acquisition unit 412 Second acquisition unit 413 Third acquisition unit 42 Learning unit 43 Conversion unit 44 Calculation unit 45 Classification unit 46 Reception unit 47 Provision unit N Network T Terminal device

Claims

1. A first acquisition unit that acquires a search query input by a user; A learning unit that generates a learning model that outputs the search query when a natural sentence included in the character information of the search result selected by the user is input from among the search results retrieved based on the search query; A conversion unit that uses the learning model to convert the search query input by the user into a search query corresponding to the search intention estimated from the user's actions after inputting the search query; An information processing apparatus comprising the above.

2. The learning unit generates a learning model that outputs the search query when a natural sentence included in the character information of the related information selected by the user is input from among the related information acquired from a plurality of information services based on the search query input by the user. The information processing apparatus according to claim 1.

3. The learning unit generates a learning model that outputs the search query when a natural sentence included in the character information of the question sentence selected by the user is input from among the related question sentences acquired from a question-and-answer service based on the search query input by the user. The information processing apparatus according to claim 1.

4. The conversion unit uses the learning model to convert a search query in natural language into a search query in keywords. The information processing apparatus according to any one of claims 1 to 3.

5. A second acquisition unit that acquires related information from among a plurality of information services based on the search query after conversion by the conversion unit. The information processing apparatus according to any one of claims 1 to 3.

6. The second acquisition unit acquires a question sentence as related information from among question-and-answer services as information services based on the search query after conversion by the conversion unit. The information processing apparatus according to claim 5.

7. A calculation unit that calculates a distributed representation corresponding to the character information; A classification unit that clusters question sentences based on the similarity of the distributed representations corresponding to the question sentences; A third acquisition unit that selects a cluster of question sentences related to the search query based on the calculation result of the distributed representation of the search query after conversion and acquires the question sentences included in the selected cluster. The information processing apparatus according to any one of claims 1 to 6.

8. An information processing method executed by a computer, comprising: A first acquisition step of acquiring a search query input by a user; A learning step of generating a learning model that outputs the search query when a natural sentence included in the character information of the search result selected by the user is input from among the search results retrieved based on the search query; A conversion step of converting the search query input by the user into a search query corresponding to the search intention estimated from the behavior after the user inputs the search query, using the learning model; An information processing method including the above.

9. A first acquisition procedure for acquiring a search query input by a user; A learning procedure for generating a learning model that outputs the search query when a natural sentence included in the character information of the search result selected by the user is input from among the search results retrieved based on the search query; A conversion procedure for converting the search query input by the user into a search query corresponding to the search intention estimated from the behavior after the user inputs the search query, using the learning model; An information processing program for causing a computer to execute the above.

Images