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

Abstract

To appropriately acquire information for improving the accuracy of response contents corresponding to input information of a user.SOLUTION: An information processing apparatus according to the present application includes a reception unit, an identification unit, a determination unit, a parameter value acquisition unit, a service information acquisition unit, and a provision unit. The specification unit specifies a type of service and values of one or more parameters among a plurality of parameters used for providing the type of service on the basis of the input information received by the reception unit. The determination unit determines an unspecified parameter whose value is unspecified among the plurality of parameters. The parameter value acquisition unit acquires the value of the unspecified parameter determined by the determination unit. The service information acquisition unit acquires information on a service based on values of a plurality of parameters including values of one or more parameters and a value of an unspecified parameter. The providing unit provides the user with the information on the service acquired by the service information acquiring 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, and causes the generation AI to generate a response message. [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 conventional technology does not disclose a technique for acquiring information to improve the accuracy of the response content corresponding to the user's input information, and there is room for improvement in terms of appropriately acquiring 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 information to improve the accuracy of response content corresponding to user input information. [Means for solving the problem]

[0006] The information processing device according to the present application includes a receiving unit, an identifying unit, a determining unit, a parameter value acquiring unit, a service information acquiring unit, and a providing unit. The receiving unit accepts input information including information related to a service from a user. The identifying unit identifies a service type and values ​​of one or more parameters among a plurality of parameters used to provide the service type based on the input information accepted by the receiving unit. The determining unit determines unspecified parameters, which are parameters whose values ​​are unspecified among the plurality of parameters. The parameter value acquiring unit acquires the values ​​of the unspecified parameters determined by the determining unit. The service information acquiring unit acquires service information based on values ​​of a plurality of parameters including the values ​​of the one or more parameters and the value of the unspecified parameter. The providing unit provides the service information acquired by the service information acquiring unit to the user. [Effects of the Invention]

[0007] According to one aspect of the embodiment, it is possible to obtain an effect that information for improving the accuracy of the response content corresponding to the input information of the user can be appropriately obtained. [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 a chat room screen including information about a service displayed on a display unit by a processing unit of the information processing terminal according to the embodiment. [Figure 5] FIG. 5 is a flowchart illustrating an example of information processing by the processing unit of the information processing terminal according to the embodiment. [Figure 6] FIG. 6 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 2. 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 In the following, information processing terminals 11, 12, . . . , 1 n 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.

[0013] The service providing device 2 includes information processing terminals 11, 12, . . . , 1 n Users U1, U2, , U n 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, and an electronic commerce service.

[0014] 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.

[0015] An instant messenger application for chatting (hereinafter, may be referred to as a chat app) is installed on the information processing terminal 1. The chat app allows sending and receiving messages in one-to-one chats, group chats, and one-to-many chats. The information processing terminal 1 is an example of an information processing device.

[0016] By operating the information processing terminal 1, the user U can start up a chat application and use the chat application to receive various services provided by the service providing device 2. The processing in the information processing terminal 11 will be described below, but the processing in the information processing terminals 12, . . . , 1 other than the information processing terminal 11 may also be performed. n The same processing can be performed on

[0017] When user U1 operates the information processing terminal 11 to start the chat application, a chat application screen, which is the screen of the chat application, is displayed on the information processing terminal 11. User U1 operates the information processing terminal 11 and selects an individual or a group as the destination of the chat message, whereby a chat room for one-on-one chat or a chat room for group chat is displayed on the chat application screen of the information processing terminal 11.

[0018] The information processing terminal 11 accepts a chat message entered by the user U1 in the chat room as input information (step S1). The chat message accepted by the information processing terminal 11 is a message addressed to an individual or group. The information processing terminal 11 displays the chat message entered by the user U1 in the chat room.

[0019] A chat message input by user U1 may include a message containing information about a service from user U1. In this case, information processing terminal 11 accepts input information containing information about the service from user U1. The information about the service is information about a service provided by service providing device 2, but may also be information about a service provided by a service providing device other than service providing device 2.

[0020] When the information processing terminal 11 receives a chat message input by the user U1 in the chat room as input information, it transmits a posting request including the received chat message to the service providing device 2 (step S2). When the service providing device 2 receives the posting request, it transmits the received chat message to the information processing terminal 1 of another user U who belongs to the same chat room and causes the information processing terminal 1 to display the chat message.

[0021] Based on the message 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 (step S3).

[0022] Information processing terminal 11 executes the process of step S3 regardless of whether or not the message received in step S1 includes information related to a service, but is not limited to this example. For example, information processing terminal 11 can execute the process of step S3 only if the message received in step S1 includes a specific term or phrase, or can execute the process of step S3 only if the message received in step S1 does not include a specific term or phrase.

[0023] The types of services identified by information processing terminal 11 include, but are not limited to, for example, a restaurant search service, a hotel search service, a restaurant reservation service, a hotel reservation service, an advertisement distribution service, a map information providing service, an e-commerce service, etc. Hereinafter, the type of service may be referred to as a service type.

[0024] 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.

[0025] If the service type is a restaurant search service, the required parameters include, for example, the area of ​​the restaurant, the planned date and time of dining, and the number of people, and the additional parameters include, but are not limited to, the type of food, price range, seating (terrace, table, tatami room), facilities (wheelchair, pets allowed), rating, allergenic ingredients, display order, and maximum number of items to be acquired.

[0026] Furthermore, if the service type is a hotel search service, the required parameters include, for example, the hotel area, planned stay date, time, and number of people, and additional parameters include, but are not limited to, the number of rooms, number of adults, number of children, rating, price range, facilities and services (wifi, Japanese-style room / Western-style room, double bed, single bed, non-smoking / smoking), display order, and maximum number of acquisitions.

[0027] Furthermore, if the service type is a restaurant reservation service, the required parameters include, for example, the area of ​​the restaurant, the planned date and time of dining, and the number of people, and the additional parameters include, but are not limited to, the type of food, seating (terrace, table, tatami room), and ingredients with allergies.

[0028] Furthermore, if the service type is a hotel reservation service, the required parameters include, for example, the area of ​​the hotel, the planned date and time of stay, and the number of people, and the additional parameters include, but are not limited to, the number of rooms, the number of adults, the number of children, the price range, the type of room, and facilities and services (wifi, Japanese-style room / Western-style room, double bed, single bed, non-smoking / smoking).

[0029] In step S3, the information processing terminal 11 can, for example, identify the values ​​of multiple parameters used to provide the service, and identifies the values ​​of parameters among these multiple parameters whose values ​​can be identified from the input information received in step S1.

[0030] For example, if the information processing terminal 11 can identify the values ​​of one or more required parameters based on the input information received in step S1, it identifies the values ​​of one or more required parameters. Also, if the information processing terminal 11 can identify the values ​​of one or more additional parameters based on the input information received in step S1, it identifies the values ​​of one or more additional parameters.

[0031] The information processing terminal 11, for example, uses a generating AI (Artificial Intelligence) to identify the service type and the values ​​of one or more parameters from among a plurality of parameters used to provide the service of that service type based on the information about the service received in step S1.

[0032] An example of a generative AI is a text generation AI, which is a large-scale language model trained to predict and output the next token from an input token sequence, such as a transformer-based model or an RNN (Recurrent Neural Network)-based model.

[0033] Examples of the transformer-based model include, but are not limited to, a generative pre-trained transformer (GPT), etc. Examples of the RNN-based model include, but are not limited to, a receptance weighted key value (RWKV).

[0034] 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.

[0035] The information processing terminal 11 inputs information including the chat message input by 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 chat message input by user U1.

[0036] The instruction information includes, for example, the string "From the given message, please identify the service type and the parameter values ​​used to provide that type of service. Please identify the service type from the service type list below, and the parameter values ​​from the parameter list below. Please output the identification results in the output format below," as well as a service type list, a parameter list, and output format information.

[0037] The service type list includes, for example, information linking a service type with information indicating the content of the service for each service type. The parameter list includes, for example, information linking a parameter with information indicating the content of the parameter for each service type. Note that the instruction information is not limited to the above example, and may be any information that can output the type of service and the value of the parameter used to provide the service of that type from a message.

[0038] 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.

[0039] Furthermore, if the generation AI is fine-tuned to output the type of service and the parameter values ​​used to provide that type of service from the message, the input information input to the generation AI does not need to include instruction information.

[0040] Furthermore, the information processing terminal 11 may be configured to identify the type of service and the value of the parameter used to provide that type of service from the message by a known slot-filling technique that does not use a generation AI.

[0041] In the example shown in FIG. 1(a), the information processing terminal 11 stores chat messages CTM1 and CTM4 from user U1, chat message CTM2 from user U2, and chat message CTM3 from user U3. m The chat message CTM3 is displayed. The name of the chat group is Group A. In the example shown in FIG. 1(a), Group A is made up of users U1, U2, U3, and U4. n It is a chat group.

[0042] For example, based on chat message CTM4, information processing terminal 11 identifies a restaurant search service as the type of service, and extracts the date "7 / 10" and the area "Around Akasaka" as the values ​​of one or more parameters from among multiple parameters used to provide the restaurant search service.

[0043] Next, the information processing terminal 11 determines unspecified parameters, whose values ​​are unspecified in step S3, from among the multiple parameters associated with the service type specified in step S3 (step S4). The process of step S4 is performed when the service type is specified in the process of step S3. If the service type is not specified in the process of step S3, the process of step S4 is not performed.

[0044] The information processing terminal 11 identifies a plurality of parameters associated with the service type identified in step S3. The information processing terminal 11 stores the service type and a plurality of parameters associated with each service. The plurality of parameters includes the necessary parameters and additional parameters described above, but may not include the additional parameters. The information processing terminal 11 identifies a plurality of parameters associated with the service type identified in step S3 from the service type and the plurality of parameters for each service type stored for each service.

[0045] For example, the information processing terminal 11 determines, as the unspecified parameter, a necessary parameter whose value is unspecified among the plurality of parameters associated with the service type identified in step S3. Furthermore, the information processing terminal 11 can also determine, as the unspecified parameter, an additional parameter whose value is unspecified in addition to the necessary parameter whose value is unspecified among the plurality of parameters.

[0046] 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 service type identified in step S3 based on the information output from the generation AI.

[0047] Next, the information processing terminal 11 acquires the value of the unidentified parameter determined in step S4 (step S5). The information processing terminal 11 can acquire the value of the unidentified parameter by, for example, inquiring of the user U1.

[0048] For example, the information processing terminal 11 outputs an inquiry message to the user U1 inquiring about the value of the unspecified parameter, and displays the inquiry message in a chat room displayed on the information processing terminal 11. The information processing terminal 11 stores information for each service type in which an inquiry message is linked to each parameter, identifies the inquiry message corresponding to the unspecified parameter determined in step S4, and outputs the identified inquiry message.

[0049] If the service type identified in step S3 is a restaurant search service and the unidentified parameter determined in step S4 is the planned time of dining, the inquiry message may be, for example, the string "Searching for restaurants that can be reserved. What time do you plan to eat at the restaurant?", but is not limited to such an example.

[0050] Furthermore, the information processing terminal 11 can also generate an inquiry message using the generation AI. For example, the information processing terminal 11 inputs information including instruction information, which is information instructing the generation AI to generate a sentence inquiring about the value of the unspecified parameter specified in step S3, to the generation AI, and causes the generation AI to generate the inquiry message.

[0051] If the service type identified in step S3 is a restaurant search service and the unidentified parameter determined in step S4 is the planned dining time, the instruction information to be input to the generation AI includes, for example, the string "Please create a sentence to inquire about the planned dining time required to search for restaurants that can be reserved."

[0052] The information processing terminal 11 has information for each service type in which query instruction information is linked to each parameter, identifies the instruction information corresponding to the unidentified parameter determined in step S4, inputs information including the identified instruction information to the generation AI, and causes the generation AI to generate an inquiry message.

[0053] User U1 operates information processing terminal 11 to input the value of the unidentified parameter. Information processing terminal 11 acquires the value of the unidentified parameter input by user U1 in response to the inquiry message. Information processing terminal 11 displays the acquired value of the unidentified parameter in the chat room as a chat message from user U1.

[0054] Furthermore, instead of inquiring about the value of the unspecified parameter from the user U1, the information processing terminal 11 can also acquire the value of the unspecified parameter from the history of chat messages in the chat room.

[0055] For example, the information processing terminal 11 inputs information to the generation AI including a history of one or more chat messages posted in the chat room before the message accepted in step S1 and instruction information instructing the generation AI to extract the value of the unidentified parameter from the history, and causes the generation AI to extract the value of the unidentified parameter.

[0056] In this case, the instruction information may include, for example, a character string "Please estimate the value of XXX used in YYY from the history of the given message," but is not limited to this example. "YYY" included in the instruction information is information indicating the service type, and "XXX" included in the instruction information is information indicating an unspecified parameter.

[0057] Furthermore, information processing terminal 11 may have a term dictionary that is a dictionary of terms corresponding to the unspecified parameter. In this case, information processing terminal 11 extracts terms using regular expressions or the like from the history of one or more chat messages posted in the chat room before the message accepted in step S1, and if the extracted term is included in the term dictionary, acquires the term as the value of the specified parameter.

[0058] Furthermore, when an unspecified parameter is set as an estimable parameter, the information processing terminal 11 can also estimate the value of the unspecified parameter. The information processing terminal 11 obtains the value of the unspecified parameter by estimating the value of the unspecified parameter.

[0059] For example, the information processing terminal 11 can estimate the value of the unidentified parameter based on the attributes of the user U1. The attributes of the user U include, for example, demographic attributes and psychographic attributes. The demographic attributes are demographic attributes of the user U. The psychographic attributes are attributes that indicate, for example, the interests, values, lifestyle, personality, etc. of the user U.

[0060] The information processing terminal 11 inputs information to the generation AI, for example, including attribute information indicating the attributes of user U1 and instruction information instructing the generation AI to estimate the value of an unidentified parameter from the attribute information, and causes the generation AI to extract the value of the unidentified parameter.

[0061] In this case, the instruction information may include, for example, a character string "Please estimate the value of XXX to be used in YYY from the given user attributes," but is not limited to this example. "YYY" included in the instruction information is information indicating the service type, and "XXX" included in the instruction information is information indicating an unspecified parameter.

[0062] In addition, the information processing terminal 11 can store estimation information that links the attributes of user U1 with parameter values, and estimate the value of a parameter that is linked to the same attribute as the attribute of user U1 in the estimation information as the value of the unidentified parameter.

[0063] Furthermore, the information processing terminal 11 can also estimate the value of the unidentified parameter based on a first conversation history, which is a conversation history between users U including user U1 in the chat room to which the message of user U1 accepted in step S1 was posted. For example, the information processing terminal 11 inputs information including the first conversation history and instruction information instructing the generation AI to estimate the value of the unidentified parameter from the first conversation history, and causes the generation AI to extract the value of the unidentified parameter.

[0064] In this case, the instruction information may include, for example, a character string "Please estimate the value of XXX used in YYY from the given conversation history," but is not limited to this example. "YYY" included in the instruction information is information indicating the service type, and "XXX" included in the instruction information is information indicating an unspecified parameter.

[0065] Furthermore, the information processing terminal 11 can also estimate the value of the unidentified parameter based on a second conversation history, which is a conversation history of multiple users U, including user U1, in a chat room other than the chat room to which the message of user U1 accepted in step S1 was posted. For example, the information processing terminal 11 inputs information including the second conversation history and instruction information instructing the generation AI to estimate the value of the unidentified parameter from the second conversation history, and causes the generation AI to extract the value of the unidentified parameter.

[0066] In this case, the instruction information may include, for example, a character string "Please estimate the value of XXX used in YYY from the given conversation history," but is not limited to this example. "YYY" included in the instruction information is information indicating the service type, and "XXX" included in the instruction information is information indicating an unspecified parameter.

[0067] In addition, the information processing terminal 11 can also estimate the value of the unidentified parameter using a generation AI similar to the above-mentioned process based on two or more of the attributes of the user U1, the first conversation history, and the second conversation history.

[0068] The instruction information used to estimate the value of the unspecified parameter may include, for example, information linking the estimated parameter value to one or more of an example of the attribute of user U1, an example of the first conversation history, and an example of the second conversation history, thereby improving the accuracy of the generation AI in estimating the value of the unspecified parameter.

[0069] The generation AI may also be fine-tuned to input information including one or more of the attributes of user U1, the first conversation history, and the second conversation history, and output estimated values ​​of the unspecified parameters. In this case, the input information to the generation AI does not need to include instruction information.

[0070] Next, the information processing terminal 11 acquires information about the service of the service type identified in step S3 based on the values ​​of multiple parameters including the values ​​of one or more parameters identified in step S3 and the value of the unidentified parameter acquired in step S5 (step S6).

[0071] For example, if the service type identified in step S3 is a restaurant search service, the information processing terminal 11 specifies the restaurant search service and sends a search request including values ​​for the restaurant area, planned dining date and time, and number of people to the service providing device 2 via the API of the service providing device 2.

[0072] The service providing device 2 searches for a plurality of restaurants in response to the search request and acquires the search results as information on the service of the service type identified in step S3. The search results include, for example, information such as the name, location, category of dishes served, and description of each of the searched restaurants, but are not limited to these examples.

[0073] Furthermore, if the service type identified in step S3 is a hotel search service, the information processing terminal 11 specifies the hotel search service and sends a search request including values ​​for the hotel area, planned stay date, time, and number of people to the service providing device 2 via the API of the service providing device 2.

[0074] The service providing device 2 searches for a plurality of hotels in response to the search request, and provides the search results as service information of the service type identified in step S3 to the information processing terminal 11. The search results include, for example, information such as the name, location, rating, and introduction of each searched hotel, but are not limited to these examples.

[0075] Furthermore, if the service type identified in step S3 is a hotel reservation service, the information processing terminal 11 specifies the hotel reservation service and sends a reservation request including values ​​for the hotel area, planned stay date, time, and number of people to the service providing device 2 via the API of the service providing device 2.

[0076] The service providing device 2 performs reservation processing in response to the reservation request, and provides the result of the reservation processing to the information processing terminal 11 as information on the service of the service type identified in step S3. The result of the reservation processing includes, for example, information such as the character string "Reservation completed" and information indicating the reservation content, but is not limited to such examples.

[0077] Next, the information processing terminal 11 provides the user U1 with the service information acquired from the service providing device 2 in step S6 (step S7). The information processing terminal 11 displays the service information acquired in step S6 as a chat message in the chat room where the chat message accepted in step S1 is displayed.

[0078] Furthermore, the information processing terminal 11 can display the service information acquired in step S6 in the chat room in a format different from the chat message, or can display the service information acquired in step S6 in a pop-up window superimposed on the chat room.

[0079] 1(b), messages CTM5 and CTM7 inquiring about the value of an unspecified parameter and messages CTM6 and CTM8 including the value of the unspecified parameter are shown in the chat room of group A on information processing terminal 11. Messages CTM5 and CTM7 are information displayed by parameter value acquisition unit 30, and messages CTM6 and CTM8 are information displayed by input by user U.

[0080] 1(b), restaurant information CTA1, restaurant information CTA2, restaurant information CTM_A1, and restaurant information CTM_A2 are displayed in the chat room of group A on 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.

[0081] Restaurant information CTM_A1 and restaurant information CTM_A2 are message-format information included in chat message CTM9. Restaurant information CTM_A1 and restaurant information CTM_A2 are displayed in the same display format as chat messages on the group chat screen. Restaurant information CTA1 and restaurant information CTA2 are banner-format information including images, text, and links.

[0082] In this way, the information processing terminal 1 accepts input information including information related to a service from the user U, and 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 based on the input information. The information processing terminal 1 determines unspecified parameters, the values ​​of which are unspecified among the plurality of parameters, and acquires the values ​​of the unspecified parameters.

[0083] Then, the information processing terminal 1 acquires information about the service based on multiple parameter values ​​including the value of the one or more identified parameters and the value of the acquired unidentified parameter, and provides the information about the service to the user U. This allows the information processing terminal 1 to appropriately acquire information for improving the accuracy of the response content corresponding to the input information of the user U.

[0084] Hereinafter, the information processing terminals 11, 12, . . . , 1 m The configuration of the information processing system including the service providing device 2 will be described in detail.

[0085] [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.

[0086] 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.

[0087] 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.

[0088] 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).

[0089] 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.

[0090] 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.

[0091] [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.

[0092] [3.2. Display section 11] The display unit 11 is, for example, an LCD (Liquid Crystal Display) or an organic EL (Electro Luminescence) display.

[0093] [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.

[0094] [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.

[0095] [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.

[0096] [3.6. Storage section 15] The storage unit 15 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk.

[0097] 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.

[0098] 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.

[0099] If the service type is a restaurant search service, the required parameters include, for example, the area of ​​the restaurant, the planned date and time of dining, and the number of people, and the additional parameters include, but are not limited to, the type of food, price range, seating (terrace, table, tatami room), facilities (wheelchair, pets allowed), rating, allergenic ingredients, display order, and maximum number of items to be acquired.

[0100] Furthermore, if the service type is a hotel search service, the required parameters include, for example, the hotel area, planned stay date, time, and number of people, and additional parameters include, but are not limited to, the number of rooms, number of adults, number of children, rating, price range, facilities and services (wifi, Japanese-style room / Western-style room, double bed / single bed, non-smoking / smoking), display order, and maximum number of acquisitions.

[0101] Furthermore, if the service type is a restaurant reservation service, the required parameters include, for example, the area of ​​the restaurant, the planned date and time of dining, and the number of people, and the additional parameters include, but are not limited to, the type of food, seating (terrace, table, tatami room), allergenic ingredients, display order, and the maximum number of items that can be obtained.

[0102] Furthermore, if the service type is a hotel reservation service, the required parameters include, for example, the hotel area, the planned date and time of stay, and the number of people, and the additional parameters include, but are not limited to, the number of rooms, the number of adults, the number of children, the price range, the room type, facilities and services (wifi, Japanese-style room / Western-style room, double bed / single bed, non-smoking / smoking), display order, and the maximum number of acquisitions.

[0103] The storage unit 15 also stores setting information. The setting information includes acquisition availability information, which is information indicating whether each parameter for each service type can be acquired, and estimation availability information, which is information indicating whether each parameter for each service type can be estimated. The setting information also includes attribute information indicating the attributes of the user U. The setting information also includes estimated usage information, which is information about other users U who have posted chat messages used to estimate the parameters.

[0104] [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.

[0105] The processing unit 16 may be partially or entirely realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array). A chat application (an example of an information processing program) is installed in the processing unit 16 as a dedicated application program that runs on an OS (Operating System). As a result, the processing unit 16 functions as a functional unit including a receiving unit 20, an identifying unit 21, a determining unit 22, an acquiring unit 23, an estimating unit 24, and a providing unit 25.

[0106] [3.7.1. Reception Unit 20] The reception unit 20 receives various requests and information. For example, the reception unit 20 receives information input in response to an input operation by the user U as input information.

[0107] For example, the receiving unit 20 receives input information including, as information related to a service, a message related to a service input by the user U in a chat room.

[0108] In addition, the information accepted by the accepting unit 20 as input information including information related to the service is not limited to messages related to the service entered by the user U in the chat room, but may also be, for example, information entered by the user U in an application other than a chat app.

[0109] The reception unit 20 also receives an estimation feasibility setting request including estimation feasibility information indicating whether parameters can be estimated. The estimation feasibility information is information indicating whether each parameter can be estimated for each service type, but may be information indicating whether parameters can be estimated for each service type, or may be information indicating whether parameters can be estimated for all service types. The reception unit 20 also receives an estimated usage information setting request including estimated usage information. The estimated usage information includes information about another user U who has posted a chat message used to estimate the parameters.

[0110] [3.7.2. Specification part 21] The identification unit 21 performs various identifications. Based on input information (e.g., a chat message) received by the reception unit 20, the identification unit 21 identifies the type of service and the value of one or more parameters among a plurality of parameters used to provide the service of that type.

[0111] For example, when the type of service can be identified based on the input information received by the receiving unit 20, the identifying unit 21 identifies the value of a parameter whose value can be identified from among multiple parameters used to provide that type of service.

[0112] For example, if the values ​​of one or more required parameters and one or more additional parameters among multiple parameters used to provide the identified type of service can be identified, the identification unit 21 identifies the values ​​of one or more required parameters and one or more additional parameters.

[0113] Furthermore, even if the values ​​of one or more necessary parameters cannot be identified, if one or more additional parameters can be identified, the identifying unit 21 identifies one or more additional parameters.

[0114] The identification unit 21, for example, uses a generation AI to identify a service type and the values ​​of one or more parameters from a plurality of parameters used to provide a service of that service type based on the input information accepted by the acceptance unit 20.

[0115] The generation AI is, for example, a text generation AI. The text generation AI is, for example, a large-scale language model trained to estimate and output the next token from an input token sequence, such as a transformer-based model or an RNN-based model. An example of a transformer-based model is, but is not limited to, GPT. An example of an RNN-based model is, but is not limited to, RWKV.

[0116] The generation AI may be a language model that has been trained (for example, fine-tuned) specifically for generating answer information. The generation AI may be located in an external information processing device, and the specification unit 21 uses the generation AI via an API, but the generation AI may also be located within the information processing terminal 1.

[0117] For example, the identification unit 21 inputs information including the input information received by the reception unit 20 and instruction information instructing the generation AI to identify the type of service and the values ​​of multiple parameters, and causes the generation AI to identify the type of service and the values ​​of one or more parameters.

[0118] The instruction information includes, for example, the string "Please identify the service type and the parameter values ​​used to provide that type of service from the following message. Please identify the service type from the service type list below, and the parameter values ​​from the parameter list below. Please output the identification results in the output format below," as well as a service type list, a parameter list, and output format information.

[0119] The service type list includes, for example, information linking a service type with information indicating the content of the service for each service type. The parameter list includes, for example, information linking a parameter with information indicating the content of the parameter for each service type. Note that the instruction information is not limited to the above example, and may be any information that can output the type of service and the value of the parameter used to provide the service of that type from a message.

[0120] 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.

[0121] Furthermore, if the generation AI is fine-tuned to output the type of service and the parameter values ​​used to provide that type of service from the message, the input information input to the generation AI does not need to include instruction information.

[0122] Furthermore, the specifying unit 21 may be configured to specify the type of service and the value of the parameter used to provide the service of that type from the message by using a known slot-filling technique that does not use a generation AI.

[0123] [3.7.3. Judgment unit 22] The determining unit 22 performs various determinations. The determining unit 22 determines, among a plurality of parameters linked to the service type identified by the identifying unit 21, an unspecified parameter whose value is unspecified.

[0124] The determination unit 22 identifies a plurality of parameters linked to the service type identified by the identification unit 21. The determination unit 22 stores the service type and a plurality of parameters linked to each other for each service. The plurality of parameters includes the necessary parameters and additional parameters described above. The determination unit 22 identifies a plurality of parameters linked to the service type identified by the identification unit 21 from the service type and the plurality of parameters for each service that are stored.

[0125] For example, the determination unit 22 determines, as an unspecified parameter, a necessary parameter whose value is unspecified among the multiple parameters linked to the service type identified by the identification unit 21. Furthermore, the determination unit 22 can determine, as an unspecified parameter, an additional parameter whose value is unspecified in addition to the necessary parameter whose value is unspecified among the multiple parameters.

[0126] 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 judgment unit 22 can also identify unspecified parameters from among multiple parameters linked to the service type identified by the identification unit 21 based on the information output from the generation AI.

[0127] [3.7.4. Acquisition part 23] The acquisition unit 23 acquires various types of information. The acquisition unit 23 includes a parameter value acquisition unit 30, a service information acquisition unit 31, and a posted information acquisition unit 32.

[0128] 3.7.4.1. Parameter Value Acquisition Unit 30 The parameter value acquisition unit 30 acquires the value of the unspecified parameter determined by the determination unit 22. The parameter value acquisition unit 30 includes an output processing unit 40 that outputs a message inquiring about the value of the unspecified parameter to the user U, and an acquisition processing unit 41 that acquires the value of the unspecified parameter input by the user U in response to the message output from the output processing unit 40.

[0129] 3.7.4.1.1. Output Processing Unit 40 The output processing unit 40 outputs an inquiry message to the display unit 11 inquiring of the user U about the value of the unidentified parameter, and causes the display unit 11 to display the inquiry message.

[0130] For example, the output processing unit 40 adds an inquiry message inquiring of the user U about the value of the unidentified parameter to the chat room displayed on the display unit 11, thereby causing the inquiry message to be displayed on the display unit 11.

[0131] The output processing unit 40 stores information for each service type in which an inquiry message is linked to each parameter, identifies the inquiry message corresponding to the unidentified parameter determined by the determination unit 22, and outputs the identified inquiry message to the display unit 11.

[0132] If the service type identified by the identification unit 21 is a restaurant search service and the unidentified parameter determined by the determination unit 22 is the planned time of dining, the inquiry message may be, for example, the string "Searching for restaurants that can be reserved. What time do you plan to eat at the restaurant?", but is not limited to such an example.

[0133] The output processing unit 40 outputs the value of the unspecified parameter input by the user U operating the input unit 12 in response to the above-mentioned inquiry message to the display unit 11, and causes the value of the unspecified parameter to be displayed on the display unit 11. The output processing unit 40 causes the value of the unspecified parameter to be displayed on the display unit 11, for example, by adding the value of the unspecified parameter to a chat room displayed on the display unit 11.

[0134] [3.7.4.1.2. Acquisition Processing Unit 41] The acquisition processing unit 41 acquires the value of the unidentified parameter determined by the determination unit 22 .

[0135] For example, the acquisition processing unit 41 acquires the value of the unidentified parameter input by the user U in response to the inquiry message output by the output processing unit 40.

[0136] Moreover, instead of inquiring of the user U about the value of the unspecified parameter, the acquisition processing unit 41 can also acquire the value of the unspecified parameter from the history of chat messages in the chat room.

[0137] For example, the acquisition processing unit 41 inputs information to the generation AI including a history of one or more chat messages posted to a chat room before the message accepted by the acceptance unit 20 and instruction information instructing the extraction of the value of an unidentified parameter from such history, and causes the generation AI to extract the value of the unidentified parameter.

[0138] In this case, the instruction information may include, for example, a character string "Please estimate the value of XXX used in YYY from the history of the given message," but is not limited to this example. "YYY" included in the instruction information is information indicating the service type, and "XXX" included in the instruction information is information indicating an unspecified parameter.

[0139] The acquisition processing unit 41 may also have a term dictionary, which is a dictionary of terms corresponding to the unspecified parameter. In this case, the acquisition processing unit 41 extracts terms using regular expressions or the like from the history of one or more chat messages posted in the chat room before the message accepted by the acceptance unit 20, and if the extracted term is included in the above-mentioned term dictionary, acquires the term as the value of the specified parameter.

[0140] Furthermore, when an unspecified parameter is set as an estimable parameter or when the value of the unspecified parameter is not acquired by the acquisition processing unit 41, the acquisition processing unit 41 acquires the value of the unspecified parameter estimated by the estimation unit 24. The acquisition processing unit 41 acquires the value of the unspecified parameter estimated by the estimation unit 24 based on, for example, one or more of the attributes of the user U, the first conversation history, and the second conversation history.

[0141] [3.7.4.2. Service information acquisition unit 31] The service information acquisition unit 31 acquires information about the service based on the values ​​of a plurality of parameters including the values ​​of one or more parameters and the value of an unspecified parameter.

[0142] For example, if the service type identified by the identification unit 21 is a restaurant search service, the service information acquisition unit 31 specifies the restaurant search service and sends a search request including values ​​for the restaurant area, planned dining date and time, and number of people to the service providing device 2 via the API of the service providing device 2.

[0143] The service providing device 2 searches for a plurality of restaurants in response to the search request, and acquires the search results as information on the service of the service type identified by the identification unit 21. The search results include, for example, information such as the name, location, category of dishes served, and description of each of the searched restaurants, but are not limited to these examples.

[0144] In addition, if the service type identified by the identification unit 21 is a hotel reservation service, the service information acquisition unit 31 specifies the hotel reservation service and sends a reservation request including values ​​for the hotel area, planned stay date, time, and number of people to the service providing device 2 via the API of the service providing device 2.

[0145] The service providing device 2 performs reservation processing in response to the reservation request, and acquires the result of the reservation processing as information on the service of the service type identified by the identification unit 21. The result of the reservation processing includes, for example, information such as the character string "Reservation completed" and information indicating the reservation content, but is not limited to such examples.

[0146] [3.7.4.3. Posted information acquisition unit 32] The posted information acquisition unit 32 acquires posted information including chat messages of other users U provided from the service providing device 2, and displays the chat messages of other users U on the display unit 11 based on the acquired posted messages.

[0147] [3.7.5. Estimation section 24] The estimation unit 24 performs various estimations. The estimation unit 24 estimates the values ​​of the unspecified parameters determined by the determination unit 22.

[0148] For example, when an unspecified parameter is set as an estimable parameter, the estimation unit 24 estimates the value of the unspecified parameter. The information stored in the storage unit 15 includes estimation feasibility information, which is information indicating whether each parameter can be estimated for each service type, and the estimation unit 24 determines whether the unspecified parameter is set as an estimable parameter based on the estimation feasibility information. Note that the estimation feasibility information may be information indicating whether a parameter can be estimated for each service type, or may be information indicating whether a parameter can be estimated for all service types.

[0149] In addition, in cases where the information stored in the memory unit 15 does not include estimation feasibility information, the estimation unit 24 can also output to the providing unit 25 an inquiry message (for example, information containing the string "May I estimate the parameters of XXX?") that inquires as to whether it is okay to estimate the unidentified parameters.

[0150] In this case, the estimation unit 24 estimates the value of the unidentified parameter corresponding to the inquiry message when the user U inputs a positive response (for example, information of the character string "yes") to the inquiry message by operating the input unit 12. Note that the estimation unit 24 can also cause the provision unit 25 to output the inquiry message even when the estimation possibility information is stored in the storage unit 15.

[0151] Furthermore, the estimation unit 24 estimates the value of the unspecified parameter when the value of the unspecified parameter is not acquired by the acquisition processing unit 41. The value of the unspecified parameter not acquired by the acquisition processing unit 41 does not include the value of the unspecified parameter estimated by the estimation unit 24.

[0152] The acquisition processing unit 41 may not acquire the value of an unidentified parameter, for example, when the acquisition processing unit 41 does not acquire the value of an unidentified parameter entered by user U in response to an inquiry message, or when the acquisition processing unit 41 does not acquire the value of an unidentified parameter from the history of chat messages in a chat room.

[0153] The estimation unit 24 estimates the value of the unspecified parameter based on the attributes of the user U. The estimation unit 24 inputs, for example, information including attribute information indicating the attributes of the user U and instruction information instructing the generation AI to estimate the value of the unspecified parameter from the attribute information, to the generation AI, and causes the generation AI to extract the value of the unspecified parameter.

[0154] In this case, the instruction information may include, for example, a character string "Please estimate the value of XXX to be used in YYY from the given user attributes," but is not limited to this example. "YYY" included in the instruction information is information indicating the service type, and "XXX" included in the instruction information is information indicating an unspecified parameter.

[0155] In addition, the estimation unit 24 can store estimation information that links the attributes of user U with the values ​​of parameters, and estimate the value of a parameter that is linked to the same attribute as the attribute of user U of the information processing terminal 1 in the estimation information as the value of the unidentified parameter.

[0156] Furthermore, the estimation unit 24 estimates the value of the unidentified parameter based on a first conversation history, which is a conversation history in the chat room displayed on the display unit 11. For example, the estimation unit 24 inputs information including the first conversation history and instruction information instructing the generation AI to estimate the value of the unidentified parameter from the first conversation history, and causes the generation AI to extract the value of the unidentified parameter.

[0157] In this case, the instruction information may include, for example, a character string "Please estimate the value of XXX used in YYY from the given conversation history," but is not limited to this example. "YYY" included in the instruction information is information indicating the service type, and "XXX" included in the instruction information is information indicating an unspecified parameter.

[0158] Furthermore, the estimation unit 24 may treat as a first conversation history only a conversation history with another user U who has been given permission in advance to use chat messages from among the conversation histories in the chat room, and estimate the value of the unspecified parameter based on the first conversation history. The other user U who has been given permission in advance to use chat messages is the other user U indicated in the estimated usage information, but is not limited to this example.

[0159] The estimation unit 24 can also estimate the value of the unspecified parameter by using the chat messages of the user U in the chat room displayed on the display unit 11 and the chat messages to the user U generated by the generation AI as the first conversation history. In this case, since the first conversation history does not include chat messages of other users U in the chat room, the estimation unit 24 can more easily narrow down the preferences and intentions of the user U from the user U's past interactions in the chat room.

[0160] The estimation unit 24 can also estimate the value of the unidentified parameter by using related chat messages posted during a predetermined period before the specific chat message is posted as the first conversation history. The specific chat message is, for example, a chat message accepted by the accepting unit 20 and used to identify the type of service by the identifying unit 21. The related chat message is, for example, a chat message associated with the type of service identified by the identifying unit 21.

[0161] The estimation unit 24 has, for example, a term list for each type of service, and determines, as a related chat message, a chat message that includes a term included in the term list corresponding to the type of service identified by the identification unit 21, among the chat messages posted in the chat room during a predetermined period before the specific chat message was posted. The estimation unit 24 can also use a generation AI to estimate a related chat message.

[0162] Furthermore, the estimation unit 24 estimates the value of the unidentified parameter based on a second conversation history, which is a conversation history of multiple users including the user U and another user U in a chat room different from the chat room displayed on the display unit 11. For example, the estimation unit 24 inputs information including the second conversation history and instruction information instructing the generation AI to estimate the value of the unidentified parameter from the second conversation history, and causes the generation AI to extract the value of the unidentified parameter.

[0163] In this case, the instruction information may include, for example, a character string "Please estimate the value of XXX used in YYY from the given conversation history," but is not limited to this example. "YYY" included in the instruction information is information indicating the service type, and "XXX" included in the instruction information is information indicating an unspecified parameter.

[0164] Furthermore, the estimation unit 24 may treat as a second conversation history only conversation histories with other users U who have been given permission in advance to use chat messages from among the conversation histories in other chat rooms, and estimate the value of the unspecified parameter based on the second conversation history. The other users U who have been given permission in advance to use chat messages are the other users U indicated in the estimated usage information, but are not limited to this example.

[0165] The estimation unit 24 can also estimate the value of the unspecified parameter by using chat messages of user U in other chat rooms and chat messages to user U generated by the generation AI as a second conversation history. In this case, since the second conversation history does not include chat messages of other users U in other chat rooms, the estimation unit 24 can more easily narrow down the preferences and intentions of user U from the past interactions of user U in other chat rooms.

[0166] The estimation unit 24 can also estimate the value of the unidentified parameter by using, as a second conversation history, other related chat messages posted to other chat rooms during a predetermined period before the other specific chat message is posted to the other chat room. The specific chat message is, for example, a chat message posted to another chat room that is accepted by the accepting unit 20 and used to identify the type of service by the identifying unit 21. The other related chat message is, for example, a chat message posted to another chat room that is related to the type of service identified by the identifying unit 21.

[0167] The estimation unit 24 has, for example, a term list for each type of service, and determines, as other related chat messages, chat messages that contain terms included in the term list corresponding to the type of service identified by the identification unit 21, among chat messages posted to other chat rooms during a predetermined period before the specific chat message was posted. The estimation unit 24 can also use a generation AI to estimate other related chat messages.

[0168] In addition, the estimation unit 24 can also estimate the value of the unidentified parameter using a generation AI similar to the above-mentioned process based on two or more of the attributes of the user U, the first conversation history, and the second conversation history.

[0169] The instruction information used to estimate the value of the unspecified parameter may include, for example, information linking the estimated parameter value to one or more of an example of the attribute of user U1, an example of the first conversation history, and an example of the second conversation history, thereby improving the accuracy of the generation AI in estimating the value of the unspecified parameter.

[0170] The generation AI may also be fine-tuned to input information including one or more of the attributes of the user U, the first conversation history, and the second conversation history, and output the estimated value of the unspecified parameter. In this case, the input information to the generation AI does not need to include instruction information.

[0171] [3.7.6.Providing Department 25] The providing unit 25 provides various services. The providing unit 25 provides the user U with information on the service acquired by the service information acquiring unit 31.

[0172] The providing unit 25 provides the user U with the information on the service acquired by the service information acquiring unit 31 by displaying the information on the service acquired by the service information acquiring unit 31 as a chat message in the chat room where the chat message accepted by the accepting unit 20 is displayed.

[0173] In addition, the providing unit 25 can provide the user U with the information on the service acquired by the service information acquiring unit 31 by displaying the information on the service acquired by the service information acquiring unit 31 in a format different from the chat message in the chat room, or by displaying the information on the service acquired by the service information acquiring unit 31 in a pop-up window superimposed on the chat room.

[0174] 4 is a diagram showing an example of a chat room screen including information about a service that is displayed on the display unit 11 by the processing unit 16 of the information processing terminal 1 according to the embodiment. A chat room screen 60 shown in FIG. 4 is a chat room screen for group A.

[0175] 4, messages CTM5 and CTM7 inquiring about the value of an unspecified parameter and messages CTM6 and CTM8 including the value of the unspecified parameter are shown in the chat room of group A on information processing terminal 11. Messages CTM5 and CTM7 are information displayed by parameter value acquisition unit 30, and messages CTM6 and CTM8 are information displayed by input by user U.

[0176] 4, restaurant information CTA1, restaurant information CTA2, restaurant information CTM_A1, and restaurant information CTM_A2 are displayed in the chat room of group A on 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.

[0177] Restaurant information CTM_A1 and restaurant information CTM_A2 are message-format information included in chat message CTM9. Restaurant information CTM_A1 and restaurant information CTM_A2 are displayed in the same display format as chat messages on the group chat screen. Restaurant information CTA1 and restaurant information CTA2 are banner-format information including images, text, and links.

[0178] [4. Processing Procedure] Next, a procedure of information processing by the processing unit 16 of the information processing terminal 1 according to the embodiment will be described. Fig. 5 is a flowchart showing an example of information processing by the processing unit 16 of the information processing terminal 1 according to the embodiment.

[0179] 5, the processing unit 16 of the information processing terminal 1 determines whether a chat message has been accepted as input information (step S10). If the processing unit 16 determines that a chat message has been accepted as input information (step S10: Yes), the processing unit 16 displays the accepted chat message on the display unit 11 (step S11) and transmits a posting request including the accepted chat message to the service providing device 2 (step S12).

[0180] Next, the processing unit 16 performs a process of identifying a service type and parameter values ​​based on the accepted chat message (step S13). The processing unit 16 determines whether or not the service type and one or more parameter values ​​have been identified in the process of step S13 (step S14).

[0181] If the processing unit 16 determines that the service type and the values ​​of one or more parameters have been identified in the identification process of step S13 (step S14: Yes), it performs a determination process to determine unidentified parameters, whose values ​​are unidentified, among the multiple parameters corresponding to the service type identified in step S13 (step S15).

[0182] The processing unit 16 determines whether or not it is determined in the determination process of step S15 that there is an unspecified parameter (step S16). If it is determined that there is an unspecified parameter (step S16: Yes), the processing unit 16 acquires the value of the unspecified parameter (step S17).

[0183] When the processing of step S17 is completed or when it is determined that there are no unspecified parameters (step S16: No), the processing unit 16 acquires service information of the service type identified in step S13 based on the values ​​of the multiple parameters (step S18).Then, the processing unit 16 provides the service information acquired in step S18 (step S19).

[0184] When the processing of step S19 is completed, when it is determined that a chat message has not been accepted as input information (step S10: No), or when it is determined that the service type and the value of one or more parameters have not been identified in the identification processing of step S13 (step S14: No), the processing unit 16 determines whether or not it is time to end the operation (step S20). The processing unit 16 determines that it is time to end the operation when, for example, the power of the information processing terminal 1 is turned off.

[0185] If the processing unit 16 determines that the operation end time has not yet arrived (step S20: No), it proceeds to step S10, and if it determines that the operation end time has arrived (step S20: Yes), it terminates the processing shown in Figure 5.

[0186] [5. Modifications] Some or all of the functions of the information processing terminal 1 described above may be implemented by the service providing device 2. For example, the service providing device 2 may be configured to have some or all of the above-mentioned reception unit 20, identification unit 21, determination unit 22, acquisition unit 23, estimation unit 24, and provision unit 25 instead of the information processing terminal 1.

[0187] 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.

[0188] Furthermore, the parameter value acquisition unit 30 can also individually output a message inquiring about the value of an unspecified parameter to the user U, for example, limited to the user U who has not yet acquired the value of the unspecified parameter.

[0189] In addition, the estimation unit 24 can also cooperate with another application or external server that is an application installed on the information processing terminal 1 but is different from the chat app, and obtain information for estimating the value of the unidentified parameter from the other application or external server.

[0190] In this case, the estimation unit 24 estimates the value of the unspecified parameter using information acquired from another application instead of or in addition to the above-mentioned information. The other application may be, but is not limited to, a schedule application, a map application, a reservation application, etc. The external server may be, but is not limited to, a web search server, etc.

[0191] The estimation unit 24 estimates the value of the unspecified parameter based on, for example, the schedule of the user U, the location of the user U, the history of the user U's travels, the details of reservations made by the user U at hotels, restaurants, etc., and the search query entered by the user U from other applications. As described above, the estimation unit 24 can estimate the value of the unspecified parameter using an estimation method that uses a generation AI, a rule-based estimation method, etc., but is not limited to these examples.

[0192] [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. 6. Fig. 6 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] [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.

[0199] 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.

[0200] 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.

[0201] Furthermore, the above-described embodiments and modifications can be combined as appropriate within the scope of not causing any contradiction in the processing content.

[0202] [8. Effects] As described above, the information processing terminal 1 according to the embodiment is an example of an information processing device and includes a receiving unit 20, an identifying unit 21, a determining unit 22, a parameter value acquiring unit 30, a service information acquiring unit 31, and a providing unit 25. The receiving unit 20 receives input information from a user U, including information related to a service. The identifying unit 21 identifies a service type and one or more parameter values ​​among a plurality of parameters used to provide the service type, based on the input information received by the receiving unit 20. The determining unit 22 determines an unspecified parameter, the value of which is an unspecified parameter among the plurality of parameters. The parameter value acquiring unit 30 acquires the value of the unspecified parameter determined by the determining unit 22. The service information acquiring unit 31 acquires service information based on the values ​​of a plurality of parameters, including the values ​​of one or more parameters and the value of the unspecified parameter. The providing unit 25 provides the user U with the service information acquired by the service information acquiring unit 31. This allows the information processing terminal 1 to appropriately acquire information for improving the accuracy of a response corresponding to the input information of the user U.

[0203] The parameter value acquisition unit 30 also includes an output processing unit 40 that outputs a message inquiring about the value of the unspecified parameter to the user U, and an acquisition processing unit 41 that acquires the value of the unspecified parameter input by the user in response to the message. This allows the information processing terminal 1 to appropriately acquire information for improving the accuracy of the response content corresponding to the input information of the user U.

[0204] Furthermore, the receiving unit 20 receives input information including, as information related to the service, a message about the service input by the user U in the chat room, and the parameter value acquiring unit 30 acquires the value of the unidentified parameter from the message history in the chat room. This allows the information processing terminal 1 to appropriately acquire information for improving the accuracy of the response content corresponding to the input information of the user U.

[0205] Furthermore, the information processing terminal 1 includes an estimation unit 24 that estimates the value of an unspecified parameter when the unspecified parameter is set as an estimable parameter, and the parameter value acquisition unit 30 acquires the value of the unspecified parameter estimated by the estimation unit 24. This allows the information processing terminal 1 to appropriately acquire information for improving the accuracy of the response content corresponding to the input information of the user U.

[0206] Furthermore, the information processing terminal 1 includes an estimation unit 24 that estimates the value of an unspecified parameter when the value of the unspecified parameter is not acquired by the acquisition processing unit 41, and the parameter value acquisition unit 30 acquires the value of the unspecified parameter estimated by the estimation unit 24. This allows the information processing terminal 1 to appropriately acquire information for improving the accuracy of the response content corresponding to the input information of the user U.

[0207] Furthermore, the estimation unit 24 estimates the value of the unidentified parameter based on the attributes of the user U. This allows the information processing terminal 1 to appropriately acquire information for improving the accuracy of the response content corresponding to the input information of the user U.

[0208] Furthermore, the receiving unit 20 receives input information including, as information related to the service, a message about the service input by the user U in the chat room, and the estimation unit 24 estimates the value of the unspecified parameter based on the conversation history in the chat room. This allows the information processing terminal 1 to appropriately acquire information for improving the accuracy of the response content corresponding to the input information of the user U.

[0209] Furthermore, the receiving unit 20 receives input information including, as information related to the service, a message about the service input by the user U in the chat room, and the estimation unit 24 estimates the value of the unspecified parameter based on conversation histories of multiple users, including the user U, in a chat room different from the chat room. This allows the information processing terminal 1 to appropriately acquire information for improving the accuracy of the response content corresponding to the input information of the user U.

[0210] The specification unit 21 also inputs information including the input information and information instructing specification of the service type and the values ​​of multiple parameters to the generation AI, causing the generation AI to specify the service type and the values ​​of one or more parameters. This allows the information processing terminal 1 to appropriately acquire information for improving the accuracy of the response content corresponding to the input information of the user U.

[0211] Furthermore, the multiple parameters include parameters necessary for providing the type of service identified by the identification unit 21. This allows the information processing terminal 1 to appropriately acquire information for improving the accuracy of the response content corresponding to the input information of the user U.

[0212] 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.

[0213] 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]

[0214] 1,11,12~1 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 Reception 21 Specific section 22 Judgment section 23 Acquisition Department 24 Estimation part 25 Providing Department 30 Parameter value acquisition section 31 Service information acquisition unit 32 Posted Information Acquisition Department 40 Output processing section 41 Acquisition processing unit 100 Information Processing Systems N Network

Claims

1. a reception unit that receives input information including information related to the service from a user; an identification unit that identifies a type of the service and values ​​of one or more parameters among a plurality of parameters used to provide the type of service based on the input information received by the reception unit; a determination unit that determines an unspecified parameter whose value is unspecified among the plurality of parameters; a parameter value acquisition unit that acquires the value of the unspecified parameter determined by the determination unit; a service information acquisition unit that acquires information about the service based on values ​​of the plurality of parameters including the value of the one or more parameters and the value of the unspecified parameter; a providing unit that provides the user with the service information acquired by the service information acquiring unit.

1. An information processing device comprising:

2. The parameter value acquisition unit an output processing unit that outputs a message inquiring about the value of the unspecified parameter to the user; an acquisition processing unit that acquires the value of the unspecified parameter input by the user in response to the message; 2. The information processing apparatus according to claim 1, wherein:

3. The reception unit receiving input information including a message about the service input by the user in a chat room as information about the service; The parameter value acquisition unit Obtaining the value of the unspecified parameter from the message history in the chat room 2. The information processing apparatus according to claim 1, wherein:

4. an estimation unit that estimates a value of the unspecified parameter when the unspecified parameter is set as an estimable parameter; The parameter value acquisition unit The value of the unspecified parameter estimated by the estimation unit is obtained.

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

5. an estimation unit that estimates a value of the unspecified parameter when the value of the unspecified parameter is not acquired by the acquisition processing unit; The parameter value acquisition unit The value of the unspecified parameter estimated by the estimation unit is obtained.

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

6. The estimation unit Estimating the value of the unspecified parameter based on the attribute of the user.

6. The information processing device according to claim 4, wherein:

7. The reception unit receiving input information including a message about the service input by the user in a chat room as information about the service; The estimation unit Estimating the value of the unspecified parameter based on the conversation history in the chat room 6. The information processing device according to claim 4, wherein:

8. The reception unit receiving input information including a message about the service input by the user in a chat room as information about the service; The estimation unit A value of the unspecified parameter is estimated based on conversation histories of a plurality of users including the user in a chat room different from the chat room.

6. The information processing device according to claim 4, wherein:

9. The identification unit Inputting information including the input information and information instructing the specification of the type of service and the values ​​of the plurality of parameters to a generation AI, and causing the generation AI to specify the type of service and the values ​​of the one or more parameters.

6. The information processing device according to claim 1, wherein:

10. The plurality of parameters are: The parameter necessary for providing the type of service identified by the identifying unit is included.

6. The information processing device according to claim 1, wherein:

11. 1. A computer-implemented information processing method, comprising: a receiving step of receiving input information including information related to the service from a user; an identifying step of identifying a type of the service and values ​​of one or more parameters among a plurality of parameters used for providing the type of service based on the input information received in the receiving step; a determination step of determining an unspecified parameter, the value of which is unspecified, from among the plurality of parameters; a parameter value acquisition step of acquiring the value of the unspecified parameter determined by the determination step; a service information acquisition step of acquiring information about the service based on values ​​of the plurality of parameters including the value of the one or more parameters and the value of the unspecified parameter; a providing step of providing the service information acquired by the service information acquiring step to the user.

1. An information processing method comprising:

12. a receiving procedure for receiving input information including information related to the service from a user; an identification step of identifying a type of the service and values ​​of one or more parameters among a plurality of parameters used for providing the type of service, based on the input information received by the reception step; a determination step of determining an unspecified parameter, the value of which is unspecified, from among the plurality of parameters; a parameter value acquisition step for acquiring the value of the unspecified parameter determined by the determination step; a service information acquisition step of acquiring information about the service based on values ​​of the plurality of parameters including the value of the one or more parameters and the value of the unspecified parameter; a providing procedure for providing the service information acquired by the service information acquisition procedure to the user, An information processing program characterized by:

Images