Information processing system, information processing method, and program

Abstract

To provide an information processing system, an information processing method, and a program which can provide an appropriate answer for each user with respect to questions from various users.SOLUTION: An information processing system comprises: first acquisition means 31 which acquires information related to questions from users; second acquisition means 32 which acquires the information related to attributes of the users; determination means 35 which determines the information related to answers with respect to the questions, on the basis of the information about the questions and the information about the attributes; and provision means 36 which provides the information about the answers for the users.SELECTED DRAWING: Figure 3

Description

[Technical field]

[0001] The present invention relates to an information processing system, an information processing method, and a program. [Background technology]

[0002] In recent years, development of systems that use information processing technology to answer questions from users has been progressing (for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2012-79161 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, with conventional technology, answers to questions from users are uniform, making it difficult to provide appropriate answers to questions from various users that are tailored to, for example, the individual personalities and characteristics of each user.

[0005] The present invention has been made in consideration of the above-mentioned problems, and aims to provide an information processing system, an information processing method, and a program that are capable of providing appropriate answers to questions from various users, for each user. [Means for solving the problem]

[0006] In order to solve the above problems, firstly, the present invention provides an information processing system comprising a first acquisition means for acquiring information regarding a question from a user, a second acquisition means for acquiring information regarding attributes of the user, a determination means for determining information regarding an answer to the question based on the information regarding the question and the information regarding the attributes, and a provision means for providing the information regarding the answer to the user.

[0007] According to this invention, information about an answer to a question is determined based on information about the question from a user and information about the user's attributes, and this information about the answer is provided to the user, so that it is possible to provide the user with an answer that takes into account the user's attributes such as personality, characteristics, etc. This makes it possible to provide appropriate answers to each user in response to questions from various users.

[0008] Secondly, the present invention provides an information processing method in which a computer executes each of the steps of acquiring information regarding a question from a user, acquiring information regarding the attributes of the user, determining information regarding an answer to the question based on the information regarding the question and the information regarding the attributes, and providing the information regarding the answer to the user.

[0009] Thirdly, the present invention provides a program for enabling a computer to realize the following functions: acquiring information regarding a question from a user; acquiring information regarding the attributes of the user; determining information regarding an answer to the question based on the information regarding the question and the information regarding the attributes; and providing the information regarding the answer to the user. Effect of the Invention

[0010] According to the information processing system, information processing method, and program of the present invention, appropriate answers can be provided to each user in response to questions from various users. [Brief description of the drawings]

[0011] [Figure 1] 1 is a diagram illustrating a basic configuration of an information processing system according to an embodiment of the present invention. [Diagram 2] FIG. 1 is a block diagram showing a configuration of an information processing device. [Diagram 3] FIG. 2 is a functional block diagram for explaining functions that play a major role in the information processing system. [Figure 4]FIG. 13 is a diagram illustrating an example of a configuration of question data. [Diagram 5] FIG. 4 is a diagram illustrating an example of the configuration of attribute data. [Figure 6] FIG. 11 is a diagram illustrating an example of a configuration of conversion data. [Figure 7] FIG. 11 is a diagram illustrating an example of a configuration of answer data. [Figure 8] 4 is a flowchart illustrating an example of main processing of an information processing system according to an embodiment of the present invention. [Figure 9] FIG. 4 is a diagram illustrating an example of a configuration of first learning data. [Figure 10] FIG. 13 is a diagram illustrating an example of the configuration of second learning data. [Figure 11] FIG. 11 is a diagram showing another example of the configuration of answer data. [Figure 12] 2 is a diagram showing an example of division of functions of an information processing system between an information processing device and an interaction device; FIG. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0012] Hereinafter, an embodiment of the present invention will be described in detail with reference to the accompanying drawings. However, this embodiment is merely an example, and the present invention is not limited thereto.

[0013] (1) Basic configuration of information processing system Fig. 1 is a diagram showing a basic configuration of an information processing system according to an embodiment of the present invention. As shown in Fig. 1, in the information processing system according to this embodiment, when a user inputs a question using a terminal device 10, information related to the input question is transmitted to an information processing device 20 via a communication network NW (network) such as the Internet or a LAN (Local Area Network).

[0014] The information processing device 20 is configured to acquire information on the attributes of the user who asked the question, for example, via the terminal device 10 and the communication network NW or from a storage device in which information on the attributes of the user is stored in advance. The information processing device 20 is configured to determine information on an answer to the question based on information on the question from the user and information on the attributes of the user, and to provide the information on the answer to the user.

[0015] The terminal device 10 may be, for example, a terminal device (for example, a mobile terminal, a smartphone, a PDA, a personal computer, a television receiver (including a so-called multi-function smart TV) equipped with a bidirectional communication function) that is operated by an individual user, having a web browser function. In addition, the terminal device 10 may transmit to the information processing device 20 a transmission request for HTML (HyperText Markup Language) data for displaying a web page for inputting a question and / or displaying an answer to the question, in response to an instruction from a user. Furthermore, when the terminal device 10 receives the HTML data transmitted from the information processing device 20 in response to the transmission request via the communication network NW, the terminal device 10 may use a web browser provided in the terminal device 10 to display a web page corresponding to the received HTML data on a display unit (not shown) such as an LCD (liquid crystal display) monitor. Furthermore, the terminal device 10 may be configured to be able to execute an application for answering questions between the terminal device 10 and the information processing device 20.

[0016] The information processing device 20 is configured to communicate with the terminal device 10 via a communication network NW. The information processing device 20 may be a device operated by an individual user, such as a mobile terminal, a smartphone, a PDA, a personal computer, or a television receiver with a two-way communication function, or may be a server computer. The information processing device 20 may have a Web server function, and may generate HTML data for displaying a web page for inputting a question and / or displaying an answer to the question in response to a request for transmission of HTML data from the terminal device 10, which is a client, and transmit the generated HTML data to the requesting terminal device 10 via the communication network NW.

[0017] The information processing device 20 may be configured to realize a dialogue system that communicates with a user in a dialogue format. Here, the information processing device 20 may realize the dialogue system by answering questions (dialogue) with the user's terminal device 10 using, for example, an artificial intelligence chatbot (for example, ChatGPT (Chat Generative Pre-trained Transformer) by OpenAI, Inc., USA) or a dialogue engine.

[0018] (2) Configuration of information processing device The configuration of the information processing device 20 will be described with reference to Fig. 2. Fig. 2 is a block diagram showing the internal configuration of the information processing device 20. As shown in Fig. 2, the information processing device 20 includes a CPU (Central Processing Unit) 21, a ROM (Read Only Memory) 22, a RAM (Random Access Memory) 23, a storage device 24, a display processing unit 25, a display unit 26, an input unit 27, and a communication interface unit 28, and is provided with a bus 20a for transmitting control signals or data signals between the units.

[0019] When the information processing device 20 is powered on, the CPU 21 loads various programs stored in the ROM 22 or the storage device 24 into the RAM 23 and executes them. In this embodiment, the CPU 21 reads out and executes the programs stored in the ROM 22 or the storage device 24, thereby realizing the functions of a first acquisition means 31, a second acquisition means 32, a conversion means 33, a storage means 34, a determination means 35, and a provision means 36 (shown in FIG. 3) described below.

[0020] The storage device 24 may be, for example, a non-volatile storage device such as a flash memory, an SSD (Solid State Drive), a magnetic storage device (e.g., an HDD (Hard Disk Drive), a floppy disk (registered trademark), a magnetic tape, etc.), an optical disk, or a volatile storage device such as a RAM, and stores the programs executed by the CPU 21 and the data referenced by the CPU 21. The storage device 24 also stores question data (shown in FIG. 4), attribute data (shown in FIG. 5), conversion data (shown in FIG. 6), and answer data (shown in FIG. 7), which will be described later.

[0021] The display processing unit 25 displays the display data provided from the CPU 21 on the display unit 26. The display unit 26 is, for example, an LCD (Liquid Crystal Display) monitor including thin film transistors arranged in a matrix on a pixel basis, and displays the data to be displayed on the display screen by driving the thin film transistors based on the display data.

[0022] When the information processing device 20 is a button input type device, the input unit 27 includes a button group including a plurality of instruction input buttons such as a direction indication button and a decision button for accepting user operation input, and a button group including a plurality of instruction input buttons such as a numeric keypad, and includes an interface circuit for recognizing the press (operation) input of each button and outputting it to the CPU 21.

[0023] When the information processing device 20 is a device that uses a touch panel input method, the input unit 27 mainly accepts touch panel input by touching the display screen with a fingertip or a pen. The touch panel input method may be a known method such as a capacitance method.

[0024] Furthermore, when the information processing device 20 is a device capable of receiving voice input, the input unit 27 may be configured to include a microphone for voice input, or may be provided with an interface circuit for outputting voice data input via an external microphone to the CPU 21. Furthermore, when the information processing device 20 is a device capable of receiving moving images and / or still images, the input unit 27 may be configured to include a digital camera or digital video camera for image input, or may be provided with an interface circuit for receiving image data captured by an external digital camera or digital video camera and outputting it to the CPU 21.

[0025] The communication interface unit 28 includes an interface circuit for communicating with other devices (such as the terminal device 10) via the communication network NW.

[0026] (3) Overview of each function in the information processing system The functions realized by the information processing system of this embodiment will be described with reference to Fig. 3. Fig. 3 is a functional block diagram for explaining the functions that play a major role in the information processing system of this embodiment. In the functional block diagram of Fig. 3, a first acquisition means 31, a second acquisition means 32, a decision means 35, and a provision means 36 correspond to the main components of the information processing system of the present invention. The other means (conversion means 33 and storage means 34) are not necessarily essential components, but are components that make the present invention more preferable.

[0027] The first acquisition means 31 has a function of acquiring information regarding a question from a user.

[0028] The first acquisition means 31 may acquire information about a question via a dialogue system that dialogues with a user. This makes it possible to easily acquire information about a question from the user using the dialogue system (for example, ChatGPT, etc.).

[0029] The function of the first acquisition means 31 is realized, for example, as follows. Here, a case will be described as an example in which the first acquisition means 31 acquires information related to a question via a dialogue system that dialogues with a user. For example, when a web page for inputting a question is displayed on a display unit (not shown) of the terminal device 10 and the user inputs a question to the web page, the terminal device 10 transmits information related to the input question to the information processing device 20 via the communication network NW. Here, the information related to the question may be transmitted to the information processing device 20 in a state in which it is associated with identification information of the user who input the question (for example, it may be a user ID, or in the case where a single terminal device 10 is associated with each individual user, it may be identification information of the terminal device 10 (for example, a serial number or a MAC (Media Access Control) address, etc., of the terminal device 10)).

[0030] In addition, in this embodiment, it is assumed that the CPU 21 of the information processing device 20 is executing an artificial intelligence chatbot (for example, ChatGPT, etc.). When the CPU 21 of the information processing device 20 receives (acquires) information on a question transmitted from the terminal device 10 in the artificial intelligence chatbot via the communication interface unit 28, the CPU 21 stores the information on the question in question data shown in FIG. 4, for example, in a state in which the information is associated with the acquisition date and time (reception date and time) of the information. The question data is data in which the identification information of the user who asked the question (user ID in the example of the figure) and the question content are described in a state in which they are associated with each other for each acquisition date and time of the question. In this way, the CPU 21 can acquire information on the question via the dialogue system.

[0031] When the first acquisition means 31 acquires information related to the question without using a dialogue system, the CPU 21 may directly receive (acquire) the information related to the question transmitted from the terminal device 10 via the communication interface unit 28 and store the information related to the question in the question data. In this manner, the CPU 21 can acquire information related to the question from the user.

[0032] The information on the question may be composed of text data, image data, etc. When the information on the question is composed of voice data, the information on the question may be input to the terminal device 10 via a voice input device such as a microphone.

[0033] The second acquisition means 32 has a function of acquiring information about the attributes of the user. Here, the information about the attributes of the user may include at least one of the following: the user's age, sex, address, occupation, hobbies, areas of interest, areas of expertise, and purchase history of a specific product or service.

[0034] Furthermore, the second acquisition means 32 may acquire information on the attributes of a user from the storage device 24 that stores information on the attributes of each of a plurality of users, based on information input by the user. This makes it possible to extract (acquire) information on the attributes of the corresponding user from the information on the attributes of each of a plurality of users stored in the storage device 24.

[0035] The function of the second acquisition means 32 is realized, for example, as follows. When the CPU 21 of the information processing device 20 acquires information on a question from a user based on the function of the first acquisition means 31 described above, it accesses the attribute data shown in FIG. 5, for example. The attribute data is data in which information on the attributes of the user (for example, at least one of the user's age, sex, address, occupation, hobby, field of interest, field of specialty, purchase history of a predetermined product or service, etc.) is described in a state in which each identification information of a plurality of users (user ID in the example of the figure) is associated with the identification information (user ID) of the user that matches the identification information (user ID) of the user corresponding to the information on the question, from the attribute data, the CPU 21 extracts (acquires) information on the attributes associated with the identification information (user ID) of the user that matches the identification information (user ID) of the user corresponding to the information on the question, from the attribute data in the storage device 24 that stores the information on the attributes of each of the plurality of users, based on the question from the user (information input by the user). In this way, the CPU 21 can extract (acquire) information on the attributes of the user from the attribute data in the storage device 24 that stores information on the attributes of the plurality of users, based on the question from the user (information input by the user).

[0036] Furthermore, when a user inputs the user's identification information (user ID) using the terminal device 10, the terminal device 10 may transmit the input user's identification information (user ID) to the information processing device 20 via the communication network NW. In this case, when the CPU 21 of the information processing device 20 receives the user's identification information (user ID) transmitted from the terminal device 10 via the communication interface unit 28, the CPU 21 may extract (obtain) information on the user's attributes associated with the user's identification information (user ID) that matches the received user's identification information (user ID) from the attribute data. In this way, the CPU 21 can extract (obtain) information on the user's attributes from the attribute data in the storage device 24 that stores information on the attributes of each of a plurality of users, based on the identification information (user ID) input by the user (information input by the user).

[0037] Note that, although the case where the attribute data is stored in the storage device 24 of the information processing device 20 is described as an example here, the attribute data may also be stored in, for example, another device communicatively connected to the information processing device 20 via the communication network NW.

[0038] Furthermore, when a user inputs information on the user's attributes using the terminal device 10, the terminal device 10 may transmit the input information on the user's attributes to the information processing device 20 via the communication network NW. In this case, when the CPU 21 of the information processing device 20 receives the information on the user's attributes transmitted from the terminal device 10 via the communication interface unit 28, the CPU 21 may store the received information on the user's attributes in, for example, the RAM 23 or the storage device 24. In this way, the CPU 21 can obtain the information on the attributes input by the user.

[0039] The second acquisition means 32 may acquire information about attributes through a dialogue system that dialogues with the user. This makes it possible to easily acquire information about the user's attributes using the dialogue system (for example, ChatGPT, etc.).

[0040] The function of the second acquisition means 32 in this case is realized, for example, as follows. It is assumed here that the CPU 21 of the information processing device 20 is executing an artificial intelligence chatbot (for example, ChatGPT, etc.). In this case, the CPU 21 of the information processing device 20 may transmit information on a reverse question for acquiring a user's attributes to the terminal device 10 in the artificial intelligence chatbot. Then, when the CPU 21 receives (acquires) information on the user's attributes input by the user using the terminal device 10 to answer the reverse question via the communication interface unit 28, the CPU 21 may store the received information on the user's attributes in, for example, the RAM 23 or the storage device 24. In this way, the CPU 21 can acquire information on the user's attributes via the dialogue system.

[0041] The information on the user's attributes may be composed of text data, image data, etc. In addition, when the information on the user's attributes is composed of voice data, the information on the user's attributes may be input to the terminal device 10 via a voice input device such as a microphone, or may be stored in the attribute data.

[0042] The conversion means 33 has a function of converting information relating to a question into vector data, which is data obtained by vectorizing the information relating to the question.

[0043] The function of the conversion means 33 is realized, for example, as follows. When the CPU 21 of the information processing device 20 acquires information on a question from a user based on the function of the first acquisition means 31, the CPU 21 converts the information on the question into vector data by vectorizing the information on the question using a text vectorization technique. Here, the text vectorization technique may be, for example, the Embeddings API provided by the above-mentioned US company OpenAI, or may be another vectorization technique. In addition, when the CPU 21 converts the information on the question into vector data, the converted vector data is stored in, for example, the conversion data shown in FIG. 6. The conversion data is data in which, for each acquisition date and time of the question, the identification information of the user who asked the question (in the example of the figure, the user ID), the question content, and the vector data of the question content are described in a state of being associated with each other. In this way, the CPU 21 can convert the information on the question into vector data.

[0044] The storage means 34 has a function of storing information about a plurality of answers associated with any one of the plurality of vector data and any one of the plurality of pieces of information about attributes.

[0045] The function of the storage means 34 is realized, for example, as follows. When the CPU 21 of the information processing device 20 acquires, for example, the answer data shown in Fig. 7, the acquired answer data may be stored in the storage device 24 (or the RAM 23). The answer data is data in which vector data converted from information regarding a question is described in association with the content of the answer to the question (information regarding the answer) for each of various combinations of one or more attributes of the user.

[0046] Here, the answer data may correspond to a plurality of different vector data (different questions) and answer contents for the same combination of attributes, or may correspond to a plurality of different combinations of attributes and answer contents for the same vector data (same question). The answer contents may include a counter-question to the user, for example, to obtain a more specific question content from the user. Furthermore, the contents of the answer data may be added and / or updated by the CPU 21 based on information input using the input unit 27, or may be added and / or updated by the CPU 21 based on information input from outside the information processing device 20 via the communication interface unit 28. In this way, the CPU 21 can store information on a plurality of answers associated with any vector data among the plurality of vector data and any information on an attribute among the information on the plurality of attributes in the storage device 24 (or the RAM 23).

[0047] The determining means 35 has a function of determining information regarding an answer to a question based on information regarding the question and information regarding the attributes.

[0048] The determination means 35 may also determine information on the answer by acquiring, from among the information on the answers, vector data that satisfies a predetermined similarity condition with vector data corresponding to information on the question, and information on the acquired attributes, and information on the answer associated with the vector data that satisfies a predetermined similarity condition with vector data corresponding to information on the question from the user (i.e., a question whose content is similar to the question from the user), and information on the attributes of the user, as the answer to the question from the user.

[0049] The function of the determination means 35 is realized, for example, as follows. The CPU 21 of the information processing device 20 acquires information on the attributes of the user based on the function of the second acquisition means 32 described above, and converts information on the question from the user into vector data based on the function of the conversion means 33 described above, and then accesses the answer data. Then, the CPU 21 may extract (acquire) answer contents associated with vector data that satisfies a predetermined similarity condition between the converted vector data and the same combination as the combination of information on the attributes of the acquired user, among a plurality of answer contents in the answer data. Here, the predetermined similarity condition may include, for example, that the cosine similarity between the converted vector data and the vector data in the answer data is a predetermined value (for example, 0.9, etc.) or more. In this way, the CPU 21 can determine information on the answer associated with a question whose content is similar to the question from the user and information on the attributes of the user as an answer to the question from the user.

[0050] The providing means 36 has a function of providing information regarding the answer to the user.

[0051] The providing means 36 may provide information about the answer to the user through a dialogue system that dialogues with the user. This makes it possible to easily provide the user with an answer to a question from the user using a dialogue system (for example, ChatGPT, etc.).

[0052] The function of the providing means 36 is realized, for example, as follows. It is assumed here that the CPU 21 of the information processing device 20 is executing an artificial intelligence chatbot (for example, ChatGPT, etc.). In this case, when the CPU 21 of the information processing device 20 determines information related to the answer based on the function of the determining means 35 described above, the artificial intelligence chatbot may transmit the information related to the answer to the terminal device 10 that is the sender of the question. Then, the terminal device 10 may display the information related to the answer received from the information processing device 20 on a display unit (not shown). In this way, the CPU 21 can provide the information related to the answer to the user via the dialogue system.

[0053] The information on the answer may be composed of text data, image data, etc. In addition, when the information on the answer is composed of voice data, the terminal device 10 may output the information on the answer from a voice output device such as a speaker.

[0054] (4) Flow of main processing of the information processing system according to this embodiment Next, an example of the flow of main processes performed by the information processing system of this embodiment will be described with reference to the flowchart of FIG.

[0055] First, the CPU 21 of the information processing device 20 acquires information related to a question from a user based on the function of the first acquisition means 31 (step S100). Next, the CPU 21 of the information processing device 20 acquires information related to user attributes based on the function of the second acquisition means 32 (step S102). Here, the CPU 21 of the information processing device 20 may convert the information related to the question into vector data, which is data obtained by vectorizing the information related to the question, based on the function of the conversion means 33.

[0056] Next, the CPU 21 of the information processing device 20 determines information on an answer to the question based on information on the question and information on the user's attributes, based on the function of the determining means 35 (step S104). Here, the CPU 21 of the information processing device 20 may determine information on the answer by acquiring, from among the information on the multiple answers, information on the answer associated with vector data that satisfies a predetermined similarity condition between the vector data corresponding to the information on the question acquired in step S100 and the information on the attributes acquired in step S102.

[0057] Next, the CPU 21 of the information processing device 20 provides the user with information related to the answer based on the function of the providing means 36 (step S106).

[0058] In this way, it becomes possible to determine information about the answer to a question based on information about a question from a user and information about the user's attributes, and to provide this information about the answer to the user.

[0059] As described above, according to the information processing system, information processing method, and program of the present embodiment, information on an answer to a question is determined based on information on a question from a user and information on the user's attributes, and this answer information is provided to the user, so that it is possible to provide the user with an answer that takes into consideration the user's attributes such as personality and characteristics, etc. This makes it possible to provide appropriate answers to each user in response to questions from various users.

[0060] The program of the present invention may be stored in a computer-readable storage medium. The storage medium on which the program is recorded may be the ROM 22, RAM 23, or storage device 24 of the information processing device 20 shown in Fig. 2. The storage medium may be a CD-ROM or the like that can be read by being inserted into a program reading device such as a CD-ROM drive. Furthermore, the storage medium may be a magnetic tape, a cassette tape, a flexible disk, an MO / MD / DVD, or a semiconductor memory.

[0061] The above-described embodiments are described for the purpose of facilitating understanding of the present invention, and are not described for the purpose of limiting the present invention. Therefore, each element disclosed in the above embodiment is intended to include all design modifications and equivalents that fall within the technical scope of the present invention.

[0062] Modifications of the above-described embodiment will now be described. (Variation 1) In the above embodiment, the determination means 35 determines information related to the answer by acquiring vector data that satisfies a predetermined similarity condition between vector data corresponding to information related to the question, among information related to a plurality of answers, and information related to the acquired attributes, and information related to the answer associated with the vector data. However, the present invention is not limited to this case. For example, the determination means 35 may determine information related to the answer based on information related to the question, information related to the attributes, and a trained model based on machine learning using information related to the question and information related to the attributes as first training data. This makes it possible to easily determine information related to the answer by using the trained model.

[0063] The function of the determination means 35 in this modified example is realized, for example, as follows: The CPU 21 of the information processing device 20 first acquires information related to a question from a user based on the function of the first acquisition means 31, and acquires information related to the attributes of the user based on the function of the second acquisition means 32. Then, the CPU 21 may determine information related to the answer by inputting the acquired information related to the question and the acquired information related to the attributes into a trained model based on machine learning that uses the information related to the question and the information related to the attributes as first training data.

[0064] An example of the first learning data is shown in FIG. 9. The first learning data shown in FIG. 9 is data in which the content of a question from a user and the content of an answer to the question (correct answer label) are described in a state in which the content is associated with each of a plurality of combinations of user attributes. Here, the first learning data may associate a plurality of different question contents and answer contents (correct answer labels) with the same combination of attributes, or may associate different combinations of attributes and answer contents (correct answer labels) with the same question content. In addition, the answer contents (correct answer labels) of the first learning data may include content to ask a counter question to a user, for example, in order to obtain more specific question contents from the user. As a result of machine learning, a learned model is configured that indicates the relationship between the content of a question from a user, the attributes of the user, and the answer to the question.

[0065] In addition, CPU 21 may learn a model used to determine an answer to a question based on the acquired information about the question and the acquired information about the attributes through machine learning using information about the question and information about the attributes as first learning data.

[0066] In this case, when a predetermined model learning instruction is input using the input unit 27, the CPU 21 may learn a model using the first learning data shown in FIG. 9. The CPU 21 may learn using, for example, a time-series neural network model. Here, as the time-series neural network, for example, a recurrent neural network (RNN) or a long short-term memory (LSTM) which is an advanced version of the RNN may be applied. The CPU 21 may learn using any one of a plurality of models such as a graph neural network (GNN) model, a convolutional neural network (CNN) model, a support vector machine (SVM) model, a fully connected neural network (FNN) model, a gradient boosting (HGB) model, a wave net (WN) model, and an extremely randomized trees (ExtraTrees) model. Furthermore, the CPU 21 may perform learning using any of a graph convolutional neural network (GCN) model, a graph attention network (GAT) model, and a graph convolutional LSTM (GC-LSTM) model, which are derivatives of GNN.

[0067] The trained model used to determine information about the answer may be provided in a device other than the information processing device 20. In this case, the CPU 21 may input the acquired information about the question and the acquired information about the attribute to a trained model provided in the other device, and receive (acquire) information about the answer determined by the trained model from the other device.

[0068] (Variation 2) In the above-mentioned modified example 1, the determination means 35 determines information about the answer based on information about the question, information about the attribute, and a trained model based on machine learning using the information about the question and the information about the attribute as first training data, but the present invention is not limited to this case. For example, the determination means 35 may determine information about the answer based on the converted vector data, information about the attribute, and a trained model based on machine learning using the vector data and the information about the attribute as second training data. Even in this case, it is possible to easily determine information about the answer by using the trained model.

[0069] The function of the determination means 35 in this modified example is realized, for example, as follows: First, the CPU 21 of the information processing device 20 converts information related to the question from the user into vector data based on the function of the conversion means 33, and acquires information related to the attributes of the user based on the function of the second acquisition means 32. Then, the CPU 21 may determine information related to the answer by inputting the converted vector data and the acquired information related to the attributes into a trained model based on machine learning that uses the vector data and the information related to the attributes as second training data.

[0070] An example of the second learning data is shown in FIG. 10. The second learning data shown in FIG. 10 is data in which vector data corresponding to the content of a question from a user and the answer content (correct answer label) to the question are described in a state in which the vector data corresponds to each of a plurality of combinations of user attributes. Here, the second learning data may correspond to a plurality of different vector data and answer content (correct answer label) for the same combination of attributes, or may correspond to the same vector data for different combinations of attributes and answer content (correct answer label). In addition, the answer content (correct answer label) of the second learning data may include a content to ask a counter question to a user, for example, in order to obtain a more specific question content from the user. As a result of machine learning, a learned model is constructed that indicates the relationship between the vector data corresponding to the content of a question from a user, the attributes of the user, and the answer to the question.

[0071] In addition, CPU 21 may learn a model used to determine an answer to a question based on the converted vector data and the acquired information on the attributes through machine learning using the vector data and information on the attributes as second learning data.

[0072] (Variation 3) In the above embodiment, the determination means 35 determines information related to the answer by acquiring vector data that satisfies a predetermined similarity condition between the vector data corresponding to the information related to the question and the acquired attribute information from among the information related to the multiple answers, but the present invention is not limited to this case. For example, the determination means 35 may determine information related to the answer by acquiring information related to the answer that is associated with a question content that matches the acquired information related to the question and an attribute that matches the acquired attribute information from among the information related to the multiple answers. In this case, too, it is possible to achieve the same effects as in the above embodiment.

[0073] A configuration example of answer data in this modification is shown in Fig. 11. The answer data shown in Fig. 11 is described in a state in which question contents (information about the question) and answer contents (information about the answer) to the question are associated with each other for each combination of one or more attributes of the user. In this modification, the CPU 21 of the information processing device 20 first acquires information about the question from the user based on the function of the first acquisition means 31, and acquires information about the attributes of the user based on the function of the second acquisition means 32. Then, the CPU 21 may determine the information about the answer by extracting, from the answer data, information about the answer associated with the question contents that match the acquired information about the question and the attributes that match the acquired information about the attributes.

[0074] In the above-described embodiment and modified examples 1 to 3, a case where a dialogue (question and answer) is conducted with one user has been described as an example, but dialogues may be conducted simultaneously with each of a plurality of users.

[0075] Furthermore, in the above-mentioned embodiment and modifications 1 to 3, the case where one information processing device 20 is provided has been described as an example, but the present invention is not limited to this case. For example, a plurality of information processing devices 20 may be provided, and in this case, the operation contents and processing results of any one of the information processing devices 20 may be presented in real time on the other information processing devices 20, or the processing results of any one of the information processing devices 20 may be shared among the plurality of information processing devices 20.

[0076] Furthermore, in the above-mentioned embodiment and modified examples 1 to 3, the information processing device 20 is configured to realize the functions of the first acquisition means 31, the second acquisition means 32, the conversion means 33, the storage means 34, the determination means 35, and the provision means 36, but this is not limited to the configuration. For example, a dialogue device 40 (shown in FIG. 12) configured to communicate with each user in a dialogue format may be provided, which is a computer (e.g., a general-purpose personal computer or a server computer) communicably connected to the information processing device 20 via a communication network such as the Internet or a LAN. In this case, the information processing device 20 and the dialogue device 40 can have substantially the same hardware configuration, so that the dialogue device 40 can realize the function of at least one of the means 31 to 36 described in the above-mentioned embodiment and modified examples. For example, the functions of the functional block diagram shown in FIG. 3 may be arbitrarily shared between the information processing device 20 and the dialogue device 40 as shown in FIGS. 12(a) and 12(b).

[0077] Furthermore, the function of at least one of the above-mentioned means 31 to 36 may be realized by the terminal device 10. [Industrial Applicability]

[0078] The information processing system, information processing method, and program of the present invention as described above can provide appropriate answers to various questions from users, and can be suitably used, for example, in information provision services that provide information on appropriate products, services, etc. according to the user's personality, characteristics, etc., and consulting services that provide appropriate advice and support, etc. according to the user's personality, characteristics, etc., and therefore have extremely great industrial applicability. [Explanation of symbols]

[0079] 10...Terminal device 20...Information processing device 24…Storage device 31…First acquisition means 32…Second acquisition means 33...Conversion method 34...Memory means 35...Decision-making means 36…Providing means 40...Dialogue device

Claims

1. A first acquisition means for acquiring information regarding a question from a user; A second acquisition means for acquiring information regarding attributes of the user; a determination means for determining information regarding an answer to the question based on information regarding the question and information regarding the attribute; providing means for providing information regarding the answer to the user; Information processing system.

2. A conversion means for converting the information regarding the question into vector data which is data obtained by vectorizing the information regarding the question; a storage means for storing information on a plurality of answers associated with any one of the plurality of vector data, information on any one of the plurality of attribute-related information, the determining means determines information regarding the answer by obtaining, from among the plurality of pieces of information regarding the answers, vector data that satisfies a predetermined similarity condition between the vector data corresponding to the information regarding the question and the obtained information regarding the attribute, and information regarding the answer associated with the vector data. The information processing system according to claim 1 .

3. The determination means determines information regarding the answer based on information regarding the question, information regarding the attribute, and a trained model based on machine learning using the information regarding the question and the information regarding the attribute as training data. The information processing system according to claim 1 .

4. a conversion means for converting the information regarding the question into vector data which is data obtained by vectorizing the information regarding the question, The determination means determines information about the answer based on the converted vector data, information about the attributes, and a trained model based on machine learning using the vector data and the information about the attributes as training data. The information processing system according to claim 1 .

5. the second acquisition means acquires information about the attributes of the users from a storage device that stores information about the attributes of each of a plurality of users based on the information input by the users; The information processing system according to claim 1 .

6. the first acquisition means acquires information about the question via a dialogue system that has a dialogue with the user; The information processing system according to claim 1 .

7. the second acquisition means acquires information about the attribute via a dialogue system that has a dialogue with the user; The information processing system according to claim 1 .

8. the providing means provides information about the answer to the user via a dialogue system that dialogues with the user. The information processing system according to claim 1 .

9. The computer obtaining information regarding a question from a user; obtaining information regarding attributes of the user; determining information regarding an answer to the question based on information regarding the question and information regarding the attributes; providing information regarding the answer to the user; Execute each step of Information processing methods.

10. On the computer, The ability to obtain information about user questions; A function of acquiring information regarding attributes of the user; determining information regarding an answer to the question based on information regarding the question and information regarding the attribute; providing information about the answer to the user; and A program to achieve this.

Images