Information processing systems, information processing methods, information processing programs, and AI agents

Abstract

The present invention provides an information processing system, information processing method, information processing program, and AI agent that can perform processing appropriate to the user's prompt, even if the user's prompt contains incomplete information. [Solution] In the information processing system 10, the AI ​​agent includes: prompt analysis means that analyzes prompts input by a user and stores user information in association with the analysis results of the prompts; input pattern learning means that learns or refers to multiple input patterns of prompts by a user based on the analysis results of multiple prompts and assigns identification information to the multiple input patterns; alternative prompt generation means that generates an alternative prompt by replacing the prompt with identification information when the prompt matches or is similar to any of the multiple input patterns; and processing execution means that executes processing corresponding to the alternative prompt.

Description

Technical Field

[0005]

[0001] The present invention relates to an information processing system, an information processing method, an information processing program using an AI agent, and an AI agent.

Background Art

[0002] Conventionally, a system including a generative AI for assisting in creating in-house articles, in which the generative AI automatically performs article composition and correction of typos and missing characters, has been proposed (see, for example, Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, although the conventional system can automatically perform article composition and correction of typos and missing characters, it has a problem that its application range is limited because it is intended for assisting in creating in-house articles.

[0005] In view of such circumstances, the present invention provides an information processing system, an information processing method, an information processing program, and an AI agent that can execute processing suitable for a user's prompt even when the content of the user's prompt contains incomplete information, can improve the user's satisfaction, and can increase the processing speed by reducing the tokens of the prompt.

Means for Solving the Problems

[0006] The information processing system according to the present invention is an information processing system configured to have an AI agent, wherein the AI ​​agent includes a prompt analysis means that analyzes prompts input by a user and stores user information relating to the user and the results of the analysis of the prompts, an input pattern learning means that learns or refers to a plurality of input patterns of the prompts by the user based on the results of the analysis of a plurality of prompts and assigns identification information to the plurality of input patterns, and the prompts input by the user or any person related to the user who can be identified by the user information , to which the above identification information is attached Matches or is similar to any of the above multiple input patterns Furthermore, the prompt contains content that does not match the intentions of the user or related party, or is ambiguous. In that case, the prompt Make corrections or additions The system comprises: an alternative prompt generation means for generating an alternative prompt, and a processing execution means for executing a process corresponding to the alternative prompt. The prompts include prompts related to management figures, and the input pattern learning means learns or references the multiple input patterns by considering the analysis results of the multiple prompts, as well as information related to sales promotion measures and store layouts. This is an information processing system characterized by the following:

[0007] Furthermore, the information processing method according to the present invention is A I An information processing method performed using an agent, wherein the AI ​​agent performs a prompt analysis step in which it analyzes a prompt entered by a user and stores the user information relating to the user and the analysis result of the prompt; an input pattern learning step in which it learns multiple input patterns of the prompt by the user based on the analysis results of multiple prompts and assigns identification information to the multiple input patterns; and the prompt entered by the user or a person related to the user who can be identified by the user information , to which the above identification information is attached Matches or is similar to any of the above multiple input patterns Furthermore, the prompt contains content that does not match the intentions of the user or related party, or is ambiguous. In that case, the prompt Make corrections or additions A step to generate an alternative prompt, and a step to execute a process corresponding to the alternative prompt, At a minimum, the process is executed, and the prompts include prompts relating to business figures, and the input pattern learning step learns or references the multiple input patterns by considering the results of the analysis of the multiple prompts, as well as information relating to promotional measures and store layouts. This is an information processing method characterized by the following features.

[0008] Furthermore, the information processing program according to the present invention is A IA program for an information processing system configured to have an agent, wherein the AI ​​agent, which is a computer, analyzes prompts input by a user, stores user information relating to the user and the results of the prompt analysis, input pattern learning means learns or references multiple input patterns of the prompts by the user based on the results of the analysis of multiple prompts, and assigns identification information to the multiple input patterns, and the prompts input by the user or any person related to the user who can be identified by the user information , to which the above identification information is attached Matches or is similar to any of the above multiple input patterns Furthermore, the prompt contains content that does not match the intentions of the user or related party, or is ambiguous. In that case, the prompt Make corrections or additions It functions as an alternative prompt generation means for generating an alternative prompt, and a processing execution means for executing a process corresponding to the alternative prompt. The prompts include prompts related to management figures, and the input pattern learning means learns or references the multiple input patterns by considering the analysis results of the multiple prompts, as well as information related to sales promotion measures and store layouts. This is an information processing program characterized by the following:

[0009] Furthermore, the AI ​​agent according to the present invention is an AI agent that acts as a substitute for a human and has the ability to learn and make decisions on its own, and the computer functions as: prompt analysis means that analyzes prompts input by a user and stores user information relating to the user and the results of the analysis of the prompts; input pattern learning means that learns or refers to multiple input patterns of the prompts by the user based on the results of the analysis of multiple prompts and assigns identification information to the multiple input patterns; alternative prompt generation means that modifies or supplements the prompt to generate an alternative prompt when the prompt input by the user or any person related to the user that can be identified by the user information matches or is similar to any of the multiple input patterns to which the identification information has been assigned, and the prompt contains content that does not match the intention of the user or the person related, or content that is ambiguous; and processing execution means that executes processing corresponding to the alternative prompt. It is an AI agentThe AI ​​agent is characterized in that the prompts include prompts relating to business figures, and the input pattern learning means learns or refers to the plurality of input patterns by considering the analysis results of the plurality of prompts as well as information on sales promotion measures and store sales floors, and acquires the correspondence between the analysis results of the plurality of prompts and the plurality of input patterns by machine learning. [Effects of the Invention]

[0010] According to the information processing system, information processing method, information processing program, and AI agent of the present invention, even if the content of the user's prompt contains incomplete information, it is possible to perform processing appropriate to the user's prompt, thereby increasing user satisfaction and achieving the excellent effect of increasing processing speed by reducing the number of prompt tokens. [Brief explanation of the drawing]

[0011] [Figure 1] This is a schematic diagram showing an overview of the information processing system 10 according to this embodiment 1. [Figure 2] This is a schematic diagram showing an overview of the information processing system 10 according to this second embodiment. [Figure 3] This is a system configuration diagram showing an example of the configuration of the information processing system 10 according to this second embodiment. [Figure 4] This figure shows an example of a prompt PRM and an alternative prompt PRM. [Figure 5] This is a schematic diagram showing an overview of the information processing system 10 according to this third embodiment. [Figure 6] This is a system configuration diagram showing an example of the configuration of the information processing system 10 according to this third embodiment. [Figure 7] This figure shows an example of a prompt PRM and an alternative prompt PRM. [Modes for carrying out the invention]

[0012] <Embodiment 1> Hereinafter, the information processing system 10 according to Embodiment 1 of the present invention will be described with reference to the drawings.

[0013] <Overview of the System> First, with reference to FIG. 1, the overview of the information processing system 10 according to Embodiment 1 will be described. FIG. 1 is an overview diagram showing the overview of the information processing system 10 according to Embodiment 1.

[0014] The information processing system 10 is an information processing system configured to include an AI agent 12. The AI agent 12 includes a prompt analysis means 12a that analyzes a prompt PRM input by a user, associates and stores user information about the user and the analysis result of the prompt PRM; an input pattern learning means 12c that learns or refers to a plurality of input patterns of the prompt PRM by the user based on the analysis results of the plurality of prompt PRMs and assigns identification information to the plurality of input patterns; an alternative prompt generation means 12c that generates an alternative prompt RPRM by replacing the prompt PRM with the identification information when the prompt PRM input by any of the user's related persons identifiable by the user or user information matches or is similar to any of the plurality of input patterns; and a processing execution means 12d that executes a process corresponding to the alternative prompt RPRM.

[0015] According to the information processing system 10, even when the content of the user's prompt contains incomplete information, it is possible to execute a process suitable for the user's prompt, improve the user's satisfaction, and increase the processing speed by reducing the tokens of the prompt.

[0016] Here, a "prompt" refers to an instruction or question given by a user to the system. For example, it includes an AI prompt given to a generative AI, a command prompt for giving an instruction by a command sentence (command), etc. Also, a "token" refers to a "meaningful character string" included in the prompt.

[0017] Furthermore, "user information relating to a user" refers to information that can identify a user, and includes, for example, the user's personal information (e.g., the user's name, user ID, user's job title, etc.) as well as the user's affiliation information (e.g., the company the user works for, the department or group the user belongs to, etc.). In addition, "people related to the user who can be identified by user information" include people with the same job title as the user, people who work for the same company as the user, people who belong to the same department or group as the user, the user's colleagues and superiors, etc.

[0018] Furthermore, "input patterns" include, for example, frequently using specific information (e.g., specific tokens), frequently entering specific prompts (questions or tasks), entering ambiguous content as a prompt (e.g., content containing pronouns, abbreviations, industry jargon, and ambiguous words), and entering content that does not match the user's intent as a prompt (e.g., content containing inaccurate words or content that does not fit the context of the prompt). "Identifying information" refers to information that can identify multiple input patterns, such as numbers, letters, and symbols.

[0019] Furthermore, the prompt PRM may include prompts related to management figures, and the input pattern learning means 12b may learn or refer to multiple input patterns by considering the analysis results of multiple prompt PRMs as well as information on sales promotion measures and store sales floors.

[0020] Here, "management figures" refer to numerical values ​​that indicate a company's management status and are used to evaluate a company's performance through management indicators and financial indicators. Furthermore, "data related to management figures" refers to data (information such as numbers and strings) that shows the management status of a company, and "data related to management figures" includes, for example, (1) sales and profit-related data (e.g., sales data, profit data), (2) sales and product management-related data (e.g., product master specifications, shelf layout data, sales performance and promotional effects), (3) inventory and procurement-related data (e.g., inventory status, ordering and procurement data), (4) customer and marketing-related data (e.g., customer ID data (ID-POS), marketing campaign results), (5) store operations and personnel management-related data (e.g., store performance, staff shifts), (6) expense and financial-related data (e.g., store and headquarters expenses, financial indicators), (7) external environment data (e.g., trade area / population data, competitor store location and price information, weather, temperature, and disaster information), (8) local event / school event information, and (9) instruction and communication-related data (e.g., work instructions and policies from superiors, reports and proposals from the field, history of collaboration with headquarters).

[0021] Furthermore, among the "data related to management figures," (2) sales and product management-related data (e.g., product master data, specifications, shelf layout data, sales performance and promotional effects) may be referred to as "data related to sales promotion (sales promotion)," and among the "data related to management figures," (4) customer and marketing-related data (e.g., customer ID data (ID-POS), results of marketing measures) may be referred to as "data related to purchase history."

[0022] Furthermore, "sales promotion" refers to "sales promotion," which is an activity that encourages sales so that a company's products or services can be sold. "Sales promotion measures" refer to strategies and measures for conducting sales promotion, such as placing mass advertisements, using transit advertising and digital signage, placing internet advertisements, managing social media and conducting campaigns, distributing product samples, holding experiential events and demonstrations, distributing discount coupons and vouchers, and awarding points.

[0023] <Embodiment 2> The information processing system 10 according to Embodiment 2 of the present invention will be described below with reference to the drawings.

[0024] <System Overview> First, an overview of the information processing system 10 according to this second embodiment will be described using Figure 2. Figure 2 is a schematic diagram showing an overview of the information processing system 10 according to this second embodiment.

[0025] The information processing system 10 is an information processing system configured to have an AI agent 12, the AI ​​agent 12 comprising: estimation means 12a that analyzes a prompt PRM input by a user and estimates the user's intent based on the analysis results of the prompt PRM; alternative prompt generation means 12b that modifies or supplements the prompt PRM to generate an alternative prompt RPRM if the prompt PRM contains content that does not match the user's intent or is ambiguous; and processing execution means 12c that executes processing corresponding to the alternative prompt RPRM.

[0026] According to the information processing system 10, by modifying or supplementing prompts in consideration of the user's intent, it is possible to execute processing that matches the user's intent, thereby increasing user satisfaction.

[0027] Here, "prompt" refers to instructions or questions given by the user to the system, and includes, for example, AI prompts given to generating AI, and command prompts that give instructions through command statements.

[0028] An "AI agent" is a system that acts as a substitute (agent) for a human, possessing the ability to learn and make decisions on its own, and integrating various AI technologies to solve complex problems. For example, when an AI agent is given a question (prompt) by a user, it will search for or generate an answer to the question and output the answer. Also, for example, when a task (prompt) is given by a user, it will search for or generate a solution to the task and output the solution to the task.

[0029] "User intent" refers to the thoughts and feelings of the user embedded in the prompts they input. In this example, AI agent 12 estimates "user intent" based on knowledge acquired through machine learning.

[0030] Examples of "user intent" include what the user wants to learn through AI agent 12, what the user wants AI agent 12 to do, what kind of information the user wants to obtain from AI agent 12, and what kind of problems or challenges the user wants to solve using AI agent 12.

[0031] "Content that does not match the user's intent" refers to content that does not align with the user's thoughts or feelings. In this example, AI agent 12 acquires information that "does not match the user's intent" through machine learning.

[0032] Examples of "content that does not match the user's intent" include content containing inaccurate words or phrases (e.g., misspellings, omissions, mistranslations, obvious errors (e.g., Showa 120), misused terminology), content that does not fit the context of the prompt, or content that is contradictory.

[0033] "Ambiguous content" refers to content that includes ambiguous (unclear) expressions. In this example, AI agent 12 acquires information on "ambiguous content" through machine learning.

[0034] Examples of "ambiguous content" include content containing pronouns (e.g., that, this, it, over there, that), content containing abbreviations (e.g., "U" for you, or "Aimitsu" for multiple quotes), content containing industry jargon used only in specific industries (e.g., "assign" in the hotel and inn industry refers to allocating various rooms to guests, but in the IT industry it refers to assigning personnel or tasks, or "Kranke" in hospitals refers to patients), and content containing polysemous words with multiple meanings (e.g., "sweet" in chocolate can mean both "sweet" and "a father is sweet to his daughter," and the English word "book" can mean both "book" and "reservation").

[0035] The prompts entered by the user may include prompts related to business figures or purchase history.

[0036] With this configuration, by considering the user's intent and modifying or supplementing prompts related to management figures and purchase history, it is possible to execute processes that match the user's intent, thereby improving the accuracy of management and purchasing processes.

[0037] Here, "management figures" refer to numerical values ​​that indicate a company's management status and are used to evaluate a company's performance through management indicators and financial indicators. Furthermore, "data related to management figures" refers to data (information such as numbers and strings) that shows the management status of a company, and "data related to management figures" includes, for example, (1) sales and profit-related data (e.g., sales data, profit data), (2) sales and product management-related data (e.g., product master specifications, shelf layout data, sales performance and promotional effects), (3) inventory and procurement-related data (e.g., inventory status, ordering and procurement data), (4) customer and marketing-related data (e.g., customer ID data (ID-POS), marketing campaign results), (5) store operations and personnel management-related data (e.g., store performance, staff shifts), (6) expense and financial-related data (e.g., store and headquarters expenses, financial indicators), (7) external environment data (e.g., trade area / population data, competitor store location and price information, weather, temperature, and disaster information), (8) local event / school event information, and (9) instruction and communication-related data (e.g., work instructions and policies from superiors, reports and proposals from the field, history of collaboration with headquarters).

[0038] Furthermore, among the "data related to management figures," (2) sales and product management-related data (e.g., product master data, specifications, shelf layout data, sales performance and promotional effects) may be referred to as "data related to sales promotion (sales promotion)," and among the "data related to management figures," (4) customer and marketing-related data (e.g., customer ID data (ID-POS), results of marketing measures) may be referred to as "data related to purchase history."

[0039] <Example of system configuration> Next, an example of the configuration of the information processing system 10 according to this second embodiment will be described using Figure 3. Figure 3 is a system configuration diagram showing an example of the configuration of the information processing system 10 according to this second embodiment.

[0040] The information processing system 10 can be configured, for example, to include a system terminal 12 that controls the entire system, and external terminals 16 that are connected to the system terminal 12 via a network NW so that they can communicate with each other.

[0041] System terminal 12 is a terminal that constitutes the AI ​​agent and controls the entire information processing system 10, and is composed of conventionally known servers, personal computers, etc. In this example, system terminal 12 is composed of one server, but it may be composed of multiple servers, personal computers, etc. The hardware configuration of system terminal 12 and the programs that system terminal 12 executes will be described later.

[0042] External terminals 16 are terminals used by users of the information processing system 10 (individuals or specific groups of people (teams, departments, companies, etc.)), and consist of personal computers, tablets, smartphones, etc. The type of external terminal 16 is not particularly limited, but examples include smartphones, personal computers, and tablets used by individuals, and smartphones, personal computers, and tablets used by employees of companies, etc.

[0043] The network NW is a line that allows system terminal 12 and external terminal 16 to communicate with each other, and is typically composed of a WAN (Wide Area Network), also known as the Internet. The network NW may be wired or wireless, a LAN (Local Area Network), a dedicated line such as a VPN (Virtual Private Network), or a combination of these lines.

[0044] <System Terminal / Hardware Configuration Example> Next, we will describe an example of the hardware configuration of system terminal 12.

[0045] As shown in Figure 3, the system terminal 12 is configured to include, for example, a CPU 21, and a ROM 22, RAM 23, external storage drive 25, storage device 26, input device 27, display device 28, communication unit 29, etc., all connected to the CPU 21 via a bus.

[0046] The CPU 21 is a control means that controls the entire system terminal 12, and performs processes such as executing application programs and operating systems (OS) stored in ROM 22 and storage devices 26, and storing data and files necessary for program execution in RAM 23 and storage devices 26.

[0047] ROM22 is a storage means for storing basic I / O programs and various data, and is composed of, for example, PROM, flash memory, etc. RAM23 is a storage means for temporarily storing data, and is composed of, for example, SDRAM, DRAM, etc. External storage drive25 is a control means that can read and write data to recording media 24 such as magnetic tape, DVD, etc., and is composed of, for example, magnetic tape storage, DVD drive, etc.

[0048] The storage device 26 is a storage means for storing application programs, the OS, control programs, related programs, various information, etc., and is composed of, for example, a hard disk drive (HDD), a solid-state drive (SDD), etc. The input device 27 is for inputting commands (instructions), etc., to the system terminal 12, and is composed of, for example, a keyboard, a pointing device (mouse, etc.), a touch panel, etc.

[0049] The display device 28 displays commands input by the input device 27, the response output of the system terminal 12 to those commands, and various other displays, and is composed of, for example, a liquid crystal display, plasma display, organic EL, etc. The communication unit 29 is a control means that controls communication with external terminals 16, etc. via the network NW, and is composed of, for example, a communication card, etc.

[0050] <System Terminal / Function> Next, we will explain the functions of the system terminal 12.

[0051] The storage device 26 of the system terminal 12 stores a program (information processing program) that causes the system terminal 12 to function as an estimation means 12a, an alternative prompt generation means 12b, and a processing execution means 12c.

[0052] <System terminal / Function / Estimation method> Next, the estimation means 12a will be described.

[0053] The estimation means 12a is a means for analyzing a prompt PRM input by a user of the information processing system 10 (an individual or a specific group consisting of multiple people (team, department, company, etc.)) and estimating the user's intent based on the analysis results of the prompt PRM. In this example, it consists of a program stored in the storage device 26 of the system terminal 12, and the storage device 26, etc.

[0054] The estimation means 12a uses an external terminal 16 to acquire a prompt PRM entered by a user of the information processing system 10, associates the acquired prompt PRM with the user's ID, and stores it in the storage device 26.

[0055] Here, "prompt PRM" refers to the information (data) of commands and questions entered by a user of the information processing system 10 using the input means (keyboard, pointing device (mouse, etc.), touch panel, microphone, etc.) of the external terminal 16. The data format of "prompt PRM" is not particularly limited and may be any of the following: text data, audio data, still image data, video data, file, etc.

[0056] Examples of "prompt PRM" include text data such as commands and questions to the information processing system 10, audio data, files uploaded by users, still image data, or video data. Next, the estimation means 12a analyzes the prompt PRM stored in the storage device 26 and estimates the user's intent based on the analysis results of the prompt PRM.

[0057] As mentioned above, "user intent" refers to the thoughts and feelings of the user embedded in the prompts they input. In this example, the estimation means 12a of the AI ​​agent 12 estimates "user intent" based on the knowledge acquired through machine learning.

[0058] Examples of "user intent" include what the user wants to learn through AI agent 12, what the user wants AI agent 12 to do, what kind of information the user wants to obtain from AI agent 12, and what kind of problems or challenges the user wants to solve using AI agent 12.

[0059] For example, if the prompt PRM is "What application is most efficient for creating feed A?", the estimation means 12a, based on the knowledge acquired through machine learning, estimates that "what the user wants to know through the AI ​​agent 12 is about document A," and stores information indicating that the prompt PRM contains content that does not match the user's intent (information indicating that "feed" is a mistake (typographical error) for "document") in the storage device 26, associating it with the user's ID.

[0060] Furthermore, for example, if the prompt PRM is given the question "Tell me about events that happened in Showa 120," the estimation means 12a, based on the knowledge acquired through machine learning, estimates that "what the user wants to obtain from the AI ​​agent 12 is about events that happened in Showa 12, Showa 20, or Showa 10," and stores information indicating that the prompt PRM contains content that does not match the user's intent (information indicating that "Showa 120" is clearly wrong and that Showa 12, Showa 20, or Showa 10 is correct) in the storage device 26, associated with the user's ID.

[0061] Furthermore, for example, if the prompt PRM includes the upload of program code along with the task "This program has a bug, so run the program," the estimation means 12a, based on the knowledge acquired through machine learning, estimates that "the task the user wants to solve using the AI ​​agent 12 is to fix a bug," and stores information indicating that the prompt PRM contains content that does not match the user's intent (information indicating that the task "Run the program" does not fit the context of the preceding sentence "This program has a bug," and that the correct task should be "Fix the bug in the program") in the storage device 26, associated with the user's ID.

[0062] <System terminal / Function / Alternative prompt generation method> Next, the means 12b for generating an alternative prompt will be described.

[0063] The alternative prompt generation means 12b is a means for generating an alternative prompt RPRM by modifying or supplementing the prompt PRM when the prompt PRM contains content that does not match the user's intent or is ambiguous. In this example, it is composed of a program stored in the storage device 26 of the system terminal 12, or the storage device 26, etc.

[0064] For example, consider a case where the prompt PRM is given the question, "What application is most efficient for creating Feed A?", and the estimation means 12a stores information in the memory device 26 indicating that the content does not match the user's intent, specifically that "Feed" is a mistake (typographical error) for "Materials".

[0065] In this case, as shown in Figure 4(a), the alternative prompt generation means 12b modifies the question (prompt) "What application is most efficient for creating feed A?" and stores the question (prompt) "What application is most efficient for creating material A?" as the alternative prompt RPRM in the storage device 26, associating it with the user's ID.

[0066] Furthermore, consider a case where, for example, the prompt PRM is given the question "Tell me what happened in Showa 120," and the estimation means 12a stores information in the memory device 26 indicating that the content does not match the user's intent, such as that "Showa 120" is clearly wrong and that Showa 12, Showa 20, or Showa 10 is correct.

[0067] In this case, as shown in Figure 4(b), the alternative prompt generation means 12b completes the question (prompt) "Tell me about events that happened in 1935" and stores three questions (prompts) as alternative prompts RPRM in the storage device 26, associated with the user's ID: "Tell me about events that happened in 1937", "Tell me about events that happened in 1945", or "Tell me about events that happened in 1935".

[0068] Furthermore, consider a case where, as a prompt PRM, along with the upload of program code, the task "This program has a bug, so run the program" is given, and the estimation means 12a stores information in the memory device 26 indicating that the task "Run the program" does not fit the context of the preceding sentence "This program has a bug," and that the correct task should be "Fix the bug in the program."

[0069] In this case, as shown in Figure 4(c), the alternative prompt generation means 12b modifies the task (prompt) "This program has a bug, so run the program" and stores the task (prompt) "This program has a bug, so fix the bug in the program" as the alternative prompt RPRM in the storage device 26, associating it with the user's ID.

[0070] Furthermore, consider a case where, for example, a prompt PRM is given, such as "Show me that document from yesterday," and this prompt PRM is stored in the memory device 26.

[0071] In this case, the alternative prompt generation means 12b, based on the knowledge acquired through machine learning, determines that "that document from yesterday" contains ambiguous expressions (pronouns) and that the user's intention is to display the document used in yesterday's internal meeting. As shown in Figure 4(d), it complements the task (prompt) "Display that document from yesterday" and stores the task (prompt) "Retrieve the document used in the internal meeting on [date] from the company's file server and display the document" as the alternative prompt RPRM, associating it with the user's ID and storing it in the storage device 26.

[0072] Furthermore, consider a case where, for example, a prompt PRM is given with the task, "We would like to outsource the design of the icon, so please provide us with quotes," and this prompt PRM is stored in the memory device 26.

[0073] In this case, the alternative prompt generation means 12b, based on the knowledge acquired through machine learning, determines that "AIMITSU" is an ambiguous expression (abbreviation) and that the user's intention is to request cost estimates from each of several contractors. As shown in Figure 4(e), it complements the task (prompt) "I would like to outsource the design of the icon, so please give me some AIMITSU" to create the task (prompt) "I would like to outsource the design of the icon, so please request cost estimates from each of several contractors," which is stored in the storage device 26 as an alternative prompt RPRM, associated with the user's ID.

[0074] <System terminal / Function / Processing execution means> Next, the processing execution means 12c will be described.

[0075] The processing execution means 12c is a means for executing processing corresponding to the alternative prompt RPRM, and in this example, it is composed of a program stored in the storage device 26 of the system terminal 12, or the storage device 26, etc.

[0076] The processing execution means 12c obtains the alternative prompt RPRM stored in the storage device 26 by the alternative prompt generation means 12b and executes the processing corresponding to the alternative prompt RPRM.

[0077] For example, if the alternative prompt RPMR, "What application is most efficient for creating material A?", is stored in the storage device 26 by the alternative prompt generation means 12b, instead of the prompt PRM, "What application is most efficient for creating feed A?", then the processing execution means 12c searches for an answer to the question, generates an answer, and transmits the answer to the question to the external terminal 16 used by the user.

[0078] Furthermore, for example, if the alternative prompt generation means 12b stores in the storage device 26 an alternative prompt RPMR consisting of three questions (prompts) such as "Tell me what happened in 1937," "Tell me what happened in 1945," or "Tell me what happened in 1935," instead of the prompt PRM "Tell me what happened in 1935," the processing execution means 12c searches for answers to these questions, generates answers, and transmits the answers to the questions to the external terminal 16 used by the user.

[0079] Furthermore, for example, if the alternative prompt RPMR, which states "This program has a bug, fix the bug in the program," is stored in the storage device 26 by the alternative prompt generation means 12b, instead of the prompt PRM, which states "This program has a bug, so run the program," then the processing execution means 12c searches for or generates a solution to the problem and transmits the solution to the problem (the program with the bug fixed) to the external terminal 16 used by the user.

[0080] Furthermore, for example, if the alternative prompt RPMR, which states "I would like to outsource the design of the icon, so please provide me with quotes," is stored in the storage device 26 by the alternative prompt generation means 12b, instead of the prompt PRM, which states "I would like to outsource the design of the icon, so please provide me with quotes," then the processing execution means 12c searches for or generates a solution to the problem and transmits the solution to the problem (quotes from multiple contractors) to the external terminal 16 used by the user.

[0081] As this example shows, by modifying or supplementing prompts based on the user's intent, it is possible to execute processes that match the user's intent, thereby increasing user satisfaction.

[0082] <Information Processing Systems / Summary> As described above, the information processing system according to this embodiment (for example, the information processing system 10 shown in Figures 2 and 3) is an information processing system configured to have an AI agent (for example, the AI ​​agent 12 shown in Figure 2, the system terminal 12 shown in Figure 3), wherein the AI ​​agent analyzes a prompt (for example, the prompt PRM shown in Figures 2 and 3) input by a user and estimates the user's intent based on the analysis result of the prompt, and the prompt contains content that does not match the user's intent (for example, content that includes inaccurate words or phrases (for example, misspellings, omissions, mistranslations, obvious errors, misused terms), or sentences The information processing system is characterized by comprising: an alternative prompt generation means (e.g., the alternative prompt RPRM shown in Figures 2 and 3) that generates an alternative prompt (e.g., the alternative prompt RPRM shown in Figures 2 and 3) by modifying (including correcting) or supplementing (e.g., adding or paraphrasing sentences or replacing words) the prompt when it contains irrelevant, contradictory, or ambiguous content (e.g., content containing pronouns, content containing abbreviations, content containing industry jargon used only in a specific industry, or content containing polysemous words with multiple meanings); and a processing execution means (e.g., the processing execution means shown in Figures 2 and 3) that executes processing corresponding to the alternative prompt.

[0083] Furthermore, the information processing method according to this embodiment is an information processing method executed using an AI agent (for example, the AI ​​agent 12 shown in Figure 2, the system terminal 12 shown in Figure 3), wherein the AI ​​agent analyzes a prompt (for example, the prompt PRM shown in Figures 2 and 3) input by a user and estimates the user's intent based on the analysis results of the prompt (for example, the process executed by the estimation means 12a shown in Figures 2 and 3), and the prompt contains content that does not match the user's intent (for example, content that includes inaccurate words or phrases (for example, misspellings, omissions, mistranslations, obvious errors, misused terms), content that does not fit the context, or content that is contradictory) or ambiguous. The information processing method is characterized by comprising: an alternative prompt generation step (for example, a process performed by the alternative prompt generation means 12b shown in Figures 2 and 3) that modifies (including correction) or supplements (for example, adding or paraphrasing sentences or replacing words) the prompt when it contains content that is inappropriate (for example, content containing pronouns, content containing abbreviations, content containing industry jargon used only in a specific industry, or content containing polysemous words with multiple meanings), and a processing execution step (for example, a process performed by the processing execution means 12c shown in Figures 2 and 3) that performs processing corresponding to the alternative prompt.

[0084] Furthermore, the program of the information processing system according to this embodiment (for example, the information processing system 10 shown in Figures 2 and 3) is a program of an information processing system configured to have an AI agent (for example, the AI ​​agent 12 shown in Figure 2, the system terminal 12 shown in Figure 3), and includes an estimation means (for example, the estimation means 12a shown in Figures 2 and 3) that analyzes a prompt (for example, the prompt PRM shown in Figures 2 and 3) input by a user and estimates the user's intent based on the analysis result of the prompt, and the program includes an estimation means (for example, the estimation means 12a shown in Figures 2 and 3) that analyzes the AI ​​agent, which is a computer, to estimate the user's intent based on the analysis result of the prompt, and includes a prompt that contains content that does not match the user's intent (for example, inaccurate words or phrases (for example, misspellings, omissions, mistranslations, obvious errors, misused terms) This information processing program is characterized by having an alternative prompt generation means (e.g., the alternative prompt RPRM shown in Figures 2 and 3) that generates an alternative prompt (e.g., the alternative prompt RPRM shown in Figures 2 and 3) by modifying (including correcting) or supplementing (e.g., adding or paraphrasing sentences, or replacing words) the prompt when it contains content that does not fit the content or context, or is contradictory, or ambiguous (e.g., content containing pronouns, content containing abbreviations, content containing industry jargon used only in a specific industry, or content containing polysemous words with multiple meanings), and a processing execution means (e.g., the processing execution means 12c shown in Figures 2 and 3) that performs processing corresponding to the alternative prompt.

[0085] Furthermore, the AI ​​agent according to this embodiment (for example, the AI ​​agent 12 shown in Figure 2, the system terminal 12 shown in Figure 3) is an AI agent that acts as a substitute for a human and has the ability to learn and make decisions on its own, and includes an estimation means (for example, the estimation means 12a shown in Figures 2 and 3) that analyzes a prompt (for example, the prompt PRM shown in Figures 2 and 3) input by a user and estimates the user's intent based on the analysis results of the prompt, and the estimation means that the prompt contains content that does not match the user's intent (for example, content that includes inaccurate words or phrases (for example, misspellings, omissions, mistranslations, obvious errors, misused terms), content that does not fit the context, or contradictory content). The AI ​​agent is characterized by having an alternative prompt generation means (e.g., the alternative prompt RPRM shown in Figures 2 and 3) that modifies (including correction) or supplements (e.g., adding or paraphrasing sentences or replacing words) the prompt when it contains ambiguous content (e.g., content containing pronouns, content containing abbreviations, content containing industry jargon used only in a specific industry, or content containing polysemous words with multiple meanings) to generate an alternative prompt (e.g., the alternative prompt RPRM shown in Figures 2 and 3), and a processing execution means (e.g., the processing execution means shown in Figures 2 and 3) that performs processing corresponding to the alternative prompt.

[0086] According to the information processing system, information processing method, information processing program, and AI agent of this embodiment, by modifying or supplementing prompts in consideration of the user's intent, it is possible to execute processing that matches the user's intent, thereby increasing user satisfaction.

[0087] Furthermore, content that does not conform to the user's intent may include inaccurate wording and content that does not conform to the context of the prompt.

[0088] With this configuration, it is possible to process a prompt after correcting or supplementing any inaccurate or inappropriate wording, and thus execute processing that matches the user's intent.

[0089] Furthermore, the aforementioned ambiguous content may include content containing pronouns, abbreviations, industry jargon, and polysemous words.

[0090] With this configuration, it is possible to process prompts after correcting or supplementing content containing pronouns, abbreviations, industry jargon, and ambiguous words, thereby enabling the execution of processing that matches the user's intent.

[0091] Furthermore, the estimation means (or estimation step) may analyze the prompt based on knowledge acquired through machine learning to estimate the user's intent.

[0092] This configuration improves the accuracy of estimating the user's intent, allowing for processing that more closely matches the user's intentions.

[0093] Furthermore, the AI ​​agent may be configured to learn and remember the correspondence between the prompt and the alternative prompt.

[0094] This configuration eliminates the need to modify or complete prompts, thereby increasing the execution speed of prompt processing.

[0095] It should be noted that the information processing system, information processing method, information processing program, and AI agent according to the present invention are not limited to the embodiments described above, and various modifications can be made without departing from the spirit of the present invention.

[0096] Therefore, for example, in the above embodiment, an example was shown in which the AI ​​agent itself obtains ambiguous expressions through machine learning, but ambiguous expressions may also be obtained from various servers and databases that are connected to each other via a network NW, or from servers and databases that are connected to each other via a local network (e.g., LAN or P2P) with the system terminal 12.

[0097] <Embodiment 3> The following describes an information processing system 10 according to Embodiment 3 of the present invention with reference to the drawings.

[0098] <System Overview> First, an overview of the information processing system 10 according to this third embodiment will be described using Figure 5. Figure 5 is a schematic diagram showing an overview of the information processing system 10 according to this third embodiment.

[0099] The information processing system 10 is an information processing system configured to have an AI agent 12, the AI ​​agent 12 comprising: detection means 12a that analyzes a prompt PRM input by a user and detects specific information from the prompt PRM that can be replaced with general information, which is more general information; alternative prompt generation means 12b that, when specific information is detected, replaces the specific information in the prompt PRM with general information to generate an alternative prompt RPRM; and processing execution means 12c that executes processing corresponding to the alternative prompt RPRM.

[0100] According to the information processing system 10, even if the user's prompt contains uncommon information, it can perform processing appropriate to the user's prompt, thereby increasing user satisfaction.

[0101] Here, "prompt" refers to instructions or questions given by the user to the system, and includes, for example, AI prompts given to generating AI, and command prompts that give instructions through command statements.

[0102] An "AI agent" is a system that acts as a substitute (agent) for a human, possessing the ability to learn and make decisions on its own, and integrating various AI technologies to solve complex problems. For example, when an AI agent is given a question (prompt) by a user, it will search for or generate an answer to the question and output the answer. Also, for example, when a task (prompt) is given by a user, it will search for or generate a solution to the task and output the solution to the task.

[0103] "Specific information" refers to information that can be changed to "general information," which is more general information. Examples of combinations of "specific information" and "general information" include postal code and address (e.g., 104-0061 and Ginza, Chuo-ku, Tokyo), Japanese Standard Commodity Classification code and product name (e.g., 723131 and Oolong Tea), International Patent Classification and technical field (e.g., H and Electrical), industry jargon and general terms (e.g., Aimitsu and comparative quotes, Agodai and food expenses, Ashidai and transportation expenses, Makuradai and accommodation expenses, Bug and program defects or errors), and abbreviations and full names (e.g., Attend and guidance, Sharpie and mechanical pencil).

[0104] The prompts entered by the user may include prompts related to business figures or purchase history.

[0105] With this configuration, specific information such as business figures and purchase history included in the prompt can be converted into more general information, allowing users to obtain results that match their intentions.

[0106] Here, "management figures" refer to numerical values ​​that indicate a company's management status and are used to evaluate a company's performance through management indicators and financial indicators. Furthermore, "data related to management figures" refers to data (information such as numbers and strings) that shows the management status of a company, and "data related to management figures" includes, for example, (1) sales and profit-related data (e.g., sales data, profit data), (2) sales and product management-related data (e.g., product master specifications, shelf layout data, sales performance and promotional effects), (3) inventory and procurement-related data (e.g., inventory status, ordering and procurement data), (4) customer and marketing-related data (e.g., customer ID data (ID-POS), marketing campaign results), (5) store operations and personnel management-related data (e.g., store performance, staff shifts), (6) expense and financial-related data (e.g., store and headquarters expenses, financial indicators), (7) external environment data (e.g., trade area / population data, competitor store location and price information, weather, temperature, and disaster information), (8) local event / school event information, and (9) instruction and communication-related data (e.g., work instructions and policies from superiors, reports and proposals from the field, history of collaboration with headquarters).

[0107] Furthermore, among the "data related to management figures," (2) sales and product management-related data (e.g., product master data, specifications, shelf layout data, sales performance and promotional effects) may be referred to as "data related to sales promotion (sales promotion)," and among the "data related to management figures," (4) customer and marketing-related data (e.g., customer ID data (ID-POS), results of marketing measures) may be referred to as "data related to purchase history."

[0108] <Example of system configuration> Next, an example of the configuration of the information processing system 10 according to this third embodiment will be described using Figure 6. Figure 6 is a system configuration diagram showing an example of the configuration of the information processing system 10 according to this third embodiment.

[0109] The information processing system 10 can be configured, for example, to include a system terminal 12 that controls the entire system, and external terminals 16 that are connected to the system terminal 12 via a network NW so that they can communicate with each other.

[0110] System terminal 12 is a terminal that constitutes the AI ​​agent and controls the entire information processing system 10, and is composed of conventionally known servers, personal computers, etc. In this example, system terminal 12 is composed of one server, but it may be composed of multiple servers, personal computers, etc. The hardware configuration of system terminal 12 and the programs that system terminal 12 executes will be described later.

[0111] External terminals 16 are terminals used by users of the information processing system 10 (individuals or specific groups of people (teams, departments, companies, etc.)), and consist of personal computers, tablets, smartphones, etc. The type of external terminal 16 is not particularly limited, but examples include smartphones, personal computers, and tablets used by individuals, and smartphones, personal computers, and tablets used by employees of companies, etc.

[0112] The network NW is a line that allows system terminal 12 and external terminal 16 to communicate with each other, and is typically composed of a WAN (Wide Area Network), also known as the Internet. The network NW may be wired or wireless, a LAN (Local Area Network), a dedicated line such as a VPN (Virtual Private Network), or a combination of these lines.

[0113] <System Terminal / Hardware Configuration Example> Next, we will describe an example of the hardware configuration of system terminal 12.

[0114] As shown in Figure 6, the system terminal 12 is configured to include, for example, a CPU 21, and a ROM 22, RAM 23, external storage drive 25, storage device 26, input device 27, display device 28, communication unit 29, etc., all connected to the CPU 21 via a bus.

[0115] The CPU 21 is a control means that controls the entire system terminal 12, and performs processes such as executing application programs and operating systems (OS) stored in ROM 22 and storage devices 26, and storing data and files necessary for program execution in RAM 23 and storage devices 26.

[0116] ROM22 is a storage means for storing basic I / O programs and various data, and is composed of, for example, PROM, flash memory, etc. RAM23 is a storage means for temporarily storing data, and is composed of, for example, SDRAM, DRAM, etc. External storage drive25 is a control means that can read and write data to recording media 24 such as magnetic tape, DVD, etc., and is composed of, for example, magnetic tape storage, DVD drive, etc.

[0117] The storage device 26 is a storage means for storing application programs, the OS, control programs, related programs, various information, etc., and is composed of, for example, a hard disk drive (HDD), a solid-state drive (SDD), etc. The input device 27 is for inputting commands (instructions), etc., to the system terminal 12, and is composed of, for example, a keyboard, a pointing device (mouse, etc.), a touch panel, etc.

[0118] The display device 28 displays commands input by the input device 27, the response output of the system terminal 12 to those commands, and various other displays, and is composed of, for example, a liquid crystal display, plasma display, organic EL, etc. The communication unit 29 is a control means that controls communication with external terminals 16, etc. via the network NW, and is composed of, for example, a communication card, etc.

[0119] <System Terminal / Function> Next, we will explain the functions of the system terminal 12.

[0120] The storage device 26 of the system terminal 12 stores a program (information processing program) that causes the system terminal 12 to function as a detection means 12a, an alternative prompt generation means 12b, and a processing execution means 12c.

[0121] <System terminal / Function / Detection means> Next, the detection means 12a will be described.

[0122] The detection means 12a analyzes prompt PRM input by a user of the information processing system 10 (an individual or a specific group of multiple people (team, department, company, etc.)) and detects specific information from the prompt PRM that can be replaced with more general information. In this example, it consists of a program stored in the storage device 26 of the system terminal 12, or the storage device 26 itself.

[0123] The detection means 12a acquires the prompt PRM entered by the user of the information processing system 10 using the external terminal 16, associates the acquired prompt PRM with the user's ID, and stores it in the storage device 26.

[0124] Here, "prompt PRM" refers to the information (data) of commands and questions entered by a user of the information processing system 10 using the input means (keyboard, pointing device (mouse, etc.), touch panel, microphone, etc.) of the external terminal 16. The data format of "prompt PRM" is not particularly limited and may be any of the following: text data, audio data, still image data, video data, file, etc.

[0125] Examples of "prompt PRM" include text data such as commands and questions to the information processing system 10, audio data, files uploaded by users, still image data, or video data. Next, the detection means 12a analyzes the prompt PRM stored in the storage device 26 and detects specific information from the prompt PRM that can be changed to general information, which is more general information.

[0126] As mentioned above, "specific information" refers to information that can be changed to "general information," which is more general information. Examples of combinations of "specific information" and "general information" include postal codes and addresses (e.g., 104-0061 and Ginza, Chuo-ku, Tokyo), Japanese Standard Commodity Classification codes and product names (e.g., 723131 and Oolong Tea), International Patent Classification and technical fields (e.g., H and Electrical), industry jargon and general terms (e.g., Aimitsu and comparative quotes, Agodai and food expenses, Ashidai and transportation expenses, Makuradai and accommodation expenses, Bug and program defects or errors), abbreviations and full names (e.g., Attend and guidance, Sharpie and mechanical pencil).

[0127] For example, if the prompt PRM asks "What is the stock quantity of product 723131?", the detection means 12a, based on the knowledge acquired through machine learning, determines that the number "723131" is a Japanese standard product classification code (specific information) and can be changed to the more general product name (general information) "Oolong tea" text data. The combination of specific information and general information, "723131" and "Oolong tea," is associated with the user's ID and stored in the storage device 26.

[0128] Also, for example, when a question such as "Tell me the shipping fee to 104-0061" is given as the prompt PRM, the detection means 12a determines, based on the knowledge acquired by machine learning, that the data consisting of the number and symbol "104-0061" can be changed to the text data of "Ginza, Chuo-ku, Tokyo" which is a postal code (specific information) and a more general address (general information). As a combination of specific information and general information, "104-0061" and "Ginza, Chuo-ku, Tokyo" are associated with the user's ID and stored in the storage device 26.

[0129] Also, for example, when a task such as "I want to commission an external icon design, so please quote" is given as the prompt PRM, the detection means 12a determines, based on the knowledge acquired by machine learning, that the text data of "quote" can be changed to the text data of "estimate" which is an industry term (specific information) and a more general general term (general information). As a combination of specific information and general information, "quote" and "estimate" are associated with the user's ID and stored in the storage device 26.

[0130] Also, for example, when a task such as "Fix the bugs in the program" is given as the prompt PRM together with the upload of program code, the detection means 12a determines, based on the knowledge acquired by machine learning, that the text data of "bug" can be changed to the text data of "program defects and errors" which is an industry term (specific information) and a more general general term (general information). As a combination of specific information and general information, "bug" and "program defects and errors" are associated with the user's ID and stored in the storage device 26.

[0131] Furthermore, for example, if the prompt PRM task is "escort the visitor to the conference room," the detection means 12a, based on the knowledge acquired through machine learning, determines that the text data "escort" is an abbreviation or industry term (specific information) and can be changed to the text data "guide," which is a more general term (general information). The detection means 12a then stores the combination of specific information and general information, "escort" and "guide," in the storage device 26, associating them with the user's ID.

[0132] <System terminal / Function / Alternative prompt generation method> Next, the means 12b for generating an alternative prompt will be described.

[0133] The alternative prompt generation means 12b is a means for generating an alternative prompt RPRM by replacing specific information in the prompt PRM with general information when specific information is detected. In this example, it is composed of a program stored in the storage device 26 of the system terminal 12, or the storage device 26, etc.

[0134] For example, consider a case where the prompt PRM is given the question, "Tell me the stock quantity of product 723131," and the detection means 12a stores the information "723131" and "oolong tea" as a combination of specific and general information in the memory device 26.

[0135] In this case, as shown in Figure 7(a), the alternative prompt generation means 12b replaces the specific information "723131" in the question (prompt) "Tell me the stock quantity of product 723131" with the general information "Oolong tea," and stores the question (prompt) "Tell me the stock quantity of Oolong tea" as an alternative prompt RPRM in the storage device 26, associating it with the user's ID.

[0136] Furthermore, consider a case where, for example, the prompt PRM is given the question "Please tell me the shipping cost to mailing address 104-0061," and the detection means 12a stores the information "104-0061" and "Ginza, Chuo-ku, Tokyo" as a combination of specific information and general information in the storage device 26.

[0137] In this case, as shown in Figure 7(b), the alternative prompt generation means 12b replaces the specific information "104-0061" in the question (prompt) "Tell me the shipping cost to mailing address 104-0061" with the general information "Ginza, Chuo-ku, Tokyo," and stores the question (prompt) "Tell me the shipping cost to Ginza, Chuo-ku, Tokyo" as an alternative prompt RPRM, associating it with the user's ID, in the storage device 26.

[0138] Furthermore, consider a case where, for example, the prompt PRM is given as "We would like to outsource the design of the icon, so please give us a quote," and the detection means 12a stores the information "aimitsu" and "comparative quote" as a combination of specific information and general information in the storage device 26.

[0139] In this case, as shown in Figure 7(c), the alternative prompt generation means 12b replaces the specific information "AIMITS" of the task (prompt) "I would like to outsource the design of the icon, so please give me a quote" with the general information "Multiple quotes," and stores the question (prompt) "I would like to outsource the design of the icon, so please give me a quote" as an alternative prompt RPRM, associated with the user's ID, in the storage device 26.

[0140] Furthermore, consider a case where, for example, along with the upload of program code, a prompt PRM (Program Management Manager) is given with the task "Fix the bug in the program," and the detection means 12a stores information such as "bug" and "program malfunction or error" as a combination of specific and general information in the storage device 26.

[0141] In this case, as shown in Figure 7(d), the alternative prompt generation means 12b replaces the specific information "bug" in the task (prompt) "Fix the bug in the program" with the general information "program malfunction or error," and stores the question (prompt) "Fix the program malfunction or error" as an alternative prompt RPRM in the storage device 26, associating it with the user's ID.

[0142] Furthermore, consider a case where, for example, the task is given to "escort the visitor to the conference room," and the detection means 12a stores the information "escort" and "guide" as a combination of specific information and general information in the memory device 26.

[0143] In this case, as shown in Figure 7(e), the alternative prompt generation means 12b replaces the specific information "attend" in the task (prompt) "attend the visitor to the conference room" with the general information "guide," and stores the question (prompt) "guide the visitor to the conference room" as an alternative prompt RPRM in the storage device 26, associating it with the user's ID.

[0144] <System terminal / Function / Processing execution means> Next, the processing execution means 12c will be described.

[0145] The processing execution means 12c is a means for executing processing corresponding to the alternative prompt RPRM, and in this example, it is composed of a program stored in the storage device 26 of the system terminal 12, or the storage device 26, etc.

[0146] The processing execution means 12c obtains the alternative prompt RPRM stored in the storage device 26 by the alternative prompt generation means 12b and executes the processing corresponding to the alternative prompt RPRM.

[0147] For example, if the alternative prompt generation means 12b stores an alternative prompt RPMR in the storage device 26, such as "Tell me the stock quantity of oolong tea," instead of the prompt PRM, such as "Tell me the stock quantity of product 723131," then the processing execution means 12c searches for an answer to the question, generates an answer, and sends the answer to the question (for example, the stock quantity of oolong tea stored in the back room) to the external terminal 16 used by the user.

[0148] Furthermore, for example, if the alternative prompt RPMR, consisting of the question (prompt) "Tell me the shipping cost to Ginza, Chuo-ku, Tokyo" instead of the prompt PRM "Tell me the shipping cost to mailing address 104-0061", is stored in the storage device 26 by the alternative prompt generation means 12b, the processing execution means 12c searches for an answer to the question or generates an answer and sends the answer to the question (for example, text data such as "The shipping cost is 2500 yen") to the external terminal 16 used by the user.

[0149] Furthermore, for example, if the alternative prompt RPMR, which states "I would like to outsource the design of the icon, so please provide multiple quotes," is stored in the storage device 26 by the alternative prompt generation means 12b, instead of the prompt PRM, which states "I would like to outsource the design of the icon, so please provide multiple quotes," then the processing execution means 12c searches for or generates a solution to the problem and sends the solution to the problem (for example, cost estimates from multiple outsourcing companies) to the external terminal 16 used by the user.

[0150] Furthermore, for example, if the alternative prompt generation means 12b stores an alternative prompt RPMR in the storage device 26, which is "Fix the bug in the program" instead of the prompt PRM "Fix the bug in the program", the processing execution means 12c searches for or generates a solution to the problem and transmits the solution to the problem (for example, a program with the bug fixed) to the external terminal 16 used by the user.

[0151] Furthermore, for example, if the alternative prompt generation means 12b stores an alternative prompt RPMR in the storage device 26, such as "Guide the visitor to the conference room" instead of the prompt PRM "Escort the visitor to the conference room", the processing execution means 12c searches for or generates a solution to the problem and transmits the solution to the problem (for example, display data for guiding the visitor to the conference room) to the external terminal 16 used by the user.

[0152] As this example demonstrates, even if the user's prompt contains unconventional information, the system can still perform appropriate actions based on the user's prompt, thereby increasing user satisfaction.

[0153] <Information Processing Systems / Summary> As described above, the information processing system according to this embodiment (for example, the information processing system 10 shown in Figures 5 and 6) is an information processing system configured to have an AI agent (for example, the AI ​​agent 12 shown in Figure 5, the system terminal 12 shown in Figure 6), and the AI ​​agent analyzes prompts input by the user (for example, prompts PRM shown in Figures 5 and 6), and from among the prompts, selects specific information (for example, postal code, Japanese Standards Trademark) that can be replaced with more general information (for example, address, product name, technical field, general term, official name), etc. The information processing system is characterized by comprising: detection means (for example, detection means 12a shown in Figures 5 and 6) for detecting product classification codes, international patent classifications, industry terms, and abbreviations; alternative prompt generation means (for example, alternative prompt generation means 12b shown in Figures 5 and 6) for generating an alternative prompt (for example, alternative prompt RPRM shown in Figures 5 and 6) by replacing the specific information in the prompt with the general information when the specific information is detected; and processing execution means (for example, processing execution means 12c shown in Figures 5 and 6) for executing processing corresponding to the alternative prompt.

[0154] Furthermore, the information processing method according to this embodiment is an information processing method that is executed using an information AI agent (for example, the AI ​​agent 12 shown in Figure 5, the system terminal 12 shown in Figure 6), and the AI ​​agent comprises: a detection step (for example, a process executed by the detection means 12a shown in Figures 5 and 6) that analyzes a prompt (for example, a prompt PRM shown in Figures 5 and 6) input by a user and detects specific information (for example, a postal code, Japanese standard commodity classification code, international patent classification, industry terminology, abbreviation) from the prompt that can be replaced with more general information (for example, an address, a product name, a technical field, a general term, a formal name); an alternative prompt generation step (for example, a process executed by the alternative prompt generation means 12b shown in Figures 5 and 6) that replaces the specific information in the prompt with the general information when the specific information is detected; and a processing execution step (for example, a process executed by the processing execution means 12c shown in Figures 5 and 6) that executes a process corresponding to the alternative prompt.

[0155] Furthermore, the program of the information processing system according to this embodiment (for example, the information processing system 10 shown in Figures 5 and 6) is a program of an information processing system configured to have an AI agent (for example, the AI ​​agent 12 shown in Figure 5, the system terminal 12 shown in Figure 6), wherein the AI ​​agent, which is a computer, analyzes a prompt (for example, the prompt PRM shown in Figures 5 and 6) input by a user, and from among the prompts, specific information (for example, postal code) that can be replaced with more general information (for example, address, product name, technical field, general term, official name) can be replaced. This information processing program is characterized by comprising: a detection means (for example, the detection means 12a shown in Figures 5 and 6) for detecting specific information (such as Japanese standard commodity classification codes, international patent classifications, industry terms, and abbreviations); an alternative prompt generation means (for example, the alternative prompt RPRM shown in Figures 5 and 6) for generating an alternative prompt (for example, the alternative prompt RPRM shown in Figures 5 and 6) when the specific information is detected; and a processing execution means (for example, the processing execution means 12c shown in Figures 5 and 6) for executing processing corresponding to the alternative prompt.

[0156] Furthermore, the AI ​​agent according to this embodiment (for example, the AI ​​agent 12 shown in Figure 5, the system terminal 12 shown in Figure 6) is an AI agent that acts as a substitute for a human and has the ability to learn and make decisions on its own, and is characterized in that the computer functions as a detection means (for example, the detection means 12a shown in Figures 5 and 6) that analyzes a prompt (for example, the prompt PRM shown in Figures 5 and 6) input by a user and detects specific information (for example, postal code, Japanese standard commodity classification code, international patent classification, industry terminology, abbreviation) that can be replaced with more general information (for example, address, product name, technical field, general term, official name) from the prompt; an alternative prompt generation means (for example, the alternative prompt generation means 12b shown in Figures 5 and 6) that, when the specific information is detected, replaces the specific information in the prompt with the general information to generate an alternative prompt (for example, the alternative prompt RPRM shown in Figures 5 and 6); and a processing execution means (for example, the processing execution means 12c shown in Figures 5 and 6) that executes processing corresponding to the alternative prompt.

[0157] According to the information processing system, information processing method, information processing program, and AI agent of this embodiment, even if the content of the user's prompt includes uncommon information, it is possible to perform processing appropriate to the user's prompt, thereby increasing user satisfaction.

[0158] Furthermore, the specified information may consist of alphanumeric characters or symbols, and the general information may consist of characters.

[0159] With this configuration, even if the user's prompt contains information consisting of alphanumeric characters or symbols, it can be replaced with information consisting of characters, thereby enabling the system to perform processing that is more appropriate to the user's prompt.

[0160] Furthermore, the specific information may consist of industry jargon or abbreviations used only in a particular industry, and the general information may be information obtained by changing the industry jargon or abbreviations into more general terms.

[0161] With this configuration, even if the user's prompt contains information consisting of industry jargon or abbreviations, it can be replaced with more general terms, allowing for processing that is more appropriate to the user's prompt.

[0162] Furthermore, the detection means (the detection step) may detect the specific information based on knowledge acquired through machine learning.

[0163] This configuration allows for the rapid detection of specific information and improves the execution speed of processing prompts.

[0164] Furthermore, the AI ​​agent may be configured to learn and store the correspondence between the specific information and the general information.

[0165] This configuration allows for the rapid detection of specific information and improves the execution speed of processing prompts.

[0166] It should be noted that the information processing system, information processing method, information processing program, and AI agent according to the present invention are not limited to the embodiments described above, and various modifications can be made without departing from the spirit of the present invention.

[0167] Therefore, for example, in the above embodiment, an example was shown in which the AI ​​agent itself learns the correspondence between specific information and general information through machine learning. However, specific information and general information may be obtained, for example, from various servers and databases that are connected to each other via a network NW, or from servers and databases that are connected to each other via a local network (e.g., LAN or P2P) with the system terminal 12. [Industrial applicability]

[0168] The information processing system, information processing method, information processing program, and AI agent according to the present invention can be widely applied in manufacturing, service, retail, and other industries. [Explanation of symbols]

[0169] 10 Information Processing Systems 12 System Terminals 12a Detection means 12b Alternative prompt generation means 12c Processing execution means 16 External terminals 21 CPU 22 ROM 23 RAM 24 Recording media 25 External storage drives 26 Storage device 27 Input devices 28 Display device 29 Communications Department PRM prompt RPRM alternative prompt

Claims

1. An information processing system configured to include an AI agent, The aforementioned AI agent, A prompt analysis means that analyzes prompts entered by a user, and stores user information about the user in association with the results of the prompt analysis, An input pattern learning means that learns or references multiple input patterns of the prompts by the user based on the analysis results of multiple prompts, and assigns identification information to the multiple input patterns, An alternative prompt generation means that generates an alternative prompt by modifying or supplementing the prompt if the prompt entered by the user or any person related to the user who can be identified by the user information matches or is similar to any of the plurality of input patterns to which the identification information has been attached, and the prompt contains content that does not match the intent of the user or the person related, or content that is ambiguous, The system includes a processing execution means for executing processing corresponding to the alternative prompt, The aforementioned prompts include prompts related to management figures. The input pattern learning means learns or references the multiple input patterns by taking into account the analysis results of the multiple prompts, as well as information related to sales promotion measures and store layouts. An information processing system characterized by the following:

2. The information processing system according to claim 1, The alternative prompt generation means further generates the alternative prompt by replacing the specific information in the prompt with general information that is more general than the specific information. An information processing system characterized by the following:

3. An information processing method that is performed using an AI agent, The aforementioned AI agent, A prompt analysis step that analyzes prompts entered by a user, associates and stores user information about the user with the results of the prompt analysis, An input pattern learning step which learns multiple input patterns of the prompts by the user based on the analysis results of multiple prompts, and assigns identification information to the multiple input patterns, An alternative prompt generation step in which, if the prompt entered by the user or any person related to the user who can be identified by the user information matches or is similar to any of the plurality of input patterns to which the identification information has been attached, and the prompt contains content that does not match the intent of the user or the person related, or contains ambiguous content, the prompt is modified or supplemented to generate an alternative prompt; The process execution step includes, at least, executing a process that performs the process corresponding to the aforementioned alternative prompt, The aforementioned prompts include prompts related to management figures. The input pattern learning step learns or references the multiple input patterns by considering the analysis results of the multiple prompts, as well as information about sales promotion measures and store layouts. An information processing method characterized by the following:

4. In the information processing method described in claim 3, The alternative prompt generation step further generates the alternative prompt by replacing specific information in the prompt with general information that is more general than the specific information. An information processing method characterized by the following:

5. A program for an information processing system configured to include an AI agent, The aforementioned AI agent, which is a computer, A prompt analysis means that analyzes prompts entered by a user, and stores user information about the user in association with the results of the prompt analysis, An input pattern learning means that learns or references multiple input patterns of the prompts by the user based on the analysis results of multiple prompts, and assigns identification information to the multiple input patterns, An alternative prompt generation means that generates an alternative prompt by modifying or supplementing the prompt if the prompt entered by the user or any person related to the user who can be identified by the user information matches or is similar to any of the plurality of input patterns to which the identification information has been attached, and the prompt contains content that does not match the intent of the user or the person related, or content that is ambiguous, This is configured to function as a processing execution means that executes the processing corresponding to the aforementioned alternative prompt. The aforementioned prompts include prompts related to management figures. The input pattern learning means learns or references the multiple input patterns by taking into account the analysis results of the multiple prompts, as well as information related to sales promotion measures and store layouts. An information processing program characterized by the following features.

6. In the information processing program described in claim 5, The alternative prompt generation means further generates the alternative prompt by replacing the specific information in the prompt with general information that is more general than the specific information. An information processing program characterized by the following features.

7. An AI agent that acts as a substitute for a human, and has the ability to learn and make decisions on its own, Computers, A prompt analysis means that analyzes prompts entered by a user, and stores user information about the user in association with the results of the prompt analysis, An input pattern learning means that learns or references multiple input patterns of the prompts by the user based on the analysis results of multiple prompts, and assigns identification information to the multiple input patterns, An alternative prompt generation means that generates an alternative prompt by modifying or supplementing the prompt if the prompt entered by the user or any person related to the user who can be identified by the user information matches or is similar to any of the plurality of input patterns to which the identification information has been attached, and the prompt contains content that does not match the intent of the user or the person related, or content that is ambiguous, This AI agent functions as a processing execution means for executing processing corresponding to the aforementioned alternative prompt. The aforementioned prompts include prompts related to management figures. The input pattern learning means learns or references the multiple input patterns by taking into account the analysis results of the multiple prompts, as well as information related to sales promotion measures and store layouts. The correspondence between the analysis results of the multiple prompts and the multiple input patterns is learned by machine learning. An AI agent characterized by the following.

Images