Information processing apparatus, information processing method, and information processing program

Abstract

To improve convenience of service provision to a plurality of grouped users.SOLUTION: An information processing device according to the present application includes a personal agent identification unit, an inquiry unit, and a provision unit. The personal agent identification unit identifies a plurality of personal agents each associated with a corresponding user among a plurality of grouped users. The inquiry unit inquires of one or more personal agents among the plurality of personal agents specified by the personal agent specifying unit about predetermined information used for providing a service to a group corresponding to the plurality of users. The provision unit provides a service to the group using information provided from the one or more personal agents in response to the inquiry by the inquiry unit.SELECTED DRAWING: Figure 3

Description

[Technical Field]

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

[0002] Conventionally, there are known techniques for providing advertisements via a network. For example, Patent Document 1 proposes a technique for forming a chat group including a user and at least one of a staff member of a customer service establishment and a cast member belonging to the customer service establishment, and providing a reservation guidance service in a chat room of the chat group. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2024-027355 Summary of the Invention [Problem to be solved by the invention]

[0004] However, with the above-mentioned conventional technology, advertisements are not provided unless the cast or staff selects the "reservation guide to the service store" button, which poses a problem in terms of convenience in providing the service.

[0005] The present application has been made in consideration of the above, and aims to provide an information processing device, an information processing method, and an information processing program that can improve the convenience of providing services to multiple grouped users. [Means for solving the problem]

[0006] The information processing device according to the present application comprises a personal agent identification unit, an inquiry unit, and a provision unit. The personal agent identification unit identifies a plurality of personal agents each associated with a corresponding user from among a plurality of grouped users. The inquiry unit inquires of one or more personal agents from among the plurality of personal agents identified by the personal agent identification unit about specific information to be used for providing a service to a group corresponding to the plurality of users. The provision unit provides a service to the group using information provided by the one or more personal agents in response to the inquiry by the inquiry unit. [Effects of the Invention]

[0007] According to one aspect of the embodiment, it is possible to improve the convenience of providing services to a plurality of users who are grouped together. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram illustrating an example of information processing according to an embodiment. [Figure 2] FIG. 2 is a diagram illustrating an example of the configuration of an information processing system according to the embodiment. [Figure 3] FIG. 3 is a diagram illustrating an example of the configuration of the information processing device according to the embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of a user information table stored in the user information storage unit of the information processing device according to the embodiment. [Figure 5] FIG. 5 is a diagram illustrating an example of a chat setting information table stored in the chat setting information storage unit of the information processing device according to the embodiment. [Figure 6] FIG. 6 is a diagram illustrating an example of a conversation history table stored in the conversation history storage unit of the information processing device according to the embodiment. [Figure 7] FIG. 7 is a diagram illustrating an example of the configuration of a group agent processing unit in the processing unit of the information processing device according to the embodiment. [Figure 8]FIG. 8 is a diagram illustrating an example of the configuration of the identification unit in the group agent processing unit of the information processing device according to the embodiment. [Figure 9] FIG. 9 is a diagram illustrating an example of the configuration of the inquiry unit in the group agent processing unit of the information processing device according to the embodiment. [Figure 10] FIG. 10 is a diagram illustrating an example of the configuration of the providing unit in the group agent processing unit of the information processing device according to the embodiment. [Figure 11] FIG. 11 is a diagram illustrating an example of service information provided to a terminal device by a providing unit in a processing unit of the information processing device according to the embodiment and displayed on the terminal device. [Figure 12] FIG. 12 is a flowchart illustrating an example of information processing by the processing unit of the information processing device according to the embodiment. [Figure 13] FIG. 13 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device according to the embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, modes for implementing an information processing device, an information processing method, and an 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 device, the information processing method, and the information processing program according to the present application are not limited to these embodiments. Furthermore, the respective embodiments can be appropriately combined within the scope of not causing any contradiction in the processing content. Furthermore, the same components in the following embodiments will be assigned the same reference numerals, and redundant explanations will be omitted.

[0010] [1. An example of information processing] FIG. 1 is a diagram showing an example of information processing according to an embodiment, and in this embodiment, an information processing method is executed by an information processing device.

[0011] As shown in FIG. 1, the information processing device 1 includes terminal devices 21, 22, . . . , 2 mand the service providing device 3 are communicably connected to the terminal devices 21, 22, . . . , 2 m and transmits and receives information to and from the service providing device 3. m is, for example, an integer of 3 or more.

[0012] The information processing device 1 includes terminal devices 21, 22, . . . , 2 m A chat service for sending and receiving chat messages between terminal devices 21, 22, . . . , 2 m Users U1, U2, , U m Provided to.

[0013] In the following, terminal devices 21, 22, . . . , 2 m When each of these is not individually distinguished, it may be referred to as terminal device 2, and users U1, U2, . . . , U m When referring to each of these without distinguishing them individually, they may be referred to as a user U. The terminal device 2 is, for example, a smartphone, a tablet PC (Personal Computer), or a notebook PC.

[0014] The service providing device 3 provides various online services, such as various search services, various reservation services, an advertisement distribution service, a map information providing service, and an electronic commerce service.

[0015] The service providing device 3 provides, for example, an API (Application Programming Interface), and the information processing device 1 and the terminal device 2 can send and receive various information for various online services via the API provided by the service providing device 3.

[0016] The terminal device 21 is used by the user U1, the terminal device 22 is used by the user U2, and the terminal device 2 m is user U m It is used by users U1, U2,...,U m are participants in the same chat group, and terminal devices 21, 22, . . . , 2m An instant messenger application for group chat, which is chatting with a chat group, is installed on the device. In the following, the instant messenger application may be referred to as a chat app.

[0017] Instant messengers allow users to send and receive messages in group chats, one-to-one chats, one-to-many chats, etc. Messages sent and received by chat apps include, for example, text, stamps, and captured images.

[0018] User U1,U2,...,U m are terminal devices 21, 22, . . . , 2 m The users U1, U2, . . . , U m are terminal devices 21, 22, . . . , 2 m , and transmits a group chat message to the information processing device 1 via a network (not shown) (steps S11, S12, . . . S1 m ).

[0019] The information processing device 1 includes terminal devices 21, 22, . . . , 2 m The group chat message is then sent to the terminal device 2 of the user U other than the user U who sent the message via a network (not shown) (steps S21, S22, . . . S2 m ) Terminal devices 21, 22,..., 2 m receives a chat message that is a group chat message sent from the information processing device 1, and displays the received chat message in the chat room of the group chat.

[0020] In the example shown in FIG. 1(a), the terminal device 21 stores chat messages CTM1 and CTM4 from user U1, chat message CTM2 from user U2, and chat message CTM3 from user U3. m The chat message CTM3 is displayed. The name of the chat group is Group A.

[0021] The chat message CTM1 is information about the character string "Shall we go out to eat on July 10th?", the chat message CTM2 is information about the character string "Like", the chat message CTM3 is information about the character string "Like, I agree!", and the chat message CTM4 is information about the character string "Then, let's go out to eat around Akasaka on July 10th!".

[0022] The information processing device 1 also includes a plurality of users U1, U2, . . . , U3 who are grouped as a chat group, group A. m Among these, multiple personal agents PA1, PA2,..., PA m (Step S3).

[0023] The information processing device 1 identifies a personal agent of a chat application to which the user ID (IDenfier) ​​of the user U is set as the personal agent of the user U. The user ID is the account of the user U set in the chat application.

[0024] For example, the information processing device 1 identifies as personal agent PA1 a personal agent of a chat application in which the user ID of user U1 is set and which is running on terminal device 21. The information processing device 1 also identifies as personal agent PA2 a personal agent of a chat application in which the user ID of user U2 is set and which is running on terminal device 22.

[0025] In addition, the information processing device 1 m A chat application in which the user ID of the terminal device 2 is set mPersonal Agent PA is a chat app running on m In the following, we will consider multiple individual agents PA1, PA2,..., PA m When referring to each of these without distinguishing them individually, they may be referred to as a personal agent PA. The personal agent PA is a service agent for each user U, and may be, for example, something like Auto-GPT.

[0026] The personal agent PA is one of the functions included in the chat application, and functions as an agent for a user U. For example, a personal agent PA1 functions as an agent for a user U1, a personal agent PA2 functions as an agent for a user U2, and so on. m is user U m acts as an agent for

[0027] The information processing device 1 performs steps S11, S12, . . . S1 m However, the present invention is not limited to this example, and the process may be performed before the process of step S4. For example, the information processing device 1 performs the process of step S3 for users U1, U2, . . . , U m When grouping is performed, the process of step S3 is performed.

[0028] User U1,U2,...,U m The timing for grouping is when group A is set up, when a chat room for group A is created, etc., but is not limited to such examples. For example, when users U1, U2, . . . , U m The timing at which grouping is performed may be the timing at which a chat message is posted in the chat room of group A, for example.

[0029] The information processing device 1 also includes users U1, U2, . . . , U m When grouping is performed, the grouped users U1, U2, . . ., U mA group agent GA for group A is set (step S4). The group agent GA is, for example, a service agent for each group, and may be something like Auto-GPT. The group agent GA is set on a group basis, but it may be set across multiple groups, or only one group agent GA may be set for all groups.

[0030] The group agent GA transmits and receives information to and from multiple personal agents PA corresponding to multiple grouped users U, thereby sharing information among the multiple personal agents PA and providing more optimal information to the group.

[0031] The group agent GA of the information processing device 1 receives the chat message input by the user U as input information (step S5). For example, in the example shown in FIG. 1(a), the group agent GA receives the chat message input by the user U from the users U1, U2, U3, U4, U5, U6, U7, U8, U9, U10, U11, U12, U13, U14, U15, U16, U17, U18, U19, U20, U21, U22, U23, U24, U25, U26, U27, U28, U29, U30, U31, U32, U33, U34, U35, U36, U37, U38, U39, U40, U41, U42, U43, U44, U45, U46, U47, U48, U49, U50, U51 m The chat messages CTM1, CTM2, CTM3, and CTM4 entered by the above are accepted as input information.

[0032] The chat messages CTM1 and CTM4 from user U1 are messages about eating and drinking, and are information about the restaurant search service provided by the service providing device 3. In step S5, the group agent GA receives the chat messages CTM1 and CTM4 from user U1 as messages including information about the service.

[0033] The information about the service is information about the service provided by the service providing device 3, but may also be information about a service provided by a service providing device other than the service providing device 3.

[0034] Next, the group agent GA generates a group of users U1, U2, . . . , U mThe predetermined information used to provide the service to the group A corresponding to the group A is identified (step S6).

[0035] The group agent GA executes the process of step S6 regardless of whether or not the input information received in step S5 includes information about the service, but this is not a limitation. For example, the group agent GA can execute the process of step S6 only if the input information received in step S5 includes a specific term or phrase, or can execute the process of step S6 only if the input information received in step S5 does not include a specific term or phrase. Below, step S6 will be explained separately as step S6-1 and step S6-2.

[0036] In step S6, the group agent GA identifies the type of service and the values ​​of one or more parameters among a plurality of parameters used to provide that type of service based on the input information received in step S5 (step S6-1).

[0037] The service types include, but are not limited to, restaurant search services, hotel search services, restaurant reservation services, hotel reservation services, advertisement distribution services, map information provision services, e-commerce services, etc. In the following, the service types may be referred to as service types.

[0038] The multiple parameters used for providing the service include necessary parameters, which are parameters necessary for providing the service, and additional parameters, which are parameters for improving the accuracy of providing the service.

[0039] If the service type is a restaurant search service, the required parameters include, for example, the area of ​​the restaurant, the planned date and time of dining, and the number of people, and the additional parameters include, but are not limited to, the type of food, price range, seating (terrace, table, tatami room), facilities (wheelchair, pets allowed), rating, allergenic ingredients, display order, and maximum number of items to be acquired.

[0040] Furthermore, if the service type is a hotel search service, the required parameters include, for example, the hotel area, planned stay date, time, and number of people, and additional parameters include, but are not limited to, the number of rooms, number of adults, number of children, rating, price range, facilities and services (wifi, Japanese-style room / Western-style room, double bed, single bed, non-smoking / smoking), display order, and maximum number of acquisitions.

[0041] Furthermore, if the service type is a restaurant reservation service, the required parameters include, for example, the area of ​​the restaurant, the planned date and time of dining, and the number of people, and the additional parameters include, but are not limited to, the type of food, seating (terrace, table, tatami room), and ingredients with allergies.

[0042] Furthermore, if the service type is a hotel reservation service, the required parameters include, for example, the area of ​​the hotel, the planned date and time of stay, and the number of people, and the additional parameters include, but are not limited to, the number of rooms, the number of adults, the number of children, the price range, the type of room, and facilities and services (wifi, Japanese-style room / Western-style room, double bed, single bed, non-smoking / smoking).

[0043] In step S6-1, the group agent GA can identify, for example, the values ​​of multiple parameters used to provide the service, and identifies the values ​​of parameters from among these multiple parameters whose values ​​can be identified from the input information received in step S5.

[0044] For example, if the group agent GA can identify one or more required parameter values ​​based on the input information received in step S5, it identifies the one or more required parameter values. Also, if the group agent GA can identify one or more additional parameter values ​​based on the input information received in step S5, it identifies the one or more additional parameter values.

[0045] The group agent GA, for example, uses a generating AI (Artificial Intelligence) to identify a service type and the values ​​of one or more parameters among a plurality of parameters used to provide a service of that service type based on the information about the service received in step S6.

[0046] An example of a generative AI is a text generation AI, which is a large-scale language model trained to predict and output the next token from an input token sequence, such as a transformer-based model or an RNN (Recurrent Neural Network)-based model.

[0047] Examples of the transformer-based model include, but are not limited to, a generative pre-trained transformer (GPT), etc. Examples of the RNN-based model include, but are not limited to, a receptance weighted key value (RWKV).

[0048] The generation AI may be a language model that has been trained (for example, fine-tuned) specifically for generating answer information. The generation AI may be located in an external information processing device, and the group agent GA uses the generation AI via an API, but the generation AI may also be located within the information processing device 1.

[0049] The group agent GA inputs information including the chat message received as input information in step S5 and instruction information to the generation AI, and can cause the generation AI to output a service type and one or more parameter values. The instruction information is information that instructs the generation AI to identify a service type and one or more parameter values ​​used to provide the service of that type from the chat message received as input information in step S5.

[0050] The instruction information includes, for example, the string "From the given message, please identify the service type and the parameter values ​​used to provide that type of service. Please identify the service type from the service type list below, and the parameter values ​​from the parameter list below. Please output the identification results in the output format below," as well as a service type list, a parameter list, and output format information.

[0051] The service type list includes, for example, information linking a service type with information indicating the content of the service for each service type. The parameter list includes, for example, information linking a parameter with information indicating the content of the parameter for each service type. Note that the instruction information is not limited to the above example, and may be any information that can output the type of service and the value of the parameter used to provide the service of that type from a message.

[0052] Furthermore, if the generation AI is GPT provided by OpenAI, the function calling function can be used to have the generation AI output the service type and one or more parameter values. In this case, the information input to the generation AI includes, for each service type, information indicating the definition of the service type and information indicating the definition of each parameter.

[0053] Furthermore, if the generation AI is fine-tuned to output the type of service and the parameter values ​​used to provide that type of service from the message, the input information input to the generation AI does not need to include instruction information.

[0054] Furthermore, the group agent GA may be configured to identify the type of service and the parameter values ​​used to provide that type of service from the message using a known slot-filling technique that does not use a generation AI.

[0055] The group agent GA identifies, as predetermined information, information on unspecified parameters whose values ​​are unspecified among a plurality of parameters corresponding to the type of service identified in step S6-1 (step S6-2).

[0056] The group agent GA identifies a plurality of parameters associated with the service type identified in step S6-1. The group agent GA associates the service type with a plurality of parameters for each service and stores them. The plurality of parameters includes the above-mentioned required parameters and additional parameters.

[0057] The group agent GA identifies a plurality of parameters linked to the service type identified in step S6-1 from the stored service types for each service and a plurality of parameters for each service type.

[0058] For example, the group agent GA identifies, as unspecified parameters, necessary parameters whose values ​​are unspecified among the multiple parameters linked to the service type identified in step S6-1. Also, the group agent GA can identify, as unspecified parameters, additional parameters whose values ​​are unspecified in addition to the necessary parameters whose values ​​are unspecified among the multiple parameters.

[0059] In addition, if the instruction information is set so that information on parameters whose values ​​are not yet specified is output from the generation AI, the group agent GA can also identify the unspecified parameters from among the multiple parameters linked to the service type identified in step S6-1 based on the information output from the generation AI.

[0060] Next, the group agent GA identifies the individual agents PA1, PA2,..., PA m For one or more personal agents, multiple users U1, U2, . . ., U mThe predetermined information used for providing the service to the group corresponding to the group is inquired (steps S71, S72, . . . , S7 m In the following, the personal agent PA to whom inquiries regarding specific information are directed may be referred to as the target personal agent.

[0061] In step S7, the group agent GA identifies one or more target individual agents TPA based on the predetermined information identified in step S6. For example, if the predetermined information identified in step S6 is information related to all users U of group A, the group agent GA identifies all users U1, U2, . . . , U of group A. m Individual agents PA1, PA2,...,PA m is identified as the target individual agent TPA.

[0062] Furthermore, if the predetermined information identified in step S6 is information related to some users U in group A, the group agent GA identifies the personal agents PA of some users U as target personal agents TPA.

[0063] In step S7, the group agent GA outputs inquiry information to the target individual agent TPA, inquiring about information relating to the unspecified parameter specified as the predetermined information in step S6-2.

[0064] The information regarding the unspecified parameter is, for example, information for obtaining the value of the unspecified parameter, and the inquiry information is information that directly inquires about the value of the unspecified parameter or information that inquires about information used to determine the value of the unspecified parameter.

[0065] The group agent GA has information for each service type in which query information is linked to each parameter, and identifies the query information corresponding to the unidentified parameter identified in step S6-2 and outputs the identified query information to the target individual agent TPA.

[0066] If the service type identified in step S6-1 is a restaurant search service and the unidentified parameter identified in step S6-2 is a cuisine genre, the inquiry information may be, for example, the string "Search for restaurants that are available for reservations. What cuisine genre would you like to find at a restaurant?", but is not limited to such an example.

[0067] Furthermore, in step S7, the group agent GA can also use the generation AI to generate query information that inquires about the value of the unspecified parameter as the predetermined information. For example, the group agent GA inputs information including instruction information, which is information that instructs the generation AI to generate a sentence that inquires about the value of the unspecified parameter specified in step S6-2, to the generation AI, and causes the generation AI to generate the query information.

[0068] If the service type identified in step S6-1 is a restaurant search service and the unidentified parameter identified in step S6-2 is a cuisine genre, the instruction information to be input to the generation AI includes, for example, the string "Please create a sentence to inquire about the cuisine genre in order to search for restaurants that can be reserved."

[0069] The group agent GA has instruction information for each service type, with instruction information linked to each parameter, and identifies the instruction information corresponding to the unidentified parameter identified in step S6-2, inputs information including the identified instruction information into the generation AI, and causes the generation AI to generate inquiry information.

[0070] Furthermore, when the information used to determine the value of the unspecified parameter is information for generating a persona for group A, the group agent GA generates or determines information for inquiring about attribute information of user U as inquiry information.

[0071] The target individual agent TPA generates answer information indicating a response to the inquiry information in response to the inquiry from the group agent GA, and outputs the generated answer information to the group agent GA (steps S81, S82, . . . , S8 m ).

[0072] The target personal agent TPA has information about the user U and can generate answer information based on the information about the user U. The information about the user U includes information indicating the attributes of the user U, information indicating the schedule of the user U, information indicating the behavioral patterns of the user U, etc. For example, the target personal agent TPA generates answer information including information about the user U of a type corresponding to the inquiry information.

[0073] The attributes of the user U include, for example, demographic attributes and psychographic attributes. Demographic attributes are demographic attributes of the user U. Psychographic attributes are attributes that indicate, for example, the interests, values, lifestyle, personality, etc. of the user U. The behavioral patterns of the user U are, for example, the online behavioral patterns of each user U, but may also include the offline behavioral patterns of each user U.

[0074] The target personal agent TPA inputs information including inquiry information and instruction information as input information to the generation AI, and causes the generation AI to identify the type of information of user U required by the inquiry information. The instruction information includes a sentence instructing the generation AI to identify the type of information of user U required by the inquiry information. The type of information of user U may be, for example, user U's age, gender, place of residence, occupation, type of interests, type of behavioral pattern, etc., but is not limited to these examples.

[0075] In addition, the target personal agent TPA has an information identification list that includes the type of information of user U and one or more characteristic words, and can identify information of a type that corresponds to the characteristic word included in the inquiry information from among the characteristic words in the information identification list as the information of user U that is required in the inquiry information.

[0076] The target personal agent TPA has, for example, answerability information for each type of service, which indicates whether or not an answer can be given for each type of information from the user U, and such answerability information is set, for example, by the user U of the terminal device 2 having the target personal agent TPA.

[0077] The target individual agent TPA generates answer information including information on the unspecified parameters if the answerability information indicates that an answer is possible for the type of information of the specified user U, and generates answer information indicating that an answer is not possible if this is not the case. The target individual agent TPA generates answer information including the information of the specified type of user U, and outputs the generated answer information to the group agent GA.

[0078] Furthermore, the target personal agent TPA may have, for example, inquiry necessity information for each type of service, which indicates whether or not an inquiry to the user U is necessary for each type of information of the user U. The inquiry necessity information is set, for example, by the user U of the terminal device 2 having the target personal agent TPA.

[0079] In this case, if the inquiry necessity information indicates that an inquiry to user U is necessary for the type of information of the identified user U, the target personal agent TPA will pop up an inquiry message in the display area of ​​the terminal device 2, asking whether it is okay to output answer information including the identified type of information of user U.

[0080] When the user U inputs affirmative information (for example, the string "yes" or the string "OK") in response to the pop-up displayed inquiry message, the target individual agent TPA outputs the generated response information to the group agent GA.

[0081] The group agent GA performs steps S71, S72, . . . , S7 mIn response to the inquiry, one or more target personal agents TPA perform steps S81, S82, ..., S8 m Using the response information provided in step S9, the service is provided to group A (step S9). The process of step S9 will be explained below by dividing it into steps S9-1, S9-2, and S9-3.

[0082] In step S9, the group agent GA acquires the response information output from each target individual agent TPA, and determines the values ​​of the unset parameters based on the acquired response information (step S9-1).

[0083] For example, if the unspecified parameter is a cuisine genre, the group agent GA determines the value of the unspecified parameter in the answer information output from each target individual agent TPA based on the cuisine genre preferred by each user U. For example, the group agent GA determines the cuisine genre preferred by a predetermined percentage (e.g., more than 50%) or more of the users U belonging to group A as the value of the unspecified parameter.

[0084] The group agent GA can also estimate the persona of group A based on the response information output from the target individual agent TPA. For example, when the response information is m If the attribute information is group A, the persona of group A is determined based on whether or not group A has various interests, the number of people in group A, the ages of group A (for example, the ages from youngest to oldest or the average age), and the gender of the group.

[0085] The group agent GA can determine the values ​​of the unspecified parameters based on the persona of group A. For example, suppose the specified service type is a restaurant search service, group A is a group of four men in their 40s who like yakiniku, and the unspecified parameters are the number of people and the food genre. In this case, the group agent GA determines that the parameter for the number of people is 4 and the parameter for the food genre is yakiniku.

[0086] The group agent GA acquires service information, which is information about the service, from the service providing device 3 based on the type of service identified in step S6-1 and the values ​​of multiple parameters corresponding to that type of service, including the values ​​of the unidentified parameters determined in step S9-1 (step S9-2).

[0087] For example, if the service type identified in step S6-1 is a restaurant search service, the group agent GA specifies the restaurant search service and sends a search request containing values ​​for the restaurant area, cuisine type, planned dining date, time, and number of people to the service providing device 3 via the service providing device 3's API.

[0088] The service providing device 3 searches for a plurality of restaurants in response to the search request and acquires the search results as information on the service of the service type identified in step S6-1. The search results include, for example, information such as the name, location, food category, and description of each of the searched restaurants, but are not limited to these examples.

[0089] In addition, if the service type identified in step S6-1 is a hotel reservation service, the group agent GA specifies the hotel reservation service and sends a reservation request including values ​​for the hotel area, planned stay date, time, and number of people to the service providing device 3 via the API of the service providing device 3.

[0090] The service providing device 3 performs reservation processing in response to the reservation request, and acquires the result of the reservation processing as information on the service of the service type identified in step S6-1. The result of the reservation processing includes, for example, information such as the character string "Reservation completed" and information indicating the reservation content, but is not limited to such examples.

[0091] The group agent GA provides the service to group A by providing the service information acquired in step S9-2 to group A (step S9-3). In step S9-3, the group agent GA provides the service information acquired in step S9-2 to users U1, U2, . . . , U belonging to group A. m Terminal devices 21, 22,...,2 m By sending the service information acquired in step S9-2 to group A, the service information is provided to group A.

[0092] Terminal devices 21, 22, . . . , 2 m When receiving the service information from the group agent GA, the group agent GA displays the received service information as a chat message in the chat room where the chat message accepted in step S5 is displayed.

[0093] In addition, terminal devices 21, 22, . . . , 2 m The service information may be displayed in the chat room in a format different from that of a chat message, or may be displayed in a pop-up window superimposed on the chat room.

[0094] 1(b), restaurant information CTA1, restaurant information CTA2, restaurant information CTM_A1, and restaurant information CTM_A2 are displayed in the chat room of group A on terminal device 21. Restaurant information CTA1 and restaurant information CTM_A1 are information on DDD Chinese restaurants, and restaurant information CTA2 and restaurant information CTM_A2 are information on FFF Sichuan restaurants.

[0095] Restaurant information CTM_A1 and restaurant information CTM_A2 are message-format information included in chat message CTM5. Restaurant information CTM_A1 and restaurant information CTM_A2 are displayed in the same display format as chat messages on the group chat screen. Restaurant information CTA1 and restaurant information CTA2 are banner-format information that includes images, text, and links.

[0096] In this way, the information processing device 1 identifies multiple personal agents PA that are each linked to a corresponding user among the multiple grouped users U, and queries one or more of these multiple personal agents PA for specific information to be used for providing services to the group corresponding to the multiple users U. The information processing device 1 then provides services to the group using information provided by the one or more personal agents PA in response to the query. This allows the information processing device 1 to improve the convenience of providing services to the multiple grouped users U.

[0097] The information processing device 1 and the terminal devices 21-2 perform the above-described processing. m The configuration of the information processing system including the above will be described in detail.

[0098] [2. Information Processing System Configuration] 2 is a diagram showing an example of the configuration of an information processing system according to an embodiment. As shown in FIG. 2, an information processing system 200 according to an embodiment includes an information processing device 1 and a plurality of terminal devices 21, 22, . . . , 2 n and the service providing device 3. n is, for example, an integer equal to or greater than the above-mentioned m.

[0099] A plurality of terminal devices 21, 22, . . . , 2 n are different users U1, U2, . n Terminal devices 21, 22,...,2 used by nExamples of the device include a laptop computer, a desktop computer, a smartphone, a tablet computer, and a wearable device, such as, but not limited to, smart glasses or a smart watch.

[0100] Information processing device 1, terminal devices 21, 22, . . . , 2 n , and the service providing device 3 are connected to each other via a network N in a wired or wireless manner so as to be able to communicate with each other. Note that the information processing system 200 shown in FIG. 2 may include a plurality of information processing devices 1 and service providing devices 3.

[0101] The network N includes, for example, a WAN (Wide Area Network) such as the Internet and a mobile communication network such as LTE (Long Term Evolution), 4G (4th Generation), and 5G (5th Generation: 5th generation mobile communication system).

[0102] The terminal device 2 can connect to the network N via short-range wireless communication such as a mobile communication network, Bluetooth (registered trademark), or wireless LAN (Local Area Network), and communicate with the information processing device 1 and the service providing device 3.

[0103] 3. Configuration of Information Processing Device 1 3 is a diagram showing an example of the configuration of the information processing device 1 according to the embodiment. As shown in FIG. 3, the information processing device 1 includes a communication unit 10, a storage unit 11, and a processing unit 12.

[0104] [3.1. Communication Unit 10] The communication unit 10 is realized by, for example, a communication module or a network interface card (NIC). The communication unit 10 is connected to a network N by wire or wirelessly, and transmits and receives information to and from various other devices. For example, the communication unit 10 transmits and receives information to and from the terminal device 2 via the network N.

[0105] [3.2. Storage section 11] The storage unit 11 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. The storage unit 11 has a user information storage unit 20, a chat setting information storage unit 21, and a conversation history storage unit 22.

[0106] [3.2.1. User information storage unit 20] The user information storage unit 20 stores user information including information about the user U. Fig. 4 is a diagram showing an example of a user information table stored in the user information storage unit 20 of the information processing device 1 according to the embodiment. As shown in Fig. 4, the user information table stored in the user information storage unit 20 includes items such as "user ID," "user name," "user information," and "personal agent ID."

[0107] "User ID" is identification information that identifies user U, and is information assigned to each user U. "User name" is the name of user U corresponding to the "user ID." "User information" is the attribute information and behavioral history of user U corresponding to the "user ID."

[0108] The attribute information of user U includes, for example, psychographic attribute information, demographic attribute information, etc. Demographic attributes include, for example, gender, age, place of residence, and occupation, while psychographic attributes include interests such as travel, clothing, cars, and religion, lifestyle, thoughts, and ideological tendencies.

[0109] The behavioral history of user U is the behavioral history of user U in online services and offline. The behavioral history of user U in online services includes information such as search history, browsing history, posting history, and purchase history.

[0110] The search history includes information on search queries used in past searches by the user U and content viewed by the user U from among the search results. Information on search queries includes, for example, search keywords and search phrases.

[0111] The browsing history includes, for example, information indicating the content that the user U has viewed on the online service, the posting history includes, for example, information indicating the content (e.g., reviews, comments, etc.) that the user U has posted in the past on the online service, and the purchase history includes information on the items of transactions that the user U has made in the past.

[0112] The offline behavioral history of user U may be, for example, user U's offline movement history, user U's usage history at physical stores (including product and service purchase history), etc., but is not limited to such examples.

[0113] The "personal agent ID" is identification information that identifies the personal agent PA of the user U corresponding to the "user ID," and is information that is assigned to each personal agent PA. As described above, the personal agent PA is a service agent for each user U, and may be, for example, something like Auto-GPT.

[0114] 3.2.2. Chat Setting Information Storage Unit 21 The chat setting information storage unit 21 stores various setting information for the chat service. Fig. 5 is a diagram showing an example of a chat setting information table stored in the chat setting information storage unit 21 of the information processing device 1 according to the embodiment.

[0115] As shown in FIG. 5, the chat setting information table stored in the chat setting information storage unit 21 includes items such as "group ID," "group name," "participating user ID," and "group agent information."

[0116] The "group ID" is an identifier for identifying a chat group, and is information assigned to each chat group. The "group name" is information indicating the name of the chat group associated with the "group ID."

[0117] The "participating user ID" includes the user ID of each user U participating in the chat group associated with the "group ID." The "group agent information" is information about the group agent GA of the chat group associated with the "group ID," and includes the agent ID, setting information, and retained information of the group agent GA. The group agent GA may be, for example, a service agent for each group, such as Auto-GPT. The group agent GA may also be, for example, a service agent assigned to multiple groups.

[0118] Although not shown, the chat setting information table shown in FIG. 6 also includes setting information other than chat groups, such as setting information for one-to-one chat and one-to-many chat.

[0119] 3.2.3. Conversation History Storage Unit 22 The conversation history storage unit 22 stores various conversation histories in the chat service. Fig. 6 is a diagram showing an example of a conversation history table stored in the conversation history storage unit 22 of the information processing device 1 according to the embodiment. As shown in Fig. 6, the conversation history table stored in the conversation history storage unit 22 includes items such as "message ID," "user ID," "group ID," "date and time," and "message."

[0120] "Message ID" is an identifier that identifies a chat message and is information assigned to each chat message. "User ID" is the user ID of the user U who posted the chat message corresponding to the "Message ID." "Group ID" is the group ID of the chat group corresponding to the chat room in which the chat message corresponding to the "Message ID" was posted.

[0121] "Date and time" is information indicating the date and time when the chat message corresponding to the "Message ID" was posted. "Message" is the chat message corresponding to the "Message ID." Although not shown, the chat setting information table shown in FIG. 6 also includes conversation history other than that of chat groups, such as conversation history of one-to-one chats and conversation history of one-to-many chats.

[0122] [3.3. Processing Unit 12] The processing unit 12 is a controller, and is realized by a processor such as a CPU (Central Processing Unit) or an MPU (Micro Processing Unit) executing various programs (corresponding to examples of information processing programs) stored in a storage device inside the information processing device 1 using RAM or the like as a working area.

[0123] The processing unit 12 is a controller, and may be realized by an integrated circuit such as an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or a general purpose graphic processing unit (GPGPU).

[0124] As shown in FIG. 3, the processing unit 12 includes a receiving unit 30, a setting unit 31, a providing unit 32, and group agent processing units 331 to 333. p and realizes or executes the information processing functions and actions described below. p is the number of group agents and is an integer of 2 or more.

[0125] The internal configuration of the processing unit 12 is not limited to the configuration shown in Fig. 3, and may be other configurations as long as they are configured to perform information processing, which will be described later. pWhen each of these is referred to without being individually distinguished, they may be referred to as a group agent processing unit 33.

[0126] 3.3.1. Reception unit 30 The reception unit 30 receives various information. For example, the reception unit 30 receives a posting request transmitted from the terminal device 2. The posting request includes information such as a chat message, a group ID, and a user ID. The reception unit 30 updates the conversation history table stored in the conversation history storage unit 22 based on the posting request.

[0127] The reception unit 30 also receives a chat group setting request transmitted from the terminal device 2. The chat group setting request is a request to set up a group of multiple users U for a group chat among the multiple users U, and includes the user IDs of the multiple users U to be grouped, the name of the group, etc.

[0128] The reception unit 30 also receives a user addition request transmitted from the terminal device 2. The user addition request includes a group ID and the user ID of a user U to be excluded from the group among multiple users U grouped by the group ID.

[0129] The reception unit 30 also receives a user deletion request transmitted from the terminal device 2. The user addition request includes a group ID and the user ID of a user U to be added to the group from among multiple users U grouped by the group ID.

[0130] [3.3.2. Setting unit 31] When the receiving unit 30 receives a group setting request, the setting unit 31 sets the group information included in the group setting request based on the group setting request. The group information includes a group ID, a group name, a participating user ID, and group agent information.

[0131] For example, the setting unit 31 adds group information to the chat setting information table stored in the chat setting information storage unit 21 based on the chat group setting request received by the receiving unit 30 .

[0132] The setting unit 31 also updates the group information in the chat setting information table based on a user addition request accepted by the accepting unit 30. The setting unit 31 also updates the group information in the chat setting information table based on a user deletion request accepted by the accepting unit 30.

[0133] [3.3.3.Providing Department 32] The providing unit 32 provides various information. For example, the providing unit 32 transmits the chat message included in the posting request accepted by the accepting unit 30 to a terminal device 2 of a user U who is the destination of the chat message and is other than the terminal device 2 that sent the posting request.

[0134] [3.3.4. Group Agent Processing Unit 33] The group agent processing unit 33 realizes the function of a group agent. Fig. 7 is a diagram showing an example of the configuration of the group agent processing unit 33 in the processing unit 12 of the information processing device 1 according to the embodiment.

[0135] 7, group agent processing unit 33 includes a receiving unit 40, a specifying unit 41, an estimating unit 42, an inquiry unit 43, and a providing unit 44. Below, the receiving unit 40, the specifying unit 41, the estimating unit 42, the inquiry unit 43, and the providing unit 44 will each be described in detail.

[0136] [3.3.4.1. Reception unit 40] The receiving unit 40 receives various types of information. The receiving unit 40 receives input information that is information input by the user U.

[0137] The receiving unit 40 receives, for example, input information including information related to a service from the user U. For example, the receiving unit 40 receives input information including a chat message posted by the user U and including information related to the service.

[0138] The information about the service is information about the service provided by the service providing device 3, but may also be information about a service provided by a service providing device other than the service providing device 3.

[0139] [3.3.4.2. Specification part 41] The identification unit 41 performs various identifications. Fig. 8 is a diagram showing an example of the configuration of the identification unit 41 in the group agent processing unit 33 of the information processing device 1 according to the embodiment. As shown in Fig. 8, the identification unit 41 includes an individual agent identification unit 50, an information identification unit 51, and an inquiry destination identification unit 52.

[0140] The personal agent identification unit 50 identifies a plurality of personal agents PA each associated with a corresponding user from among the grouped plurality of users U. For example, the personal agent identification unit 50 identifies a personal agent of a chat application to which the user ID of the user U is set as the personal agent of that user U. The user ID is the account of the user U set in the chat application.

[0141] The personal agent identification unit 50 identifies multiple personal agents PA of multiple users U grouped in each group based on the user information table stored in the user information storage unit 20 and the chat setting information table stored in the chat setting information storage unit 21.

[0142] When the user information table is in the state shown in Fig. 4 and the chat setting information table is in the state shown in Fig. 5, the user IDs of the multiple users U grouped in group A are "U1," "U2," and "U3." Therefore, the personal agent identification unit 50 identifies personal agents PA1, PA2, and PA3, whose personal agent IDs are PA1, PA2, and PA3, as personal agents PA of group A.

[0143] Based on the input information received by the receiving unit 40, the information identifying unit 51 identifies predetermined information to be used for providing a service to a group to which the user U who input the input information belongs.

[0144] For example, based on the input information received by the receiving unit 40, the information identifying unit 51 identifies predetermined information used to provide services to the group in the chat room to which the user U has input the input information.

[0145] The information identifying unit 51 executes a process for identifying predetermined information regardless of whether or not the input information accepted by the accepting unit 40 includes information related to a service, but is not limited to this example.

[0146] For example, the information identification unit 51 can execute a process to identify specified information only when the input information accepted by the receiving unit 40 contains a specific term or phrase, or can execute a process to identify specified information only when the input information accepted by the receiving unit 40 does not contain a specific term or phrase.

[0147] The information identification unit 51 includes a first identification processing unit 60 and a second identification processing unit 61. Based on the input information received by the reception unit 40, the first identification processing unit 60 identifies the type of service and the values ​​of one or more parameters among a plurality of parameters used to provide the service of that type.

[0148] The types of services include, but are not limited to, restaurant search services, hotel search services, restaurant reservation services, hotel reservation services, advertisement distribution services, map information provision services, and e-commerce services, for example.

[0149] The multiple parameters used for providing the service include necessary parameters, which are parameters necessary for providing the service, and additional parameters, which are parameters for improving the accuracy of providing the service.

[0150] If the service type is a restaurant search service, the required parameters include, for example, the area of ​​the restaurant, the planned date and time of dining, and the number of people, and the additional parameters include, but are not limited to, the type of food, price range, seating (terrace, table, tatami room), facilities (wheelchair, pets allowed), rating, allergenic ingredients, display order, and maximum number of items to be acquired.

[0151] Furthermore, if the service type is a hotel search service, the required parameters include, for example, the hotel area, planned stay date, time, number of people, etc., and additional parameters include, but are not limited to, the number of rooms, number of adults, number of children, rating, price range, facilities and services (wifi, Japanese-style room, Western-style room, double bed, single bed, non-smoking, smoking), display order, and maximum number of acquisitions.

[0152] Furthermore, if the service type is a restaurant reservation service, the required parameters include, for example, the area of ​​the restaurant, the planned date and time of dining, and the number of people, and the additional parameters include, but are not limited to, the type of food, seating (terrace, table, tatami room), allergenic ingredients, display order, and the maximum number of items that can be acquired.

[0153] Furthermore, if the service type is a hotel reservation service, the required parameters include, for example, the hotel area, the planned date and time of stay, and the number of people, and the additional parameters include, but are not limited to, the number of rooms, the number of adults, the number of children, the price range, the room type, facilities and services (wifi, Japanese-style room, Western-style room, double bed, single bed, non-smoking, smoking), display order, and the maximum number of acquisitions.

[0154] The first identification processing unit 60 is capable of identifying, for example, the values ​​of multiple parameters used to provide a service, and identifies the values ​​of parameters among these multiple parameters whose values ​​can be identified from the input information accepted by the accepting unit 40.

[0155] For example, the first identification processing unit 60 identifies the values ​​of one or more required parameters when the values ​​of one or more required parameters can be identified based on the input information accepted by the accepting unit 40. Furthermore, the first identification processing unit 60 identifies the values ​​of one or more additional parameters when the values ​​of one or more additional parameters can be identified based on the input information accepted by the accepting unit 40.

[0156] The first identification processing unit 60, for example, uses a generation AI to identify a service type and the values ​​of one or more parameters from multiple parameters used to provide a service of that service type based on information about the service accepted by the acceptance unit 40.

[0157] The generation AI is, for example, a text generation AI. The text generation AI is, for example, a large-scale language model trained to estimate and output the next token from an input token sequence, such as a transformer-based model or an RNN-based model. An example of a transformer-based model is, but is not limited to, GPT. An example of an RNN-based model is, but is not limited to, RWKV.

[0158] The generation AI may be a language model that has been trained (for example, fine-tuned) specifically for generating answer information. The generation AI may be located in an external information processing device, and the first specification processing unit 60 uses the generation AI via an API, but the generation AI may also be located within the information processing device 1.

[0159] The first identification processing unit 60 inputs information including instruction information and a chat message accepted as input information by the accepting unit 40 to the generation AI, and can cause the generation AI to output a service type and one or more parameter values. The instruction information is information that instructs the generation AI to identify a service type and one or more parameter values ​​used to provide the service of that type from the chat message accepted as input information by the accepting unit 40.

[0160] The instruction information includes, for example, the string "Please identify the service type and the parameter values ​​used to provide that type of service from the following message. Please identify the service type from the service type list below, and the parameter values ​​from the parameter list below. Please output the identification results in the output format below," as well as a service type list, a parameter list, and output format information.

[0161] The service type list includes, for example, information linking a service type with information indicating the content of the service for each service type. The parameter list includes, for example, information linking a parameter with information indicating the content of the parameter for each service type. Note that the instruction information is not limited to the above example, and may be any information that can output the type of service and the value of the parameter used to provide the service of that type from a message.

[0162] Furthermore, if the generation AI is GPT provided by OpenAI, the function calling function can be used to have the generation AI output the service type and one or more parameter values. In this case, the information input to the generation AI includes, for each service type, information indicating the definition of the service type and information indicating the definition of each parameter.

[0163] Furthermore, if the generation AI is fine-tuned to output the type of service and the parameter values ​​used to provide that type of service from the message, the input information input to the generation AI does not need to include instruction information.

[0164] The first identification processing unit 60 may also be configured to identify the type of service and the parameter values ​​used to provide that type of service from the message using a known slot-filling technique that does not use a generation AI.

[0165] The second identification processing unit 61 identifies, as predetermined information, information on unspecified parameters, which are parameters whose values ​​have not been specified by the first identification processing unit 60, from among the multiple parameters corresponding to the service type specified by the first identification processing unit 60.

[0166] The second identification processing unit 61 identifies a plurality of parameters associated with the service type identified by the first identification processing unit 60. The second identification processing unit 61 associates the service type with a plurality of parameters for each service and stores them. The plurality of parameters include the above-mentioned required parameters and additional parameters.

[0167] The second identification processing unit 61 identifies a plurality of parameters linked to the service type identified by the first identification processing unit 60 from among the stored service types for each service and a plurality of parameters for each service type.

[0168] For example, the second identification processing unit 61 identifies, as unspecified parameters, necessary parameters whose values ​​have not been specified by the first identification processing unit 60 among the multiple parameters linked to the service type specified by the first identification processing unit 60. Furthermore, the second identification processing unit 61 can also identify, as unspecified parameters, additional parameters that have not been specified in addition to the necessary parameters whose values ​​have not been specified among the multiple parameters.

[0169] In addition, when instruction information is set so that information on parameters whose values ​​are not yet specified is output from the generation AI, the second identification processing unit 61 can also identify unspecified parameters from among multiple parameters linked to the service type identified by the first identification processing unit 60 based on the information output from the generation AI.

[0170] The inquiry destination specifying unit 52 specifies one or more personal agents PA based on the predetermined information specified by the information specifying unit 51 .

[0171] For example, if the predetermined information identified by the second identification processing unit 61 is information related to all users U of the group, the inquiry destination identification unit 52 identifies the personal agents PA of all users in the group as the target personal agents TPA.

[0172] Also, 1,PA2,···,PA m If the specified information identified by the second identification processing unit 61 is information related to some of the users U among multiple users U belonging to the group, the personal agents PA of some of the users U are identified as the target personal agents TPA.

[0173] The inquiry destination specifying unit 52 specifies, for example, among multiple users U belonging to the group, the personal agents PA of users U other than the user U who has already acquired the value of the parameter corresponding to the specified information as the target personal agent TPA.

[0174] Furthermore, the inquiry destination specifying unit 52 stores information on the personal agent PA to be the inquiry destination for each parameter, and can also specify the personal agent PA linked to the parameter corresponding to the predetermined information as the target personal agent TPA.

[0175] [3.3.4.3. Estimation section 42] The estimation unit 42 performs various estimations. The estimation unit 42 estimates the situation of a group in a chat room using a generation AI based on the message histories of multiple users U in the chat room.

[0176] The group situation may be, but is not limited to, the type of topic of the group, the depth of the topic of the group, the atmosphere of the group, the hierarchical relationship of the users U in the group, the level of intimacy of the group, the level of humor, etc.

[0177] The estimation unit 42 inputs, for example, information including the message history of multiple users U in a chat room and instruction information instructing the generation AI to estimate the group situation as input information, and causes the generation AI to estimate the group situation in the chat room.

[0178] The instruction information includes, for example, the string "The given message history is the message history of multiple users U in a chat room. Based on this message history, please estimate the situation of the group in the chat room. The situation is defined as follows." and situation definition information.

[0179] The instruction information may include information showing examples linking message history examples with situation examples, thereby enabling the generation AI to accurately estimate the situation. The generation AI may also be a generation AI trained by fine tuning or the like using a data set of message histories and situations of multiple users U, in which case the input information input to the generation AI may not include instruction information.

[0180] Furthermore, the estimation unit 42 estimates the characteristics of the group using the generation AI based on the attribute information of multiple users U in the chat room. For example, the estimation unit 42 estimates the persona of the chat group as the group's characteristics based on the attribute information of multiple users U belonging to the chat group.

[0181] For example, the estimation unit 42 estimates a characteristic common to the multiple users U as the persona of group A based on the attribute information of the multiple users U. The characteristic common to the multiple users U may be, for example, an attribute, interest, or behavioral pattern common to the multiple users U, but is not limited to such examples.

[0182] Common attributes include, but are not limited to, age, gender, family, occupation, etc. Common interests include, but are not limited to, car enthusiasts, shopping enthusiasts, and travel enthusiasts. Common behavioral patterns include, but are not limited to, traveling at least once a month, eating out on weekday nights at least three times a week, and going shopping every weekend.

[0183] The estimation unit 42 can determine, for example, whether or not the group has various interests, the number of people in group A, the ages of group A (for example, the ages from youngest to oldest or the average age), the gender of the group, etc. as the persona of the group.

[0184] Personas of chat groups may be, for example, a group of four male office workers in their 40s who love yakiniku, a group of three male university students who love traveling to Osaka, or a group of 16 people in their 20s to 40s who love a particular restaurant, but are not limited to such examples.

[0185] [3.3.4.4. Inquiry section 43] The inquiry unit 43 makes various inquiries to the personal agent PA.

[0186] The inquiry unit 43 inquires of one or more personal agents PA identified by the inquiry destination identification unit 52 as target personal agents TPA, among the multiple personal agents PA identified by the personal agent identification unit 50, about specific information to be used for providing services to a group corresponding to multiple users U.

[0187] When inquiring about the predetermined information, the inquiry unit 43 provides the one or more personal agents with information indicating the estimation result by the estimation unit 42. The estimation result by the estimation unit 42 is, for example, one or both of the characteristics of the group and the situation of the group in the chat room.

[0188] 9 is a diagram showing an example of the configuration of the inquiry unit 43 in the group agent processing unit 33 of the information processing device 1 according to the embodiment. As shown in FIG. 9, the providing unit 44 includes a generation processing unit 53 and an output processing unit 54.

[0189] The generation processing unit 53 generates inquiry information indicating a sentence inquiring about the predetermined information identified by the information identifying unit 51 using the generation AI.

[0190] For example, the generation processing unit 53 inputs information including instruction information, which is information that instructs the generation of a sentence inquiring about the value of an unidentified parameter identified by the information identification unit 51, to the generation AI, and causes the generation AI to generate inquiry information.

[0191] If the service type identified by the information identification unit 51 is a restaurant search service and the unidentified parameter identified by the information identification unit 51 is a cuisine genre, the instruction information to be input to the generation AI includes, for example, the string "Please create a sentence inquiring about cuisine genres to search for restaurants that can be reserved."

[0192] The generation processing unit 53 has information for each service type in which instruction information is linked to each parameter, identifies instruction information corresponding to the unidentified parameter identified by the information identification unit 51, inputs information including the identified instruction information to the generation AI, and causes the generation AI to generate inquiry information.

[0193] Furthermore, the generation processing unit 53 has information for each service type in which each parameter is linked to inquiry information, and can also identify inquiry information corresponding to the unidentified parameter identified by the information identifying unit 51.

[0194] For example, if the service type identified by the information identification unit 51 is a restaurant search service and the unidentified parameter identified by the information identification unit 51 is a cuisine genre, the inquiry information may be, for example, the string "Search for restaurants that are available for reservations. What cuisine genre would you like to see at a restaurant?", but is not limited to such an example.

[0195] Furthermore, when the information used to determine the value of the unspecified parameter is information for generating a persona of a group, the generation processing unit 53 generates or determines information for inquiring about the attribute information of the user U as the inquiry information.

[0196] The output processing unit 54 outputs the inquiry information generated by the generation processing unit 53 to a target personal agent TPA, which is one or more personal agents PA. The output processing unit 54 outputs the inquiry information to the target personal agent TPA by transmitting the inquiry information generated by the generation processing unit 53 to the terminal device 2 including the target personal agent TPA via the communication unit 10.

[0197] In the terminal device 2, the target personal agent TPA has information about the user U and can generate answer information based on the information about the user U. The information about the user U includes information indicating the attributes of the user U, information indicating the schedule of the user U, information indicating the behavioral patterns of the user U, etc. For example, the target personal agent TPA generates answer information that includes information about the user U of a type corresponding to the inquiry information.

[0198] The target personal agent TPA inputs information including inquiry information and instruction information as input information to the generation AI, and causes the generation AI to identify the type of information of user U required by the inquiry information. The instruction information includes a sentence instructing the generation AI to identify the type of information of user U required by the inquiry information. The type of information of user U may be, for example, user U's age, gender, place of residence, occupation, type of interests, type of behavioral pattern, etc., but is not limited to these examples.

[0199] In addition, the target personal agent TPA has an information identification list that includes the type of information of user U and one or more characteristic words, and can identify information of a type that corresponds to the characteristic word included in the inquiry information from among the characteristic words in the information identification list as the information of user U that is required in the inquiry information.

[0200] The target personal agent TPA has, for example, answerability information for each type of service, which indicates whether or not an answer can be given for each type of information from the user U, and such answerability information is set, for example, by the user U of the terminal device 2 having the target personal agent TPA.

[0201] The target individual agent TPA generates answer information including information on the unspecified parameters if the answerability information indicates that an answer is possible for the type of information of the specified user U, and generates answer information indicating that an answer is not possible if this is not the case. The target individual agent TPA generates answer information including the information of the specified type of user U, and outputs the generated answer information to the group agent GA.

[0202] The target personal agent TPA can also inquire of the user U about whether or not answer information can be provided, and provide answer information based on the answer from the user U. For example, the target personal agent TPA provides answer information when the user U gives permission to provide answer information.

[0203] The target personal agent TPA may have, for example, inquiry necessity information for each type of service, which indicates whether or not an inquiry to the user U is necessary for each type of information of the user U. The inquiry necessity information is set, for example, by the user U of the terminal device 2 having the target personal agent TPA.

[0204] In this case, if the inquiry necessity information indicates that an inquiry to user U is necessary for the type of information of the identified user U, the target personal agent TPA will pop up an inquiry message in the display area of ​​the terminal device 2, asking whether it is okay to output answer information including the identified type of information of user U.

[0205] When the user U inputs affirmative information (for example, the string "yes" or the string "OK") in response to the pop-up displayed inquiry message, the target individual agent TPA outputs the generated response information to the group agent GA.

[0206] Furthermore, when inquiring about predetermined information, the output processing unit 54 can also provide one or more personal agents with information indicating the results of estimation by the estimation unit 42. The results of estimation by the estimation unit 42 are, for example, one or both of the characteristics of the group and the situation of the group in the chat room.

[0207] The target individual agent TPA has answerability information indicating whether an answer is possible for each group characteristic or situation, and determines whether to generate answer information including information on unspecified parameters based on the estimation results by the estimation unit 42.

[0208] For example, if the answerability information indicates that an answer is possible for the characteristics or situation of the group estimated by the estimation unit 42, the target individual agent TPA generates answer information including information about the unspecified parameters, and if not, generates answer information indicating that an answer is not possible.

[0209] In addition, the target personal agent TPA has inquiry necessity information indicating whether an inquiry to the user U is necessary for each group characteristic or situation, and based on the estimation result by the estimation unit 42, inquires whether it is okay to output answer information including information of the identified type of user U.

[0210] In addition, the target individual agent TPA has information indicating the type of information that can be answered for each combination of one or more of the group's characteristics and situations, and can also output answer information including information on the type of information that can be answered corresponding to the group's characteristics and situations indicated in the estimation result by the estimation unit 42.

[0211] [3.3.4.5.Providing Department 44] The providing unit 44 provides various information, and uses information provided by one or more personal agents PA in response to an inquiry by the inquiry unit 43 to provide a service to the group.

[0212] 10 is a diagram showing an example of the configuration of the providing unit 44 in the group agent processing unit 33 of the information processing device 1 according to the embodiment. As shown in FIG. 10, the providing unit 44 includes an estimation processing unit 56, a determination processing unit 57, an acquisition processing unit 58, and a providing processing unit 59.

[0213] The estimation processing unit 56 estimates the situation of the group in the chat room using the generation AI based on the message histories of multiple users U in the chat room. The estimation processing unit 56 estimates the situation of the group in the chat room by processing similar to that of the estimation unit 42.

[0214] Furthermore, the estimation processing unit 56 estimates the characteristics of the group in the chat room using the generation AI based on the attribute information of multiple users U in the chat room. The estimation processing unit 56 estimates the characteristics of the group by processing similar to that of the estimation unit 42.

[0215] The estimation processing unit 56 can also estimate the persona of the group based on the response information output from the target personal agent TPA. For example, when the response information is attribute information of each user U of the group, the estimation processing unit 56 estimates the persona of the group based on the attribute information of each user U by processing similar to that of the estimation unit 42.

[0216] The determination processing unit 57 determines the value of the unspecified parameter based on information provided by one or more personal agents in response to an inquiry by the inquiry unit 43 .

[0217] For example, when the unspecified parameter is a cuisine genre, the determination processing unit 57 determines the value of the unspecified parameter in the answer information output from each target personal agent TPA based on the cuisine genre of each user U. For example, the determination processing unit 57 determines the cuisine genre that is common to a predetermined percentage (e.g., more than 50%) or more of the users U belonging to the group as the value of the unspecified parameter.

[0218] If information in response to an inquiry by the inquiry unit 43 is not provided from one or more personal agents PA, the determination processing unit 57 determines the value of the unidentified parameter based on the estimation result by the estimation processing unit 56.

[0219] The determination processing unit 57 can determine the value of the unspecified parameter based on, for example, the persona of the group estimated by the estimation processing unit 56. For example, assume that the service type identified by the information identification unit 51 is a restaurant search service, the persona of the group estimated by the estimation processing unit 56 is a group of four men in their 40s who like yakiniku, and the unspecified parameters are the number of people and the food genre. In this case, the determination processing unit 57 determines that the parameter of the number of people is 4 and the parameter of the food genre is yakiniku.

[0220] Furthermore, the determination processing unit 57 can determine the value of the unspecified parameter based on, for example, the situation of the group estimated by the estimation processing unit 56. For example, assume that the service type identified by the information identification unit 51 is a restaurant search service, the topic type of the group estimated by the estimation processing unit 56 is Chinese food, and the unspecified parameter is a food genre. In this case, the determination processing unit 57 determines that the parameter for the food genre is yakiniku.

[0221] Also, assume that the service type identified by the information identification unit 51 is a restaurant search service, the group intimacy estimated by the estimation processing unit 56 is a high intimacy level, and the unidentified parameter is a food genre. In this case, the determination processing unit 57 determines that the food genre parameter is izakaya cuisine. Furthermore, if the group intimacy level is low, the determination processing unit 57 determines that the food genre parameter is cafe.

[0222] The acquisition processing unit 58 acquires service information, which is information about the service, from the service providing device that provides the service based on the values ​​of multiple parameters including the values ​​of the unidentified parameters determined by the determination processing unit 57 and the type of service identified by the first identification processing unit 60.

[0223] For example, if the information identification unit 51 determines that the service type is a restaurant search service, the acquisition processing unit 58 specifies the restaurant search service and sends a search request including values ​​for the restaurant area, food genre, planned dining date, time, and number of people to the service providing device 3 via the service providing device 3's API.

[0224] The service providing device 3 searches for a plurality of restaurants in response to the search request, and acquires the search results as information on the service of the service type identified by the information identifying unit 51. The search results include, for example, information such as the name, location, food category, and description of each of the searched restaurants, but are not limited to these examples.

[0225] In addition, if the information identification unit 51 determines that the service type is a hotel reservation service, the acquisition processing unit 58 specifies the hotel reservation service and sends a reservation request including values ​​for the hotel area, planned stay date, time, and number of people to the service providing device 3 via the API of the service providing device 3.

[0226] The service providing device 3 performs reservation processing in response to the reservation request, and acquires the result of the reservation processing as service information of the service type by the information identifying unit 51. The result of the reservation processing includes, for example, information such as the character string "Reservation completed" and information indicating the reservation content, but is not limited to such examples.

[0227] The provision processing unit 59 provides the group with the service information acquired by the acquisition processing unit 58. The provision processing unit 59 provides the group with the service information acquired by the acquisition processing unit 58 by transmitting the service information acquired by the acquisition processing unit 58 to the terminal device 2 of the user U who belongs to the group.

[0228] When the terminal device 2 receives the service information from the provision processing unit 59, it displays the received service information as a chat message in the group's chat room. Furthermore, the terminal device 2 can display the received service information in the chat room in a format different from that of the chat message, or display the received service information in a pop-up window superimposed on the chat room.

[0229] 11 is a diagram showing an example of service information provided to the terminal device 2 by the providing unit 44 in the processing unit 12 of the information processing device 1 according to the embodiment and displayed on the terminal device 2. A chat room screen 70 shown in FIG. 11 is a chat room screen for group A.

[0230] 11, restaurant information CTA1, restaurant information CTA2, restaurant information CTM_A1, and restaurant information CTM_A2 are displayed in the chat room of group A on chat room screen 70. Restaurant information CTA1 and restaurant information CTM_A1 are information on DDD Chinese restaurants, and restaurant information CTA2 and restaurant information CTM_A2 are information on FFF Sichuan restaurants.

[0231] Restaurant information CTM_A1 and restaurant information CTM_A2 are message-format information included in chat message CTM9. Restaurant information CTM_A1 and restaurant information CTM_A2 are displayed in the same display format as chat messages on the group chat screen. Restaurant information CTA1 and restaurant information CTA2 are banner-format information including images, text, and links.

[0232] [4. Processing Procedure] Next, a procedure of information processing by the processing unit 12 of the information processing device 1 according to the embodiment will be described. Fig. 12 is a flowchart showing an example of information processing by the processing unit 12 of the information processing device 1 according to the embodiment.

[0233] 12, the processing unit 12 of the information processing device 1 determines whether or not a posting request has been received (step S10). If the processing unit 12 determines that the posting request has been received (step S10: Yes), the processing unit 12 outputs the posting request to the terminal device 2 of the user U in the same group as the terminal device 2 that sent the posting request (step S11).

[0234] Next, when the processing of step S11 is completed or when it is determined that a posting request has not been received (step S10: No), the processing unit 12 determines whether or not it is time to group (step S12). For example, when a chat group setting request has been received, the processing unit 12 determines that it is time to group.

[0235] When the processing unit 12 determines that it is time to group (step S12: Yes), it identifies the personal agent PA of each grouped user U (step S13) and sets a group agent GA for the group (step S14).

[0236] When the processing of step S11 is completed or when it is determined that the timing for grouping has not arrived (step S12: No), the processing unit 12 determines whether input information has been received from a user U of the group (step S15).

[0237] If the processing unit 12 determines that the input information has been received (step S15: Yes), it identifies the type of service and the value of the parameter based on the input information (step S16). Furthermore, the processing unit 12 identifies predetermined information based on the type of service and the value of the parameter identified in step S16 (step S17), and queries the identified target personal agent for the predetermined information (step S18).

[0238] The processing unit 12 acquires service information based on the response information in response to the inquiry in step S18 (step S19), and then provides the service information acquired in step S19 (step S20).

[0239] When the processing of step S20 is completed or when it is determined that no input information has been received (step S15: No), the processing unit 12 determines whether or not the operation end timing has arrived (step S21). The processing unit 12 determines that the operation end timing has arrived when, for example, the power of the information processing device 1 is turned off.

[0240] If the processing unit 12 determines that the operation end time has not yet arrived (step S21: No), it proceeds to step S10, and if it determines that the operation end time has arrived (step S21: Yes), it terminates the processing shown in Figure 12.

[0241] [5. Modifications] Furthermore, in the above description, a chat group has been taken as an example of a group of user U, but the processing unit 12 of the information processing device 1 can perform similar processing on groups other than chat groups.

[0242] Some or all of the functions of the above-described service providing device 3 may be realized by the information processing device 1. For example, the information processing device 1 may have a configuration in which some or all of the above-described service providing device 3 is included instead of the information processing device 1.

[0243] Furthermore, some or all of the functions of the information processing device 1 described above may be implemented by one of the terminal devices 2 of the multiple users U included in the group. For example, the terminal device 2 may have a configuration that replaces some or all of the functions of the information processing device 1 described above.

[0244] The setting unit 31 can also set reply availability information and inquiry necessity information based on the attribute information of the user U. In this way, reply availability information and inquiry necessity information according to the attributes of the user U are set.

[0245] In the above-described example, the processing unit 12 of the information processing device 1 inquires of one or more personal agents among the plurality of personal agents linked to the plurality of grouped users U about predetermined information used to provide services to the group, but is not limited to such an example. The processing unit 12 can also make a thoughtful response or suggestion, for example, taking into consideration the characteristics of each user U and the relationships between users U in the group.

[0246] The processing unit 12, as an acquisition unit, acquires information about each user U, conversation history in the chat group, etc. from the storage unit 11 or an external server, etc. The identification unit 41 of the processing unit 12 identifies the characteristics of each user U and the relationships between users U in the group based on the information about each user U, conversation history in the chat group, etc.

[0247] The characteristics of the user U include, for example, the attributes of the user U and the behavioral patterns of the user U. The attributes of the user U include, for example, demographic attributes and psychographic attributes. The behavioral patterns of the user U include, for example, purchasing behavior patterns, travel patterns, web search patterns, and the like, but are not limited to these examples.

[0248] Relationships between users U include, for example, parent-child relationships, coworker relationships, superior-subordinate relationships, friendships, and student-teacher relationships. Friendships include, but are not limited to, friendships on social networking services (SNS), friendships based on shared hobbies, and friendships in online games. Relationships between users U also include intimacy, trust, dependence, frequency of communication, degree of influence, and physical proximity (physical distance).

[0249] The identification unit 41 identifies the relationships between the users U in the group, for example, based on a conversation history, which is a history of chat messages between the users U. Furthermore, the identification unit 41 can identify the relationships between the users U in the group, for example, based on the attributes of each user U in the group in addition to or instead of the conversation history.

[0250] The identification unit 41 can, for example, input information to the generation AI including a history of chat messages between users U and instruction information that instructs the identification of the relationship between users U from such history, and output the identification result of the relationship between users U.

[0251] In this case, the instruction information may be, for example, a string of characters such as "Please identify the relationship between the given users from the chat message history between the users," but is not limited to such an example. The instruction information may also include a relationship list, example information of a combination of message history examples and relationship examples, and the like.

[0252] In addition, the inquiry unit 43 inquires of one or more users U in the group about predetermined information, which is information about unidentified parameters, based on the characteristics of each user U identified by the identification unit 41 and the relationships between users U in the group.

[0253] For example, the inquiry unit 43 has information for each type of service that indicates the contact point associated with at least one of the attributes of each user U and the relationships between users U for each unspecified parameter, and based on such information, determines the user U who inquires about specified information as the contact point user.

[0254] The inquiry unit 43 inquires about the predetermined information from the determined inquiry user. In this case, the determination processing unit 57 determines the value of the unidentified parameter based on the information provided by the inquiry user in response to the inquiry by the inquiry unit 43.

[0255] The inquiry unit 43 can also adjust the content of the inquiry message based on the characteristics of each user U identified by the identification unit 41 and the relationships between users U in the group. For example, the generation processing unit 53 of the inquiry unit 43 can further include information instructing consideration of the characteristics of the inquired user and the relationships between users U in the group in the instruction information to be input to the generation AI.

[0256] For example, the generation processing unit 53 can input the following information as instruction information to the generation AI: the string "The characteristics of each user in the group and the relationships between the users are as follows. Please take these into consideration when creating your sentence.", and further information indicating the characteristics of each user U in the group and the relationships between users U in the group.

[0257] In addition, the generation processing unit 53 has information for each service type that is linked to multiple instruction information that corresponds to the characteristics of each user U in the group and the relationships between users U in the group, and can also identify instruction information that corresponds to the unidentified parameters identified by the information identification unit 51.

[0258] Furthermore, when there is a chat message from a user U inquiring about the generation AI in a chat room of a group chat, the providing unit 44 can also generate a response to the inquiry from the user U based on the characteristics of each user U in the group and the relationships between the users U in the group. An example of a chat message from a user U inquiring about the generation AI is, for example, information such as the character string "AI, tell me about XXX" (where XXX is, for example, a proper noun or a specific phrase), but is not limited to such an example.

[0259] The providing unit 44 inputs information to the generation AI, for example, including a chat message from user U inquiring about the generation AI, information indicating the characteristics of user U in the chat message, and instruction information instructing a response to the chat message, and causes the generation AI to generate information indicating a response to the chat message.

[0260] In this case, the instruction information may be, for example, a character string such as "Generate an answer to the given inquiry. When doing so, please consider the characteristics of the given user and create an appropriate answer for that user," but is not limited to such an example. Note that the instruction information may also include example information of a combination of an example inquiry message, an example characteristic of user U, and an example answer.

[0261] The providing unit 44 can also provide information according to the relationships between users U in the group to the user U. For example, the providing unit 44 inputs information including an inquiry chat message from the user U to the generation AI, information indicating the relationships between the users U in the group, and instruction information instructing a response to the chat message to the generation AI, and can cause the generation AI to generate information indicating a response to the chat message.

[0262] In this case, the instruction information may be, for example, a character string such as "Generate an answer to the given inquiry. When doing so, please consider the relationships between the users U in the given group and create an appropriate answer," but is not limited to such an example. Note that the instruction information may also include example information such as a combination of an example chat message for the inquiry, an example relationship between the users U in the group, and an example answer.

[0263] The providing unit 44 can also provide information according to the characteristics of each user U in the group and the relationships between the users U in the group to the user U. For example, the providing unit 44 inputs information to the generation AI including a chat message inquiring about the generation AI from the user U, information indicating the characteristics of the user U in the chat message, information indicating the relationships between the users U in the group, and instruction information instructing a reply to the chat message, and can cause the generation AI to generate information indicating a reply to the chat message.

[0264] In this case, the instruction information may be, for example, a character string such as "Generate an answer to the given inquiry. When doing so, please consider the characteristics of the given user and the relationships between users U in the given group to create an appropriate answer," but is not limited to such an example. Note that the instruction information may also include example information of combinations of example chat messages for inquiries, the characteristics of users U, examples of relationships between users U in the group, and example answers.

[0265] The providing unit 44 can provide answers to chat messages that inquire about the generation AI, as well as answers corresponding to messages that satisfy predetermined conditions. For example, a message that satisfies the predetermined conditions is a chat message that does not specify the destination of the inquiry and has not had any other chat messages posted in the chat room within a predetermined period of time since it was posted, but is not limited to such an example.

[0266] [6. Hardware Configuration] The information processing device 1 according to the embodiment described above is realized by, for example, a computer 80 configured as shown in Fig. 13. Fig. 13 is a hardware configuration diagram showing an example of the computer 80 that realizes the functions of the information processing device 1 according to the embodiment. The computer 80 has a CPU 81, a RAM 82, a ROM (Read Only Memory) 83, an HDD (Hard Disk Drive) 84, a communication interface (I / F) 85, an input / output interface (I / F) 86, and a media interface (I / F) 87.

[0267] The CPU 81 operates and controls each part based on programs stored in the ROM 83 or the HDD 84. The ROM 83 stores a boot program executed by the CPU 81 when the computer 80 starts up, programs that depend on the hardware of the computer 80, and the like.

[0268] The HDD 84 stores programs executed by the CPU 81, data used by such programs, etc. The communication interface 85 receives data from other devices via the network N (see FIG. 2) and sends it to the CPU 81, and transmits data generated by the CPU 81 to other devices via the network N.

[0269] The CPU 81 controls output devices such as a display and a printer, and input devices such as a keyboard or a mouse, via the input / output interface 86. The CPU 81 acquires data from the input devices via the input / output interface 86. The CPU 81 also outputs generated data to the output devices via the input / output interface 86.

[0270] The media interface 87 reads a program or data stored in a recording medium 88 and provides it to the CPU 81 via the RAM 82. The CPU 81 loads the program or data from the recording medium 88 onto the RAM 82 via the media interface 87 and executes the loaded program. The recording medium 88 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase Change Rewritable Disc), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0271] For example, when the computer 80 functions as the information processing device 1 according to the embodiment, the CPU 81 of the computer 80 executes programs loaded onto the RAM 82 to realize the functions of the processing unit 12. In addition, the HDD 84 stores data in the storage unit 11. The CPU 81 of the computer 80 reads and executes these programs from a recording medium 88, but as another example, the CPU 81 may obtain these programs from another device via the network N.

[0272] [7. Other] 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 using known methods. In addition, the information including the processing procedures, specific names, various data, and parameters shown in the above documents and drawings can be changed as desired unless otherwise specified. For example, the various information shown in each drawing is not limited to the information shown in the drawings.

[0273] Furthermore, the components of each device shown in the figure are conceptual functional components and do not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc.

[0274] For example, the information processing device 1 described above may be realized by a terminal device and a server computer, or may be realized by multiple server computers. Furthermore, depending on the function, the configuration can be flexibly changed, such as by calling an external platform using an API or network computing.

[0275] Furthermore, the above-described embodiments and modifications can be combined as appropriate within the scope of not causing any contradiction in the processing content.

[0276] [8. Effects] As described above, the information processing device 1 according to the embodiment includes a personal agent identification unit 50, an inquiry unit 43, and a provision unit 44. The personal agent identification unit 50 identifies a plurality of personal agents PA each associated with a corresponding user from among a plurality of grouped users U. The inquiry unit 43 inquires of one or more personal agents PA from among the plurality of personal agents PA identified by the personal agent identification unit 50 about specific information used to provide a service to a group corresponding to the plurality of users U. The provision unit 44 provides a service to the group using information provided from the one or more personal agents PA in response to the inquiry by the inquiry unit 43. This allows the information processing device 1 to improve the convenience of providing services to a plurality of grouped users U. This allows the information processing device 1 to improve the convenience of providing services to a plurality of grouped users U.

[0277] The information processing device 1 also includes a reception unit 40 that receives input information including information related to services from the user U, and an information identification unit 51 that identifies predetermined information based on the input information received by the reception unit 40. This enables the information processing device 1 to improve the convenience of providing services to a plurality of grouped users U.

[0278] The information identifying unit 51 also includes a first identifying processing unit 60 that identifies the type of service and the value of one or more parameters among a plurality of parameters used to provide the type of service based on the input information received by the receiving unit 40, and a second identifying processing unit 61 that identifies, as predetermined information, information on an unspecified parameter, the value of which is unspecified among the plurality of parameters. This enables the information processing device 1 to improve the convenience of providing services to a plurality of users U who are grouped together.

[0279] The information processing device 1 also includes an inquiry destination identification unit 52 that identifies one or more personal agents PA based on the predetermined information identified by the information identification unit 51. This enables the information processing device 1 to improve the convenience of providing services to a plurality of grouped users U.

[0280] The providing unit 44 also includes a determination processing unit 57 that determines the value of an unspecified parameter based on information provided from one or more personal agents PA in response to an inquiry by the inquiry unit 43, an acquisition processing unit 58 that acquires service information, which is information about a service, from the service providing device 3 that provides the service based on the values ​​of multiple parameters including the value of the unspecified parameter determined by the determination processing unit 57 and the type of service identified by the first identification processing unit 60, and a providing processing unit 59 that provides the service information acquired by the acquisition processing unit 58 to the group. This enables the information processing device 1 to improve the convenience of providing services to multiple users U who are grouped together.

[0281] The reception unit 40 also receives settings for grouping multiple users U for group chat among the multiple users U. This allows the information processing device 1 to improve the convenience of providing services to multiple users U who have been grouped for group chat.

[0282] The providing unit 44 also includes an estimation processing unit 56 that estimates the group situation in the chat room using a generation AI based on the message history of multiple users U in the chat room of the group chat, and a determination processing unit 57 that determines the value of an unspecified parameter based on the estimation result by the estimation processing unit 56 when information in response to an inquiry by the inquiry unit 43 is not provided from one or more personal agents PA. This enables the information processing device 1 to improve the convenience of providing services to multiple users U who are grouped together.

[0283] The providing unit 44 also includes an estimation processing unit 56 that estimates the characteristics of the group in the chat room using a generation AI based on attribute information of multiple users U in the chat room of the group chat, and a determination processing unit 57 that, when information in response to an inquiry by the inquiry unit 43 is not provided from one or more personal agents PA, determines the value of an unspecified parameter based on the estimation result by the estimation processing unit 56. This enables the information processing device 1 to improve the convenience of providing services to multiple users U who are grouped together.

[0284] The information processing device 1 also includes an estimation unit 42 that estimates the group situation in a chat room using a generation AI based on the message history of multiple users U in the group chat chat room, and an inquiry unit 43 provides information indicating the estimation result by the estimation unit 42 to one or more personal agents when inquiring about predetermined information. This enables the information processing device 1 to improve the convenience of providing services to multiple users U who are grouped together.

[0285] The information processing device 1 also includes an estimation unit that uses a generation AI to estimate the characteristics of the group based on attribute information of multiple users in the chat room of the group chat, and the inquiry unit 43 provides information indicating the estimation results by the estimation unit 42 to one or more personal agents PA when inquiring about predetermined information. This enables the information processing device 1 to improve the convenience of providing services to multiple users U who are grouped together.

[0286] The inquiry unit 43 also includes a generation processing unit 53 that uses a generation AI to generate inquiry information indicating a sentence inquiring about predetermined information, and an output processing unit 54 that outputs the inquiry information generated by the generation processing unit 53 to one or more personal agents PA. This allows the information processing device 1 to appropriately make inquiries to the personal agents PA.

[0287] Furthermore, each of the plurality of personal agents PA uses a generation AI to generate answer information indicating an answer corresponding to the inquiry information, thereby enabling the personal agent PA to provide an appropriate answer.

[0288] Furthermore, each of the multiple personal agents PA inquires of the user U about whether or not answer information can be provided, and provides the answer information based on the answer from the user U. This allows the personal agent PA to prevent information from being provided without the user U's knowledge.

[0289] The above describes the embodiments of the present application in detail based on the drawings, but this is merely an example, and the present invention can be implemented in other forms that include the embodiments described in the Disclosure of the Invention section and that have been modified and improved in various ways based on the knowledge of those skilled in the art.

[0290] Furthermore, the above-mentioned "section, module, unit" can be read as "means" or "circuit," etc. For example, an acquisition unit can be read as an acquisition means or an acquisition circuit. [Explanation of symbols]

[0291] 1. Information processing equipment 2,21,22,···,2 m ,2 n terminal device 3 Service provision equipment 10. Communications Department 11 Storage section 12 Processing section 20 User information storage unit 21 Chat setting information storage unit 22 Conversation history memory section 30,40 Reception 31 Setting section 32,44 Providing Department 33,331~33 p Group Agent Processing Unit 41 Specific part 42 Estimation part 43 Inquiry Department 50 Personal Agent Identification Unit 51 Information Specification Department 52 Contact details 53 Generation processing section 54 Output processing section 56 Estimation processing unit 57 Decision Processing Unit 58 Acquisition processing unit 59 Provision Processing Unit 60 First Specific Processing Department 61 Second Specific Processing Department N Network

Claims

1. a personal agent identifying unit that identifies a plurality of personal agents associated with corresponding users from among the plurality of grouped users; an inquiry unit that inquires of one or more of the plurality of personal agents identified by the personal agent identification unit about predetermined information used for providing a service to a group corresponding to the plurality of users; a providing unit that provides the service to the group using information provided by the one or more personal agents in response to the inquiry made by the inquiry unit.

1. An information processing device comprising:

2. a reception unit that receives input information including information related to the service from the user; an information identifying unit that identifies the predetermined information based on the input information accepted by the accepting unit.

2. The information processing apparatus according to claim 1, wherein:

3. The information identification unit a first identification processing unit that identifies a type of the service and values ​​of one or more parameters among a plurality of parameters used to provide the type of service, based on the input information accepted by the accepting unit; a second identification processing unit that identifies, as the predetermined information, information on an unspecified parameter whose value is unspecified among the plurality of parameters.

3. The information processing apparatus according to claim 2, wherein:

4. and an inquiry destination specifying unit that specifies the one or more personal agents based on the predetermined information specified by the information specifying unit.

4. The information processing apparatus according to claim 2, wherein the information processing apparatus is a computer.

5. The providing unit a determination processing unit that determines values ​​of the unspecified parameters based on information provided by the one or more personal agents in response to the inquiry by the inquiry unit; an acquisition processing unit that acquires service information, which is information on the service, from a service providing device that provides the service, based on values ​​of the plurality of parameters including the value of the unspecified parameter determined by the determination processing unit and the type of the service specified by the first specification processing unit; a providing processing unit that provides the service information acquired by the acquisition processing unit to the group.

4. The information processing apparatus according to claim 3,

6. The reception unit Accepting a grouping setting for the plurality of users for a group chat among the plurality of users 4. The information processing apparatus according to claim 3,

7. The providing unit an estimation processing unit that estimates a situation of the group in the chat room using a generation AI based on message histories of the plurality of users in the chat room of the group chat; a determination processing unit that determines the value of the unspecified parameter based on the estimation result by the estimation processing unit when information in response to the inquiry by the inquiry unit is not provided by the one or more personal agents.

7. The information processing apparatus according to claim 6,

8. The providing unit an estimation processing unit that estimates characteristics of the group in the chat room using a generation AI based on attribute information of the plurality of users in the chat room of the group chat; a determination processing unit that determines the value of the unspecified parameter based on the estimation result by the estimation processing unit when information in response to the inquiry by the inquiry unit is not provided by the one or more personal agents.

7. The information processing apparatus according to claim 6,

9. an estimation unit that estimates a situation of the group in the chat room using a generation AI based on message histories of the plurality of users in the chat room of the group chat; The inquiry unit When inquiring about the predetermined information, information indicating the estimation result by the estimation unit is provided to the one or more personal agents.

7. The information processing apparatus according to claim 6,

10. an estimation unit that estimates characteristics of the group using a generation AI based on attribute information of the plurality of users in the chat room of the group chat; The inquiry unit When inquiring about the predetermined information, information indicating the estimation result by the estimation unit is provided to the one or more personal agents.

7. The information processing apparatus according to claim 6,

11. The inquiry unit a generation processing unit that generates inquiry information indicating a sentence inquiring about the predetermined information using a generation AI; an output processing unit that outputs the inquiry information generated by the generation processing unit to the one or more personal agents; 4. The information processing device according to claim 1, wherein the information processing device is a computer.

12. Each of the plurality of personal agents: Generate answer information indicating an answer corresponding to the inquiry information using a generation AI.

12. The information processing apparatus according to claim 11,

13. Each of the plurality of personal agents: Inquiring the user about whether or not to provide the answer information, and providing the answer information based on the answer from the user 13. The information processing apparatus according to claim 12.

14. 1. A computer-implemented information processing method, comprising: a personal agent identifying step of identifying a plurality of personal agents each associated with a corresponding user from among the plurality of grouped users; an inquiry step of inquiring of one or more of the plurality of personal agents identified by the personal agent identification step about predetermined information used for providing services to a group corresponding to the plurality of users; and providing the service to the group using information provided by the one or more personal agents in response to the inquiry made by the inquiry step.

1. An information processing method comprising:

15. a personal agent identifying step of identifying a plurality of personal agents each associated with a corresponding user from among the plurality of grouped users; an inquiry procedure for inquiring of one or more of the plurality of personal agents identified by the personal agent identification procedure about predetermined information used for providing services to a group corresponding to the plurality of users; and a provision step of providing the service to the group using information provided by the one or more personal agents in response to an inquiry made by the inquiry step. An information processing program characterized by:

Images