Programs, methods, information processing devices, systems

Abstract

There is a challenge in that we have not been able to obtain suitable output results using large-scale language models. [Solution] A program to be executed by a computer comprising a processor and a memory unit, wherein the processor executes: an instruction receiving step in which it receives a first instruction input by a user; a first generation step in which it generates a first prompt by including the first instruction received in the instruction receiving step and information relating to a plurality of processing processes for a task using a generation AI in an instruction A that identifies a processing process suitable for the instruction; a processing identification step in which it identifies a predetermined processing process based on information output from a large-scale language model by inputting the first prompt into the large-scale language model; an output acquisition step in which it acquires an output result that is output by inputting the first instruction received in the instruction receiving step into the predetermined processing process identified in the processing identification step; and a presentation step in which it presents information based on the output result acquired in the output acquisition step to the user.

Description

Technical Field

[0001] This disclosure relates to programs, methods, information processing apparatuses, and systems.

Background Art

[0002] Techniques for processing tasks related to business using large language models are known. Patent Document 1 discloses a technique for accurately giving instructions and advice related to sales activities to each salesperson without being affected by the skill level of the administrator.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] There is a problem that suitable output results cannot be obtained using a large language model. Therefore, this disclosure has been made to solve the above problems, and its object is to provide a technique for obtaining suitable output results using a large language model.

Means for Solving the Problems

[0005] A program for execution on a computer comprising a processor and a memory unit, wherein the processor executes: an instruction receiving step of receiving a first instruction input by a user; a first generation step of generating a first prompt by including the first instruction received in the instruction receiving step and information relating to multiple processing processes for a task using a generation AI in an instruction A that identifies a processing process suitable for the instruction; a processing identification step of identifying a predetermined processing process based on information output from a large-scale language model by inputting the first prompt into the large-scale language model; an output acquisition step of acquiring an output result that is output by inputting the first instruction received in the instruction receiving step into the predetermined processing process identified in the processing identification step; and a presentation step of presenting information based on the output result acquired in the output acquisition step to the user. [Effects of the Invention]

[0006] According to this disclosure, suitable output results can be obtained using a large-scale language model. [Brief explanation of the drawing]

[0007] [Figure 1] This is a block diagram showing the functional configuration of System 1. [Figure 2] This block diagram shows the functional configuration of Server 10. [Figure 3] This is a block diagram showing the functional configuration of user terminal 20. [Figure 4] This diagram shows the data structure of user table 1012. [Figure 5] This diagram shows the data structure of instruction table 1013. [Figure 6] This diagram shows the data structure of session table 1021. [Figure 7] This diagram shows the data structure of chat table 1022. [Figure 8] This flowchart shows the operation of the processing process registration process. [Figure 9]This is a flowchart showing the operation of the instruction processing. [Figure 10] A block diagram showing the basic hardware configuration of Computer 90. [Modes for carrying out the invention]

[0008] The embodiments of this disclosure will be described below with reference to the drawings. In all the drawings illustrating the embodiments, common components are denoted by the same reference numerals, and repeated explanations are omitted. The following embodiments are not intended to unduly limit the content of this disclosure as described in the claims. Not all components shown in the embodiments are necessarily essential components of this disclosure. Also, each drawing is a schematic diagram and is not necessarily a strict illustration.

[0009] <System 1 Configuration> System 1 in this disclosure is an information processing system that causes an artificial intelligence system to perform a suitable process on predetermined information. System 1 comprises a server 10, a user terminal 20, and an information processing device for generating AI 50, all connected via network N. Figure 1 is a block diagram showing the functional configuration of System 1. Figure 2 is a block diagram showing the functional configuration of server 10. Figure 3 is a block diagram showing the functional configuration of the user terminal 20.

[0010] Each information processing device consists of a computer equipped with an arithmetic unit and a memory device. The basic hardware configuration of the computer and the basic functional configuration of the computer realized by said hardware configuration will be described later. For each of the server 10, user terminal 20, and generation AI 50, explanations that overlap with the basic hardware configuration and basic functional configuration of the computer described later will be omitted.

[0011] <Server 10 Configuration> Server 10 is an information processing system that causes an artificial intelligence system to execute suitable processing for predetermined information. Server 10 includes a storage unit 101 and a control unit 104.

[0012] <Configuration of the storage unit 101 of server 10> The storage unit 101 of server 10 includes an application program 1011, a user table 1012, an instruction table 1013, a session table 1021, and a chat table 1022.

[0013] The application program 1011 is a program for causing the control unit 104 of server 10 to function as each functional unit. The application program 1011 includes applications such as a web browser application.

[0014] The user table 1012 is a table that stores and manages information of member users (hereinafter referred to as users) who use the service. By registering for use of the service, the information of the user is stored in a new record of the user table 1012. Thereby, the user can use the service according to the present disclosure. The user table 1012 is a table having columns of user ID, user name, and user data with the user ID as the primary key. FIG. 4 is a diagram showing the data structure of the user table 1012.

[0015] The user ID is an item for storing user identification information for identifying a user. The user identification information is an item for which a unique value is set for each user. The user name is an item for storing the name of the user. The user name may be set to any string such as a nickname instead of the real name. The user data includes the unique information of the user individual and the attribute information regarding the characteristics and background of the user. The unique information of the user includes the unique information of the user such as the date of birth (age) and gender of the user. User attribute information includes information such as the user's educational history (highest level of education, major, graduation year), occupation, work history, interests, place of residence, and language.

[0016] The instruction table 1013 is a table for storing and managing information (instruction information) related to instructions for executing processing related to the processing process. In this disclosure, it stores instruction statements (descriptive information) for executing predetermined processing on the generating AI 50, but is not limited to this. For example, a rule-based function, method, or other processing by an artificial intelligence model such as an arbitrary machine learning model or deep learning model that outputs predetermined output content for input content may be stored associated with each instruction. Note that one instruction information may contain multiple processing. Instruction table 1013 is a table with instruction ID as the primary key, and has columns for instruction ID, user ID, instruction type, instruction content, and descriptive information. Figure 5 shows the data structure of the instruction table 1013.

[0017] The instruction ID is an item that stores instruction identification information to identify an instruction. Each instruction has a unique value assigned to it. The User ID is an item that stores user identification information used to identify a user. The instruction type is an item that stores the type of instruction. For example, it is an item that stores the type of task to be executed and processed by the instruction. For example, strings such as "goal setting / evaluation," "instruction / coaching," "market research / strategy planning," "internal data search," and "audio transcription / meeting minute creation" may be stored. The instruction content is an item that stores the content of the instruction. Specifically, it includes strings of text, image information, etc., related to the instruction content. The instruction content is an item used as an instruction statement when actually executing the processing process. Note that one instruction information may contain multiple instruction contents. Descriptive information is an item that stores information (strings, text, image information, etc.) for describing instructions. Specifically, descriptive information is an item that stores an overview of the processing process and an overview of the instructions specified in the descriptive information.

[0018] Session table 1021 is a table for storing and managing information about sessions (session information). Session table 1021 is a table with session ID as the primary key and containing session ID and user ID columns. Figure 6 shows the data structure of session table 1021.

[0019] The session ID is an item that stores session identification information used to identify a session. Session identification information is an item with a unique value assigned to each session. The User ID is an item that stores user identification information used to identify a user.

[0020] Chat table 1022 is a table for storing and managing information related to chats (chat information). Chat table 1022 is a table that has columns for chat ID, session ID, input content, instruction ID, prompt, response, and date and time. Figure 7 shows the data structure of chat table 1022.

[0021] The chat ID is an item that stores chat identification information to identify a chat. The session ID is an item that stores session identification information used to identify a session. The input fields are items that store input strings, input images, etc., such as instructions received from the user. The instruction ID is an item that stores instruction identification information to identify an instruction. A prompt is an item that stores the prompt. The response is an item that stores information indicating the output content generated when a prompt is input to the AI50. The output content includes information such as strings and images. The date and time field stores the date and time when a new record was added or updated in the chat table.

[0022] <Configuration of the control unit 104 of server 10> The control unit 104 of the server 10 includes a user registration control unit 1041. The control unit 104 realizes each functional unit by executing the application program 1011 stored in the storage unit 101.

[0023] The user registration control unit 1041 processes information of users who wish to use the services related to this disclosure and stores it in the user table 1012. Information stored in the user table 1012 is obtained when a user opens a web page operated by the service provider from any information processing terminal, enters information into a designated input form, and sends it to the server 10. The user registration control unit 1041 stores the received information in a new record in the user table 1012, and user registration is completed. As a result, users stored in the user table 1012 can use the service. Prior to the registration of user information in the user table 1012 by the user registration control unit 1041, the service provider may perform a prescribed review and restrict whether or not the user can use the service. The user ID can be any string or number that can identify the user, and may be any string or number desired by the user, or the user registration control unit 1041 may automatically set any string or number.

[0024] <Configuration of User Terminal 20> The user terminal 20 is an information processing device operated by a user of the service. The user terminal 20 may be, for example, a mobile device such as a smartphone or tablet, or a stationary PC (Personal Computer) or laptop PC. It may also be a wearable device such as an HMD (Head Mount Display) or a smartwatch. The user terminal 20 includes a storage unit 201, a control unit 204, an input device 206, and an output device 208.

[0025] <Configuration of the storage unit 201 of the user terminal 20> The storage unit 201 of the user terminal 20 includes a user ID 2011 and an application program 2012.

[0026] User ID 2011 is the user's account ID. The user sends User ID 2011 from user terminal 20 to server 10. Server 10 identifies the user based on User ID 2011 and provides the services related to this disclosure to the user. User ID 2011 includes information such as a session ID that is temporarily assigned by server 10 to identify the user using user terminal 20.

[0027] The application program 2012 may be pre-stored in the memory unit 201, or it may be configured to be downloaded from a web server operated by the service provider via a communication interface. Application Program 2012 includes applications such as web browser applications. Application program 2012 includes an interpreted programming language such as JavaScript (registered trademark) that runs on a web browser application stored on the user terminal 20.

[0028] <Configuration of the control unit 204 of the user terminal 20> The control unit 204 of the user terminal 20 comprises an input control unit 2041 and an output control unit 2042. The control unit 204 realizes each functional unit by executing the application program 2012 stored in the memory unit 201.

[0029] <Configuration of the input device 206 of the user terminal 20> The input device 206 of the user terminal 20 includes a camera 2061, a microphone 2062, a position information sensor 2063, a motion sensor 2064, and a touch device 2065.

[0030] <Configuration of the output device 208 of the user terminal 20> The output device 208 of the user terminal 20 includes a display 2081 and a speaker 2082.

[0031] <Configuration of Generation AI50> Generative AI50 refers to large-scale artificial intelligence models used in the field of natural language processing (NLP). These models learn from large amounts of text data (web pages, books, articles, etc.) to understand patterns in human language and effectively perform natural language generation (NLG) tasks. Generative AI50 is used in many NLP tasks, such as generating responses to specific questions, automatically generating text, summarizing text, translation, and sentiment analysis. It can also be used in a variety of applications, including education, entertainment, customer service, and product development. Generative AI50 includes the following types. In this disclosure, large-scale language models that primarily output text information as output are described as a type of Generative AI50. OpenAI ChatGPT Anthropic Claude Google Gemini Stable Diffusion Midjourney Furthermore, the generation AI50 may be implemented as part of the functions of server 10.

[0032] <Configuration of Additional Configuration 40> Additional configuration 40 is...

[0033] <System 1 operation> The following describes each process in System 1. Figure 8 is a flowchart showing the operation of the processing process registration process. Figure 9 is a flowchart showing the operation of the instruction processing.

[0034] <Processing process registration process> The processing process registration process is a process that stores information related to the processing process in the storage unit 101 of the server 10 in advance. In this disclosure, each step of the processing process is configured to be executed by the administrator terminal 30, but this is not limited to this configuration. For example, it may be configured to be executed using the server 10 connected to the administrator terminal 30 via a network, or other information processing terminals.

[0035] <Overview of the processing process registration process> The processing process registration process is a series of operations that involves displaying the processing process registration screen on the administrator terminal, receiving input examples of the processing process's input and output from the administrator terminal, receiving input of descriptive information describing the overview of the processing process, inputting the input information into the generating AI 50 to obtain the instructions related to the processing process from the output, and storing those instructions. In this disclosure, the administrator is an employee or other person of the business operator that operates the information processing service related to this disclosure. The administrator is a type of user who has the authority to manage the information processing service related to this disclosure.

[0036] <Details of the processing process registration process> The details of the process registration process are described below.

[0037] <Displaying the registration screen> In step S101, the control unit 304 of the administrator terminal 30 performs a display step in which the processing process registration screen is displayed on the display 3081 of the administrator terminal 30. Specifically, the administrator opens the processing process registration page D1 by operating the input device 206 of the administrator terminal 30, running a browser application, and entering the URL of the web page (processing process registration page) for executing the processing process registration process. The control unit 304 of the administrator terminal 30 sends a request to the server 10 that includes the administrator ID 3011 to open the processing process registration page.

[0038] When server 10 receives a request, it generates a processing process registration page and sends it to administrator terminal 30. The control unit 304 of administrator terminal 30 displays the processing process registration page on the administrator terminal 30's display 3081 and presents it to the administrator terminal 30. The administrator terminal 30's display 3081 shows the processing process registration page D1. The processing process registration page D1 includes an input example input field D101, an output example input field D102, a description information input field D103, an instruction content input field D104, and a send button D111.

[0039] <Input / Output Example Input> In step S102, the control unit 304 of the administrator terminal 30 executes an input / output example input step to input input / output examples. The administrator operates the input device 306 of the administrator terminal 30 to input input examples and output examples of the processing process into the input example input field D101 and the output example input field D102, respectively. For example, in business processes such as "goal setting and evaluation," "instruction and coaching," "market research and strategy planning," "internal data search," and "voice transcription and meeting minute creation," text such as strings of characters and images indicating human instructions are entered into the input example input field D101. In addition, suitable output examples for the text such as strings of characters and images indicating those instructions are entered into the output example input field D102. For example, in the past, when requesting services such as "goal setting and evaluation," "instruction and coaching," "market research and strategy planning," "internal data search," and "audio transcription and meeting minute creation" from experts, the contents of the order forms, etc., are entered into input field D101, and the contents of the deliverables, etc., delivered by those experts are entered into input field D102.

[0040] <Enter descriptive information> In step S103, the control unit 304 of the administrator terminal 30 performs a descriptive information input step in which descriptive information is entered. The administrator operates the input device 306 of the administrator terminal 30 to input descriptive information into the descriptive information input field D103, which describes an outline of the instructions related to the processing process. For example, you would input descriptive information that outlines the instructions for processing tasks such as "goal setting and evaluation," "instruction and coaching," "market research and strategy planning," "internal data search," and "audio transcription and meeting minute creation."

[0041] In step S103, the control unit 104 of the server 10 performs a description evaluation step that evaluates the similarity between multiple descriptive pieces of information. Specifically, the control unit 104 of the server 10 transmits the input content of the description information input field D103 to the server 10. Based on the input content of the description information input field D103, the control unit 104 of the server 10 searches the description information items in the instruction table 1013 and identifies one or more description information items similar to the input content. The description evaluation step performs the step of evaluating the similarity between one or more description information items received in the processing acceptance step and multiple description information items that describe the processing content of each of the multiple processing processes stored in the storage unit. For example, similarity may be evaluated using cosine similarity, Jacquard similarity, the reciprocal of Euclidean distance, Manhattan distance, Levenshtein distance, or other methods such as generative AI. For example, evaluation may be based on the response obtained by generating a prompt that includes the input content of the descriptive information input field D103 and one or more descriptive information stored in the instruction table 1013, and inputting the prompt to the generative AI 50.

[0042] For example, the control unit 104 of the server 10 generates a similar evaluation prompt by including the input content of the descriptive information input field D103 in the ${input content} part of the similar evaluation prompt below, and one or more descriptive information stored in the instruction table 1013 in the ${descriptive information} part. The control unit 304 of the administrator terminal 30 obtains an evaluation result by comparing the similarity between the input content in the descriptive information input field D103 and the descriptive information in the instruction table 1013, based on the response content output when the generated similarity evaluation prompt is input to the generation AI 50. <Similar evaluation prompt> The following are instructions for the generating AI to perform a specific process. Compare the instructions with the comparison instructions. If the instructions are so similar that the processing results would be confused with the comparison instructions, output "Similar." Otherwise, output "Not Similar." Also, output the instructions that were determined to be similar. #Instructions ${Input content} #Comparison directive ${Descriptive Information}

[0043] Furthermore, instead of comparing the input content of the description information input field D103 with all the instruction information in the instruction table 1013, the control unit 104 of the server 10 may, for example, search for the instruction type item in the instruction table 1013 based on the instruction type entered in the instruction type input field D105, and compare it only with the description information relating to one or more instruction information that matches that instruction type. This eliminates the need to compare the input content of the description information input field D103 with the description information of a processing process with a completely different instruction type. In other words, the control unit 104 of the server 10 may be configured to compare multiple descriptive pieces of information having the same or similar instruction type (category).

[0044] The control unit 104 of the server 10 identifies one or more descriptive information items whose similarity is equal to or greater than a predetermined value. A predetermined number of descriptive information items may be identified in descending order of similarity.

[0045] In step S103, the control unit 304 of the administrator terminal 30 executes a correction notification step, which outputs a notification prompting the correction of multiple descriptive information that were evaluated as similar in the description evaluation step. The correction notification step executes a step of outputting a notification prompting the correction of one or more descriptive information that were evaluated as similar in the processing comparison step from among the one or more descriptive information received in the processing acceptance step. Specifically, when the control unit 104 of the server 10 identifies one or more descriptive pieces of information with a similarity score equal to or greater than a predetermined value, it sends a response containing one or more descriptive pieces of information to the administrator terminal 30. The control unit 304 of the administrator terminal 30 displays a notification on the administrator terminal 30's display 3081 indicating that the input content in the descriptive information input field D103 is similar to instruction information already stored in the instruction table 103 of the server 10, and presents it to the administrator. The notification may also include instructions to correct the input content in the descriptive information input field D103. For example, the control unit 304 of the administrator terminal 30 outputs and displays the message "This is similar to instruction information already registered; please correct it" on the display 3081 of the administrator terminal 30. Alternatively, the control unit 304 of the administrator terminal 30 may display and present one or more descriptive pieces of information similar to the content entered in the descriptive information input field D103 on the display 3081 of the administrator terminal 30. This allows the administrator to intuitively understand how to correct the content entered in the descriptive information input field D103.

[0046] Furthermore, the administrator may operate the input device 306 of the administrator terminal 30 to edit the input content of the descriptive information input field D103 and one or more descriptive information (one or more descriptive information similar to the input content) stored in the instruction table 1013. This allows the administrator to edit the input content of the descriptive information input field D103 during the processing process registration process, and also to edit the one or more descriptive information stored in the instruction table 1013 to a suitable format. This allows users to be prompted to modify the description information of one or more pre-stored processing processes when registering a new processing process, as the description information is similar to that of the previous processing processes.

[0047] Furthermore, this disclosure discloses, as an example, a configuration in which the input content of the description information input field D103 is compared with one or more description information stored in the instruction table 1013 during the processing process registration process, but is not limited to this. For example, the control unit 104 of the server 10 may evaluate the similarity between multiple description information stored in the instruction table 1013, display the multiple similar description information on the display 3081 of the administrator terminal 30, present it to the user, and prompt them to make corrections.

[0048] In this disclosure, the configuration in which the similarity evaluation is performed by the control unit 104 of the server 10 is given as an example, but the disclosure is not limited to this. For example, the similarity evaluation may be performed by the control unit 304 of the administrator terminal 30.

[0049] <Instruction content output> In step S104, the control unit 304 of the administrator terminal 30 performs a processing reception step in which it receives input from the user of one or more processing processes and one or more instruction contents describing the processing content of each processing process. Specifically, the administrator operates the input device 306 of the administrator terminal 30 to input text such as strings of characters, images, etc., related to the instructions for the processing process into the instruction input field D104. For example, the administrator inputs text such as strings of characters, images, etc., that indicate human-generated instructions in business processes such as "goal setting and evaluation," "instruction and coaching," "market research and strategy planning," "internal data search," and "voice transcription and meeting minute creation" into the instruction input field D104. The difference between the input content in the descriptive information input field D103 and the input content in the instruction content input field D104 is that, in the instruction processing described later, the input content in the descriptive information input field D103 is used when identifying the processing process (used to search for and identify the appropriate processing process), while the input content in the instruction content input field D104 is used when obtaining the processing result (used when executing the processing of the processing process).

[0050] Note that the instruction content and the descriptive information may be the same (or common to both). For example, you may omit either the descriptive information input field D103 or the instruction content input field D104.

[0051] Either the instruction content or the descriptive information may be generated using the generation AI 50 based on the other. Alternatively, the instruction content and descriptive information may be generated using the generation AI 50 based on the input example, output example, etc. entered in the input field D101. The control unit 304 of the administrator terminal 30 may be configured to input the input content acquired from the generating AI 50 into at least one of the following: input example input field D101, output example input field D102, description information input field D103, and instruction content input field D104.

[0052] For example, the control unit 304 of the administrator terminal 30 generates prompt C by including descriptive information in the ${descriptive information} section, an input example in the ${input example} section, and an output example in the ${output example} section of the following instruction C. Note that descriptive information, input examples, and output examples are not necessarily all required; a configuration using one or more of them is also acceptable. The control unit 304 of the administrator terminal 30 may also obtain the instruction content based on the response content output by inputting the generated prompt C to the generation AI 50. <Instruction C> Based on the following descriptive information, please create instructions to provide specific guidance for that information. #Descriptive information ${Descriptive Information} #Input example ${Input Example} #Output example ${Example Output} #Instructions

[0053] For example, the control unit 304 of the administrator terminal 30 generates prompt D by including the instruction content in the ${instruction content} part of the instruction D below. Alternatively, prompt D may be generated by including an input example and an output example in instruction D. The control unit 304 of the administrator terminal 30 may also acquire descriptive information based on the output content when the generated prompt D is input to the generation AI 50. <Instruction D> Based on the following instructions, please output a summary of those instructions. #Instructions ${Instruction content} #overview

[0054] In this disclosure, steps S102 to S104 are configured to input input / output examples, descriptive information, and instruction content in that order, but the administrator is not limited to this. The administrator may input each input field in any order. The control unit 304 of the administrator terminal 30 may also generate a prompt by including the input content of the previously entered input field in the instruction to generate the input content of the input field to be entered, based on the input content of the previously entered input field. The control unit 304 of the administrator terminal 30 may also obtain the input content of the input field to be entered based on the response content output by inputting the generated prompt to the generation AI 50. Furthermore, the control unit 304 of the administrator terminal 30 may obtain the input contents of multiple input items from the generation AI 50 based on the input contents of one input item. For example, the control unit 304 of the administrator terminal 30 may obtain the input contents of descriptive information and instruction content from input / output examples. For example, the control unit 304 of the administrator terminal 30 may obtain the input contents of input / output examples and instruction content from descriptive information. For example, the control unit 304 of the administrator terminal 30 may obtain the input contents of input / output examples and descriptive information from instruction content.

[0055] <Memorize instructions> In step S105, the control unit 104 of the server 10 performs an instruction content storage step to store the instruction content. The administrator selects the send button D111 by operating the input device 306 of the administrator terminal 30. The control unit 304 of the administrator terminal 30 sends the input values ​​of the administrator ID 3011, the descriptive information input field D103, and the instruction content input field D104 to the server 10. The control unit 104 of the server 10 receives and accepts the input values ​​of the administrator ID 3011, the descriptive information input field D103, and the instruction content input field D104. The control unit 104 of the server 10 stores the input values ​​of the administrator ID 3011, the descriptive information input field D103, and the instruction content input field D104 in the user ID, instruction content, and descriptive information fields of the new record in the instruction table 1013. The input values ​​of the input example input field D101 and the output example input field D102 may also be stored in columns not shown in the instruction table 1013.

[0056] Alternatively, the administrator may input the instruction type (category) into the instruction type input field D105 on the processing process registration page D1 by operating the input device 306 of the administrator terminal 30. The control unit 304 of the administrator terminal 30 sends the input value from the instruction type input field D105 to the server 10. The control unit 104 of the server 10 stores the received input value from the instruction type input field D105 in the instruction type field of the new record in the instruction table 1013.

[0057] The administrator stores instructions in the instruction table 1013, associating them with the instruction type and descriptive information, to implement processing processes for various tasks.

[0058] <Instruction Processing> Instruction processing is the process of executing a task using the generated AI50 in response to an instruction received from the user.

[0059] <Overview of Instruction Processing> The instruction processing is a series of processes that involves displaying an instruction screen on the user terminal, receiving input of a first instruction from the user, generating a first prompt to identify a processing process suitable for the first instruction, identifying a processing process based on the response output by inputting the first instruction prompt into the generating AI 50, obtaining the processing result by inputting the first instruction to that processing process, and presenting the processing result to the user terminal.

[0060] <Details of instruction processing> The details of the instruction processing are explained below.

[0061] <Instruction screen display> The user opens instruction page D1 by operating the input device 206 of the user terminal 20, running a browser application or the like, and entering the URL of a web page (instruction page) for executing the instruction process. The control unit 204 of the user terminal 20 sends a request to the server 10 that includes the user ID 2011 to open the instruction page.

[0062] When server 10 receives a request, it generates an instruction page and sends it to user terminal 20. The control unit 204 of user terminal 20 displays the instruction page on the user terminal 20's display 2081 and presents it to the user. The user terminal 20's display 2081 shows instruction page D1. Instruction page D3 includes instruction input field D301.

[0063] <First instruction input> In step S302, the control unit 104 of the server 10 performs an instruction reception step to receive a first instruction entered by the user. Specifically, the user inputs instructions into the instruction input field D301 by operating the input device 206 of the user terminal 20. For example, the following instructions may be entered for each business process. Goal setting and evaluation "Clarify your goals." "I want to check on the progress." "We will hold an evaluation meeting." Instruction and coaching "Set a goal." "Conduct a role-playing exercise." "Please specify the areas for improvement." Market research and strategy planning "Research the competition." "We want to understand the needs." "Collect the data" Internal Data Search "Please provide relevant information." "Extract the data" "Compare the search results" Audio transcription and meeting minute creation "Transcribe the audio." "Please correct the typographical error." "Let's organize the agenda."

[0064] In step S302, the instruction reception step performs the step of receiving a first instruction entered by the user via the messenger service. Specifically, the user may input instructions via any messenger service (Slack, Chatwork, LINE Works, etc.) by operating the input device 206 of the user terminal 20. For example, the configuration may involve inputting the first instruction into a designated channel or room within the messenger service. The messenger service is configured to send pre-entered instructions to the server 10 related to this disclosure, and is configured to output information received from the control unit 104 of the server 10 to the user terminal 20 via the messenger service.

[0065] <Generate the first prompt> In step S303, the control unit 104 of the server 10 executes a first generation step to generate a first prompt by including the first instruction received in the instruction reception step and information related to multiple processing processes for a task using the generation AI in instruction A, which identifies a processing process suitable for the instruction. The first generation step executes a step to generate a first prompt by including the first instruction and multiple descriptive pieces of information describing the processing content of each of the multiple processing processes in instruction A. Specifically, the control unit 104 of the server 10 generates prompt A by including the first instruction received in step S302 in the ${instruction statement} part of instruction A, and one or more descriptive information in the ${descriptive information 1}, ${descriptive information 2}... parts. <Instruction A> Refer to the following instructions and output the appropriate descriptive information (which indicates a task that performs the processing related to the instructions) from among the descriptive information that is suitable for executing the instructions. #Instructions ${indicative text} #Descriptive information ${Description Information 1} ${Description Information 2} ... #Output content

[0066] <Process Identification> In step S304, the control unit 104 of the server 10 inputs a first prompt to the large-scale language model and performs a processing identification step to identify a predetermined processing process based on the information output from the large-scale language model. Specifically, the control unit 104 of the server 10 obtains a string of descriptive information contained in the output response content by inputting the generated prompt A to the generation AI 50. In addition, prompt A may also include an instruction to output an instruction ID associated with the descriptive information. The control unit 104 of server 10 searches the descriptive information items in the instruction table 1013 based on the acquired descriptive information to identify the instruction information (processing process). Alternatively, the control unit 104 of server 10 may also search the instruction ID item in the instruction table 1013 based on the acquired instruction ID to identify the instruction information (processing process). Note that Prompt A may be configured to output multiple descriptive pieces of information (instruction IDs) instead of just one descriptive piece of information (instruction ID). In other words, it may be configured to identify multiple suitable instruction pieces of information (processing processes) for the instruction received in step S302.

[0067] In step S304, the process identification step includes identifying multiple processing processes based on information output from a large-scale language model, presenting multiple processing processes to the user for selection, and receiving a selection operation from the user for a predetermined processing process from among the presented multiple processing processes, and identifying the selected predetermined processing process. Includes. Specifically, if multiple instruction pieces are identified, the control unit 104 of the server 10 transmits these multiple instruction pieces to the user terminal 20. The control unit 204 of the user terminal 20 displays and presents the descriptive information contained in the received multiple instruction pieces on the display 2081 of the user terminal 20 in a selectable format. The user selects and identifies a predetermined instruction piece (processing process) from the presented multiple instruction pieces by operating the input device 206 of the user terminal 20. Furthermore, it is also acceptable to have a configuration in which multiple instruction pieces are identified in step S304.

[0068] The control unit 104 of server 10 may pre-process the descriptive information in the instruction table 1013 by vectorizing and converting it into a KnowledgeGraph, thereby transforming it into a form suitable for the processing process. Alternatively, when identifying a processing process, the descriptive information in the instruction table 1013 may be pre-processed by vectorizing and converting it into a KnowledgeGraph. Furthermore, when identifying a processing process, it is not necessarily required to use a large-scale language model; the system may be configured to acquire instruction information that has similar descriptive information to the first instruction received from the user (semantic search method). Similarity may be evaluated using cosine similarity, Jacquard similarity, Euclidean distance, Manhattan distance, Levenshtein distance, or other reciprocals, or by using generative AI, etc. The control unit 104 of server 10 may also rank the descriptive information based on the KnowledgeGraph, etc., based on the first instruction, and identify the instruction information according to that ranking (KnowledgeGraph method). Furthermore, the control unit 104 of the server 10 may identify and acquire instruction information by combining methods such as semantic search, knowledge graphs, and large-scale language models.

[0069] <Acquisition of processing results (first embodiment)> In step S305, the control unit 104 of the server 10 executes an output acquisition step to acquire the output result that is output by inputting the first instruction received in the instruction reception step to a predetermined processing process identified in the processing identification step. Specifically, the control unit 104 of the server 10 inputs the first instruction received in step S302 to the processing process identified based on the instruction information identified in step S304. The control unit 104 of the server 10 then acquires the output result output from the processing process. For example, the instruction information may be rule-based, with each instruction associated with a function, method, or other process performed by an artificial intelligence model such as a machine learning model or deep learning model that outputs a predetermined output for a given input. The control unit 104 of the server 10 inputs the first instruction received in step S302 to the processing process of the function, method, or artificial intelligence model such as a machine learning model or deep learning model associated with the instruction information. The control unit 104 of the server 10 acquires the output result output from the processing process.

[0070] <Acquisition of processing results (second embodiment)> The output acquisition step includes a second generation step which generates a second prompt by including the first instruction received in the instruction reception step in instruction B corresponding to a predetermined processing process, and a step which acquires the output result output from the large-scale language model by inputting the second prompt to the large-scale language model. Instruction B includes an instruction that prompts for additional instructions for any missing information in the first instruction. Specifically, the control unit 104 of the server 10 generates prompt B by including the first instruction received in step S302 in the ${instruction statement} part of instruction B below, and the instruction content included in the instruction information identified in step S304 in the ${instruction content} part. The control unit 104 of the server 10 obtains the output result based on the response content output by inputting the generated prompt B to the generation AI 50. <Instruction B> For each of the following instructions, execute the process described in the instructions and output the result. If there are any missing details in the instructions, do not execute the instructions, but instead output a message prompting you to provide additional instructions for the missing details. Also, if you are unable to process the instructions properly, output information indicating that you are unable to process them. #Instructions ${indicative text} #Instructions ${Instruction content} #Output content

[0071] The output result for prompt B may include a script language such as a predetermined program, structured data such as JSON, depending on the instruction statement and instruction content. The control unit 104 of server 10 may execute predetermined processing according to the script language included in the output result. The output result for script B may include instructions (commands) to be executed by referring to other instruction information. The control unit 104 of server 10 may execute the processing process related to other instruction information in accordance with the instructions (commands) that refer to the processing process related to other instruction information included in the output result.

[0072] For example, in response to the instruction "clarify the objective," the following processing steps will be executed. Note that each processing step does not need to be included in a single instruction; it may also be executed by separately referring to processing steps defined in other independent instruction information. Furthermore, the processing steps do not need to be executed by a single serial processing step; multiple processing steps may be selectively branched and executed according to various conditions. <Execution of the process for clarifying objectives> Processing step 1: Collection of internal documents • Retrieve the following documents from the business plan folder. Medium-term management plan, annual business plan, departmental goal setting documents, past performance reports Processing Process 2: Analysis of related documents • Review of existing goals and progress • Extraction and evaluation of KPIs Identifying the problem areas

[0073] <Processing results displayed> In step S306, the control unit 104 of the server 10 performs a presentation step in which it presents information to the user based on the output results acquired in the output acquisition step. Specifically, the control unit 104 of the server 10 acquires the processing result in step S305 and sends it to the user terminal 20. The control unit 204 of the user terminal 20 displays the received processing result on the display 2081 of the user terminal 20. For example, in the process of clarifying goals, the user is presented with a report containing items such as confirmation of existing goals and achievement status, extraction and evaluation of KPIs, and identification of issues.

[0074] In step S306, the presentation step performs the step of presenting information based on the output results to the user via the messenger service. Specifically, the control unit 104 of the server 10 may acquire the processing result in step S305 and send the processing result to a predetermined channel or room in the messenger service. The information received from the control unit 104 of the server 10 is output to the user terminal 20 via the messenger service as the processing result.

[0075] The presentation step includes an additional input step that prompts the user to enter additional instructions if the output results indicate that there are deficiencies in the first instruction. Specifically, if the processing result in step S305 includes output content prompting the input of additional instructions based on any deficiencies in the instruction statement, the control unit 104 of the server 10 transmits the output content to the user terminal 20. The control unit 204 of the user terminal 20 displays and presents the received output content on the display 2081 of the user terminal 20.

[0076] <Processing result presentation (variant)> In step S306, if the control unit 104 of the server 10 contains information indicating that the large-scale language model cannot properly process the first instruction received in the instruction reception step, it executes an instruction notification step to notify a predetermined contact connected via a network to the computer of the first instruction. The instruction notification step executes a step to notify a predetermined contact associated with a predetermined processing process of the first instruction. Specifically, if the processing result in step S305 includes output content that cannot properly process the content of the instruction statement, the control unit 104 of the server 10 will notify a predetermined contact, associated with an unillustrated column of the instruction information identified in step S302, via email or messenger service. Notification may also be made via telephone, fax, or other means. The predetermined contact is, for example, an external contractor capable of processing the first instruction. The external contractor can process the first instruction and deliver the processing result to the user. This allows the user to have the large-scale language model process the first instruction if it is capable of doing so, and to have a designated external vendor process the first instruction if it is not capable of doing so.

[0077] The control unit 104 of the server 10 executes a contact output step in which the output results acquired in the output acquisition step output predetermined contacts connected to a computer via a network. The contact output step is a step in which predetermined contacts associated with a predetermined processing process are output. The control unit 104 of the server 10 is not necessarily required to send a notification to a predetermined contact. The control unit 104 of the server 10 may output information indicating the predetermined contact to the user terminal 20 and display it on the user terminal 20's display 2081. Furthermore, the control unit 104 of the server 10 may always output information indicating the predetermined contact, not only when it contains information indicating that the large-scale language model cannot properly process the first instruction, or it may output information indicating the predetermined contact depending on any conditions. In addition, instruction B may include an instruction statement that associates predetermined conditions (for example, conditions under which the first instruction cannot be processed properly) with information indicating predetermined contact information (email address, URL, or any identifying information indicating contact information) according to those conditions. In this case, a large-scale language model that receives input of prompt B, which includes instruction B, will output information indicating predetermined contact information according to the content of the first instruction. For example, instruction B may include multiple conditions associated with information indicating multiple contacts corresponding to those multiple conditions. The control unit 104 of the server 10 can send the response content output from the large-scale language model to the user terminal 20, thereby presenting the user with information regarding appropriate contacts for external contractors, etc., depending on the conditions.

[0078] <Basic Computer Hardware Configuration> Figure 10 is a block diagram showing the basic hardware configuration of computer 90. Computer 90 comprises at least a processor 901, main memory 902, auxiliary storage 903, and a communication interface IF991. These are electrically connected to each other by a communication bus 921.

[0079] The processor 901 is hardware for executing the instruction set written in a program. The processor 901 consists of an arithmetic unit, registers, peripheral circuits, etc.

[0080] Main memory 902 is used to temporarily store programs and data processed by programs, etc. For example, it is a volatile memory such as DRAM (Dynamic Random Access Memory).

[0081] Auxiliary storage device 903 refers to a storage device for saving data and programs. Examples include flash memory, HDD (Hard Disc Drive), magneto-optical disk, CD-ROM, DVD-ROM, and semiconductor memory.

[0082] The IF991 communication interface is an interface for inputting and outputting signals for communication with other computers via a network using wired or wireless communication standards. A network consists of various mobile communication systems, such as the internet, LANs, and wireless base stations. For example, a network includes 3G, 4G, and 5G mobile communication systems, LTE (Long Term Evolution), and wireless networks that can connect to the internet via designated access points (e.g., Wi-Fi®). When connecting wirelessly, communication protocols include, for example, Z-Wave®, ZigBee®, and Bluetooth®. When connecting via a wired connection, the network also includes connections made directly via USB (Universal Serial Bus) cables, etc.

[0083] Furthermore, by distributing all or part of each hardware configuration across multiple computers 90 and connecting them to each other via a network, a computer 90 can be virtually realized. Thus, the concept of computer 90 includes not only a computer 90 housed in a single enclosure or case, but also a virtualized computer system.

[0084] <Basic Functional Configuration of Computer 90> The functional configuration of the computer realized by the basic hardware configuration of computer 90 (Figure 10) is described below. The computer comprises at least one functional unit: a control unit, a memory unit, and a communication unit.

[0085] Furthermore, the functional units of computer 90 can also be realized by distributing all or part of each functional unit across multiple computers 90 interconnected via a network. The concept of computer 90 includes not only a single computer 90 but also a virtualized computer system.

[0086] The control unit is realized when the processor 901 reads various programs stored in the auxiliary storage device 903, loads them into the main memory device 902, and executes processing according to those programs. The control unit can realize various functional units that perform information processing depending on the type of program. In this way, the computer is realized as an information processing device that performs information processing.

[0087] The functions realized by the components described herein may be implemented in a circuitry or processing circuitry, including general-purpose processors, application-specific processors, integrated circuits, ASICs (Application Specific Integrated Circuits), CPUs (a Central Processing Unit), conventional circuits, and / or combinations thereof, programmed to realize the functions described herein. A processor includes transistors and other circuits and is considered a circuitry or processing circuitry. A processor may be a programmed processor that executes a program stored in memory. In this specification, circuitry, unit, and means are hardware programmed to perform or execute the functions described herein. Such hardware may be any hardware disclosed herein, or any hardware known to be programmed to perform or execute the functions described herein. If the hardware is a processor that is considered to be a type of circuitry, then the circuitry, means, or unit is a combination of hardware and software used to constitute the hardware and / or processor.

[0088] The memory unit is implemented by the main memory 902 and the auxiliary memory 903. The memory unit stores data, various programs, and various databases. The processor 901 can also reserve memory areas corresponding to the memory unit in the main memory 902 or the auxiliary memory 903 according to the program. The control unit can also cause the processor 901 to perform operations such as adding, updating, and deleting data stored in the memory unit according to the various programs.

[0089] A database, specifically a relational database, is used to manage and link together tabular data sets called masters, which are structurally defined by rows and columns. In a database, tables are called tables, masters are called masters, the columns of tables are called columns, and the rows of tables are called records. In a relational database, relationships can be established and linked between tables and masters. Typically, each table and master has a primary key column to uniquely identify records, but setting a primary key column is not mandatory. The control unit can instruct the processor 901 to add, delete, or update records in specific tables and masters stored in the memory unit, according to various programs. Furthermore, by storing data, various programs, and various databases in the memory unit, the information processing device and information processing system related to this disclosure can be considered to have been manufactured.

[0090] Furthermore, the databases and masters in this disclosure may include any data structures (lists, dictionaries, associative arrays, objects, etc.) in which information is structurally defined. Data structures also include data that can be considered as data structures by combining data with functions, classes, methods, etc., written in any programming language.

[0091] The communication unit is implemented by the communication IF991. The communication unit provides the functionality to communicate with other computers 90 via the network. The communication unit can receive information transmitted from other computers 90 and input it to the control unit. The control unit can cause the processor 901 to perform information processing on the received information according to various programs. The communication unit can also transmit information output from the control unit to other computers 90.

[0092] <Note> The details described in each of the above embodiments are noted below.

[0093] (Note 1) A program for execution on a computer comprising a processor and a memory unit, wherein the processor executes: an instruction reception step (S302) in which it receives a first instruction input by a user; a first generation step (S303) in which it generates a first prompt by including the first instruction received in the instruction reception step and information relating to a plurality of processing processes for a task using a generation AI in an instruction A that identifies a processing process suitable for the instruction; a processing identification step (S304) in which it identifies a predetermined processing process based on information output from a large-scale language model by inputting the first prompt into the large-scale language model; an output acquisition step (S305) in which it acquires an output result that is output by inputting the first instruction received in the instruction reception step into the predetermined processing process identified in the processing identification step; and a presentation step (S306) in which it presents information based on the output result acquired in the output acquisition step to the user. This allows the system to identify a processing process suitable for a first instruction input by the user, and to process the first instruction more appropriately based on that processing process. For the first instruction, a more suitable output result can be obtained using a large-scale language model.

[0094] (Note 2) The program described in Appendix 1 includes an output acquisition step (S305) which includes a second generation step which generates a second prompt by including the first instruction received in the instruction reception step in instruction B corresponding to a predetermined processing process, and a step which acquires an output result output from a large-scale language model by inputting the second prompt to the large-scale language model. This allows for obtaining a more suitable output result for the first instruction using a large-scale language model.

[0095] (Note 3) Instruction B includes instructions prompting for additional instructions if there are deficiencies in the first instruction, and the presentation step (S306) includes an additional input step prompting the user to input additional instructions if the program evaluates that there are deficiencies in the first instruction based on the output result, as described in Appendix 2. This allows the user to be prompted to provide additional instructions even if there are deficiencies in the first instruction. A more suitable output result can be obtained using a large-scale language model.

[0096] (Note 4) The program as described in Appendix 1, wherein the first generation step (S303) is the step of generating a first prompt by including a first instruction and a plurality of descriptive pieces of information describing the processing content of each of the plurality of processing processes in instruction A. This allows for obtaining a more suitable output result for the first instruction using a large-scale language model.

[0097] (Note 5) The program described in Appendix 4, wherein the processor performs a description evaluation step (S103) in which it evaluates the similarity between multiple descriptive pieces of information, and a correction notification step (S103) in which it outputs a notification prompting the correction of multiple descriptive pieces of information that were evaluated as similar in the description evaluation step. If the descriptive information associated with each of multiple processing processes is similar, it is possible that the processing process identification step may not properly identify the intended processing process. Even in such cases, if similar descriptive information is associated with each of multiple processing processes, the user can be prompted to correct that descriptive information.

[0098] (Note 6) The program as described in Appendix 5, wherein the processor performs a processing reception step (S103) in which it receives input from a user of one or more processing processes and one or more descriptive pieces of information describing the processing content of each of those processing processes; the description evaluation step (S103) is a step in which the similarity between the one or more descriptive pieces of information received in the processing reception step and the multiple descriptive pieces of information stored in the memory that describe the processing content of each of the multiple processing processes; and the correction notification step (S103) is a step in which it outputs a notification prompting correction of one or more descriptive pieces of information that were evaluated as similar in the description evaluation step from among the one or more descriptive pieces of information received in the processing reception step. This allows users to be prompted to modify the description information of one or more pre-stored processing processes when registering a new processing process, as the description information is similar to that of the previous processing processes.

[0099] (Note 7) The program described in Appendix 1 includes the steps of: identifying multiple processing processes based on information output from a large-scale language model; presenting multiple processing processes to the user for selection; and receiving a selection operation from the user for a predetermined processing process from among the presented multiple processing processes, and identifying the selected predetermined processing process. This allows the system to present multiple processing processes to the user and accept the user's selection of the most suitable process, even when multiple processing processes are output based on the first prompt.

[0100] (Note 8) The program described in Appendix 1, wherein the processor performs a contact output step (S306) in which the output result obtained in the output acquisition step outputs a predetermined contact connected to a computer via a network. This allows the first instruction to be notified to a designated contact even if the large-scale language model is unable to process it. This designated contact could be, for example, an external contractor capable of processing the first instruction. The contractor can then process the first instruction and deliver the processing results to the user. The user can have the large-scale language model process the first instruction if it is capable of doing so, or have a designated external contractor process the first instruction if it is not capable of doing so.

[0101] (Note 9) The program described in Appendix 8 is a step in which the contact output step (S306) outputs a predetermined contact associated with a predetermined processing process. This allows the first instruction to be processed by an external contractor according to the processing process.

[0102] (Note 10) The program as described in Appendix 1, wherein the instruction reception step (S302) is a step of receiving a first instruction entered by the user via a messenger service, and the presentation step (S306) is a step of presenting information based on the output result to the user via the messenger service. This allows the AI ​​system to issue instructions to humans via messenger services such as chat tools, and to receive responses to those instructions from the messenger services.

[0103] (Note 11) A method to be performed on an information processing apparatus comprising a processor and a memory unit, wherein the processor performs all steps performed in the invention according to any of the appendices 1 to 10. This allows the system to identify a processing process suitable for a first instruction input by the user, and to process the first instruction more appropriately based on that processing process. For the first instruction, a more suitable output result can be obtained using a large-scale language model.

[0104] (Note 12) An information processing apparatus comprising a processor and a memory unit, wherein the processor performs all steps performed in any of the inventions described in Appendix 1 to Appendix 10. This allows the system to identify a processing process suitable for a first instruction input by the user, and to process the first instruction more appropriately based on that processing process. For the first instruction, a more suitable output result can be obtained using a large-scale language model.

[0105] (Note 13) A system comprising means for performing all steps performed in any of the inventions described in Appendix 1 to Appendix 10. This allows the system to identify a processing process suitable for a first instruction input by the user, and to process the first instruction more appropriately based on that processing process. For the first instruction, a more suitable output result can be obtained using a large-scale language model. [Explanation of symbols]

[0106] 1 System, 10 Servers, 101 Memory Unit, 104 Control Unit, 106 Input Device, 108 Output Device, 20 User Terminals, 201 Memory Unit, 204 Control Unit, 206 Input Device, 208 Output Device, 50 Generating AI, 501 Memory Unit, 504 Control Unit, 506 Input Device, 508 Output Device

Claims

1. A program to be executed by a computer having a processor and a memory unit, The aforementioned processor, An instruction reception step that receives the first instruction entered by the user, A first generation step generates a first prompt by including the first instruction received in the instruction reception step and information related to multiple processing processes for a task using the generation AI in instruction A, which identifies a processing process suitable for the instruction. A processing identification step involves inputting the first prompt into a large-scale language model to identify a predetermined processing process based on the information output from the large-scale language model, An output acquisition step that acquires an output result that is output by inputting the first instruction received in the instruction reception step to the predetermined processing process identified in the processing identification step, A presentation step in which information based on the output results obtained in the output acquisition step is presented to the user, A program that executes this task.

2. The output acquisition step described above is: A second generation step generates a second prompt by including the first instruction received in the instruction reception step in the instruction B corresponding to the predetermined processing process, The steps include: inputting the second prompt to the large-scale language model to obtain the output result from the large-scale language model; including, The program according to claim 1.

3. Instruction B includes instructions prompting for additional instructions to address any deficiencies in the first instruction, The presentation step includes an additional input step that prompts the user to input additional instructions if the output result indicates that there are deficiencies in the first instruction. The program according to claim 2.

4. The first generation step is to generate a first prompt by including the first instruction and a plurality of descriptive pieces of information describing the processing content of each of the plurality of processing processes in the instruction A. The program according to claim 1.

5. The aforementioned processor, A descriptive evaluation step that evaluates the similarity between the multiple descriptive pieces of information, A correction notification step which outputs a notification prompting correction of multiple descriptive pieces of information that were evaluated as similar in the description evaluation step, Execute The program according to claim 4.

6. The aforementioned processor, A processing reception step that receives input from a user, including one or more processing processes and one or more descriptive pieces of information describing the processing content of each of those processing processes, Execute, The description evaluation step is a step of evaluating the similarity between the one or more description pieces of information received in the processing acceptance step and the multiple description pieces of information that describe the processing content of each of the multiple processing processes stored in the storage unit. The correction notification step is a step of outputting a notification prompting correction of one or more descriptive pieces of information that were evaluated as similar in the description evaluation step, from among the one or more descriptive pieces of information received in the processing acceptance step. The program according to claim 5.

7. The aforementioned processing identification step is: The steps include identifying multiple processing processes based on information output from a large-scale language model, The steps include presenting the user with a selection of the aforementioned multiple processing processes, The steps include: receiving a selection operation from the user for a predetermined processing process from among the multiple processing processes presented, and identifying the predetermined processing process selected; including, The program according to claim 1.

8. The aforementioned processor, The output result obtained in the output acquisition step is used in a contact output step that outputs a predetermined contact connected to the computer via a network, Execute The program according to claim 1.

9. The contact output step is a step of outputting a predetermined contact associated with the predetermined processing process. The program according to claim 8.

10. The aforementioned instruction reception step is a step of receiving a first instruction entered by the user via a messenger service, The aforementioned presentation step is the step of presenting information based on the output result to the user via a messenger service. The program according to claim 1.

11. A method to be performed on an information processing apparatus comprising a processor and a storage unit, wherein the processor performs all steps performed in the invention according to any one of claims 1 to 10.

12. An information processing apparatus comprising a processor and a storage unit, wherein the processor performs all steps performed in the invention according to any one of claims 1 to 10.

13. A system comprising means for performing all steps performed in the invention according to any one of claims 1 to 10.

Images