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

Abstract

To provide an information processor, an information processing method and an information processing program for properly acquiring the information of a user, and for providing a service.SOLUTION: The information processing terminal includes an unacquired information determination unit, a target agent identification unit, an inquiry unit, and a provision unit. The unacquired information determination unit determines whether or not there is unacquired information among information used for providing a service to a user. When the unacquired information determination unit determines that there is unacquired information, the subject agent identification unit identifies an agent estimated to include the unacquired information as a subject agent. The inquiry unit inquires about unacquired information in the subject agent specified by the subject agent specifying unit. The providing unit provides the service to the user by using information obtained 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, services that exchange messages with users in a conversational format have been known. For example, Patent Document 1 proposes a technology that receives an input message input by a user through speech, inputs information including the input message into a generation AI such as a language model, causes the generation AI to generate a response message, and provides the response message to the user. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the above-mentioned technology does not disclose, for example, technology for appropriately acquiring user information in order to improve the accuracy of response messages corresponding to user input messages, and there is room for improvement in terms of appropriately acquiring user information.

[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 appropriately acquire user information and provide services. [Means for solving the problem]

[0006] The information processing device according to the present application includes an unacquired information determination unit, a target agent identification unit, an inquiry unit, and a providing unit. The unacquired information determination unit determines whether or not there is unacquired information among the information used to provide a service to a user. When the unacquired information determination unit determines that there is unacquired information, the target agent identification unit identifies an agent that is presumed to contain the unacquired information as a target agent. The inquiry unit inquires about the unacquired information of the target agent identified by the target agent identification unit. The providing unit provides the service to the user using the information obtained 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 provide a service by appropriately acquiring user information. [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 terminal according to the embodiment. [Figure 4] FIG. 4 is a diagram showing an example of the configuration of an inquiry unit in the personal agent processing unit of the information processing terminal according to the embodiment. [Figure 5] FIG. 5 is a diagram showing an example of a chat room screen provided by a providing unit in a processing unit of the information processing terminal according to the embodiment and displayed on a display unit. [Figure 6] FIG. 6 is a diagram illustrating an example of the configuration of an inquiry response unit in the personal agent processing unit of the information processing terminal according to the embodiment. [Figure 7] FIG. 7 is a flowchart showing an example of information processing by the personal agent processing unit of the processing unit of the information processing terminal according to the embodiment. [Figure 8] FIG. 8 is a hardware configuration diagram illustrating an example of a computer that realizes the functions of the information processing terminal 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 terminal.

[0011] As shown in FIG. 1, information processing terminals 11, 12, . . . , 1 n are communicably connected to the service providing device 2, and transmit and receive information to and from the service providing device 2. n is an integer equal to or greater than 3. n Examples of such devices include smartphones, tablets, and mobile personal computers (PCs).

[0012] Information processing terminals 11, 12, . . . , 1 n are users U1, U2, . . ., U n For example, the information processing terminal 11 is used by a user U1, the information processing terminal 12 is used by a user U2, and the information processing terminal 1 n is user U n Used by.

[0013] In the following, information processing terminals 11, 12, . . . , 1n When each of these is not individually identified, it may be referred to as information processing terminal 1, and users U1, U2, . . . , U n When referring to each of these without distinguishing them individually, they may be referred to as user U.

[0014] The service providing device 2 provides various services to the user U of the information processing terminal 1. The service providing device 2 provides online services such as a chat service, various search services, various reservation services, an advertisement distribution service, a map information providing service, an e-commerce service, a service information providing service, and a profile providing service.

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

[0016] In the example shown in FIG. 1, in a chat service provided by a service providing device 2, multiple 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 n A chat group called Group A is formed for multiple users U1, U2, U n can exchange messages in Group A's chat room.

[0017] An instant messenger application for chatting (hereinafter, sometimes referred to as a chat app) is installed on each information processing terminal 1. The chat app allows for sending and receiving messages in one-to-one chats, group chats, and one-to-many chats. Sending and receiving messages in one-to-one chats includes sending and receiving messages between a chatbot and a user U.

[0018] The information processing terminal 1 is an example of an information processing device. In the following, the processing in the information processing terminal 11 will be described, but the processing in the information processing terminals 12, . . . , 1 other than the information processing terminal 11 will also be described. n The same processing can be performed.

[0019] The information processing terminal 11 accepts the information entered by the user U1 as input information (step S1). The input information includes, for example, information related to a service. The information related to the service is information related to a service provided by the service providing device 2, but may also be information related to a service provided by a service providing device other than the service providing device 2.

[0020] Based on the input information received in step S1, the information processing terminal 11 determines whether there is any information that has not yet been acquired among the information used to provide a service to the user U1 (step S2). The information used to provide a service to the user U1 may include information about the user U1 and information about other users U.

[0021] Based on the input information received in step S1, information processing terminal 11 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. Hereinafter, the type of service may be referred to as the service type.

[0022] 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.

[0023] When the service type is a product search service, the required parameters are, for example, the type of product or the name of the product, and the additional parameters are parameters other than the required parameters, such as, but not limited to, the price range, model name, color, rating, display order, and maximum number of acquisitions.

[0024] If the service type is a restaurant search service, the required parameters are, for example, at least one of the restaurant area and cuisine type, and the additional parameters are parameters other than the required parameters, such as price range, seating (terrace, table, tatami room), facilities (wheelchair, pets allowed), rating, allergenic ingredients, display order, maximum number of items to be acquired, etc., but are not limited to these examples.

[0025] Furthermore, if the service type is a hotel search service, the required parameters are, for example, at least one of the hotel area, planned stay date, time, number of people, etc., and the additional parameters are parameters other than the required parameters, such as 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, maximum number of acquisitions, etc., but are not limited to such examples.

[0026] In step S2, the information processing terminal 11 inputs information including the input information received in step S1 and information instructing the identification of a service type and values ​​of multiple parameters into a generation AI (Artificial Intelligence), and obtains the service type and parameter values ​​identified by the generation AI.

[0027] 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 (Recurrent Neural Network)-based model. An example of a transformer-based model is, but is not limited to, a GPT (Generative Pre-trained Transformer). An example of an RNN-based model is, but is not limited to, a RWKV (Receptance Weighted Key Value).

[0028] The generation AI may be a language model that has been trained (for example, fine-tuned) specifically for generating answer information. The generation AI is disposed in an external information processing device, and the information processing terminal 11 uses the generation AI via an API, but the generation AI may also be disposed within the information processing terminal 11.

[0029] The information processing terminal 11 inputs information including the input information input by the user U1 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 input information input by the user U1.

[0030] The instruction information includes, for example, the string "From the given information, 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.

[0031] The service type list includes, for example, information linking each service type with information indicating the content of the service. The parameter list includes, for example, information linking each 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 that type of service from the input information entered by user U1.

[0032] 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.

[0033] 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 input information entered by user U1, the input information entered into the generation AI does not need to include instruction information.

[0034] In addition, the information processing terminal 11 may be configured to identify the type of service and the parameter values ​​used to provide that type of service from the input information entered by the user U1 using a known slot-filling technique that does not use a generation AI.

[0035] The information processing terminal 11 determines, among the plurality of parameters identified as described above, parameters whose values ​​are not yet specified as unacquired information. The information processing terminal 11 stores, for each service, a service type and a plurality of parameters in association with each other, and identifies the plurality of parameters associated with the service type identified as described above.

[0036] The plurality of parameters includes necessary parameters and additional parameters, but it is not necessary to include either the necessary parameters or the additional parameters. The information processing terminal 11 identifies a plurality of parameters linked to the service type identified in step S3 from the stored service types for each service and the plurality of parameters for each service type.

[0037] Then, the information processing terminal 11 determines, as unspecified parameters, necessary parameters whose values ​​are unspecified among the plurality of parameters associated with the specified service type. Furthermore, the information processing terminal 11 can also determine, as unspecified parameters, additional parameters whose values ​​are unspecified in addition to necessary parameters whose values ​​are unspecified among the plurality of parameters.

[0038] 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 information processing terminal 11 can also identify unspecified parameters from among multiple parameters linked to the specified service type based on the information output from the generation AI.

[0039] When it is determined in step S3 that there is unacquired information, the information processing terminal 11 specifies an agent that is presumed to include the unacquired information as a target agent (step S3). An agent that is presumed to include the unacquired information is an agent that is presumed to be able to provide the unacquired information.

[0040] For example, when the unobtained information is a profile of user U1, the information processing terminal 11 estimates, among a plurality of service agents each providing a service, an agent of a profile providing service that provides the profile of user U1 as the service agent that includes the unobtained information. The profile of user U1 includes, for example, information such as attributes of user U1 and information about user U1.

[0041] Furthermore, for example, when the unobtained information is the service history of user U1 for a specific service, information processing terminal 11 estimates an agent for the specific service among multiple service agents that provide the service as the service agent that includes the unobtained information. The specific service is, for example, a restaurant search service, a hotel search service, etc., but is not limited to these examples.

[0042] In addition, when the unacquired information is API information of the target service type, the information processing terminal 11 estimates that, among the multiple service agents that provide the service, an agent of a service information providing service that provides API information of various services is the service agent that includes the unacquired information.

[0043] Furthermore, when the unacquired information is information about another user U different from user U1, information processing terminal 11 identifies as the target agent a personal agent of the other user U that is presumed to contain the unacquired information.

[0044] For example, the information processing terminal 11 is connected to a user U1 and other users U2 and U n Multiple users U1, U2, U n Other users U2, U3 in the chat room of group A set up for n One or more of the personal agents are identified as target agents.

[0045] Information processing terminals 11, 12, . . . , 1 n Each of these is composed of multiple individual agents PA1, PA2,..., PA n In the following, we will consider multiple personal agents PA1, PA2,..., PA n When referring to each of the above 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 something like Auto-GPT, for example.

[0046] A personal agent PA 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. n is user U n The processing of steps S1 to S5 shown in Fig. 1 is executed by the personal agent PA1.

[0047] For example, suppose the input information received in step S1 is the character string "I'm thinking of sending chocolate to XXX on Valentine's Day. What kind of chocolate does she like?" and "XXX" is user U2.

[0048] In this case, the information processing terminal 11 identifies the personal agent PA2 of the user U2 as the target agent. In addition, in this case, the service type identified in step S2 is a "product search service," and the type of unacquired information determined in step S3 is a "type of chocolate."

[0049] The input information received in step S1 is, as shown in the message CTM1 in FIG. 1(a), information on the character string "I'm thinking of going to eat with YYY around Akasaka. What kind of restaurant would be good?", and "YYY" is the user U. n Let us assume that:

[0050] In this case, the information processing terminal 11 receives the user U n Personal Agent PA n is identified as the target agent. In this case, the service type identified in step S2 is a "restaurant search service," the parameter value identified in step S2 is "Around Akasaka," and the type of unacquired information determined in step S3 is a "cuisine genre."

[0051] Furthermore, when the input information received in step S1 is a message to be posted in the chat room of group A, information processing terminal 11 receives the message from other users U2, . . . , U3 in the chat room of group A. n Alternatively, one or more of the personal agents PA of other users U may be identified as target agents.

[0052] The information processing terminal 11 inquires of the target agent identified in step S4 about the unacquired information determined in step S4 (step S4).

[0053] For example, in step S4, the information processing terminal 11 creates a request sentence that requests the target agent identified in step S2 to notify the unacquired information determined in step S3. Then, the information processing terminal 11 uses the created request sentence to inquire about the unacquired information determined in step S3.

[0054] For example, the information processing terminal 11 inputs information including the type of unobtained information and instruction information as input information to the generation AI, and causes the generation AI to create a request sentence. The type of unobtained information is, for example, a type of unspecified parameter, but is not limited to such an example. Furthermore, the instruction information is, for example, information such as "Please create a sentence to inquire of the agent about the given information," but is not limited to such an example.

[0055] For example, if the type of unobtained information is the service usage history of user U1 for a restaurant search service and the information is obtained from a service agent of the restaurant search service, the request text is a text for obtaining the service usage history, such as a text in JSON (JavaScript (registered trademark) Object Notation) format. Also, if the service agent can interpret natural language text using a generation AI or the like, the request text may be, for example, information such as the character string "Please output the service usage history of user U1.", but is not limited to such an example.

[0056] Furthermore, for example, if the type of unobtained information is the profile of user U1 and the information is obtained from a service agent of a profile providing service, the request text is a text for obtaining the profile of user U1, such as a text in JSON format. Furthermore, if the service agent can interpret text in natural language using a generation AI or the like, the request text is, for example, information such as the character string "Please output the profile of user U1.", but is not limited to such an example.

[0057] For example, if the type of unobtained information is information indicating a type of chocolate and the inquiry is directed to personal agent PA2, the request text may be the string "Please tell me what type of chocolate XXX likes.", but is not limited to such an example.

[0058] In addition, the request text may be, for example, a case where the type of unobtained information is a food genre and the contact person is a personal agent PA. n In this case, the information is a character string "Please tell us what type of food XXX likes." However, the information is not limited to this example.

[0059] The information processing terminal 11 is connected to a plurality of users U1, U2, . . . , U n The information processing terminal 11 can generate a message to be posted in the chat room of group A set for the target agent PA, inquiring about unobtained information. Then, by posting the generated message in the chat room of group A, the information processing terminal 11 can also inquire about unobtained information from the individual agent PA, who is the target agent PA.

[0060] For example, when information processing terminal 11 is set to non-display mode, which is a non-display setting, it can inquire about unobtained information from personal agent PA, who is the target agent PA. In this case, a message inquiring about unobtained information is not displayed in the chat room of group A. Also, when personal agent PA, who is the target agent PA, is set to non-display mode, a message inquiring about unobtained information is not displayed in the chat room of group A.

[0061] Here, it is assumed that the target agent for which an inquiry about unobtained information has been made is the personal agent PA2 of user U2. In this case, the personal agent PA2 accepts the inquiry about unobtained information from the personal agent PA1. The personal agent PA2 determines whether or not to provide the unobtained information in response to the accepted inquiry.

[0062] The personal agent PA2 has, for example, provision availability information indicating whether or not each type of unacquired information can be provided, and determines whether or not to provide the unacquired information based on the provision availability information. The provision availability information is set, for example, by the user U2.

[0063] If the provision propriety information indicates that provision of unacquired information is permitted, the personal agent PA2 determines to provide the unacquired information, and if not, determines not to provide the unacquired information.

[0064] Furthermore, the personal agent PA2 may have, for example, inquiry necessity information indicating whether an inquiry to the user U2 is necessary for each type of unacquired information. The inquiry necessity information is set, for example, by the user U2. When the type of unacquired information (for example, the type of unspecified parameter) is a type that requires an inquiry to the user U2, the personal agent PA2 pops up an inquiry message in the display area of ​​the information processing terminal 12, inquiring whether it is okay to provide the user U2 with the unacquired information.

[0065] When the user U2 inputs affirmative information (for example, the string "yes" or the string "OK") in response to the popup-displayed inquiry message, the personal agent PA2 outputs the unacquired information to the personal agent PA1.

[0066] The information processing terminal 12 stores information about the user U2, such as attribute information about the user U2 and information indicating the user U2's behavior history, and the personal agent PA2 extracts information in response to the inquiry from the information about the user U2 as unacquired information. The personal agent PA2 then provides the unacquired information that it has determined should be provided to the personal agent PA1.

[0067] For example, if the type of unacquired information is the type of chocolate that user U2 likes and user U2 likes bitter chocolate, personal agent PA2 outputs the string "bitter chocolate" or the string "XXX likes bitter chocolate" as unacquired information.

[0068] In addition, the target agent for which the unobtained information was inquired is the user U. n Personal Agent PA n In this case, the same processing as that of the personal agent PA2 of the user U2 is performed. For example, n The type of unobtained information is user U n It is the favorite food genre of user U n If YYY likes Chinese food, the information of the string "Chinese food" or the string "YYY likes Chinese food." is output as unobtained information.

[0069] When an inquiry message, which is a message inquiring about unobtained information, is posted in the chat room of group A by information processing terminal 11, information processing terminal 11 can display the inquiry message and the unobtained information output in response to the inquiry message from the personal agent PA of another user U. The unobtained information is an example of information indicating the content of a response.

[0070] Furthermore, when the information processing terminal 11 is set to a non-display mode, for example, the information processing terminal 11 does not display the inquiry message and the unobtained information in the chat room of group A. The non-display mode is set in the information processing terminal 11 by the user U1, and the non-display mode is set in the information processing terminal 12 by the user U2. n The setting of hidden mode is n This is done by:

[0071] The information processing terminal 11 provides a service to the user U1 using the information provided by the target agent in response to the inquiry in step S4 (step S5). For example, the information processing terminal 11 acquires information on the service of the service type identified in step S2 based on the service type identified in step S2 and the information provided by the target agent in response to the inquiry in step S4.

[0072] For example, if the service type identified in step S2 is a product search service, the information processing terminal 11 specifies the product search service and sends a search request to the service providing device 2 via the API of the service providing device 2, the search request including information indicating the type of product as parameter information.

[0073] The service providing device 2 searches for multiple products in response to the search request, and provides the search results as service information of the service type identified in step S2 to the information processing terminal 11. The search results include, for example, information such as the name, price, rating, and description of each searched product, but are not limited to these examples.

[0074] For example, if the service type identified in step S2 is a restaurant search service, the information processing terminal 11 specifies the restaurant search service and sends a search request to the service providing device 2 via the API of the service providing device 2, with information indicating the cuisine genre as parameter information.

[0075] The service providing device 2 searches for a plurality of restaurants in response to the search request, and provides the search results as service information of the service type identified in step S2 to the information processing terminal 11. The search results include, for example, information such as the name, location, rating, and introduction of each of the searched restaurants, but are not limited to these examples.

[0076] 1(b), restaurant information CTA1, restaurant information CTA2, restaurant information CTM_A1, and restaurant information CTM_A2 are displayed as service information in a chat room on information processing terminal 11. 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.

[0077] Restaurant information CTM_A1 and restaurant information CTM_A2 are message-format information included in chat message CTM2. 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.

[0078] In this way, the information processing terminal 1 determines whether or not there is any information that has not been acquired among the information used to provide a service to the user U, and identifies an agent that is presumed to contain the information that has not been acquired as a target agent. The information processing terminal 1 then inquires about the information that has not been acquired from the target agent, and provides the service to the user U using the information provided by the target agent in response to the inquiry by the inquiry unit. This allows the information processing terminal 1 to appropriately acquire information about the user U and provide the service.

[0079] Hereinafter, the information processing terminals 11, 12, . . . , 1 n The configuration of the information processing system including the service providing device 2 will be described in detail.

[0080] [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, the information processing system 100 according to an embodiment includes information processing terminals 11, . . . , 1 n and a service providing device 2.

[0081] The information processing terminals 1 are used by different users U. Each information processing terminal 1 is, for example, a smartphone, a tablet PC, a notebook PC, a desktop PC, or the like, but is not limited to these examples.

[0082] The information processing terminal 1 and the service providing device 2 are connected to each other so as to be able to communicate with each other by wire or wirelessly via a network N. Note that the information processing system 100 shown in FIG.

[0083] 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).

[0084] Each information processing terminal 1 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 service providing device 2.

[0085] 3. Configuration of Information Processing Terminal 1 Fig. 3 is a diagram showing an example of the configuration of an information processing terminal 1 according to an embodiment. As shown in Fig. 3, the information processing terminal 1 includes a communication unit 10, a display unit 11, an input unit 12, an imaging unit 13, a sensor group 14, a storage unit 15, and a processing unit 16. Although not shown, the information processing terminal 1 is also provided with a speaker and the like.

[0086] [3.1. Communication Unit 10] The communication unit 10 is realized by, for example, a communication module or a NIC (Network Interface Card), etc. The communication unit 10 is connected to a network N by wire or wirelessly, and transmits and receives information to and from the service providing device 2 via the network N.

[0087] [3.2. Display section 11] The display unit 11 is, for example, an LCD (Liquid Crystal Display) or an organic EL (Electro Luminescence) display.

[0088] [3.3. Input section 12] The input unit 12 includes, for example, a keyboard including keys for inputting letters, numbers, and spaces, an enter key, arrow keys, etc., a mouse, a power button, etc. If the display unit 11 is a touch panel compatible display, the input unit 12 includes a touch panel.

[0089] [3.4. Imaging unit 13] The imaging unit 13 is an image sensor (camera) that captures an image of a subject. For example, the imaging unit 13 is a CMOS (Complementary Metal Oxide Semiconductor) image sensor or a CCD (Charge-Coupled Device) image sensor. Note that the imaging unit 13 is not limited to a built-in camera, and may be an external camera such as a wireless camera or a web camera that can communicate with the communication unit 10.

[0090] [3.5. Sensor Group 14] The sensor group 14 includes, for example, a positioning sensor, a microphone, an acceleration sensor, and a gyro sensor. The positioning sensor is a position sensor that detects the position of the information processing terminal 1. The microphone is a sensor that detects sounds around the information processing terminal 1. The acceleration sensor is a sensor that detects the acceleration of the information processing terminal 1. The gyro sensor is a sensor that detects the attitude of the information processing terminal 1, such as tilt and rotation.

[0091] [3.6. Storage section 15] The storage unit 15 is realized by, for example, a semiconductor memory element such as a random access memory (RAM) or a flash memory, or a storage device such as a hard disk or an optical disk.

[0092] The storage unit 15 stores, for example, information transmitted from the service providing device 2 and acquired by the processing unit 16 via the network N and the communication unit 10, and detection information which is information detected by the sensor group 14, etc.

[0093] Furthermore, the storage unit 15 stores a service type and a plurality of parameters associated with each service. The plurality of parameters include necessary parameters and additional parameters. The necessary parameters are parameters necessary for providing the service. The additional parameters are parameters for improving the accuracy of providing the service.

[0094] The storage unit 15 also stores setting information. The setting information includes acquisition availability information, which is information indicating whether each parameter for each information type can be acquired, and inquiry necessity information, which is information indicating whether an inquiry is necessary for each information type. The setting information also includes attribute information indicating the attributes of the user U.

[0095] The storage unit 15 also stores user information, which is information about the user U. The user information may be attribute information about the user U, information indicating the behavior history of the user U, or the like, but is not limited to these examples.

[0096] 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.

[0097] 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.

[0098] 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.

[0099] The browsing history includes, for example, information indicating the content that the user U viewed in the online service, and the posting history includes, for example, information indicating the content (e.g., reviews, comments, etc.) that the user U posted in the past in the online service, information indicating the chat messages that the user U posted in the past in the chat service, etc. The purchase history includes information on the transaction objects with which the user U has previously traded.

[0100] 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.

[0101] [3.7. Processing Unit 16] The processing unit 16 is a controller, and is realized, for example, by a CPU (Central Processing Unit) or an MPU (Micro Processing Unit) executing various programs stored in a storage device inside the information processing terminal 1 using RAM as a working area.

[0102] The processing unit 16 may be realized in part or in whole by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array). An information processing program is installed in the processing unit 16 as a dedicated application program (including, for example, a chat application) that runs on an OS (Operating System), and the processing unit 16 thereby functions as a functional unit including a reception unit 20, an acquisition unit 21, a provision unit 22, and a personal agent processing unit 23. The personal agent is a service agent for each user, and may be, for example, something like Auto-GPT.

[0103] [3.7.1. Reception Unit 20] The reception unit 20 receives various requests and information. For example, the reception unit 20 receives, as input information, information input in response to an input operation by the user U. For example, the reception unit 20 receives, as input information, a chat message input by the user U in a chat room.

[0104] [3.7.2. Acquisition part 21] The acquisition unit 21 acquires various types of information from the service providing device 2, the storage unit 15, etc. For example, the acquisition unit 21 acquires posted information including chat messages of other users U provided from the service providing device 2.

[0105] [3.7.3.Providing Department 22] The providing unit 22 provides various types of information to the user U. For example, the providing unit 22 provides various types of information to the user U by causing the display unit 11 to display the various types of information.

[0106] The providing unit 22 adds the chat message received by the receiving unit 20 to the chat room displayed on the display unit 11, thereby providing the chat message received by the receiving unit 20 to the user U in a recognizable manner.

[0107] In addition, the providing unit 22 adds the chat message acquired by the acquiring unit 21 from the service providing device 2 or the like to the chat room displayed on the display unit 11, thereby providing the chat message acquired by the acquiring unit 21 in a recognizable manner to the user U.

[0108] [3.7.4. Personal Agent Processing Unit 23] The personal agent processing unit 23 executes the functions of the personal agent PA described above. The personal agent processing unit 23 includes a reception unit 30, a service identification unit 31, an unacquired information determination unit 32, a target agent identification unit 33, an inquiry unit 34, a provision unit 35, and an inquiry response unit 36.

[0109] [3.7.4.1. Reception unit 30] The reception unit 30 receives input information from the user U. For example, the reception unit 30 receives the input information received by the reception unit 20.

[0110] The input information includes, for example, information about the service or information about other users U. The information about the service is information about a service provided by the service providing device 2, but may also be information about a service provided by a service providing device other than the service providing device 2.

[0111] [3.7.4.2. Service Identification Unit 31] Based on the input information received by the receiving unit 30, the service specifying unit 31 specifies the service type and the value of one or more parameters from among a plurality of parameters used to provide the service of that service type.

[0112] The service identification unit 31 inputs information including the input information received by the reception unit 30 and information instructing the identification of the service type and the values ​​of multiple parameters to the generation AI, and obtains the service type and parameter values ​​identified by the generation AI.

[0113] 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-based model.

[0114] An example of a transformer-based model is GPT, but is not limited to such an example. An example of an RNN-based model is RWKV, but is not limited to such an example. The generation AI is disposed in an external information processing device, and the service identification unit 31 uses the generation AI via an API, but the generation AI may be disposed in the information processing terminal 1.

[0115] The service identification unit 31 inputs information including the input information input by the user U and accepted by the acceptance unit 30 and instruction information to the generation AI, and can cause the generation AI to output a service type and parameter values. The service identification unit 31 identifies the service type and parameter values ​​based on the information indicating the service type and the parameter values ​​output from the generation AI. The instruction information is information that instructs the generation AI to identify the service type and the parameter values ​​used to provide the service of that type from the input information accepted by the acceptance unit 30.

[0116] The instruction information includes, for example, the string "From the given information, 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.

[0117] The service type list includes, for example, information in which a service type is linked to information indicating the content of the service for each service type. The parameter list includes, for example, information in which a parameter is linked to information indicating the content of the parameter for each service type. Note that the instruction information is not limited to the above-described example, and may be any information that can output a service type and parameter values ​​used to provide the service of that type from the input information accepted by the accepting unit 30.

[0118] 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.

[0119] Furthermore, if the generation AI is fine-tuned to output the type of service and the value of the parameters used to provide that type of service from the input information received by the reception unit 30, the input information input to the generation AI does not need to include instruction information.

[0120] In addition, the service identification unit 31 may be configured to identify the type of service and the value of the parameters used to provide that type of service from the input information accepted by the acceptance unit 30 using a known slot-filling technique that does not use a generation AI.

[0121] Assume that the input information received by the receiving unit 30 is a chat message posted by the user U in a chat room of a chat group to which the user U belongs. In this case, the unacquired information determination unit 32 can use a generation AI to identify the value of the parameter based on, for example, a group of chat messages including the chat message received by the receiving unit 30 and other chat messages posted in the chat room. The other chat messages are, for example, messages from a predetermined period ago, but are not limited to this example.

[0122] Furthermore, if the service type cannot be identified using the generation AI, the service identification unit 31 does not identify the value of the parameter, and identifies the value of the parameter whose value can be identified, but is not limited to this example.

[0123] [3.7.4.3. Unobtained information determination unit 32] The unacquired information determination unit 32 determines whether or not there is any information that has not been acquired among the information used to provide the service to the user U.

[0124] The unacquired information determination unit 32 determines, for example, as unacquired information, information on an unspecified parameter whose value is unspecified among the multiple parameters identified by the service identification unit 31. The information on an unspecified parameter determined as unacquired information is information indicating an unspecified parameter, but may be information that can identify the unspecified parameter.

[0125] When there are multiple unspecified parameters, the unacquired information determination unit 32 can determine, based on the input information received by the reception unit 30, information on one or more unspecified parameters among the multiple unspecified parameters as unspecified information.

[0126] For example, if the input information accepted by the accepting unit 30 is the character string "I'm thinking of sending chocolate to XXX on Valentine's Day, but what kind of chocolate does she like?" and the "type of chocolate" cannot be identified, the unacquired information determining unit 32 will determine that the "type of chocolate" is unspecified information. In this case, the unacquired information determining unit 32 can also determine, in addition to the "type of chocolate," for example, the "production area of ​​chocolate" and the "maker of chocolate" as unspecified information.

[0127] Furthermore, when the input information accepted by the accepting unit 30 is the character string "I'm thinking of going to dinner with YYY around Akasaka, what kind of restaurant would be good?" and the "catering genre" cannot be identified, the unacquired information determining unit 32 determines that the "catering genre" is unspecified information. In this case, the unacquired information determining unit 32 can also determine, in addition to the "catering genre", for example, the "area of ​​the restaurant" and the "price range of the restaurant" as unspecified information.

[0128] The unacquired information determination unit 32 stores a service type and a plurality of parameters associated with each service, and identifies the plurality of parameters associated with the identified service type. The plurality of parameters includes, but is not limited to, required parameters and additional parameters. The unacquired information determination unit 32 identifies the plurality of parameters associated with the service type identified by the service identification unit 31 from the service type and the plurality of parameters for each service that are stored.

[0129] Then, the unacquired information determination unit 32 determines, as unspecified parameters, necessary parameters whose values ​​are unspecified among the plurality of parameters linked to the service type identified by the service identification unit 31. Furthermore, the unacquired information determination unit 32 can also determine, as unspecified parameters, additional parameters whose values ​​are unspecified in addition to necessary parameters whose values ​​are unspecified among the plurality of parameters.

[0130] 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 unacquired information determination unit 32 can also identify unspecified parameters from among multiple parameters linked to the service type identified by the service identification unit 31 based on the information output from the generation AI.

[0131] Furthermore, the unacquired information determination unit 32 can also determine unacquired information directly from the input information accepted by the acceptance unit 30. For example, when a service corresponding to the service information provided by the provision unit 35 is specified, the unacquired information determination unit 32 can use a term list of the specified service to determine unacquired information or have the generation AI determine unacquired information.

[0132] [3.7.4.4. Target Agent Identification Unit 33] When the unacquired information determination unit 32 determines that there is unacquired information, the target agent identification unit 33 identifies an agent that is presumed to contain the unacquired information as a target agent. An agent that is presumed to contain the unacquired information is an agent that is presumed to be able to provide the unacquired information.

[0133] For example, the target agent specifying unit 33 specifies, as the target agent, a service agent that is estimated to contain the unacquired information determined by the unacquired information determining unit 32 from among a plurality of service agents that respectively provide services.

[0134] For example, when the unobtained information is a profile of user U1, the target agent identification unit 33 estimates, among a plurality of service agents that each provide a service, an agent of a profile providing service that provides a profile of user U as the service agent that includes the unobtained information. The profile of user U includes, for example, information such as attributes of user U and user U. In the service information device 2, a service agent is provided for each type of service, for example, but one service agent may be provided for multiple types of services.

[0135] For example, when the unobtained information is the service history of the user U in a specific service, the target agent identification unit 33 estimates an agent of the specific service among multiple service agents that provide the service as the service agent that includes the unobtained information. The specific service is, for example, a restaurant search service, a hotel search service, etc., but is not limited to such examples.

[0136] In addition, when the unacquired information is API information of the target service type, the target agent identification unit 33 estimates that, among the multiple service agents that provide the service, an agent of a service information providing service that provides API information of various services is the service agent that includes the unacquired information.

[0137] For example, if the unacquired information is information about another user U different from user U1, the target agent identification unit 33 identifies the personal agent PA of the other user U that is estimated to contain the unacquired information as the target agent.

[0138] The target agent identification unit 33 identifies, for example, as the target agent, a personal agent PA of another user U in a group chat room set for a plurality of users U including the user U and the other users U. Here, it is assumed that the target agent identification unit 33 is the target agent identification unit 33 of the information processing terminal 11 of user U1.

[0139] The input information received by the reception unit 30 is the character string "I'm thinking of sending chocolate to XXX on Valentine's Day. What kind of chocolate does she like?", and "XXX" is the user U2.

[0140] In this case, the target agent identification unit 33 identifies the personal agent PA2 of user U2 as the target agent. In addition, in this case, the service type identified by the service identification unit 31 is a "product search service," and the type of unacquired information determined by the unacquired information determination unit 32 is a "type of chocolate."

[0141] Furthermore, the input information received by the reception unit 30 is information on the character string "I'm thinking of going to eat with YYY around Akasaka. What kind of restaurant would be good?", and "YYY" is the user U. n Let us assume that:

[0142] In this case, the target agent specifying unit 33 identifies the user U n Personal Agent PA n is identified as the target agent. In this case, the service type identified by the service identification unit 31 is a "restaurant search service," the parameter value identified by the service identification unit 31 is "Area Akasaka," and the type of unacquired information determined by the unacquired information determination unit 32 is a "food genre."

[0143] Furthermore, when the input information received by the receiving unit 30 is a message to be posted in the chat room of group A, the target agent specifying unit 33 identifies other users U2, U3, U4, U5, U6, U7, U8, U9, U10, U11, U12, U13, U14, U15, U16, U17, U18, U19, U20, U21, U22, U23, U24, U25, n Alternatively, one or more of the personal agents PA of other users U may be identified as target agents.

[0144] For example, the target agent specifying unit 33 may specify other users U2, U n Among these, the personal agent PA of the user U that needs to acquire the unacquired information as determined by the unacquired information determination unit 32 is specified as the target agent.

[0145] For example, the unacquired information determined by the unacquired information determination unit 32 is "food genre." The food genre that user U2 likes can be identified from the chat messages of user U2 in the chat room of group A. n In this case, the target agent specifying unit 33 determines the type of cuisine that the user U likes. n Personal Agent PA n is identified as the target agent.

[0146] The target agent specification unit 33 determines the target agent of user U2 from the chat message of user U2. n The process of identifying the favorite food genre of each user U is performed, for example, by using a generation AI. For example, the target agent identification unit 33 inputs information including the chat message history in the chat room of group A and instruction information instructing the generation AI to estimate the favorite food genre of each user U from the chat message history as input information, and causes the generation AI to output information indicating the favorite food genre of each user U.

[0147] In addition, the target agent identification unit 33 can also estimate the favorite food genre of each user U from the chat message history in the chat room of group A, for example, using a food genre list, which is a list of words that indicate food genres.

[0148] [3.7.4.5. Inquiry section 34] The inquiry unit 34 inquires about unacquired information from the target agent identified by the target agent identification unit 33. The inquiry unit 34 inquires about acquired information from the target agent, for example, by sending a message including information identifying the unacquired information to the target agent. The inquiry unit 34 acquires the unacquired information provided by the target agent in response to the inquiry.

[0149] 4 is a diagram showing an example of the configuration of the inquiry unit 34 in the personal agent processing unit 23 of the information processing terminal 1 according to the embodiment. As shown in FIG. 4, the inquiry unit 34 includes a request text creation unit 40, an estimation processing unit 41, a generation processing unit 42, and an inquiry processing unit 43.

[0150] The request sentence creation unit 40 creates a request sentence that is a sentence requesting notification of unobtained information from the target agent identified by the target agent identification unit 33. The request sentence creation unit 40 can create the request sentence using, for example, a generation AI.

[0151] For example, the request sentence creation unit 40 inputs information including the type of unobtained information and instruction information as input information to the generation AI, causing the generation AI to create a request sentence. The type of unobtained information is, for example, a type of unspecified parameter, but is not limited to such an example. Also, the instruction information is, for example, information such as "Please create a sentence to inquire of the agent about the given information," but is not limited to such an example.

[0152] The request text creation unit 40 also has a template for the request text, and can create the request text by adding information indicating the type of unobtained information to the template. The request text creation unit 40 also has a template for the request text for each type of unobtained information, and can create the request text using the template.

[0153] The estimation processing unit 41 estimates the situation of a group in a chat room based on the message histories of multiple users U in the chat room. For example, the estimation processing unit 41 estimates the situation of a group in a chat room based on the message histories of multiple users U1, U2, U3, U4, U5, U6, U7, U8, U9, U10, U11, U12, U13, U14, U15, U16, U17, U18 n Based on the message history, the situation in Group A's chat room can be inferred.

[0154] 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 between multiple users U in the group, the level of intimacy of the group, the level of humor, etc.

[0155] The estimation processing unit 41 can also input information including, for example, the message history of multiple users U in the chat room of group A and instruction information instructing the generation AI to estimate the group situation in the chat room as input information, and cause the generation AI to output the estimated result of the group situation.

[0156] In this case, the instruction information may be, for example, a string of characters such as "Please estimate the group situation in the chat room of multiple users U from the chat message history between these multiple users U," but is not limited to such an example. The instruction information may also include a situation list, example information of a combination of message history examples and situation examples, and the like.

[0157] The generation processing unit 42 generates a message to be posted in a chat room of a group set up for a plurality of users U, including the user U and other users U, inquiring about unobtained information.

[0158] The message generated by the generation processing unit 42 is a chat message that is displayed in the group's chat room, but is a chat message that is displayed only in the chat room of the information processing terminal 1 of the user U that corresponds to the target agent identified by the target agent identification unit 33. Note that the chat message generated by the generation processing unit 42 may be displayed in the chat rooms of the information processing terminals 1 of all users U that belong to the group.

[0159] The message generated by the generation processing unit 42 is the same as the request text generated by the request text generation unit 40, and is generated by the same processing as that of the request text generation unit 40.

[0160] The generation processing unit 42 can also generate a message inquiring about unobtained information based on the situation estimated by the estimation processing unit 41. For example, if the estimation processing unit 41 estimates that the atmosphere of the group is bad, the generation processing unit 42 generates a message written in polite language, and if the estimation processing unit 41 estimates that the atmosphere of the group is bad, the generation processing unit 42 generates a message written in casual language.

[0161] Furthermore, when the estimation processing unit 41 determines that the topic of the group is not a topic of a specific food genre, the generation processing unit 42 generates a message inquiring about what type of food genre the user likes. When the estimation processing unit 41 determines that the topic of the group is Chinese food, the generation processing unit 42 generates a message inquiring about what type of Chinese food the user likes.

[0162] The query processing unit 43 queries the target agent for unobtained information using the request text created by the request text creation unit 40. The query processing unit 43 queries the target agent for unobtained information by sending information including the request text created by the request text creation unit 40 to the target agent. The query processing unit 43 acquires the unobtained information provided by the target agent in response to the query.

[0163] Furthermore, the inquiry processing unit 43 can also inquire about unobtained information from the target agent identified by the target agent identifying unit 33 by posting the message generated by the generation processing unit 42 to a chat room.

[0164] For example, when a non-display mode is set, which is a non-display setting, the inquiry processing unit 43 can notify the personal agent PA of the inquiry destination to not display the message generated by the generation processing unit 42. Also, for example, when a display mode is set, which is a display setting, the inquiry processing unit 43 can notify the personal agent PA of the inquiry destination to display the message generated by the generation processing unit 42.

[0165] [3.7.4.6.Providing Department 35] The providing unit 35 provides a service to the user U using information provided by the target agent in response to an inquiry by the inquiry unit 34.

[0166] For example, the providing unit 35 acquires information about the service of the service type identified by the service identifying unit 31 based on the service type identified by the service identifying unit 31 and the information provided by the target agent in response to an inquiry by the inquiry unit 34.

[0167] The providing unit 35 transmits to the service providing device 2 a service provision request including, for example, information indicating the service type identified by the service identifying unit 31 and information including, as parameter values, information provided by the target agent in response to the inquiry by the inquiry unit 34. As a result, information on the service in response to the service provision request is output from the service providing device 2.

[0168] If there is a parameter whose value has been specified by the service specifying unit 31, the providing unit 35 transmits information further including the value of the parameter as a service provision request to the service providing device 2. This allows the providing unit 35 to obtain more detailed information about the service.

[0169] In this way, the providing unit 35, for example, acquires information on a service of the service type identified by the service identifying unit 31 from the service providing device 2, and provides the acquired information on the service to the user U. For example, the providing unit 35 provides the information on the service acquired from the service providing device 2 to the user U by displaying the information on the service acquired from the service providing device 2 on the display unit 11.

[0170] For example, when the service type identified by the service identification unit 31 is a product search service, the providing unit 35 specifies the product search service and sends a search request including information indicating the type of product as parameter information to the service providing device 2 as a service provision request via the API of the service providing device 2.

[0171] The service providing device 2 searches for multiple products in response to the search request, and provides the search results to the providing unit 35 as information on services of the service type identified by the service identifying unit 31. The search results include, for example, information such as the name, price, rating, and description of each searched product, but are not limited to these examples.

[0172] For example, when the service type identified by the service identification unit 31 is a restaurant search service, the providing unit 35 specifies the restaurant search service and sends a search request as a service provision request to the service providing device 2 via the API of the service providing device 2, with information indicating the cuisine genre as parameter information.

[0173] The service providing device 2 searches for a plurality of restaurants in response to the search request, and provides the search results to the providing unit 35 as information on the service of the service type identified by the service identifying unit 31. The search results include, for example, information such as the name, location, rating, and introduction of each of the searched restaurants, but are not limited to these examples.

[0174] Fig. 5 is a diagram showing an example of a chat room screen 60 provided by the providing unit 35 in the processing unit 16 of the information processing terminal 1 according to the embodiment and displayed on the display unit 11. In the example shown in Fig. 5, restaurant information CTA1, restaurant information CTA2, restaurant information CTM_A1, and restaurant information CTM_A2 are displayed as service information on the chat room screen 60. The restaurant information CTA1 and restaurant information CTM_A1 are information on DDD Chinese restaurants, and the restaurant information CTA2 and restaurant information CTM_A2 are information on FFF Sichuan restaurants.

[0175] Restaurant information CTM_A1 and restaurant information CTM_A2 are message-format information included in chat message CTM2. 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.

[0176] The chat room screen 60 is a chat room of a chatbot where chats are exchanged between a personal agent PA and a user U, but if the input information received by the reception unit 30 is a chat message for a group chat, service information is displayed in the chat room for the group chat.

[0177] [3.7.4.7. Inquiry Response Unit 36] The inquiry response unit 36 ​​responds to an inquiry about unacquired information. For example, the inquiry response unit 36 ​​receives an inquiry about unacquired information from another personal agent PA, and provides the information in response to the inquiry from the other personal agent PA as unacquired information to the other personal agent PA.

[0178] 6 is a diagram showing an example of the configuration of the inquiry response unit 36 ​​in the personal agent processing unit 23 of the information processing terminal 1 according to the embodiment. As shown in FIG. 6, the inquiry response unit 36 ​​includes an inquiry reception unit 50, a provision availability determination unit 51, an inquiry necessity determination unit 52, an estimation processing unit 53, and a provision processing unit 54.

[0179] The inquiry receiving unit 50 receives an inquiry from a personal agent PA of another user U about unobtained information.

[0180] The provision possibility determination unit 51 determines whether or not to provide unobtained information in response to an inquiry received by the inquiry reception unit 50. The provision possibility determination unit 51 has, for example, provision possibility information indicating whether or not each type of unobtained information can be provided, and determines whether or not to provide the unobtained information based on the provision possibility information. The provision possibility information is set, for example, by the user U.

[0181] The provision possibility determination unit 51 determines that the unacquired information will be provided if the provision possibility information indicates that the provision of the unacquired information is possible, and otherwise determines that the unacquired information will not be provided.

[0182] The inquiry necessity determination unit 52 inquires of the user U as to whether or not the unacquired information can be provided in response to an inquiry received by the inquiry reception unit 50. The inquiry necessity determination unit 52 may have inquiry necessity information indicating whether or not an inquiry to the user U is necessary for each type of unacquired information, for example. The inquiry necessity information is set by the user U, for example.

[0183] If the type of unobtained information (for example, the type of unidentified parameter) is a type that requires an inquiry to user U, the inquiry necessity determination unit 52 pops up an inquiry message in the display area of ​​the display unit 11 to inquire about whether user U may be provided with the unobtained information.

[0184] If the user U inputs positive information (for example, the string "yes" or the string "OK") in response to the pop-up displayed inquiry message, the inquiry necessity determination unit 52 outputs the unobtained information to the personal agent PA that made the inquiry.

[0185] The estimation processing unit 53 estimates the relationship between the user U and another user U corresponding to the personal agent PA that made the inquiry. The relationship between the user U and another user U may be, for example, a parent-child relationship, a colleague relationship, a superior-subordinate relationship, a hobby relationship, etc. The relationship between the user U and another user U may also include the degree of intimacy, etc.

[0186] The estimation processing unit 53 estimates the relationship between the other user U and the user U, for example, based on the history of chat messages between the other user U and the user U.

[0187] The estimation processing unit 53 can, for example, input information to the generation AI including a history of chat messages between other users U and user U and instruction information instructing the generation AI to estimate the relationship between other users U and user U, and cause the generation AI to output an estimation result of the relationship between other users U and user U.

[0188] In this case, the instruction information may be, for example, a character string such as "Please estimate the relationship between given users from the chat message history between them," 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.

[0189] The provision processing unit 54 provides the personal agent PA with the unacquired information that the provision determination unit 51 has determined to be provided. For example, the provision processing unit 54 acquires the unacquired information that the provision determination unit 51 has determined to be provided from the storage unit 15 or the like, and provides the acquired unacquired information to the personal agent PA. Furthermore, the provision processing unit 54 provides the unacquired information to the personal agent PA when the user U has given permission in response to an inquiry made by the inquiry necessity determination unit 52.

[0190] In addition, the provision processing unit 54 provides the unacquired information to the personal agent PA when the provision possibility determination unit 51 determines that the unacquired information should be provided and the user U gives permission in response to the inquiry by the inquiry necessity determination unit 52.

[0191] For example, if the type of unobtained information is the type of chocolate that user U likes and user U likes bitter chocolate, the provision processing unit 54 outputs the string "bitter chocolate" or the string "XXX likes bitter chocolate" as unobtained information.

[0192] Also, for example, if the type of unobtained information is the genre of user U's favorite food and user U likes Chinese food, the information of the string "Chinese food" or the string "YYY likes Chinese food" is output as unobtained information.

[0193] Furthermore, the providing processing unit 54 provides the personal agent PA that made the inquiry with a message that corresponds to the estimation result of the estimation processing unit 53 and includes unacquired information. For example, the providing processing unit 54 provides the personal agent PA that made the inquiry with a message that is generated by the generation processing unit 42 according to the estimation result of the providing processing unit 54.

[0194] Furthermore, before providing the message generated by the generation processing unit 42 to the personal agent PA that made the inquiry, the providing processing unit 54 can also inquire of the user U as to whether or not the message can be provided. For example, the providing processing unit 54 displays the message generated by the generation processing unit 42 on the display unit 11 and inquires of the user U as to whether or not the message can be provided. If the providing processing unit 54 receives a response from the user U indicating that the message can be provided, the providing processing unit 54 provides the message generated by the generation processing unit 42 to the personal agent PA that made the inquiry.

[0195] For example, an inquiry as to whether or not to provide the message generated by the generation processing unit 42 is made by displaying information including the string "May I provide the following information to Mr. / Ms. YYY's terminal?" and the message generated by the generation processing unit 42 on the display unit 11, but is not limited to such an example.

[0196] The providing processing unit 54 can display, for example, in the chat room of the chat group, the inquiry information of the message generated by the generation processing unit 42. In this case, the inquiry information is not displayed in the chat rooms of other users U in the chat group.

[0197] The user U can operate the input unit 12 to respond to an inquiry from the provision processing unit 54. For example, the user U can respond to an inquiry from the provision processing unit 54 by inputting information such as the character string "My agent, this statement is wrong. I'd prefer ZZZ instead" (where "ZZZ" is, for example, a proper name of a certain category or a specific phrase) into the information processing terminal 1.

[0198] Furthermore, the user U can respond to the inquiry from the provision processing unit 54 by inputting the information of the character string "My agent, give it a softer nuance" into the information processing terminal 1. Note that the response to the inquiry from the provision processing unit 54 is not limited to the above-described example.

[0199] The providing processing unit 54 causes the generating processing unit 42 to regenerate the message based on the response from the user U. For example, the providing processing unit 54 causes the generating processing unit 42 to regenerate the message by outputting a regeneration instruction to the generating processing unit 42. The providing processing unit 54 can also inquire of the user U as to whether or not to provide the message regenerated by the generating processing unit 42 to the contacting personal agent PA by a process similar to that described above.

[0200] Furthermore, if there is no problem with the information in the inquiry from the providing processing unit 54, the user U can respond to the inquiry from the providing processing unit 54 by inputting information indicating a positive response, such as information on the character string "yes" or information on the character string "good", into the information processing terminal 1. If there is a positive response from the user U, the providing processing unit 54 provides the message generated by the generation processing unit 42 to the personal agent PA that made the inquiry.

[0201] [4. Processing Procedure] Next, a procedure for information processing by the processing unit 16 of the information processing terminal 1 according to the embodiment will be described. Fig. 7 is a flowchart showing an example of information processing by the personal agent processing unit 23 of the processing unit 16 of the information processing terminal 1 according to the embodiment.

[0202] 7, the personal agent processing unit 23 in the processing unit 16 of the information processing terminal 1 determines whether or not input information has been received (step S10). If the personal agent processing unit 23 determines that input information has been received (step S10: Yes), it determines what information has not yet been acquired based on the received input information (step S11).

[0203] Next, the personal agent processing unit 23 determines whether there is any unacquired information (step S12). If the personal agent processing unit 23 determines that there is any unacquired information (step S12: Yes), it identifies the target agent (step S13). Then, the personal agent processing unit 23 inquires about the unacquired information from the target agent identified in step S13 (step S14).

[0204] When the processing of step S14 is completed or when it is determined that there is no unacquired information (step S12: No), the personal agent processing unit 23 acquires service information from the service providing device 2 or the like (step S15) and provides the acquired service information to the user U (step S16).

[0205] When the processing of step S16 is completed or when it is determined that input information has not been accepted (step S10: No), the personal agent processing unit 23 determines whether there is an inquiry about unobtained information from another personal agent PA (step S17). When it determines that there is an inquiry (step S17: Yes), the personal agent processing unit 23 determines whether the unobtained information that is the subject of the inquiry is set to be available (step S18).

[0206] If the personal agent processing unit 23 determines that the unobtained information that is the subject of the inquiry is set to be available (step S18: Yes), it outputs the information corresponding to the inquiry to the personal agent PA that made the inquiry (step S19).

[0207] When the processing of step S19 is completed, when it is determined that there is no inquiry (step S17: No), or when it is determined that the unobtained information that is the subject of the inquiry is not set to be available (step S18: No), personal agent processing unit 23 determines whether or not it is time to end its operation (step S20). For example, personal agent processing unit 23 determines that it is time to end its operation when the power of information processing terminal 1 is turned off.

[0208] If the personal agent processing unit 23 determines that it is not time to end the operation (step S20: No), it proceeds to step S10, and if it determines that it is time to end the operation (step S20: Yes), it terminates the processing shown in Figure 7.

[0209] [5. Modifications] Some or all of the functions of the information processing terminal 1 described above may be realized by the service providing device 2. For example, the service providing device 2 may be configured to have some or all of the personal agent processing unit 23 described above in place of the information processing terminal 1.

[0210] In the above example, the generation AI is described as a text generation AI, but the generation AI is not limited to such an example and may be, for example, a multimodal generation AI. A multimodal generation AI is, for example, a generation AI that can generate text and images from text and images.

[0211] Furthermore, in the above-described example, the inquiry unit 34 inquires about unobtained information from the target agent identified by the target agent identification unit 33, but it is sufficient if the inquiry unit 34 can inquire about the unobtained information from the target agent identified by the target agent identification unit, and it is also possible to inquire about unobtained information from the target agent via another agent or device.

[0212] In the above example, the query unit 34 acquires the unacquired information provided by the target agent in response to the query, but the present invention is not limited to this example. For example, the target agent may request another agent or device to provide the unacquired information, and acquire the unacquired information provided by the other agent or device. The provision unit 35 provides a service to the user U using the unacquired information obtained in response to the query by the query unit 34.

[0213] [6. Hardware Configuration] The information processing terminal 1 according to the embodiment described above is realized by, for example, a computer 80 configured as shown in Fig. 8. Fig. 8 is a hardware configuration diagram showing an example of the computer 80 that realizes the functions of the information processing terminal 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.

[0214] 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.

[0215] 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.

[0216] 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.

[0217] 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.

[0218] For example, when the computer 80 functions as the information processing terminal 1 according to the embodiment, the CPU 81 of the computer 80 executes a program loaded onto the RAM 82, thereby realizing the functions of the processing unit 16. Furthermore, the HDD 84 stores data in the storage unit 15. The CPU 81 of the computer 80 reads and executes these programs from the recording medium 88, but as another example, these programs may be acquired from another device via the network N.

[0219] [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.

[0220] 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.

[0221] For example, the information processing terminal 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.

[0222] Furthermore, the above-described embodiments and modifications can be combined as appropriate within the scope of not causing any contradiction in the processing content.

[0223] [8. Effects] As described above, the information processing terminal 1 according to the embodiment is an example of an information processing device, and includes an unacquired information determination unit 32, a target agent identification unit 33, an inquiry unit 34, and a providing unit 22. The unacquired information determination unit 32 determines whether or not there is unacquired information among the information used to provide a service to the user U. When the unacquired information determination unit 32 determines that there is unacquired information, the target agent identification unit 33 identifies an agent that is presumed to contain the unacquired information as a target agent. The inquiry unit 34 inquires about the unacquired information of the target agent identified by the target agent identification unit 33. The providing unit 35 uses information obtained in response to the inquiry by the inquiry unit 34 to provide a service to the user U. This allows the information processing terminal 1 to appropriately acquire information about the user U and provide a service.

[0224] Furthermore, the target agent identification unit 33 identifies, as the target agent, a service agent that is estimated to contain unacquired information from among a plurality of service agents that respectively provide services, thereby enabling the information processing terminal 1 to appropriately acquire information about the user U and provide the service.

[0225] Furthermore, the target agent identification unit 33 identifies as the target agent a personal agent PA of another user U that is presumed to contain unacquired information. This enables the information processing terminal 1 to appropriately acquire information about the user U and provide a service.

[0226] The information processing terminal 1 also includes a reception unit 30 that receives input information from the user U, and a service identification unit 31 that identifies the type of service based on the input information received by the reception unit 30, and an unacquired information determination unit 32 that determines, as unacquired information, information on parameters whose values ​​have not been identified among parameters used to provide another service. This enables the information processing terminal 1 to more appropriately obtain information on the user U and provide the service.

[0227] Furthermore, the service identification unit 31 inputs the input information received by the reception unit 30 and information including the type of service to the generation AI, and identifies the type of service based on the information indicating the type of service identified by the generation AI. This allows the information processing terminal 1 to appropriately acquire information about the user U and provide the service.

[0228] The inquiry unit 34 also includes a request text creation unit 40 that creates a request text, which is a text that requests the target agent identified by the target agent identification unit 33 to notify the target agent of unobtained information, and an inquiry processing unit 43 that uses the request text created by the request text creation unit 40 to inquire about the unobtained information. This allows the information processing terminal 1 to more appropriately acquire information about the user U and provide services.

[0229] The information processing terminal 1 also includes an inquiry reception unit 50 that receives an inquiry about unacquired information from the personal agent PA, a provision determination unit 51 that determines whether or not to provide the unacquired information in response to the inquiry received by the inquiry reception unit 50, and a provision processing unit 54 that provides the unacquired information that the provision determination unit 51 determines to be provided to the personal agent. This enables the information processing terminal 1 to more appropriately obtain information about the user U and provide services.

[0230] Furthermore, the target agent identification unit 33 identifies, as the target agent, the personal agent PA of another user U in a group chat room set for a plurality of users U including the user U and the other user U. This enables the information processing terminal 1 to more appropriately acquire information about the user U and provide services.

[0231] The inquiry unit 34 also includes a generation processing unit 42 that generates a message to be posted in a chat room of a group set for multiple users U, including the user U and other users U, inquiring about unobtained information, and an inquiry processing unit 43 that posts the message generated by the generation processing unit 42 in the chat room to inquire about unobtained information from the target agent identified by the target agent identification unit 33. This enables the information processing terminal 1 to more appropriately acquire information about the user U and provide services.

[0232] The inquiry unit 34 also includes an estimation processing unit 41 that estimates the group situation in the chat room based on the message histories of multiple users U in the chat room, and the generation processing unit 42 generates a message inquiring about unobtained information based on the situation estimated by the estimation processing unit 41. This allows the information processing terminal 1 to more appropriately acquire information about the users U and provide services.

[0233] The information processing terminal 1 also includes an estimation processing unit 53 that estimates the relationship between the user U and other users U, and the provision processing unit 54 provides the personal agent with a message that includes unobtained information and corresponds to the estimation result of the estimation processing unit 53. This allows the information processing terminal 1 to more appropriately obtain information about the user U and provide services.

[0234] 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.

[0235] 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]

[0236] 11,12,···,1 n Information processing terminal 2. Service provision device 10. Communications Department 11 Display section 12 Input section 13 Imaging unit 14 Sensor Group 15 Storage section 16 Processing section 20,30 Reception 21 Acquisition Department 22,35 Providing Department 23 Personal Agent Processing Unit 31 Service Specific Department 32 Unobtained information determination unit 33 Target agent identification section 34 Inquiry Department 36 Query response section 40 Request Writing Department 41,53 Estimation processing unit 42 Generation processing section 43 Query processing section 50 Inquiry Reception Department 51 Provision availability determination unit 52 Inquiry necessity determination unit 54 Provision Processing Unit 100 Information Processing Systems N Network

Claims

1. an unacquired information determination unit that determines whether or not there is unacquired information among the information used to provide the service to the user; a target agent identification unit that, when it is determined by the unacquired information determination unit that there is unacquired information, identifies an agent that is estimated to include the unacquired information as a target agent; an inquiry unit that inquires about the unacquired information of the target agent identified by the target agent identification unit; a providing unit that provides the service to the user using information obtained in response to the inquiry by the inquiry unit.

1. An information processing device comprising:

2. The target agent identification unit Among a plurality of service agents each providing a service, a service agent that is estimated to include the unacquired information is identified as the target agent.

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

3. The target agent identification unit A personal agent of another user that is presumed to contain the unobtained information is identified as the target agent.

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

4. a reception unit that receives input information from a user; a service identification unit that identifies a type of the service based on the input information received by the reception unit, The unacquired information determination unit Among the parameters used to provide the service of the type, information of a parameter whose value is not specified is determined as the unacquired information.

4. The information processing device according to claim 1, wherein the information processing device is a computer.

5. The service specifying unit Inputting information including the input information received by the reception unit and information instructing identification of the type of the service to a generation AI, and identifying the type of the service based on the information indicating the type of the service identified by the generation AI.

5. The information processing apparatus according to claim 4,

6. The inquiry unit a request text creation unit that creates a request text, which is a text that requests the target agent identified by the target agent identification unit to notify the target agent of the unacquired information; an inquiry processing unit that uses the request text created by the request text creation unit to inquire about the unacquired information.

4. The information processing device according to claim 1, wherein the information processing device is a computer.

7. an inquiry receiving unit that receives an inquiry from the personal agent about the unacquired information; a provision possibility determination unit that determines whether or not to provide the unacquired information in response to the inquiry received by the inquiry reception unit; a provision processing unit that provides the unacquired information that has been determined to be provided by the provision determination unit to the personal agent.

4. The information processing apparatus according to claim 3,

8. The target agent identification unit A personal agent of the other user in a group chat room set for a plurality of users including the user and the other user is identified as the target agent.

4. The information processing apparatus according to claim 3,

9. The inquiry unit a message generation processing unit that generates a message to be posted in a chat room of a group set for a plurality of users including the user and the other user, the message inquiring about the unobtained information; an inquiry processing unit that inquires about the unacquired information from the target agent identified by the target agent identification unit by posting the message generated by the generation processing unit to the chat room.

9. The information processing apparatus according to claim 8,

10. The inquiry unit an estimation processing unit that estimates a situation of the group in the chat room based on message histories of the plurality of users in the chat room; The generation processing unit A message inquiring about the unobtained information is generated as the message based on the situation estimated by the estimation processing unit.

10. The information processing apparatus according to claim 9,

11. an estimation processing unit that estimates a relationship between the user and the other user; The providing processing unit A message according to the estimation result of the estimation processing unit, which message includes the unacquired information, is provided to the personal agent.

8. The information processing apparatus according to claim 7,

12. 1. A computer-implemented information processing method, comprising: a determining step of determining whether or not there is any information that has not yet been acquired among the information used to provide the service to the user; an identifying step of identifying an agent that is estimated to include the unacquired information as a target agent when it is determined that the unacquired information exists in the determining step; an inquiry step of inquiring about the unacquired information in the target agent identified by the identification step; and a providing step of providing the service to the user using information obtained in response to the inquiry made in the inquiry step. An information processing method comprising:

13. a determination step of determining whether or not there is any information that has not yet been acquired among the information used to provide the service to the user; an identification step of identifying an agent that is estimated to include the unacquired information as a target agent when it is determined by the determination step that the unacquired information exists; an inquiry step of inquiring about the unacquired information in the target agent identified by the identification step; and a provision procedure for providing the service to the user using information obtained in response to the inquiry made by the inquiry procedure. An information processing program characterized by:

Images