Information processing device, information processing method, and information processing program

Abstract

To provide an information processing device, an information processing method, and an information processing program that can provide appropriate answers to questions. [Solution] The information processing device according to the present invention comprises a reception unit that receives questions from a user, a determination unit that determines which answer generation agent matches the question from among a plurality of answer generation agents, each of which has learned to provide answers based on different answer policies and is linked in a hierarchical structure for each predetermined event, and a generation unit that generates an answer to the question using the determined answer generation agent.

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] Conventionally, a service that provides appropriate search results as an answer to a search query based on a search query input by a user has been known (see, for example, Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in the prior art, there is room for improvement in providing an appropriate answer to a question such as a user's search query.

[0005] The present application has been made in view of the above, and an object thereof is to provide an information processing apparatus, an information processing method, and an information processing program capable of providing an appropriate answer to a question.

Means for Solving the Problems

[0006] The information processing apparatus according to the present application includes a reception unit that receives a question from a user, and a plurality of answer generation agents that are learned so that answers are given based on different answer policies, and among the plurality of answer generation agents associated in a hierarchical structure for each predetermined event, a determination unit that determines the answer generation agent that matches the question, and a generation unit that generates an answer to the question by the determined answer generation agent.

Effects of the Invention

[0007] According to one embodiment, the effect is to provide appropriate answers to questions. [Brief explanation of the drawing]

[0008] [Figure 1A] Figure 1A is a diagram showing the process performed by the information processing device according to the embodiment. [Figure 1B] Figure 1B shows an example of a response provided by the information processing device according to the embodiment. [Figure 2] Figure 2 is a block diagram showing an example configuration of an information processing system according to the embodiment. [Figure 3] Figure 3 shows an example of the configuration of an information processing device according to the embodiment. [Figure 4] Figure 4 shows an example of user information. [Figure 5] Figure 5 shows an example of AG information. [Figure 6] Figure 6 is a flowchart showing the processing procedure of the information processing device executed by the information processing device according to the embodiment. [Figure 7] Figure 7 shows an example of a hardware configuration. [Modes for carrying out the invention]

[0009] The following describes in detail, with reference to the drawings, embodiments for implementing the information processing device, information processing method, and information processing program according to the present application (hereinafter referred to as "embodiments"). Note that these embodiments do not limit the information processing device, information processing method, and information processing program according to the present application. Furthermore, the same parts are denoted by the same reference numerals in each of the following embodiments, and redundant descriptions are omitted.

[0010] (Embodiment) First, the processes performed by the information processing device according to the embodiment will be described using Figures 1A and 1B. Figure 1A is a diagram showing the processes performed by the information processing device according to the embodiment. Figure 1B is a diagram showing an example of a response provided by the information processing device according to the embodiment. Note that Figure 1A shows an example of the operation of the information processing system S, which includes the information processing device 1 according to the embodiment.

[0011] As shown in Figure 1A, the information processing system S according to this embodiment includes an information processing device 1 and a user terminal 100.

[0012] As shown in Figure 1A, the information processing system S according to the embodiment receives a question from a user and consists of multiple answer generation agents, each trained to provide an answer based on a different answer policy. The system determines which answer generation agent matches the question from among the multiple answer generation agents linked in a hierarchical structure for each predetermined event, and generates an answer to the question using the determined answer generation agent. Hereafter, "agent" will be referred to as "AG".

[0013] Specifically, first, the information processing device 1 receives a user's question from the user terminal 100 (step S1). For example, the information processing device 1 accepts a search query as a question to search for a predetermined event. For example, the information processing device 1 accepts the text of a conversation entered by the user in chat format as a search query. The information processing device 1 may accept not only text, but also images, audio, etc., as questions. In addition, the information processing device 1 may accept a search query entered by the user in a search service as a question, for example.

[0014] The specified event may be somewhat abstract, such as commerce or travel, or it may be specific, such as home appliances or tourism. In other words, the specified event may be abstract, such as a category, or specific, such as a product name.

[0015] Next, the information processing apparatus 1 determines an answer generation AG that matches the question (step S2). Specifically, the information processing apparatus 1 stores in advance a response agent (AG) RM, which is a learning model, and a plurality of answer generation agents (AG) AM with different answer policies for a predetermined event. The response AGRM determines an answer generation AGAM with an answer policy that can appropriately answer the question from among the answer generation AGAMs.

[0016] The response AGRM is, for example, a model composed of an LLM (Large Language Models) and trained to appropriately respond to the input question. Specifically, the response AGRM analyzes the input question to grasp the content (event, etc.) of the question and is trained to determine an answer generation AGAM with an answer policy that can generate an appropriate answer for the grasped content of the question. For example, the response AGRM learns in advance the answer policies that each answer generation AGAM can answer, and among the learned answer policies, determines an answer generation AGAM with an answer policy that matches the content of the question.

[0017] The plurality of answer generation AGAMs are, for example, models composed of an LLM and trained to generate an answer to the input question according to a predetermined answer policy. The plurality of answer generation AGAMs each have a different answer policy for a predetermined event. In FIG. 1A, commerce related to e-commerce and travel related to travel are shown as predetermined events. As shown in FIG. 1A, the plurality of answer generation AGAMs are associated in a hierarchical structure for each predetermined event. The response AGRM is associated with the answer generation AGAM in the first layer among the plurality of answer generation AGAMs.

[0018] In commerce, which is one of the predetermined events, Commerce AG is placed in the first layer, Home Appliance AG and Fashion AG in the second layer, and Refrigerator AG, Air Conditioner AG, Coordination AG, and Formal Dress AG in the third layer. The Home Appliance AG and Fashion AG in the second layer are linked to the Commerce AG in the first layer. The Refrigerator AG and Air Conditioner AG in the third layer are linked to the Home Appliance AG in the second layer, and the Coordination AG and Formal Dress AG are linked to the Fashion AG. That is, the plurality of response generation AGs are arranged in the lower layer as the range of the response policy becomes narrower.

[0019] Commerce AG is a model with commerce in general as the response policy. In other words, Commerce AG is not a model that generates responses specialized for specific products, but a model that generates responses to broad questions such as "What is the return policy in commerce?" Home Appliance AG is a model with home appliances as the response policy. Fashion AG is a model with fashion as the response policy. Refrigerator AG is a model with refrigerators as the response policy. Air Conditioner AG is a model with air conditioners as the response policy. Coordination AG is a model with coordination as the response policy. Formal Dress AG is a model with formal dresses as the response policy.

[0020] Also, in travel, which is one of the predetermined events, Travel AG is placed in the first layer, and Sightseeing AG, Accommodation Reservation AG, and Gourmet AG in the second layer. The Sightseeing AG, Accommodation Reservation AG, and Gourmet AG in the second layer are linked to the Travel AG in the first layer.

[0021] Travel AG is a model with travel in general as the response policy. Sightseeing AG is a model with sightseeing as the response policy. Accommodation Reservation AG is a model with accommodation reservations as the response policy. Gourmet AG is a model with gourmet as the response policy.

[0022] In addition, in FIG. 1A, an example in which commerce is configured up to the third layer and travel is configured up to the second layer is shown, but it may be configured with four or more layers, the number of layers for each event may be different as in FIG. 1A, or they may be aligned to have the same number of layers.

[0023] Information processing device 1 inputs the input question into the response AGRM. The response AGRM analyzes the question to identify the event indicated by the question's content and determines a first-level answer generation AG that matches the identified event. For example, if the question concerns commerce, information processing device 1 determines a commerce AG. If the question concerns a refrigerator, information processing device 1 may determine a first-level commerce AG, or it may directly determine a third-level refrigerator AG. Even if information processing device 1 determines a first-level commerce AG in the case of a question about a refrigerator, it may be deemed inappropriate in a subsequent response appropriateness assessment, and the system will gradually change to deeper levels, such as the second and third levels, to generate an appropriate answer.

[0024] Furthermore, the response AGRM may also determine the answer generation AGAM by taking into account the user information of the user who entered the question. In other words, the response AGRM determines the answer generation AGAM based on the question and the user information.

[0025] For example, the response AGRM determines the answer generation AGAM based on the question and the user's location history. For instance, in Figure 1A, if the lower level (third level) of the tourism AG is divided into tourism AGs by region, the response AGRM identifies the user's current location from their location history and determines the tourism AG for the region that matches the current location. In addition to location history, the answer generation AGAM may also be determined based on user information such as attribute information.

[0026] Furthermore, the response AGRM may determine the answer generation AGAM based on the question and the question history. For example, if there is a question history about a bar, and the most recent question is "What are the opening hours?", that is, if a question is asked about an unknown opening, the response AGRM will determine an answer generation AG (not shown) that will answer with the bar's opening hours.

[0027] Next, the information processing device 1 causes the determined answer generation AG to generate an answer to the question (step S3). Specifically, the information processing device 1 inputs the question to the answer generation AG determined from the response AGRM and causes the answer generation AG to output (generate) an answer.

[0028] Next, the information processing device 1 determines the appropriateness of the generated response (step S4). Specifically, the response AGRM determines the appropriateness of the generated response. Specifically, the response AGRM calculates a score indicating the degree of appropriateness of the generated response, and determines that it is appropriate if the score is above a threshold. For example, the response AGRM analyzes the response using LLM and calculates a score for the degree of agreement between the content of the response and the content of the question. For example, the response AGRM calculates a score for the degree of agreement between the category of the event indicated by the response and the category of the event indicated by the question. For example, if the category of the event indicated by the response is related to "commerce in general" and the category of the event indicated by the question is related to "refrigerators", the score will be calculated to be low, that is, it will be determined to be inappropriate.

[0029] If the information processing device 1 determines that the response is inappropriate, it re-determines another response generation AG and has it generate a response again. For example, if the response AGRM determines that the response is inappropriate, it determines a lower-level response generation AG, has the determined lower-level response generation AG generate a response, and determines its appropriateness. For example, if the response generated by the Commerce AG is determined to be inappropriate, it inputs a question to the second-level Home Appliance AG and Fashion AG respectively and has them generate a response. In this case, if the responses generated by both the Home Appliance AG and Fashion AG are inappropriate, the response AGRM may have the lower-level response generation AGAM (Refrigerator AG, Air Conditioner AG, Coordination AG, Formal Wear AG) of the Home Appliance AG and Fashion AG generate a response, or it may have the lower-level response generation AG of the Home Appliance AG and Fashion AG with the higher score generate the response.

[0030] Next, if the information processing device 1 determines that the generated response is appropriate, it provides the response to the user terminal 100 (step S5). Specifically, the response AGRM provides all responses with a score above the threshold to the user terminal 100. Alternatively, the response AGRM may provide only the response with the highest score among those responses with a score above the threshold to the user terminal 100.

[0031] Here, using Figure 1B, we will explain an example of a response provided by the information processing device 1. In Figure 1B, the question "Tell me about izakayas in Echigo-Yuzawa" is input, and the response is given as an example.

[0032] In the example shown in Figure 1B, the information processing device 1 provides four answers that have been determined to be appropriate. Each of the four answers has a different answer generation AG. When the user operates the user terminal 100 and selects one of the answers, the information processing device 1 displays the selected answer.

[0033] Furthermore, as shown in Figure 1B, the screen displaying the answers is in a chat format, allowing users to add questions after answering.

[0034] As described above, according to the information processing device 1 of the embodiment, by determining an answer generation AG that matches the question from among a plurality of answer generation AGAMs linked in a hierarchical structure for each predetermined event and generating an answer, it is possible to provide an appropriate answer to the question generated by the answer generation AG.

[0035] Next, an example of the configuration of the information processing system S according to the embodiment will be described using Figure 2. Figure 2 is a block diagram showing an example of the configuration of the information processing system S according to the embodiment. As shown in Figure 2, in the information processing system S according to the embodiment, the information processing device 1 and a plurality of user terminals 100 are connected to a network N by wire or wireless. The network N is, for example, a network such as the Internet, a WAN (Wide Area Network), or a LAN (Local Area Network).

[0036] The information processing device 1 is a server device that executes the information processing method according to the embodiment. The information processing device 1 receives a question from a user and has a plurality of answer generation agents, each of which has been learned to provide an answer based on a different answer policy. From among the plurality of answer generation agents linked in a hierarchical structure for each predetermined event, it determines the answer generation agent that matches the question and generates an answer to the question using the determined answer generation agent.

[0037] Furthermore, the information processing device 1 is an information processing device that interacts with multiple user terminals 100 and provides various API (Application Programming Interface) services for various applications (hereinafter referred to as "apps") and various data to the multiple user terminals 100, and is realized by a server device or a cloud system.

[0038] Furthermore, the information processing device 1 may be an information processing device that provides some kind of web service online to multiple user terminals 100. For example, the information processing device 1 may provide services such as internet connection, search services, SNS (Social Networking Service), e-commerce (EC), electronic payment, online games, online banking, online trading, accommodation / ticket reservations, video / music distribution, news, maps, route search, route guidance, route information, service information, and weather forecasts as web services. In practice, the information processing device 1 may cooperate with various servers that provide the above-mentioned web services and act as an intermediary for web services, or it may be responsible for processing web services.

[0039] The user terminal 100 is a terminal device owned by the user. The user terminal 100 can be any type of terminal device, such as a smartphone, desktop PC, notebook PC, or tablet PC. The user terminal 100 transmits various types of information to the information processing device 1, etc., and receives information provided by the information processing device 1, etc.

[0040] Next, with reference to Figure 3, an example configuration of the information processing device 1 will be described.

[0041] Figure 3 is a diagram showing an example configuration of an information processing device 1 according to an embodiment. As shown in Figure 3, the information processing device 1 has a communication unit 2, a control unit 3, and a storage unit 4. The control unit 3 includes a receiving unit 31, a determination unit 32, a generation unit 33, and a provision unit 34. The storage unit 4 stores user information 41 and AG information 42.

[0042] The communication unit 2 is implemented, for example, by a NIC (Network Interface Card). The communication unit 2 is connected to the network by wire or wireless connection.

[0043] The control unit 3 is a controller and is implemented by a processor such as a CPU (Central Processing Unit) or MPU (Micro Processing Unit) executing various programs (corresponding to an example of an information processing program) stored in the memory device inside the information processing device 1, using RAM or the like as a working area. Alternatively, the control unit 3 is a controller and may be implemented by an integrated circuit such as an ASIC (Application Specific Integrated Circuit), FPGA (Field Programmable Gate Array), or GPGPU (General Purpose Graphic Processing Unit).

[0044] The memory unit 4 is implemented by, for example, semiconductor memory elements such as RAM (Random Access Memory) and flash memory, or by storage devices such as hard disks and optical discs.

[0045] User information 41 is information about the user.

[0046] Figure 4 shows an example of user information 41. As shown in Figure 4, user information 41 includes items such as "User ID," "Attribute Information," and "Behavioral Information."

[0047] "User ID" is identification information that identifies a user. "Attribute information" is information about the user's attributes. Attribute information includes, for example, psychographic attributes and demographic attributes. "Behavioral information" is information about the user's behavioral history, including search behavior, purchasing behavior, visiting behavior, viewing behavior such as articles and posted information, and location information history.

[0048] AG information 42 is information related to the response generation AG.

[0049] Figure 5 shows an example of AG information 42. As shown in Figure 5, AG information 42 includes items such as "Agent ID," "Event," "Response Policy," "Hierarchy," and "Model Parameters."

[0050] "Agent ID" is identification information that identifies the agent (response AG and answer generation AG). "Event" is information that indicates the event of the answer generation AG. "Answer Policy" is information that indicates the answer policy of the answer generation AG for a given event. "Hierarchy" is information about the hierarchy in which the answer generation AG is located. "Model Parameters" is information that indicates the parameters of the learning model of the answer generation AG.

[0051] Next, we will describe the functions of the control unit 3 of the information processing device 1 (reception unit 31, determination unit 32, generation unit 33, and provision unit 34).

[0052] The reception unit 31 receives various types of information. The reception unit 31 receives user questions from the user terminal 100. For example, the reception unit 31 receives search queries as questions to search for a predetermined event. For example, the reception unit 31 receives text of a conversation entered by the user in chat format as a search query. The reception unit 31 may accept images, audio, etc., as questions, not just text. In addition, the reception unit 31 may accept search queries entered by the user in a search service as questions, for example.

[0053] The decision unit 32 determines an answer generation AG that matches the question. Specifically, the decision unit 32 has in advance stored a response agent (AG) RM, which is a learning model, and multiple answer generation agents (AG) AM, each with a different answer strategy for a given event. The response AGRM determines an answer generation AGAM from among the answer generation AGAMs that has an answer strategy that can provide an appropriate answer to the question. The decision unit 32 inputs the input question into the response AGRM. The response AGRM analyzes the question to identify the event indicated by the content of the question and determines a first-level answer generation AG that matches the identified event. For example, if the question is about commerce, the decision unit 32 determines a commerce AG. If the question is about refrigerators, the decision unit 32 may determine a first-level commerce AG, or it may directly determine a third-level refrigerator AG. Furthermore, in the case of a question about a refrigerator, even if the decision unit 32 determines a first-level Commerce AG, if it is deemed inappropriate by the subsequent response appropriateness judgment, it will gradually change to deeper levels such as the second and third levels to generate an appropriate response.

[0054] Furthermore, the response AGRM may also determine the answer generation AGAM by taking into account the user information of the user who entered the question. In other words, the response AGRM determines the answer generation AGAM based on the question and the user information.

[0055] For example, the response AGRM determines the answer generation AGAM based on the question and the user's location history. For instance, in Figure 1A, if the lower level (third level) of the tourism AG is divided into tourism AGs by region, the response AGRM identifies the user's current location from their location history and determines the tourism AG for the region that matches the current location. In addition to location history, the answer generation AGAM may also be determined based on user information such as attribute information.

[0056] Furthermore, the response AGRM may determine the answer generation AGAM based on the question and the question history. For example, if there is a question history about a bar, and the most recent question is "What are the opening hours?", that is, if a question is asked about an unknown opening, the response AGRM will determine an answer generation AG (not shown) that will answer with the bar's opening hours.

[0057] The generation unit 33 generates an answer to the question. Specifically, the generation unit 33 causes the determined answer generation AG to generate an answer to the question. Specifically, the generation unit 33 inputs the question to the answer generation AG determined from the response AGRM and causes the answer generation AG to output (generate) an answer. The generation unit 33 also determines the appropriateness of the generated answer. Specifically, the generation unit 33 causes the response AGRM to determine the appropriateness. Specifically, the response AGRM determines the appropriateness of the generated answer. Specifically, the response AGRM calculates a score indicating the degree of appropriateness of the generated answer, and determines that it is appropriate if the score is above a threshold. For example, the response AGRM analyzes the answer using LLM and calculates a score for the degree of agreement between the content of the answer and the content of the question. For example, the response AGRM calculates a score for the degree of agreement between the category of event indicated by the answer and the category of event indicated by the question. For example, if the category of the event indicated by the answer is related to "commerce in general," but the category of the event indicated by the question is related to "refrigerators," the score will be calculated low, meaning it will be judged as inappropriate.

[0058] If the generation unit 33 determines that the response is inappropriate, it re-determines another response generation AG and has the response generation AG generate the response again. For example, if the response AGRM determines that the response is inappropriate, it determines a lower-level response generation AG, has the determined lower-level response generation AG generate the response, and determines its appropriateness. For example, if the response generated by the Commerce AG is determined to be inappropriate, it inputs a question to the second-level Home Appliance AG and Fashion AG respectively and has them generate a response. At this time, if the responses generated by both the Home Appliance AG and Fashion AG are inappropriate, the response AGRM may have the lower-level response generation AGAM (Refrigerator AG, Air Conditioner AG, Coordination AG, Formal Wear AG) of the Home Appliance AG and Fashion AG respectively generate the response, or it may have the lower-level response generation AG of the Home Appliance AG and Fashion AG with the higher score generate the response.

[0059] If the providing unit 34 determines that the generated response is appropriate, it provides the response to the user terminal 100. Specifically, the providing unit 34 provides all responses with a score above the threshold to the user terminal 100 via the response AGRM. Alternatively, the response AGRM may provide only the response with the highest score among those responses with a score above the threshold to the user terminal 100.

[0060] Next, the processing procedure of the process executed by the information processing device 1 according to the embodiment will be described using Figure 6. Figure 6 is a flowchart showing the processing procedure of the process executed by the information processing device 1 according to the embodiment.

[0061] As shown in Figure 6, the control unit 3 first receives a user's question from the user terminal 100 (step S101).

[0062] Next, the control unit 3 determines an answer generation AG for an answer policy that matches the received question (step S102).

[0063] Next, the control unit 3 causes the determined answer generation AG to generate an answer to the question (step S103).

[0064] Next, the control unit 3 determines whether the generated response is appropriate (step S104) and whether the response is appropriate (step S105). If the response is appropriate (step S105: Yes), the control unit 3 provides the response to the user terminal 100 (step S106) and terminates the process.

[0065] On the other hand, if the answer is inappropriate (step S105: No), the control unit 3 determines a deeper (lower) answer generation AG than the answer generation AG determined in step S102 (step S107), and returns to step S103 to regenerate the answer.

[0066] Furthermore, some of the processes described as being performed automatically in the above embodiments can be performed manually. Alternatively, all or part of the processes described as being performed manually can be performed automatically by known methods. In addition, the processing procedures, specific names, and various data and parameters shown in the above documents and drawings can be changed at will unless otherwise specified. For example, the various information shown in each figure is not limited to the information shown.

[0067] Furthermore, the components of each illustrated device are functionally conceptual and do not necessarily need to be physically configured as shown. In other words, the specific forms of distribution and integration of each device are not limited to those shown, and all or part of them can be functionally or physically distributed and integrated in any unit according to various loads and usage conditions.

[0068] For example, some or all of the storage unit 4 shown in Figure 3 may be stored in a storage server or the like, rather than being held by each device. In this case, each device obtains various information by accessing the storage server.

[0069] [Hardware configuration] Furthermore, the information processing device 1 according to the above embodiment is realized by a computer 1000 having a configuration such as that shown in Figure 7. Figure 7 is a diagram showing an example of a hardware configuration. The computer 1000 is connected to an output device 1010 and an input device 1020, and has a configuration in which an arithmetic unit 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.

[0070] The arithmetic unit 1030 operates based on programs stored in the primary storage device 1040 and the secondary storage device 1050, as well as programs read from the input device 1020, and executes various processes. The primary storage device 1040 is a memory device, such as RAM, that temporarily stores data used by the arithmetic unit 1030 for various calculations. The secondary storage device 1050 is a storage device where data used by the arithmetic unit 1030 for various calculations and various databases are registered, and is implemented using ROM (Read Only Memory), HDD (Hard Disk Drive), flash memory, etc.

[0071] Output IF1060 is an interface for transmitting information to be output to output devices 1010, which output various types of information such as monitors and printers. It is implemented using connectors of standards such as USB (Universal Serial Bus), DVI (Digital Visual Interface), and HDMI (High Definition Multimedia Interface). Input IF1070 is an interface for receiving information from various input devices 1020, such as mice, keyboards, and scanners. It is implemented using, for example, USB.

[0072] The input device 1020 may also be a device that reads information from, for example, an optical recording medium such as a CD (Compact Disc), DVD (Digital Versatile Disc), or PD (Phase Change Rewritable Disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), tape media, magnetic recording media, or semiconductor memory. Furthermore, the input device 1020 may also be an external storage medium such as a USB memory stick.

[0073] Network IF1080 receives data from other devices via network N and sends it to the arithmetic unit 1030, and also transmits data generated by the arithmetic unit 1030 to other devices via network N.

[0074] 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.

[0075] For example, when computer 1000 functions as information processing device 1, the arithmetic unit 1030 of computer 1000 realizes the functions of control unit 3 by executing a program loaded on primary storage device 1040.

[0076] 〔effect〕 As described above, the information processing device 1 according to the embodiment includes a reception unit 31 that receives questions from a user, a determination unit 32 that determines which answer generation agent matches the question from among a plurality of answer generation agents, each of which has been learned to provide answers based on different answer policies and is linked in a hierarchical structure for each predetermined event, and a generation unit 33 that generates an answer to the question using the determined answer generation agent.

[0077] With this configuration, the information processing device 1 can provide an appropriate answer to a question.

[0078] Although some embodiments of the present invention have been described in detail above with reference to the drawings, these are illustrative examples, and the present invention can be implemented in various other forms with modifications and improvements based on the knowledge of those skilled in the art, starting with the embodiments described in the disclosure section of the invention.

[0079] 〔others〕 Furthermore, among the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically by known methods. In addition, the processing procedures, specific names, and various data and parameters shown in the above document and drawings can be changed at will unless otherwise specified. For example, the various information shown in each figure is not limited to the information shown.

[0080] Furthermore, the components of each illustrated device are functionally conceptual and do not necessarily need to be physically configured as shown. In other words, the specific forms of distribution and integration of each device are not limited to those shown, and all or part of them can be functionally or physically distributed and integrated in any unit according to various loads and usage conditions.

[0081] Furthermore, each of the processes described in the embodiments above can be combined as appropriate, provided that the processing content does not contradict each other.

[0082] Furthermore, the terms "section, module, unit" used above can be replaced with "means" or "circuit," etc. For example, control unit 3 can be replaced with control means or control circuit. [Explanation of symbols]

[0083] 1. Information Processing Device 2 Communications Department 3. Control Unit 4 Storage section 31 Reception Department 32 Decision Section 33 Generation part 34 Providing Department 41 User Information 42 AG Information 100 user terminals S Information Processing System

Claims

1. A reception desk that receives questions from users, Multiple answer generation agents, each trained to provide answers based on different answer policies, comprising a determination unit that determines which answer generation agent matches the question from among multiple answer generation agents linked in a hierarchical structure for each predetermined event, A generation unit that generates an answer to the question using the determined answer generation agent, An information processing device equipped with the following features.

2. The aforementioned determination unit, The answer generation agent is determined based on the aforementioned questions and the user information of the user. The information processing apparatus according to claim 1.

3. The aforementioned user information is Including the user's location history, The aforementioned determination unit, The answer generation agent is determined based on the aforementioned questions and the location history. The information processing apparatus according to claim 2.

4. The aforementioned user information is This includes the question history, which is the history of the questions received from the user. The aforementioned determination unit, The answer generation agent is determined based on the aforementioned questions and the question history. The information processing apparatus according to claim 2.

5. The generating unit is The response generation agent determines whether the response it generates is appropriate for the question, and if it determines that the response is appropriate for the question, it is set as the generated result. The information processing apparatus according to claim 1.

6. The aforementioned determination unit, If the generation unit determines that the answer is not appropriate for the question, another answer generation agent is determined. The generating unit is The aforementioned other response generation agent generates the response. The information processing apparatus according to claim 5.

7. The aforementioned multiple response generation agents The narrower the scope of the aforementioned response policy, the more it is linked in the hierarchical structure located at the lower levels. The aforementioned determination unit, If the generation unit determines that the answer is not appropriate for the question, it determines the lower-level answer generation agent. The generating unit is The response is generated by the lower-level response generation agent. The information processing apparatus according to claim 6.

8. A method of information processing performed by a computer, The process of receiving questions from users, Multiple answer generation agents, each trained to provide answers based on different answer policies, comprising a decision step of determining which answer generation agent matches the question from among multiple answer generation agents linked in a hierarchical structure for each predetermined event, A generation process in which the determined answer generation agent generates an answer to the question. Information processing methods including

9. The procedure for receiving questions from users, Multiple answer generation agents, each trained to provide answers based on different answer policies, comprising a decision procedure for determining which answer generation agent matches the question from among multiple answer generation agents linked in a hierarchical structure for each predetermined event, A generation procedure for generating an answer to the question using the determined answer generation agent, and An information processing program that causes a computer to execute something.

Images