System

Abstract

A system is provided.SOLUTION: A system comprising: means for a user to input a problem; server means for receiving the problem; AI means for abstracting and converting the received problem into fictitious examples; means for sharing the abstracted problem to a community; means for community members and independent AI to propose solutions; means for summarizing the proposed solutions; means for translating the proposed solutions; and means for a user to select and reward a solution.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

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

[0004] In modern society, it is difficult to gather a wide range of opinions on the various problems we face in our hobbies and work. Obtaining external opinions is especially difficult when confidentiality or sensitive information is involved in the problem. As a result, problems are only solved from a limited perspective, making it difficult to find effective solutions. Furthermore, the lack of a platform for providing solutions makes it even more difficult to obtain diverse solutions from around the world. Another problem is the lack of a way to make the solutions provided easier to understand. [Means for solving the problem]

[0005] To solve the above-mentioned problems, the present invention provides the following means. First, a means for a user to input their own problem is provided. Next, a server has a means for receiving the problem. Confidentiality and sensitive information are concealed by using AI means for abstracting the received problem and converting it into a fictitious case. Finally, the server has a means for sharing the abstracted problem with the community. This provides a means for community members and autonomous AI to propose solutions, enabling a wide range of solutions to be solicited. The server also has a means for summarizing the proposed solutions and a translation means for enabling understanding in multiple languages. Finally, a means for users to select the optimal solution and receive a reward is provided, thereby revitalizing the community. In this way, the present invention provides a system that solves users' problems from various perspectives while maintaining anonymity.

[0006] A "user" is an individual or entity that accesses the system and enters their problem.

[0007] A "server" is a central computer system that receives user questions and handles subsequent processing.

[0008] A "problem" refers to a specific challenge a user faces in their hobby or work.

[0009] "AI means" refers to artificial intelligence techniques for abstracting and transforming received problems into fictional cases.

[0010] A "community" is a group of users or autonomous AIs that come together to propose solutions to a problem.

[0011] A "fictional case" is a case that has been abstracted using AI means and presented in a way that avoids sensitive information about the specific issue.

[0012] "Solutions" are specific responses to hypothetical cases proposed by community members or autonomous AI.

[0013] A "summarization tool" is a technique or method for concisely summarizing a proposed solution.

[0014] "Translation tools" are techniques and methods for translating the proposed solution into multiple languages.

[0015] A "reward mechanism" is a mechanism by which users can show appreciation and reward community members who provide the most useful solutions. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0017] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0020] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0021] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0037] The embodiment of the present invention is a system in which a user inputs a problem and solicits solutions from a wide range of sources. This system is composed of a terminal, a server, and an AI means. The specific roles and processing flow of each element are explained below.

[0038] User's device

[0039] The user's terminal provides an interface for inputting problems. The user inputs specific problems they are facing in their hobbies or work in text format through the terminal. The input problem is sent from the user's terminal to the server.

[0040] Server Processing

[0041] The server centrally processes the problems received from the user's terminal and provides the means to proceed to the next step.

[0042] 1. Receiving the problem:

[0043] The server receives the question sent from the terminal.

[0044] 2. Problem Abstraction:

[0045] The received problem is analyzed by AI means on the server and abstracted to eliminate sensitive information. This abstracted problem is then reconstructed as a fictional case that hides the real problem.

[0046] 3. Generating fictitious cases:

[0047] The server uses AI tools to generate fictitious cases based on abstracted problems, which are constructed as generalized and widely applicable problems.

[0048] 4. Sharing fictional stories:

[0049] The generated fictional cases are shared with the community via the server, which consists of other users and autonomous AIs participating in the system.

[0050] Community members and autonomous AI proposals

[0051] Community members can propose solutions to published fictitious cases. The autonomous AI can also propose solutions based on its prior knowledge. These proposals are sent to the server for further processing.

[0052] Solution Processing

[0053] 1. Solution Summary:

[0054] The server uses AI summarization to concisely summarize the proposed solutions, providing a clear overview of each solution.

[0055] 2. Solution Translation:

[0056] The server translates the summarized solution using a multilingual translation means, making it easier for users around the world to understand the solution.

[0057] User Choice and Rewards

[0058] Users can review a list of solutions provided by the server, complete with summaries and translations, and select the most suitable solution. Based on this selection, they can obtain specific measures to adapt to their own problems. Furthermore, users can reward community members who propose the most useful solutions.

[0059] Specific examples

[0060] Example 1: Engineer's Concerns

[0061] 1. User problem input:

[0062] A user (engineer) enters a problem: "I don't know how to optimize the performance of a project in a specific programming language."

[0063] 2. Server processing:

[0064] The server receives this problem and uses AI means to convert it into a fictional case study titled "General methods for improving the performance of software systems."

[0065] 3. Community Suggestions:

[0066] Community members and autonomous AI propose solutions such as cache optimization, code refactoring, and algorithm improvements.

[0067] 4. Solution summary and translation:

[0068] The proposed solutions are summarized by the server and translated into multiple languages.

[0069] 5. User Choice and Action:

[0070] Users can choose the best solution and apply it to their own projects, and members who make the best suggestions are rewarded.

[0071] Example 2: Gardening problems

[0072] 1. User problem input:

[0073] The user (gardener) inputs the problem, "I don't know the cause of a certain plant dying and what to do about it."

[0074] 2. Server processing:

[0075] The server receives this problem and uses AI tools to convert it into a fictional case study called "General methods for plant health management."

[0076] 3. Community Suggestions:

[0077] Community members and autonomous AI will suggest solutions such as soil improvement, watering timing, and proper sunlight.

[0078] 4. Solution summary and translation:

[0079] The proposed solutions are summarized by the server and translated into multiple languages.

[0080] 5. User Choice and Action:

[0081] Users can choose the best solution and apply it to their own gardening activities, and members who make the best suggestions will be rewarded.

[0082] With this configuration, the present invention provides a system that can solve a user's problem from various perspectives while maintaining anonymity.

[0083] The processing flow will be explained below.

[0084] Step 1: User enters problem

[0085] Users log in to the IdeaQuest app from their device and enter the specific problem they are facing into a text box.

[0086] For example: "I don't know how to optimize the performance of my project in a specific programming language."

[0087] Step 2: The server receives the problem

[0088] The server receives the problem data sent from the terminal, including the specific problem text entered by the user.

[0089] Step 3: Abstract the problem using AI tools

[0090] An AI tool on the server analyzes the received problem and converts it into a fictitious case so as not to extract sensitive information.

[0091] Example: Remove information about specific programming languages ​​and abstract it as "a general method for improving the performance of software systems."

[0092] Step 4: Generate fictitious cases

[0093] The server generates specific fictitious cases based on the content abstracted by the AI.

[0094] For example, a hypothetical case study generated might be: "What techniques or approaches are effective in a situation where a software system is performing poorly?"

[0095] Step 5: Share your fictional story with the community

[0096] The server makes the generated fictitious cases public to all users and autonomous AIs in the community.

[0097] Step 6: Community members propose solutions

[0098] Community members come up with solutions to the fictitious cases that are published and post their solutions from their own devices.

[0099] For example: cache optimization, code refactoring, algorithm improvements, etc.

[0100] Step 7: Autonomous AI proposes a solution

[0101] The autonomous AI also analyzes fictitious cases provided to it and generates and proposes solutions based on its prior knowledge.

[0102] Step 8: The server summarizes the solution

[0103] The server uses an AI summary model to summarize multiple solutions proposed by community members and autonomous AIs, concisely summarizing the key points of each solution.

[0104] Step 9: Server translates the solution

[0105] The server translates the summarized solution using a multilingual translation model, allowing users around the world to understand the solution across language barriers.

[0106] Step 10: User selects optimal solution

[0107] The user reviews a list of solutions provided by the server, complete with summaries and translations, and selects the solution that seems most useful.

[0108] Step 11: User Gives Reward

[0109] Users can show their appreciation by rewarding community members who propose optimal solutions, either in the form of points in the system or actual rewards.

[0110] Through the above processing steps, the "IdeaQuest" system abstracts the user's specific problem, gathers solutions from a variety of perspectives, and presents them in an easy-to-understand format.

[0111] Example 1

[0112] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0113] Conventional problem-solving systems have difficulty providing direct solutions to problems entered by users, and sharing problems while maintaining user privacy. Furthermore, their proposed solutions lack multilingual support, making it difficult for users of different languages ​​to communicate with each other. To solve these problems, a system is needed that protects privacy by anonymizing and abstracting users' problems, and that also allows for multilingual solution proposals.

[0114] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0115] In this invention, the server includes means for a user to input a problem, means for receiving a problem, artificial intelligence means for abstracting the received problem and converting it into a fictitious case, means for generating a fictitious case based on the abstracted problem, means for publishing the generated fictitious case to the community, means for community members and the autonomous artificial intelligence to propose solutions, means for summarizing the proposed solutions, means for translating the proposed solutions, means for a user to select a solution, and means for providing a reward. This makes it possible to share problems while maintaining user privacy, and makes it easier for users of different languages ​​to obtain solutions.

[0116] "User" means a person or entity that uses the System to enter a problem and request a solution.

[0117] "Input means" refers to an interface or device that allows a user to input and submit a question in text format.

[0118] "Server" refers to a central management system that receives and processes problems submitted by users.

[0119] "Means for receiving" refers to a function that allows the server to receive questions sent by users in real time.

[0120] "Abstraction" refers to the process of removing sensitive information from an incoming problem and reconstructing it into a generalized problem.

[0121] "Artificial intelligence tools" refers to machine learning models and algorithms used to analyze problems, abstract, and generate fictitious cases.

[0122] "Fictional cases" refer to general and broadly applicable problems that are generated based on abstract problems.

[0123] "Community" refers to a group of other users and autonomous artificial intelligences participating in the system.

[0124] "Means for sharing" refers to a method for communicating the generated fictional cases to community members and autonomous artificial intelligence.

[0125] "Community Members" refers to other users who use the system to propose solutions.

[0126] "Autonomous artificial intelligence" refers to an AI system that uses pre-trained models to generate solutions independently.

[0127] "Solution" refers to a specific method of dealing with a hypothetical case.

[0128] "Means for Proposing" refers to the methods by which community members and autonomous artificial intelligences submit solutions to the server.

[0129] "Means for summarizing" refers to a function for concisely summarizing multiple proposed solutions.

[0130] "Means for translation" refers to the functionality for translating the summarized solution into multiple languages.

[0131] "Means of selection" refers to the interface and functionality that allows users to choose the optimal solution.

[0132] "Reward mechanisms" refers to a feature that provides rewards to community members who propose good solutions.

[0133] The system mainly consists of a user terminal, a server, and an artificial intelligence means. The user inputs the problem using the terminal, and the system then executes the process of proposing a solution.

[0134] User's device

[0135] The user's device refers to an input device such as a general personal computer or smartphone. The user inputs a problem in the form of text input through the device's interface. For example, the user inputs a problem such as "I don't know how to optimize the performance of a project in a specific programming language." After inputting the problem, the device sends it to the server. This transmission requires an internet connection.

[0136] Server Processing

[0137] The server receives the questions sent from the user's terminal and performs the following process to proceed to the next step.

[0138] 1. Receiving the Problem

[0139] The server receives the user's problem via a REST API and temporarily stores it in a database, ensuring that the problem content is preserved.

[0140] 2. Problem Abstraction

[0141] The server analyzes the received problem using artificial intelligence means (e.g., a machine learning model). Specifically, it uses a generative AI model and invokes the AI ​​with the prompt, "Abstract the input problem and reconstruct it into a general problem." The problem is then converted into a generalized problem that does not contain sensitive information.

[0142] 3. Generating fictional cases

[0143] The server uses a generative AI model to generate fictitious cases based on the abstract problem. The prompt is "Generate specific fictitious cases based on the abstract problem." For example, the server generates a generalized problem called "improving the performance of a software system" as "a method for improving the performance of a large-scale data processing system."

[0144] 4. Sharing fictional stories

[0145] The generated fictional cases are shared with the community via a server, using messaging protocols and SNS APIs.

[0146] Community members and autonomous AI proposals

[0147] Community members (other users) and the autonomous AI propose solutions based on fictitious cases shared by the server. Community members input solutions from their own devices and send them to the server. The autonomous AI generates solutions using a pre-trained model and sends them to the server.

[0148] Solution Processing

[0149] 1. Solution Summary

[0150] The server uses a generative AI model to summarize the proposed solutions. It invokes the AI ​​with the prompt "Please briefly summarize these solutions" to generate a concise solution.

[0151] 2. Translation of the solution

[0152] The summarized solution is translated using a multilingual translation means. The server uses the prompt sentence "Please translate from English to Japanese" and runs a machine translation model.

[0153] User Choice and Rewards

[0154] Users can view a list of solutions with abridged translations on their device, choose the best solution, and adopt it to solve their problem. Community members who propose particularly good solutions can be rewarded using a points system or virtual currency.

[0155] Examples of specific examples and prompts

[0156] As a concrete example, suppose a user inputs a problem such as "I don't know the cause of a particular plant dying and what to do about it." This problem is sent to the server, which uses artificial intelligence to abstract it into the form of "general methods for plant health management." Then, a generative AI model is used to generate fictitious examples such as "improving the soil, watering at the right time, and providing adequate sunlight." After the problem is shared, community members and autonomous AI propose solutions, which the server then summarizes and translates.

[0157] Examples of prompts include:

[0158] "Abstract the input problem and reconstruct it into a general problem."

[0159] "Generate concrete, fictional cases based on abstract problems."

[0160] Please briefly summarize these multiple solutions.

[0161] Please translate from English to Japanese.

[0162] Thus, the present invention provides a system for efficient, multilingual management and resolution of user problems while preserving their anonymity.

[0163] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0164] The flow of this system's program processing

[0165] Step 1: User Problem Input

[0166] The user enters the problem on their device. Specifically, the user writes the problem in text format in the input form on the device and presses the submit button. For example, the user might enter, "I don't know how to optimize the performance of a project in a specific programming language."

[0167] Input: Problem text

[0168] Output: The problem request sent to the server

[0169] Step 2: The server receives the problem

[0170] The server receives the problem sent by the user using the REST API and saves the problem in the database. This is to temporarily store the problem content and ensure subsequent processing.

[0171] Input: User submitted text question

[0172] Output: Saved problem data

[0173] Step 3: Abstract the problem

[0174] The server analyzes and abstracts the received problem using artificial intelligence. It passes the prompt "Abstract the input problem and reconstruct it into a general problem" to the generative AI model. The AI ​​analyzes the problem, removes sensitive information, and generalizes it.

[0175] Input: Saved problem data

[0176] Output: Abstracted problem

[0177] Step 4: Generate fictional cases

[0178] The server uses a generative AI model to generate a fictitious case based on the abstracted problem. The prompt is "Generate a concrete fictitious case based on the abstracted problem." For example, it could be described as "How to improve the performance of a software system."

[0179] Input: Abstracted problem

[0180] Output: fictitious example

[0181] Step 5: Share a fictional example

[0182] The server shares the generated fictional cases with the community. The server uses messaging protocols and SNS APIs to send the cases to community members and autonomous AI.

[0183] Input: fictional case

[0184] Output: Share the case study with the community

[0185] Step 6: Community members and autonomous AI proposals

[0186] Community members and the autonomous AI propose solutions based on shared fictional cases. Members input and submit solutions on their own devices, and the autonomous AI generates solutions using a pre-trained model. The server receives the proposed solutions.

[0187] Input: Solution proposals from community members and autonomous AI

[0188] Output: Proposal data stored on the server

[0189] Step 7: Solution Summary

[0190] The server summarizes the proposed solutions using a generative AI model. The AI ​​is invoked with the prompt "Please briefly summarize these solutions" to generate a concise summary.

[0191] Input: Proposal data

[0192] Output: Summarized solution

[0193] Step 8: Translating the solution

[0194] The server translates the summarized solution using a multilingual translation means. The server uses the prompt "Please translate from English to Japanese" and executes a machine translation service.

[0195] Input: Abridged solution

[0196] Output: Translated solution

[0197] Step 9: User Choice and Reward

[0198] The user reviews the translated list of solutions on their device, selects the best solution, and rewards the proposer of the selected solution using a points system or virtual currency.

[0199] Input: translated solution list, user selection

[0200] Output: Selected solution, reward given

[0201] This allows users to solve problems while maintaining their privacy, and creates a system that can be used by users of different languages.

[0202] (Application example 1)

[0203] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0204] In modern factories, it is important to find a quick and accurate solution when an abnormality or problem occurs. However, many current solution methods require human effort and time, and are inefficient. In addition, it is difficult to identify and abstract the problem, making it difficult for workers without specialized knowledge to deal with it. In such situations, there is a risk of reduced productivity and increased costs.

[0205] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0206] In this invention, the server includes: a means for a user to input a problem; a server means for receiving the problem; an AI means for abstracting the received problem and converting it into a fictitious case; a means for sharing the abstracted problem with the community; a means for community members and the autonomous AI to propose solutions; a means for summarizing the proposed solutions; a means for a user to select a solution and a means for providing a reward; a means for a factory robot to detect anomalies; a means including a sensor and a camera for describing anomalies in text format; and a means for automatically collecting and processing the proposed solutions. This enables rapid detection of anomalies in factories and the proposal and selection of solutions.

[0207] The "means for the user to input a question" refers to a device or software that provides an interface for the user to input a specific question in text format.

[0208] The "server means for receiving questions" is a central server for receiving and managing questions sent by users.

[0209] "AI means for abstracting received problems and converting them into fictional cases" refers to an artificial intelligence algorithm for generalizing received specific problems and removing sensitive information.

[0210] "Means for sharing abstracted problems with the community" refers to the means by which abstracted problems can be sent to other users and AI models in the system to broadly solicit solutions.

[0211] "Means for community members and autonomous AIs to propose solutions" refers to the means by which other users participating in the system and autonomous AIs with previously learned knowledge can make proposals.

[0212] A "means for summarizing proposed solutions" is a summarization algorithm for concisely summarizing multiple proposed solutions.

[0213] A "means for translating the proposed solution" is a translation algorithm or API that translates the summarized solution into other languages ​​so that it can be understood by multilingual users.

[0214] The "means for users to select solutions and provide rewards" is a mechanism by which users can select the best solution from the proposed solutions and provide a reward to the person who proposed it.

[0215] "Means for factory robots to detect abnormalities" refers to devices such as sensors and cameras used to detect abnormalities within the factory.

[0216] "Means including a sensor and a camera for describing anomalies in text form" refers to a device for describing information on detected anomalies in text form and software that supports it.

[0217] "Means for automatically collecting and processing proposed solutions" means a system for automatically collecting, analyzing, and processing proposed solutions from the community.

[0218] Specifically, an embodiment of the present invention is realized as a system that detects anomalies using factory robots and widely solicits solutions to the anomalies. The system includes: means for a user to input a problem; a server means for receiving the problem; an AI means for abstracting the received problem and converting it into a fictitious case; means for sharing the abstracted problem with a community; means for community members and autonomous AIs to propose solutions; means for summarizing the proposed solutions; means for a user to select a solution and provide a reward; means for a factory robot to detect anomalies; means including a sensor and a camera for describing the anomaly in text form; and means for automatically collecting and processing the proposed solutions.

[0219] First, we will explain how factory robots detect abnormalities. Factory robots are equipped with hardware such as temperature sensors, pressure sensors, and cameras, which detect abnormalities. For example, if a conveyor belt stops during transportation, the cameras and sensors detect the abnormality and record the information in text format. This text data is sent to a server.

[0220] The server then abstracts the received text data. Specifically, it uses a Transformer-based AI model such as BERT to generalize the specific content of the anomaly and remove sensitive information. The abstracted problem is reconstructed as a fictitious example that hides the real problem. This allows it to be shared as useful information for other users with similar problems.

[0221] The abstracted problem is then shared with the community through a web application. Users can submit problem-solving proposals using their own PCs or smartphones. The proposed solutions are collected on a server, where they are summarized and translated. The translation is done using the Google (registered trademark) Translate API, and the summarization is done using generative AI models such as GPT-3 (registered trademark). This allows the proposed solutions to be understood in other languages.

[0222] Finally, users select the best solution from the list and apply it to their own system. Community members who make excellent suggestions are rewarded. This process quickly detects abnormalities in factories and effectively derives solutions.

[0223] Specific examples

[0224] For example, consider the case where a conveyor belt in a factory suddenly stops. The factory robot's cameras and sensors detect the abnormality and input the problem into the system in text format. This problem is described as "the conveyor belt stops." The server receives this problem and abstracts it into a "general conveyor system stoppage problem." After it is shared with the community, other users and AI can make suggestions such as "motor failure" or "abnormal belt stretch." These suggestions are summarized and translated into multiple languages ​​and provided to users.

[0225] Prompt Sentence Examples

[0226] User: "The conveyor belt in our factory suddenly stopped. I don't know what caused it or what to do about it."

[0227] System: "Abstracting the problem..."

[0228] AI model: "What are some common problems that cause conveyor belts to stop?"

[0229] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0230] Now, the processing flow of the program of the system that realizes the application example will be explained in detail, broken down into steps.

[0231] Step 1:

[0232] Factory robots detect abnormalities. Sensors (temperature sensors, pressure sensors, etc.) and cameras installed on the factory robots are activated to detect abnormalities. For example, abnormal events such as a stopped conveyor belt, a motor failure, or an abnormal rise in temperature are detected. This abnormality detection data is obtained as numerical data or image data.

[0233] Step 2:

[0234] Anomaly detection data is converted into text format. A terminal inside the robot receives data from the sensors and cameras and describes the anomaly in text format. For example, abnormal temperature data obtained from a temperature sensor is converted into text such as "The temperature has exceeded the set value." This generates specific information about the anomaly as text data.

[0235] Step 3:

[0236] The server receives the text data. The central server receives the text data sent from the factory robot. The input is text data, and the received text data becomes the input for the next step.

[0237] Step 4:

[0238] The received problem is abstracted and converted into a fictitious case. The received text data is abstracted using AI means (e.g., the BERT model) installed on a central server. This process converts concrete information into a general problem. The input is the received text data, and the output is an abstracted problem such as "a general problem of a conveyor belt stopping." This data conversion generalizes the data to make it easier to find a solution while hiding specific anomaly information.

[0239] Step 5:

[0240] The abstracted problem is shared with the community. The server publishes the abstracted problem to the community through a web front end (for example, an application using React). The input is the abstracted problem, and the output is information shared with all members of the community. This sharing process makes it possible to solicit solution proposals from a wide range of users.

[0241] Step 6:

[0242] Community members and autonomous AI propose solutions. Other users participating in the community and autonomous AI models propose solutions to abstracted problems. The input is the abstracted problem, and the output is multiple proposed solutions. This behavior is achieved by users directly entering the solution on the web application, or by the AI ​​automatically generating the solution.

[0243] Step 7:

[0244] Summarize proposed solutions and translate them into multiple languages. Multiple proposed solutions are concisely summarized on the server using an AI summarization tool (e.g., GPT-3). Furthermore, the solutions are translated into other languages ​​using a multilingual translation tool such as the Google Translate API. The input is the proposed solution, and the output is the summarized and translated solution. This makes the solution easily understandable to users around the world.

[0245] Step 8:

[0246] The user selects the best solution and is rewarded. The user reviews the summarized and translated solution list provided by the server and selects the best solution. After selection, the community member who made the best proposal is rewarded. The input is the summarized and translated solution list, and the output is the selected solution and reward information. This operation allows the user to obtain a concrete means to solve the problem, and provides appropriate incentives to the contributing members.

[0247] In this way, the entire system works together to efficiently support anomaly detection and problem resolution within the factory.

[0248] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0249] The embodiment of the present invention is a system in which a user inputs a problem and solicits solutions from a wide range of people, and is combined with an emotion engine that recognizes the user's emotions. This system is composed of a terminal, a server, an AI means, and an emotion engine, and the specific roles and processing flow of each element are explained below.

[0250] User's device

[0251] The user's device provides an interface for inputting problems and communicating emotions. The user inputs specific problems they are facing in their hobbies or work through the device. The system also provides a function for reading emotions from the user's input and interactions. This input information is sent from the user's device to the server.

[0252] Server Processing

[0253] The server centrally processes the data received from the user's device about the problem and emotions and provides the means to take the next step.

[0254] 1. Receiving the problem and recognizing emotions:

[0255] The server receives the problem data and emotion data sent from the device, which includes emotions analyzed from the user's input and interactions.

[0256] 2. Problem Abstraction:

[0257] The received problem is analyzed by AI means on the server, and abstracted without sensitive information, referring to the data from the emotion engine. This abstracted problem is reconstructed as a fictional case that hides the real problem.

[0258] 3. Generating fictitious cases:

[0259] The server uses AI tools to generate concrete fictional cases based on abstractions, which are constructed as generalized and widely applicable problems.

[0260] 4. Sharing fictional stories:

[0261] The generated fictitious cases are made public to all users and autonomous AIs in the community via the server.

[0262] Community members and autonomous AI proposals

[0263] Community members can propose solutions to published fictitious cases. The autonomous AI can also propose solutions based on its pre-trained knowledge. These proposals are filtered by the emotion engine to match the user's emotions and sent to the server.

[0264] Solution Processing

[0265] 1. Solution Summary:

[0266] The server uses an AI summary model to concisely summarize multiple solutions proposed by community members and autonomous AIs. This summary concisely summarizes the key points of each solution.

[0267] 2. Solution Translation:

[0268] The server translates the summarized solution using a multilingual translation model, making the solution easier to understand for users around the world.

[0269] User Choice and Rewards

[0270] Users can review a list of solutions with summaries and translations provided by the server, and select the most useful one from the solutions filtered by the emotion engine. Based on this selection, they can obtain specific measures to apply to their own problem. Furthermore, users can reward community members who propose the most useful solutions.

[0271] Specific examples

[0272] Example 1: Engineer's Concerns

[0273] 1. User problem input and emotion recognition:

[0274] The user (engineer) enters a problem such as "I don't know how to optimize the performance of a project in a specific programming language," and expresses the stress and confusion they feel at the time.

[0275] 2. Server processing:

[0276] The server receives the problem and user sentiment data and uses AI means to convert it into a fictional case study of "general methods for improving the performance of software systems."

[0277] 3. Community Suggestions and Sentiment Filtering:

[0278] Community members and autonomous AI suggest solutions such as cache optimization, code refactoring, and algorithm improvements, and an emotion engine filters them in a tone that reduces user stress.

[0279] 4. Solution summary and translation:

[0280] The proposed solutions are summarized by the server and translated into multiple languages.

[0281] 5. User Choice and Action:

[0282] Users can choose the best solution and apply it to their own projects, and members who make the best suggestions are rewarded.

[0283] Example 2: Gardening problems

[0284] 1. User problem input and emotion recognition:

[0285] The user (gardener) inputs the problem, "I don't know why a certain plant is dying and what to do about it," and expresses the sadness and concern he or she feels at the time.

[0286] 2. Server processing:

[0287] The server receives the problem and the user's emotional data and converts it into a fictional case study called "General methods for plant health management" using AI means.

[0288] 3. Community Suggestions and Sentiment Filtering:

[0289] Community members and autonomous AI suggest solutions such as soil improvement, watering times, and proper sunlight, and an emotion engine filters them with a tone that alleviates the user's concerns.

[0290] 4. Solution summary and translation:

[0291] The proposed solutions are summarized by the server and translated into multiple languages.

[0292] 5. User Choice and Action:

[0293] Users can choose the best solution and apply it to their own gardening activities, and members who make the best suggestions will be rewarded.

[0294] With this configuration, the present invention provides a system that can solve a user's problem in a way that takes into consideration their emotions while maintaining anonymity, and can obtain suggestions from a variety of perspectives.

[0295] The processing flow will be explained below.

[0296] Step 1: User enters problem

[0297] Users log in to the "IdeaQuest" app using their own devices and enter specific problems in text format.

[0298] For example: "I don't know how to optimize the performance of my project in a specific programming language."

[0299] Step 2: Enter user emotions

[0300] The user selects or describes their own emotion when entering a question. The terminal provides an option for entering emotions.

[0301] For example, enter emotions such as confusion, anxiety, or tension.

[0302] Step 3: Server receives the problem and sentiment

[0303] The server receives the question text data and emotion data sent from the user terminal.

[0304] Step 4: Abstract the problem

[0305] An AI means on the server analyzes the received problem and generalizes the problem while excluding sensitive information.

[0306] Example: Remove information about specific programming languages ​​and abstract it as a "general method for improving the performance of software systems."

[0307] Step 5: Generate fictional cases

[0308] The server generates fictitious cases based on problems abstracted using AI means.

[0309] For example, a fictitious case study was generated: "What techniques or approaches are effective in a situation where a software system is performing poorly?"

[0310] Step 6: Share your fictional story with the community

[0311] The server shares the generated fictional cases with all users and autonomous AIs in the community.

[0312] Step 7: Community members propose solutions

[0313] Community members can think of solutions to the fictitious cases that are published and post their suggestions from their own devices.

[0314] For example: cache optimization, code refactoring, algorithm improvements, etc.

[0315] Step 8: Autonomous AI proposes a solution

[0316] The autonomous AI also proposes solutions to fictitious cases that are made public based on knowledge it has learned in advance.

[0317] Step 9: Filtering solutions with the emotion engine

[0318] The emotion engine on the server filters the proposed solutions according to the user's emotion. The solution is selected in a tone that matches the user's emotion and is presented in a way that is less stressful for the user.

[0319] Step 10: Solution Summary

[0320] The server summarizes the solutions filtered by the emotion engine, using an AI summarization model to concisely summarize each solution.

[0321] Step 11: Translating the Solution

[0322] The server translates the summarized solutions into multiple languages, using a multilingual translation model to provide appropriate translations for each language.

[0323] Step 12: User selects optimal solution

[0324] The user reviews the list of translated solutions provided by the server and selects the solution that seems most useful.

[0325] Step 13: User Gives Reward

[0326] Users can show their appreciation and reward community members who propose optimal solutions, either in the form of points in the system or real money.

[0327] Through the above processing steps, the "IdeaQuest" system abstracts the user's specific problem, gathers solutions from various perspectives, and provides the solutions according to the user's feelings.

[0328] Example 2

[0329] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0330] Conventional problem-solving systems have been unable to properly recognize users' emotions and provide filtered solutions. This makes it difficult for users to receive suggestions that are appropriate for their emotions, resulting in reduced problem-solving efficiency. Furthermore, the proposed solutions are not multilingual, making it difficult for global users to efficiently utilize the system.

[0331] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes emotion recognition means for analyzing user emotion data, means for analyzing the user emotion using an emotion engine, and means for filtering proposed solutions through the emotion engine. This allows the system to provide solutions suited to the user's emotions, and the system's multilingual support enables users around the world to efficiently use the system.

[0332] A "user" is a person or entity that utilizes the system to enter their problem and receive a solution.

[0333] A "terminal" is a device that provides an interface for users to input questions and communicate their feelings.

[0334] A "server" is a central system that receives data sent from terminals and analyzes and processes it.

[0335] The "means for receiving questions" is a function by which the server receives question data sent from the user's terminal.

[0336] "Problem abstraction" is the process of generalizing the problem received from the user by excluding sensitive information.

[0337] "AI means for converting into fictional cases" is an artificial intelligence technology that reconstructs abstract problems into concrete fictional cases.

[0338] "Emotion recognition means" is a technology that analyzes and recognizes emotions from user input and interactions.

[0339] The "emotion engine" is a system that analyzes user emotions, filters proposed solutions, and analyzes emotional data.

[0340] "Sharing means" is the process of making abstracted problems available to other users and autonomous AIs.

[0341] "Community members" are multiple users who participate in the system and propose solutions.

[0342] "Independent AI" is artificial intelligence that proposes solutions based on its own learning data.

[0343] "Filtering" is the process of sorting proposed solutions in a way that is appropriate to the user's emotions.

[0344] "Means to summarize" is a function that succinctly summarizes the proposed solution.

[0345] "Translation means" is a technique for translating summarized solutions into multiple languages.

[0346] "Selection" is the process by which a user chooses the most beneficial solution from those offered.

[0347] "Rewarding" is a feature that provides rewards to community members who propose the most beneficial solutions.

[0348] A "multilingual translation model" is an artificial intelligence model designed to handle different languages.

[0349] This invention is a system in which a user inputs a problem, analyzes and abstracts the problem, and solicits solutions from a broad community. This system achieves more effective problem solving by combining it with an emotion engine that recognizes the user's emotions and proposes appropriate solutions. A specific embodiment of this system is described below.

[0350] User's device

[0351] The user's device provides an interface for inputting problems and communicating emotions. Users input specific problems they are facing in their hobbies or work through the device. The system also provides a function for reading emotions from the user's input and interactions. This function uses a natural language processing (NLP) engine and a facial recognition system. This input information is sent from the user's device to a server.

[0352] Server Processing

[0353] The server centrally processes the data received from the user's device about the problem and emotions and provides the means to take the next step.

[0354] Problem reception and emotion recognition:

[0355] The server receives the problem data and emotion data sent from the device, which includes emotions analyzed from the user's input and interactions.

[0356] Problem Abstraction:

[0357] The AI ​​means on the server analyzes the received problem data and abstracts the problem by removing sensitive information based on the data from the emotion engine. This converts the user's specific problem into a generalized form such as "a general method for improving the performance of software systems."

[0358] Fictional Case Generation:

[0359] The server generates specific fictitious examples based on the abstracted content using AI means. The technology used is a generative AI model (e.g., GPT-3, GPT-4 (registered trademark), etc.). The examples are created in a general-purpose format that can be applied to many situations.

[0360] Sharing a fictional example:

[0361] The generated fictitious cases are made public via the server to all users and autonomous AIs in the community. After the cases are made public, users and autonomous AIs can propose solutions to new cases.

[0362] Community members and autonomous AI proposals

[0363] Community members propose solutions to fictitious cases that have been published. The autonomous AI also proposes solutions based on its pre-trained knowledge. These proposals are filtered by the emotion engine to match the user's emotions and sent to the server.

[0364] Solution Processing

[0365] Solution Summary:

[0366] The server uses an AI summary model to concisely summarize multiple solutions proposed by community members and autonomous AIs. This summary concisely summarizes the key points of each solution.

[0367] Solution translation:

[0368] The server translates the summarized solution using a multilingual translation model, making the solution easier to understand for users around the world.

[0369] User Choice and Rewards

[0370] Users review a list of solutions with summaries and translations provided by the server, and select the most useful one from the solutions filtered by the emotion engine. Users then apply the selected solution to their own problem. Community members who propose the most useful solution can also be rewarded.

[0371] Specific examples

[0372] Engineer's Concerns

[0373] User problem input and emotion recognition:

[0374] The user (engineer) enters a problem such as "I don't know how to optimize the performance of a project in a specific programming language," and expresses the stress and confusion they feel at the time.

[0375] Server Action:

[0376] The server receives the problem and user sentiment data and uses AI means to convert it into a fictional case study of "general methods for improving the performance of software systems."

[0377] Community Suggestions and Sentiment Filtering:

[0378] Community members and autonomous AI suggest solutions such as cache optimization, code refactoring, and algorithm improvements, and an emotion engine filters them in a tone that reduces user stress.

[0379] Solution summary and translation:

[0380] The proposed solutions are summarized by the server and translated into multiple languages.

[0381] User selection and execution:

[0382] Users choose the best solution and apply it to their own projects, and members who make the best suggestions are rewarded.

[0383] Example prompt: "An engineer is struggling and frustrated with how to optimize the performance of a project in a specific programming language. Please provide some generally applicable advice to solve this problem."

[0384] In this way, the present invention provides a system that can solve individual user problems in a way that takes into consideration emotions while maintaining anonymity, and can obtain suggestions from a variety of perspectives.

[0385] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0386] System program processing flow

[0387] Step 1:

[0388] The user uses the device to input their specific problem. They can also input their emotions or communicate them through emotion recognition. The device's NLP engine and facial recognition system analyze the user's input and interactions to extract emotion data. The input data is in the form of "I don't know how to optimize the performance of a project in a specific programming language," and the output data is the analysis result (e.g., emotion = stress, confusion).

[0389] Step 2:

[0390] The server receives the problem and emotion data sent from the device. The received data includes the user's specific problem and the emotion they felt at the time. The server's program analyzes this data and provides feedback to the emotion engine. The input data is the received user problem and emotion data, and the output data is the analyzed emotion information.

[0391] Step 3:

[0392] The AI ​​means on the server analyzes the received problem data and abstracts the problem while removing sensitive information using the emotion engine data as a reference. Specifically, NLP engines and data mining techniques are used. For example, the problem "I don't know how to optimize the performance of a project in a specific programming language" is abstracted into "general methods for improving the performance of software systems." The input data of this step is specific problem information, and the output data is abstracted problem information.

[0393] Step 4:

[0394] The server uses AI means to generate specific fictitious cases based on abstracted problem data. Generative AI models (e.g., GPT-3, GPT-4) are used for generation. These cases are constructed in a general form that can be applied to many situations. For example, they are reconstructed as "general methods for improving the performance of software systems." The input data is the abstracted problem, and the output data is the generated fictitious case.

[0395] Step 5:

[0396] The server publishes the generated fictitious cases to all users and autonomous AIs in the community. After the cases are published, users and autonomous AIs use them as prompts to propose solutions for new cases. The input data is the generated fictitious case, and the output data is the published case.

[0397] Step 6:

[0398] Community members and autonomous AI propose solutions to fictitious cases. These proposals are filtered by an emotion engine to match the user's emotions and sent to the server. The input data are the solutions for each proposal, and the output data are the solutions filtered by the emotion engine.

[0399] Step 7:

[0400] The server summarizes the proposed solutions concisely using an AI summarization model. This summary concisely extracts the key points of each solution. The summarized solutions are then translated using a multilingual translation model. The input data for this step are the filtered solutions for each proposal, and the output data are the summarized solutions and their translations.

[0401] Step 8:

[0402] The user reviews a list of solutions with summaries and translations provided by the server. The user selects the most useful solution from the solutions filtered by the emotion engine and applies it to solving their own problem. The user can also award a reward to the community member who proposes the most useful solution. The input data is the summarized solution list, and the output data is the selected optimal solution and reward data.

[0403] (Application example 2)

[0404] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0405] Customer service in traditional brick-and-mortar stores has been heavily dependent on the experience and skills of staff, resulting in inconsistent quality of service. It has also been difficult to properly recognize customer emotions and respond accordingly. The objective of this invention is to provide a system that solves these problems, quickly resolves customer problems, and provides emotionally sensitive service.

[0406] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for a user to input a problem; server means for receiving the problem; AI means for abstracting the received problem and converting it into a fictitious case; means for sharing the abstracted problem with the community; means for community members and autonomous AI to propose solutions; means for summarizing the proposed solution; means for translating the proposed solution; means for a user to select a solution and provide a reward; means for inputting a problem from the voice or text of a customer in a physical store and recognizing their emotions; and means for generating suggestions based on the customer's emotions and providing an optimal solution. This makes it possible to solve customer problems quickly and in a manner that takes their emotions into consideration.

[0407] Key Word Definitions

[0408] The "means for users to input problems" refers to a means for providing an interface for users to input problems such as questions or concerns by text or voice.

[0409] The "server means for receiving questions" is a server device for receiving and processing question information sent from a user.

[0410] "AI means for abstracting received problems and converting them into fictional cases" refers to artificial intelligence means for analyzing received problems, excluding specific information, and reconstructing them in a generalized form as fictional cases.

[0411] A "means for sharing abstract problems with the community" is a means for publishing abstract problems to an online community so that they can be widely viewed and suggested.

[0412] "Means for community members and autonomous AI to propose solutions" means means that enable community members and autonomous AI to propose solutions to specified problems.

[0413] A "means for summarizing proposed solutions" is a means for concisely summarizing multiple solutions provided and extracting their main points.

[0414] A "means for translating the proposed solution" is a means for translating the summarized solution into other languages.

[0415] The "means for users to select a solution and to give a reward" refers to a means by which a user can select the most suitable solution from among the solutions provided and send a reward to the proposer of the solution.

[0416] "Means for inputting problems and recognizing emotions from voices and texts of customers in physical stores" refers to a means for analyzing the voices uttered by customers and the texts they input in physical stores and identifying their emotions from them.

[0417] The "means for generating proposals based on customer emotions and providing optimal solutions" is a means for taking into account the recognized emotions of a customer and generating and providing a solution that is appropriate for the customer.

[0418] An embodiment of the present invention will be described in detail below. This embodiment is a system for quickly resolving customer problems and responding in an emotionally sensitive manner in order to improve the quality of customer service in brick-and-mortar stores.

[0419] User's device

[0420] The user device is a device such as a smartphone or tablet. The user can use this device to input customer problems or questions by voice or text. The device converts speech to text using speech recognition software (such as the Google Speech Recognition API). It also includes an emotion recognition engine (such as the Hugging Face Transformers library) to recognize emotions from the customer's facial expressions and tone of voice.

[0421] Server Processing

[0422] The server receives the questions and emotion data sent from the user's terminal and performs the following processing.

[0423] 1. Problem Abstraction:

[0424] The server analyzes the received data using AI (such as TextBlob or a custom natural language processing model) and abstracts it into a generalized problem, excluding specific information.

[0425] 2. Generating fictitious cases:

[0426] Generate concrete fictitious cases based on abstract problems and share them with the community.

[0427] 3. Share with the community:

[0428] We provide an environment where community members (other store staff, related parties, etc.) and autonomous AI can propose solutions to this fictional case.

[0429] 4. Summary and translation of the proposed solution:

[0430] The proposed solution is summarized using an AI summarization model (such as Hugging Face's Transformers library) and translated using a multilingual translation model (such as Helsinki-NLP's opus-mt-en-jp).

[0431] Specific processing flow example

[0432] The following example shows a specific processing flow.

[0433] Example 1: "Product not found"

[0434] The user voice-inputs the customer's problem into their smartphone, saying, "I can't find the product."

[0435] The server converts the voice into text and uses an emotion recognition engine to recognize the customer's "confusion" emotion.

[0436] AI abstracts the problem into "optimizing product information" and generates solutions such as "providing product layout diagrams" and "direct guidance by staff."

[0437] The solutions are summarized and translated into other languages ​​(e.g., English) using a multilingual translation model.

[0438] Example prompt sentence:

[0439] "A customer has expressed difficulty finding a particular product. They seem confused. How should I respond?"

[0440] As shown in this specific example, the present invention is a system that can solve customer problems quickly and in an emotionally sensitive manner, thereby significantly improving customer satisfaction in physical stores.

[0441] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0442] Program processing flow

[0443] Step 1:

[0444] Users input their customer's problem by voice or text using a smartphone or tablet, and the input voice data is converted into text using voice recognition software.

[0445] Input: Customer voice or text input

[0446] How it works: Uses speech recognition software (Google Speech Recognition API) to convert speech to text.

[0447] Output: Text data

[0448] Step 2:

[0449] The user's device sends the converted text data to the server, which also uses an emotion recognition engine to analyze the customer's emotions and sends the results to the server.

[0450] Input: Text data and customer sentiment data obtained in Step 1

[0451] How it works: Analyzes emotions using an emotion recognition engine (Hugging Face's Transformers library). Sends the data to the server.

[0452] Output: Text data and emotion data

[0453] Step 3:

[0454] The server receives the question text data and emotion data from the user's terminal and stores them.

[0455] Input: Text data and emotion data sent in Step 2

[0456] Action: Save to database.

[0457] Output: Saved text data and emotion data

[0458] Step 4:

[0459] The server analyzes the stored problem data using a natural language processing model (such as TextBlob), removes specific information, and abstracts it into a generalized problem.

[0460] Input: Saved text data

[0461] How it works: Analyzes data using a natural language processing model, filtering out and abstracting specific information.

[0462] Output: Abstracted problem data

[0463] Step 5:

[0464] Based on the abstracted problem, the server uses AI means to generate concrete fictitious cases and shares them with community members and autonomous AI.

[0465] Input: Abstracted problem data

[0466] How it works: Generate fictional cases using AI tools. Share the fictional cases with the community.

[0467] Output: fictional example

[0468] Step 6:

[0469] Solutions proposed by community members and autonomous AIs are collected on a server using an online platform.

[0470] Input: Solutions from community members and autonomous AI

[0471] How it works: Collect suggestions through an online platform.

[0472] Output: Collected solutions

[0473] Step 7:

[0474] The collected solutions are summarized on the server using a summarization model (from the Transformers library in Hugging Face).

[0475] Input: Collected solutions

[0476] What it does: Summarize the solution using a summary model.

[0477] Output: Summarized solution

[0478] Step 8:

[0479] The summarized solution is translated using a multilingual translation model, using the opus-mt-en-jp model from Helsinki-NLP.

[0480] Input: Abridged solution

[0481] What it does: Translates the solution using a translation model.

[0482] Output: Translated solution

[0483] Step 9:

[0484] The server provides the translated solutions to the user, who then selects the best solution. Furthermore, the server rewards the proposer who provides the best solution based on the evaluation.

[0485] Input: translated solution

[0486] Behavior: Show the translated solution to the user. Reward the user based on their choice and rating.

[0487] Output: Selected solution and evaluation results

[0488] In this way, a system is created that can quickly resolve customer problems in brick-and-mortar stores and respond in an emotionally sensitive manner.

[0489] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0490] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0491] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0492] [Second embodiment]

[0493] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0494] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0495] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0496] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0497] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0498] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0499] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0500] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0501] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0502] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0503] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0504] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0505] The embodiment of the present invention is a system in which a user inputs a problem and solicits solutions from a wide range of sources. This system is composed of a terminal, a server, and an AI means. The specific roles and processing flow of each element are explained below.

[0506] User's device

[0507] The user's terminal provides an interface for inputting problems. The user inputs specific problems they are facing in their hobbies or work in text format through the terminal. The input problem is sent from the user's terminal to the server.

[0508] Server Processing

[0509] The server centrally processes the problems received from the user's terminal and provides the means to proceed to the next step.

[0510] 1. Receiving the problem:

[0511] The server receives the question sent from the terminal.

[0512] 2. Problem Abstraction:

[0513] The received problem is analyzed by AI means on the server and abstracted to eliminate sensitive information. This abstracted problem is then reconstructed as a fictional case that hides the real problem.

[0514] 3. Generating fictitious cases:

[0515] The server uses AI tools to generate fictitious cases based on abstracted problems, which are constructed as generalized and widely applicable problems.

[0516] 4. Sharing fictional stories:

[0517] The generated fictional cases are shared with the community via the server, which consists of other users and autonomous AIs participating in the system.

[0518] Community members and autonomous AI proposals

[0519] Community members can propose solutions to published fictitious cases. The autonomous AI can also propose solutions based on its prior knowledge. These proposals are sent to the server for further processing.

[0520] Solution Processing

[0521] 1. Solution Summary:

[0522] The server uses AI summarization to concisely summarize the proposed solutions, providing a clear overview of each solution.

[0523] 2. Solution Translation:

[0524] The server translates the summarized solution using a multilingual translation means, making it easier for users around the world to understand the solution.

[0525] User Choice and Rewards

[0526] Users can review a list of solutions provided by the server, complete with summaries and translations, and select the most suitable solution. Based on this selection, they can obtain specific measures to adapt to their own problems. Furthermore, users can reward community members who propose the most useful solutions.

[0527] Specific examples

[0528] Example 1: Engineer's Concerns

[0529] 1. User problem input:

[0530] A user (engineer) enters a problem: "I don't know how to optimize the performance of a project in a specific programming language."

[0531] 2. Server processing:

[0532] The server receives this problem and uses AI means to convert it into a fictional case study titled "General methods for improving the performance of software systems."

[0533] 3. Community Suggestions:

[0534] Community members and autonomous AI propose solutions such as cache optimization, code refactoring, and algorithm improvements.

[0535] 4. Solution summary and translation:

[0536] The proposed solutions are summarized by the server and translated into multiple languages.

[0537] 5. User Choice and Action:

[0538] Users can choose the best solution and apply it to their own projects, and members who make the best suggestions are rewarded.

[0539] Example 2: Gardening problems

[0540] 1. User problem input:

[0541] The user (gardener) inputs the problem, "I don't know the cause of a certain plant dying and what to do about it."

[0542] 2. Server processing:

[0543] The server receives this problem and uses AI tools to convert it into a fictional case study called "General methods for plant health management."

[0544] 3. Community Suggestions:

[0545] Community members and autonomous AI will suggest solutions such as soil improvement, watering timing, and proper sunlight.

[0546] 4. Solution summary and translation:

[0547] The proposed solutions are summarized by the server and translated into multiple languages.

[0548] 5. User Choice and Action:

[0549] Users can choose the best solution and apply it to their own gardening activities, and members who make the best suggestions will be rewarded.

[0550] With this configuration, the present invention provides a system that can solve a user's problem from various perspectives while maintaining anonymity.

[0551] The processing flow will be explained below.

[0552] Step 1: User enters problem

[0553] Users log in to the IdeaQuest app from their device and enter the specific problem they are facing into a text box.

[0554] For example: "I don't know how to optimize the performance of my project in a specific programming language."

[0555] Step 2: The server receives the problem

[0556] The server receives the problem data sent from the terminal, including the specific problem text entered by the user.

[0557] Step 3: Abstract the problem using AI tools

[0558] An AI tool on the server analyzes the received problem and converts it into a fictitious case so as not to extract sensitive information.

[0559] Example: Remove information about specific programming languages ​​and abstract it as "a general method for improving the performance of software systems."

[0560] Step 4: Generate fictitious cases

[0561] The server generates specific fictitious cases based on the content abstracted by the AI.

[0562] For example, a hypothetical case study generated might be: "What techniques or approaches are effective in a situation where a software system is performing poorly?"

[0563] Step 5: Share your fictional story with the community

[0564] The server makes the generated fictitious cases public to all users and autonomous AIs in the community.

[0565] Step 6: Community members propose solutions

[0566] Community members come up with solutions to the fictitious cases that are published and post their solutions from their own devices.

[0567] For example: cache optimization, code refactoring, algorithm improvements, etc.

[0568] Step 7: Autonomous AI proposes a solution

[0569] The autonomous AI also analyzes fictitious cases provided to it and generates and proposes solutions based on its prior knowledge.

[0570] Step 8: The server summarizes the solution

[0571] The server uses an AI summary model to summarize multiple solutions proposed by community members and autonomous AIs, concisely summarizing the key points of each solution.

[0572] Step 9: Server translates the solution

[0573] The server translates the summarized solution using a multilingual translation model, allowing users around the world to understand the solution across language barriers.

[0574] Step 10: User selects optimal solution

[0575] The user reviews a list of solutions provided by the server, complete with summaries and translations, and selects the solution that seems most useful.

[0576] Step 11: User Gives Reward

[0577] Users can show their appreciation by rewarding community members who propose optimal solutions, either in the form of points in the system or actual rewards.

[0578] Through the above processing steps, the "IdeaQuest" system abstracts the user's specific problem, gathers solutions from a variety of perspectives, and presents them in an easy-to-understand format.

[0579] Example 1

[0580] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0581] Conventional problem-solving systems have difficulty providing direct solutions to problems entered by users, and sharing problems while maintaining user privacy. Furthermore, their proposed solutions lack multilingual support, making it difficult for users of different languages ​​to communicate with each other. To solve these problems, a system is needed that protects privacy by anonymizing and abstracting users' problems, and that also allows for multilingual solution proposals.

[0582] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0583] In this invention, the server includes means for a user to input a problem, means for receiving a problem, artificial intelligence means for abstracting the received problem and converting it into a fictitious case, means for generating a fictitious case based on the abstracted problem, means for publishing the generated fictitious case to the community, means for community members and the autonomous artificial intelligence to propose solutions, means for summarizing the proposed solutions, means for translating the proposed solutions, means for a user to select a solution, and means for providing a reward. This makes it possible to share problems while maintaining user privacy, and makes it easier for users of different languages ​​to obtain solutions.

[0584] "User" means a person or entity that uses the System to enter a problem and request a solution.

[0585] "Input means" refers to an interface or device that allows a user to input and submit a question in text format.

[0586] "Server" refers to a central management system that receives and processes problems submitted by users.

[0587] "Means for receiving" refers to a function that allows the server to receive questions sent by users in real time.

[0588] "Abstraction" refers to the process of removing sensitive information from an incoming problem and reconstructing it into a generalized problem.

[0589] "Artificial intelligence tools" refers to machine learning models and algorithms used to analyze problems, abstract, and generate fictitious cases.

[0590] "Fictional cases" refer to general and broadly applicable problems that are generated based on abstract problems.

[0591] "Community" refers to a group of other users and autonomous artificial intelligences participating in the system.

[0592] "Means for sharing" refers to a method for communicating the generated fictional cases to community members and autonomous artificial intelligence.

[0593] "Community Members" refers to other users who use the system to propose solutions.

[0594] "Autonomous artificial intelligence" refers to an AI system that uses pre-trained models to generate solutions independently.

[0595] "Solution" refers to a specific method of dealing with a hypothetical case.

[0596] "Means for Proposing" refers to the methods by which community members and autonomous artificial intelligences submit solutions to the server.

[0597] "Means for summarizing" refers to a function for concisely summarizing multiple proposed solutions.

[0598] "Means for translation" refers to the functionality for translating the summarized solution into multiple languages.

[0599] "Means of selection" refers to the interface and functionality that allows users to choose the optimal solution.

[0600] "Reward mechanisms" refers to a feature that provides rewards to community members who propose good solutions.

[0601] The system mainly consists of a user terminal, a server, and an artificial intelligence means. The user inputs the problem using the terminal, and the system then executes the process of proposing a solution.

[0602] User's device

[0603] The user's device refers to an input device such as a general personal computer or smartphone. The user inputs a problem in the form of text input through the device's interface. For example, the user inputs a problem such as "I don't know how to optimize the performance of a project in a specific programming language." After inputting the problem, the device sends it to the server. This transmission requires an internet connection.

[0604] Server Processing

[0605] The server receives the questions sent from the user's terminal and performs the following process to proceed to the next step.

[0606] 1. Receiving the Problem

[0607] The server receives the user's problem via a REST API and temporarily stores it in a database, ensuring that the problem content is preserved.

[0608] 2. Problem Abstraction

[0609] The server analyzes the received problem using artificial intelligence means (e.g., a machine learning model). Specifically, it uses a generative AI model and invokes the AI ​​with the prompt, "Abstract the input problem and reconstruct it into a general problem." The problem is then converted into a generalized problem that does not contain sensitive information.

[0610] 3. Generating fictional cases

[0611] The server uses a generative AI model to generate fictitious cases based on the abstract problem. The prompt is "Generate specific fictitious cases based on the abstract problem." For example, the server generates a generalized problem called "improving the performance of a software system" as "a method for improving the performance of a large-scale data processing system."

[0612] 4. Sharing fictional stories

[0613] The generated fictional cases are shared with the community via a server, using messaging protocols and SNS APIs.

[0614] Community members and autonomous AI proposals

[0615] Community members (other users) and the autonomous AI propose solutions based on fictitious cases shared by the server. Community members input solutions from their own devices and send them to the server. The autonomous AI generates solutions using a pre-trained model and sends them to the server.

[0616] Solution Processing

[0617] 1. Solution Summary

[0618] The server uses a generative AI model to summarize the proposed solutions. It invokes the AI ​​with the prompt "Please briefly summarize these solutions" to generate a concise solution.

[0619] 2. Translation of the solution

[0620] The summarized solution is translated using a multilingual translation means. The server uses the prompt sentence "Please translate from English to Japanese" and runs a machine translation model.

[0621] User Choice and Rewards

[0622] Users can view a list of solutions with abridged translations on their device, choose the best solution, and adopt it to solve their problem. Community members who propose particularly good solutions can be rewarded using a points system or virtual currency.

[0623] Examples of specific examples and prompts

[0624] As a concrete example, suppose a user inputs a problem such as "I don't know the cause of a particular plant dying and what to do about it." This problem is sent to the server, which uses artificial intelligence to abstract it into the form of "general methods for plant health management." Then, a generative AI model is used to generate fictitious examples such as "improving the soil, watering at the right time, and providing adequate sunlight." After the problem is shared, community members and autonomous AI propose solutions, which the server then summarizes and translates.

[0625] Examples of prompts include:

[0626] "Abstract the input problem and reconstruct it into a general problem."

[0627] "Generate concrete, fictional cases based on abstract problems."

[0628] Please briefly summarize these multiple solutions.

[0629] Please translate from English to Japanese.

[0630] Thus, the present invention provides a system for efficient, multilingual management and resolution of user problems while preserving their anonymity.

[0631] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0632] The flow of this system's program processing

[0633] Step 1: User Problem Input

[0634] The user enters the problem on their device. Specifically, the user writes the problem in text format in the input form on the device and presses the submit button. For example, the user might enter, "I don't know how to optimize the performance of a project in a specific programming language."

[0635] Input: Problem text

[0636] Output: The problem request sent to the server

[0637] Step 2: The server receives the problem

[0638] The server receives the problem sent by the user using the REST API and saves the problem in the database. This is to temporarily store the problem content and ensure subsequent processing.

[0639] Input: User submitted text question

[0640] Output: Saved problem data

[0641] Step 3: Abstract the problem

[0642] The server analyzes and abstracts the received problem using artificial intelligence. It passes the prompt "Abstract the input problem and reconstruct it into a general problem" to the generative AI model. The AI ​​analyzes the problem, removes sensitive information, and generalizes it.

[0643] Input: Saved problem data

[0644] Output: Abstracted problem

[0645] Step 4: Generate fictional cases

[0646] The server uses a generative AI model to generate a fictitious case based on the abstracted problem. The prompt is "Generate a concrete fictitious case based on the abstracted problem." For example, it could be described as "How to improve the performance of a software system."

[0647] Input: Abstracted problem

[0648] Output: fictitious example

[0649] Step 5: Share a fictional example

[0650] The server shares the generated fictional cases with the community. The server uses messaging protocols and SNS APIs to send the cases to community members and autonomous AI.

[0651] Input: fictional case

[0652] Output: Share the case study with the community

[0653] Step 6: Community members and autonomous AI proposals

[0654] Community members and the autonomous AI propose solutions based on shared fictional cases. Members input and submit solutions on their own devices, and the autonomous AI generates solutions using a pre-trained model. The server receives the proposed solutions.

[0655] Input: Solution proposals from community members and autonomous AI

[0656] Output: Proposal data stored on the server

[0657] Step 7: Solution Summary

[0658] The server summarizes the proposed solutions using a generative AI model. The AI ​​is invoked with the prompt "Please briefly summarize these solutions" to generate a concise summary.

[0659] Input: Proposal data

[0660] Output: Summarized solution

[0661] Step 8: Translating the solution

[0662] The server translates the summarized solution using a multilingual translation means. The server uses the prompt "Please translate from English to Japanese" and executes a machine translation service.

[0663] Input: Abridged solution

[0664] Output: Translated solution

[0665] Step 9: User Choice and Reward

[0666] The user reviews the translated list of solutions on their device, selects the best solution, and rewards the proposer of the selected solution using a points system or virtual currency.

[0667] Input: translated solution list, user selection

[0668] Output: Selected solution, reward given

[0669] This allows users to solve problems while maintaining their privacy, and creates a system that can be used by users of different languages.

[0670] (Application example 1)

[0671] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0672] In modern factories, it is important to find a quick and accurate solution when an abnormality or problem occurs. However, many current solution methods require human effort and time, and are inefficient. In addition, it is difficult to identify and abstract the problem, making it difficult for workers without specialized knowledge to deal with it. In such situations, there is a risk of reduced productivity and increased costs.

[0673] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0674] In this invention, the server includes: a means for a user to input a problem; a server means for receiving the problem; an AI means for abstracting the received problem and converting it into a fictitious case; a means for sharing the abstracted problem with the community; a means for community members and the autonomous AI to propose solutions; a means for summarizing the proposed solutions; a means for a user to select a solution and a means for providing a reward; a means for a factory robot to detect anomalies; a means including a sensor and a camera for describing anomalies in text format; and a means for automatically collecting and processing the proposed solutions. This enables rapid detection of anomalies in factories and the proposal and selection of solutions.

[0675] The "means for the user to input a question" refers to a device or software that provides an interface for the user to input a specific question in text format.

[0676] The "server means for receiving questions" is a central server for receiving and managing questions sent by users.

[0677] "AI means for abstracting received problems and converting them into fictional cases" refers to an artificial intelligence algorithm for generalizing received specific problems and removing sensitive information.

[0678] "Means for sharing abstracted problems with the community" refers to the means by which abstracted problems can be sent to other users and AI models in the system to broadly solicit solutions.

[0679] "Means for community members and autonomous AIs to propose solutions" refers to the means by which other users participating in the system and autonomous AIs with previously learned knowledge can make proposals.

[0680] A "means for summarizing proposed solutions" is a summarization algorithm for concisely summarizing multiple proposed solutions.

[0681] A "means for translating the proposed solution" is a translation algorithm or API that translates the summarized solution into other languages ​​so that it can be understood by multilingual users.

[0682] The "means for users to select solutions and provide rewards" is a mechanism by which users can select the best solution from the proposed solutions and provide a reward to the person who proposed it.

[0683] "Means for factory robots to detect abnormalities" refers to devices such as sensors and cameras used to detect abnormalities within the factory.

[0684] "Means including a sensor and a camera for describing anomalies in text form" refers to a device for describing information on detected anomalies in text form and software that supports it.

[0685] "Means for automatically collecting and processing proposed solutions" means a system for automatically collecting, analyzing, and processing proposed solutions from the community.

[0686] Specifically, an embodiment of the present invention is realized as a system that detects anomalies using factory robots and widely solicits solutions to the anomalies. The system includes: means for a user to input a problem; a server means for receiving the problem; an AI means for abstracting the received problem and converting it into a fictitious case; means for sharing the abstracted problem with a community; means for community members and autonomous AIs to propose solutions; means for summarizing the proposed solutions; means for a user to select a solution and provide a reward; means for a factory robot to detect anomalies; means including a sensor and a camera for describing the anomaly in text form; and means for automatically collecting and processing the proposed solutions.

[0687] First, we will explain how factory robots detect abnormalities. Factory robots are equipped with hardware such as temperature sensors, pressure sensors, and cameras, which detect abnormalities. For example, if a conveyor belt stops during transportation, the cameras and sensors detect the abnormality and record the information in text format. This text data is sent to a server.

[0688] The server then abstracts the received text data. Specifically, it uses a Transformer-based AI model such as BERT to generalize the specific content of the anomaly and remove sensitive information. The abstracted problem is reconstructed as a fictitious example that hides the real problem. This allows it to be shared as useful information for other users with similar problems.

[0689] The abstracted problems are then shared with the community through a web application. Users can submit solutions using their own PCs or smartphones. The proposed solutions are collected on a server, where they are summarized and translated. The translation is done using the Google Translate API, and the summarization is done using generative AI models such as GPT-3. This allows the proposed solutions to be understood in other languages.

[0690] Finally, users select the best solution from the list and apply it to their own system. Community members who make excellent suggestions are rewarded. This process quickly detects abnormalities in factories and effectively derives solutions.

[0691] Specific examples

[0692] For example, consider the case where a conveyor belt in a factory suddenly stops. The factory robot's cameras and sensors detect the abnormality and input the problem into the system in text format. This problem is described as "the conveyor belt stops." The server receives this problem and abstracts it into a "general conveyor system stoppage problem." After it is shared with the community, other users and AI can make suggestions such as "motor failure" or "abnormal belt stretch." These suggestions are summarized and translated into multiple languages ​​and provided to users.

[0693] Prompt Sentence Examples

[0694] User: "The conveyor belt in our factory suddenly stopped. I don't know what caused it or what to do about it."

[0695] System: "Abstracting the problem..."

[0696] AI model: "What are some common problems that cause conveyor belts to stop?"

[0697] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0698] Now, the processing flow of the program of the system that realizes the application example will be explained in detail, broken down into steps.

[0699] Step 1:

[0700] Factory robots detect abnormalities. Sensors (temperature sensors, pressure sensors, etc.) and cameras installed on the factory robots are activated to detect abnormalities. For example, abnormal events such as a stopped conveyor belt, a motor failure, or an abnormal rise in temperature are detected. This abnormality detection data is obtained as numerical data or image data.

[0701] Step 2:

[0702] Anomaly detection data is converted into text format. A terminal inside the robot receives data from the sensors and cameras and describes the anomaly in text format. For example, abnormal temperature data obtained from a temperature sensor is converted into text such as "The temperature has exceeded the set value." This generates specific information about the anomaly as text data.

[0703] Step 3:

[0704] The server receives the text data. The central server receives the text data sent from the factory robot. The input is text data, and the received text data becomes the input for the next step.

[0705] Step 4:

[0706] The received problem is abstracted and converted into a fictitious case. The received text data is abstracted using AI means (e.g., the BERT model) installed on a central server. This process converts concrete information into a general problem. The input is the received text data, and the output is an abstracted problem such as "a general problem of a conveyor belt stopping." This data conversion generalizes the data to make it easier to find a solution while hiding specific anomaly information.

[0707] Step 5:

[0708] The abstracted problem is shared with the community. The server publishes the abstracted problem to the community through a web front end (for example, an application using React). The input is the abstracted problem, and the output is information shared with all members of the community. This sharing process makes it possible to solicit solution proposals from a wide range of users.

[0709] Step 6:

[0710] Community members and autonomous AI propose solutions. Other users participating in the community and autonomous AI models propose solutions to abstracted problems. The input is the abstracted problem, and the output is multiple proposed solutions. This behavior is achieved by users directly entering the solution on the web application, or by the AI ​​automatically generating the solution.

[0711] Step 7:

[0712] Summarize proposed solutions and translate them into multiple languages. Multiple proposed solutions are concisely summarized on the server using an AI summarization tool (e.g., GPT-3). Furthermore, the solutions are translated into other languages ​​using a multilingual translation tool such as the Google Translate API. The input is the proposed solution, and the output is the summarized and translated solution. This makes the solution easily understandable to users around the world.

[0713] Step 8:

[0714] The user selects the best solution and is rewarded. The user reviews the summarized and translated solution list provided by the server and selects the best solution. After selection, the community member who made the best proposal is rewarded. The input is the summarized and translated solution list, and the output is the selected solution and reward information. This operation allows the user to obtain a concrete means to solve the problem, and provides appropriate incentives to the contributing members.

[0715] In this way, the entire system works together to efficiently support anomaly detection and problem resolution within the factory.

[0716] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0717] The embodiment of the present invention is a system in which a user inputs a problem and solicits solutions from a wide range of people, and is combined with an emotion engine that recognizes the user's emotions. This system is composed of a terminal, a server, an AI means, and an emotion engine, and the specific roles and processing flow of each element are explained below.

[0718] User's device

[0719] The user's device provides an interface for inputting problems and communicating emotions. The user inputs specific problems they are facing in their hobbies or work through the device. The system also provides a function for reading emotions from the user's input and interactions. This input information is sent from the user's device to the server.

[0720] Server Processing

[0721] The server centrally processes the data received from the user's device about the problem and emotions and provides the means to take the next step.

[0722] 1. Receiving the problem and recognizing emotions:

[0723] The server receives the problem data and emotion data sent from the device, which includes emotions analyzed from the user's input and interactions.

[0724] 2. Problem Abstraction:

[0725] The received problem is analyzed by AI means on the server, and abstracted without sensitive information, referring to the data from the emotion engine. This abstracted problem is reconstructed as a fictional case that hides the real problem.

[0726] 3. Generating fictitious cases:

[0727] The server uses AI tools to generate concrete fictional cases based on abstractions, which are constructed as generalized and widely applicable problems.

[0728] 4. Sharing fictional stories:

[0729] The generated fictitious cases are made public to all users and autonomous AIs in the community via the server.

[0730] Community members and autonomous AI proposals

[0731] Community members can propose solutions to published fictitious cases. The autonomous AI can also propose solutions based on its pre-trained knowledge. These proposals are filtered by the emotion engine to match the user's emotions and sent to the server.

[0732] Solution Processing

[0733] 1. Solution Summary:

[0734] The server uses an AI summary model to concisely summarize multiple solutions proposed by community members and autonomous AIs. This summary concisely summarizes the key points of each solution.

[0735] 2. Solution Translation:

[0736] The server translates the summarized solution using a multilingual translation model, making the solution easier to understand for users around the world.

[0737] User Choice and Rewards

[0738] Users can review a list of solutions with summaries and translations provided by the server, and select the most useful one from the solutions filtered by the emotion engine. Based on this selection, they can obtain specific measures to apply to their own problem. Furthermore, users can reward community members who propose the most useful solutions.

[0739] Specific examples

[0740] Example 1: Engineer's Concerns

[0741] 1. User problem input and emotion recognition:

[0742] The user (engineer) enters a problem such as "I don't know how to optimize the performance of a project in a specific programming language," and expresses the stress and confusion they feel at the time.

[0743] 2. Server processing:

[0744] The server receives the problem and user sentiment data and uses AI means to convert it into a fictional case study of "general methods for improving the performance of software systems."

[0745] 3. Community Suggestions and Sentiment Filtering:

[0746] Community members and autonomous AI suggest solutions such as cache optimization, code refactoring, and algorithm improvements, and an emotion engine filters them in a tone that reduces user stress.

[0747] 4. Solution summary and translation:

[0748] The proposed solutions are summarized by the server and translated into multiple languages.

[0749] 5. User Choice and Action:

[0750] Users can choose the best solution and apply it to their own projects, and members who make the best suggestions are rewarded.

[0751] Example 2: Gardening problems

[0752] 1. User problem input and emotion recognition:

[0753] The user (gardener) inputs the problem, "I don't know why a certain plant is dying and what to do about it," and expresses the sadness and concern he or she feels at the time.

[0754] 2. Server processing:

[0755] The server receives the problem and the user's emotional data and converts it into a fictional case study called "General methods for plant health management" using AI means.

[0756] 3. Community Suggestions and Sentiment Filtering:

[0757] Community members and autonomous AI suggest solutions such as soil improvement, watering times, and proper sunlight, and an emotion engine filters them with a tone that alleviates the user's concerns.

[0758] 4. Solution summary and translation:

[0759] The proposed solutions are summarized by the server and translated into multiple languages.

[0760] 5. User Choice and Action:

[0761] Users can choose the best solution and apply it to their own gardening activities, and members who make the best suggestions will be rewarded.

[0762] With this configuration, the present invention provides a system that can solve a user's problem in a way that takes into consideration their emotions while maintaining anonymity, and can obtain suggestions from a variety of perspectives.

[0763] The processing flow will be explained below.

[0764] Step 1: User enters problem

[0765] Users log in to the "IdeaQuest" app using their own devices and enter specific problems in text format.

[0766] For example: "I don't know how to optimize the performance of my project in a specific programming language."

[0767] Step 2: Enter user emotions

[0768] The user selects or describes their own emotion when entering a question. The terminal provides an option for entering emotions.

[0769] For example, enter emotions such as confusion, anxiety, or tension.

[0770] Step 3: Server receives the problem and sentiment

[0771] The server receives the question text data and emotion data sent from the user terminal.

[0772] Step 4: Abstract the problem

[0773] An AI means on the server analyzes the received problem and generalizes the problem while excluding sensitive information.

[0774] Example: Remove information about specific programming languages ​​and abstract it as a "general method for improving the performance of software systems."

[0775] Step 5: Generate fictional cases

[0776] The server generates fictitious cases based on problems abstracted using AI means.

[0777] For example, a fictitious case study was generated: "What techniques or approaches are effective in a situation where a software system is performing poorly?"

[0778] Step 6: Share your fictional story with the community

[0779] The server shares the generated fictional cases with all users and autonomous AIs in the community.

[0780] Step 7: Community members propose solutions

[0781] Community members can think of solutions to the fictitious cases that are published and post their suggestions from their own devices.

[0782] For example: cache optimization, code refactoring, algorithm improvements, etc.

[0783] Step 8: Autonomous AI proposes a solution

[0784] The autonomous AI also proposes solutions to fictitious cases that are made public based on knowledge it has learned in advance.

[0785] Step 9: Filtering solutions with the emotion engine

[0786] The emotion engine on the server filters the proposed solutions according to the user's emotion. The solution is selected in a tone that matches the user's emotion and is presented in a way that is less stressful for the user.

[0787] Step 10: Solution Summary

[0788] The server summarizes the solutions filtered by the emotion engine, using an AI summarization model to concisely summarize each solution.

[0789] Step 11: Translating the Solution

[0790] The server translates the summarized solutions into multiple languages, using a multilingual translation model to provide appropriate translations for each language.

[0791] Step 12: User selects optimal solution

[0792] The user reviews the list of translated solutions provided by the server and selects the solution that seems most useful.

[0793] Step 13: User Gives Reward

[0794] Users can show their appreciation and reward community members who propose optimal solutions, either in the form of points in the system or real money.

[0795] Through the above processing steps, the "IdeaQuest" system abstracts the user's specific problem, gathers solutions from various perspectives, and provides the solutions according to the user's feelings.

[0796] Example 2

[0797] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0798] Conventional problem-solving systems have been unable to properly recognize users' emotions and provide filtered solutions. This makes it difficult for users to receive suggestions that are appropriate for their emotions, resulting in reduced problem-solving efficiency. Furthermore, the proposed solutions are not multilingual, making it difficult for global users to efficiently utilize the system.

[0799] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes emotion recognition means for analyzing user emotion data, means for analyzing the user emotion using an emotion engine, and means for filtering proposed solutions through the emotion engine. This allows the system to provide solutions suited to the user's emotions, and the system's multilingual support enables users around the world to efficiently use the system.

[0800] A "user" is a person or entity that utilizes the system to enter their problem and receive a solution.

[0801] A "terminal" is a device that provides an interface for users to input questions and communicate their feelings.

[0802] A "server" is a central system that receives data sent from terminals and analyzes and processes it.

[0803] The "means for receiving questions" is a function by which the server receives question data sent from the user's terminal.

[0804] "Problem abstraction" is the process of generalizing the problem received from the user by excluding sensitive information.

[0805] "AI means for converting into fictional cases" is an artificial intelligence technology that reconstructs abstract problems into concrete fictional cases.

[0806] "Emotion recognition means" is a technology that analyzes and recognizes emotions from user input and interactions.

[0807] The "emotion engine" is a system that analyzes user emotions, filters proposed solutions, and analyzes emotional data.

[0808] "Sharing means" is the process of making abstracted problems available to other users and autonomous AIs.

[0809] "Community members" are multiple users who participate in the system and propose solutions.

[0810] "Independent AI" is artificial intelligence that proposes solutions based on its own learning data.

[0811] "Filtering" is the process of sorting proposed solutions in a way that is appropriate to the user's emotions.

[0812] "Means to summarize" is a function that succinctly summarizes the proposed solution.

[0813] "Translation means" is a technique for translating summarized solutions into multiple languages.

[0814] "Selection" is the process by which a user chooses the most beneficial solution from those offered.

[0815] "Rewarding" is a feature that provides rewards to community members who propose the most beneficial solutions.

[0816] A "multilingual translation model" is an artificial intelligence model designed to handle different languages.

[0817] This invention is a system in which a user inputs a problem, analyzes and abstracts the problem, and solicits solutions from a broad community. This system achieves more effective problem solving by combining it with an emotion engine that recognizes the user's emotions and proposes appropriate solutions. A specific embodiment of this system is described below.

[0818] User's device

[0819] The user's device provides an interface for inputting problems and communicating emotions. Users input specific problems they are facing in their hobbies or work through the device. The system also provides a function for reading emotions from the user's input and interactions. This function uses a natural language processing (NLP) engine and a facial recognition system. This input information is sent from the user's device to a server.

[0820] Server Processing

[0821] The server centrally processes the data received from the user's device about the problem and emotions and provides the means to take the next step.

[0822] Problem reception and emotion recognition:

[0823] The server receives the problem data and emotion data sent from the device, which includes emotions analyzed from the user's input and interactions.

[0824] Problem Abstraction:

[0825] The AI ​​means on the server analyzes the received problem data and abstracts the problem by removing sensitive information based on the data from the emotion engine. This converts the user's specific problem into a generalized form such as "a general method for improving the performance of software systems."

[0826] Fictional Case Generation:

[0827] The server generates concrete fictitious examples based on the abstracted content using AI means. The technology used is a generative AI model (e.g., GPT-3, GPT-4, etc.). These examples are created in a general-purpose format that can be applied to many situations.

[0828] Sharing a fictional example:

[0829] The generated fictitious cases are made public via the server to all users and autonomous AIs in the community. After the cases are made public, users and autonomous AIs can propose solutions to new cases.

[0830] Community members and autonomous AI proposals

[0831] Community members propose solutions to fictitious cases that have been published. The autonomous AI also proposes solutions based on its pre-trained knowledge. These proposals are filtered by the emotion engine to match the user's emotions and sent to the server.

[0832] Solution Processing

[0833] Solution Summary:

[0834] The server uses an AI summary model to concisely summarize multiple solutions proposed by community members and autonomous AIs. This summary concisely summarizes the key points of each solution.

[0835] Solution translation:

[0836] The server translates the summarized solution using a multilingual translation model, making the solution easier to understand for users around the world.

[0837] User Choice and Rewards

[0838] Users review a list of solutions with summaries and translations provided by the server, and select the most useful one from the solutions filtered by the emotion engine. Users then apply the selected solution to their own problem. Community members who propose the most useful solution can also be rewarded.

[0839] Specific examples

[0840] Engineer's Concerns

[0841] User problem input and emotion recognition:

[0842] The user (engineer) enters a problem such as "I don't know how to optimize the performance of a project in a specific programming language," and expresses the stress and confusion they feel at the time.

[0843] Server Action:

[0844] The server receives the problem and user sentiment data and uses AI means to convert it into a fictional case study of "general methods for improving the performance of software systems."

[0845] Community Suggestions and Sentiment Filtering:

[0846] Community members and autonomous AI suggest solutions such as cache optimization, code refactoring, and algorithm improvements, and an emotion engine filters them in a tone that reduces user stress.

[0847] Solution summary and translation:

[0848] The proposed solutions are summarized by the server and translated into multiple languages.

[0849] User selection and execution:

[0850] Users choose the best solution and apply it to their own projects, and members who make the best suggestions are rewarded.

[0851] Example prompt: "An engineer is struggling and frustrated with how to optimize the performance of a project in a specific programming language. Please provide some generally applicable advice to solve this problem."

[0852] In this way, the present invention provides a system that can solve individual user problems in a way that takes into consideration emotions while maintaining anonymity, and can obtain suggestions from a variety of perspectives.

[0853] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0854] System program processing flow

[0855] Step 1:

[0856] The user uses the device to input their specific problem. They can also input their emotions or communicate them through emotion recognition. The device's NLP engine and facial recognition system analyze the user's input and interactions to extract emotion data. The input data is in the form of "I don't know how to optimize the performance of a project in a specific programming language," and the output data is the analysis result (e.g., emotion = stress, confusion).

[0857] Step 2:

[0858] The server receives the problem and emotion data sent from the device. The received data includes the user's specific problem and the emotion they felt at the time. The server's program analyzes this data and provides feedback to the emotion engine. The input data is the received user problem and emotion data, and the output data is the analyzed emotion information.

[0859] Step 3:

[0860] The AI ​​means on the server analyzes the received problem data and abstracts the problem while removing sensitive information using the emotion engine data as a reference. Specifically, NLP engines and data mining techniques are used. For example, the problem "I don't know how to optimize the performance of a project in a specific programming language" is abstracted into "general methods for improving the performance of software systems." The input data of this step is specific problem information, and the output data is abstracted problem information.

[0861] Step 4:

[0862] The server uses AI means to generate specific fictitious cases based on abstracted problem data. Generative AI models (e.g., GPT-3, GPT-4) are used for generation. These cases are constructed in a general form that can be applied to many situations. For example, they are reconstructed as "general methods for improving the performance of software systems." The input data is the abstracted problem, and the output data is the generated fictitious case.

[0863] Step 5:

[0864] The server publishes the generated fictitious cases to all users and autonomous AIs in the community. After the cases are published, users and autonomous AIs use them as prompts to propose solutions for new cases. The input data is the generated fictitious case, and the output data is the published case.

[0865] Step 6:

[0866] Community members and autonomous AI propose solutions to fictitious cases. These proposals are filtered by an emotion engine to match the user's emotions and sent to the server. The input data are the solutions for each proposal, and the output data are the solutions filtered by the emotion engine.

[0867] Step 7:

[0868] The server summarizes the proposed solutions concisely using an AI summarization model. This summary concisely extracts the key points of each solution. The summarized solutions are then translated using a multilingual translation model. The input data for this step are the filtered solutions for each proposal, and the output data are the summarized solutions and their translations.

[0869] Step 8:

[0870] The user reviews a list of solutions with summaries and translations provided by the server. The user selects the most useful solution from the solutions filtered by the emotion engine and applies it to solving their own problem. The user can also award a reward to the community member who proposes the most useful solution. The input data is the summarized solution list, and the output data is the selected optimal solution and reward data.

[0871] (Application example 2)

[0872] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0873] Customer service in traditional brick-and-mortar stores has been heavily dependent on the experience and skills of staff, resulting in inconsistent quality of service. It has also been difficult to properly recognize customer emotions and respond accordingly. The objective of this invention is to provide a system that solves these problems, quickly resolves customer problems, and provides emotionally sensitive service.

[0874] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for a user to input a problem; server means for receiving the problem; AI means for abstracting the received problem and converting it into a fictitious case; means for sharing the abstracted problem with the community; means for community members and autonomous AI to propose solutions; means for summarizing the proposed solution; means for translating the proposed solution; means for a user to select a solution and provide a reward; means for inputting a problem from the voice or text of a customer in a physical store and recognizing their emotions; and means for generating suggestions based on the customer's emotions and providing an optimal solution. This makes it possible to solve customer problems quickly and in a manner that takes their emotions into consideration.

[0875] Key Word Definitions

[0876] The "means for users to input problems" refers to a means for providing an interface for users to input problems such as questions or concerns by text or voice.

[0877] The "server means for receiving questions" is a server device for receiving and processing question information sent from a user.

[0878] "AI means for abstracting received problems and converting them into fictional cases" refers to artificial intelligence means for analyzing received problems, excluding specific information, and reconstructing them in a generalized form as fictional cases.

[0879] A "means for sharing abstract problems with the community" is a means for publishing abstract problems to an online community so that they can be widely viewed and suggested.

[0880] "Means for community members and autonomous AI to propose solutions" means means that enable community members and autonomous AI to propose solutions to specified problems.

[0881] A "means for summarizing proposed solutions" is a means for concisely summarizing multiple solutions provided and extracting their main points.

[0882] A "means for translating the proposed solution" is a means for translating the summarized solution into other languages.

[0883] The "means for users to select a solution and to give a reward" refers to a means by which a user can select the most suitable solution from among the solutions provided and send a reward to the proposer of the solution.

[0884] "Means for inputting problems and recognizing emotions from voices and texts of customers in physical stores" refers to a means for analyzing the voices uttered by customers and the texts they input in physical stores and identifying their emotions from them.

[0885] The "means for generating proposals based on customer emotions and providing optimal solutions" is a means for taking into account the recognized emotions of a customer and generating and providing a solution that is appropriate for the customer.

[0886] An embodiment of the present invention will be described in detail below. This embodiment is a system for quickly resolving customer problems and responding in an emotionally sensitive manner in order to improve the quality of customer service in brick-and-mortar stores.

[0887] User's device

[0888] The user device is a device such as a smartphone or tablet. The user can use this device to input customer problems or questions by voice or text. The device converts speech to text using speech recognition software (such as the Google Speech Recognition API). It also includes an emotion recognition engine (such as the Hugging Face Transformers library) to recognize emotions from the customer's facial expressions and tone of voice.

[0889] Server Processing

[0890] The server receives the questions and emotion data sent from the user's terminal and performs the following processing.

[0891] 1. Problem Abstraction:

[0892] The server analyzes the received data using AI (such as TextBlob or a custom natural language processing model) and abstracts it into a generalized problem, excluding specific information.

[0893] 2. Generating fictitious cases:

[0894] Generate concrete fictitious cases based on abstract problems and share them with the community.

[0895] 3. Share with the community:

[0896] We provide an environment where community members (other store staff, related parties, etc.) and autonomous AI can propose solutions to this fictional case.

[0897] 4. Summary and translation of the proposed solution:

[0898] The proposed solution is summarized using an AI summarization model (such as Hugging Face's Transformers library) and translated using a multilingual translation model (such as Helsinki-NLP's opus-mt-en-jp).

[0899] Specific processing flow example

[0900] The following example shows a specific processing flow.

[0901] Example 1: "Product not found"

[0902] The user voice-inputs the customer's problem into their smartphone, saying, "I can't find the product."

[0903] The server converts the voice into text and uses an emotion recognition engine to recognize the customer's "confusion" emotion.

[0904] AI abstracts the problem into "optimizing product information" and generates solutions such as "providing product layout diagrams" and "direct guidance by staff."

[0905] The solutions are summarized and translated into other languages ​​(e.g., English) using a multilingual translation model.

[0906] Example prompt sentence:

[0907] "A customer has expressed difficulty finding a particular product. They seem confused. How should I respond?"

[0908] As shown in this specific example, the present invention is a system that can solve customer problems quickly and in an emotionally sensitive manner, thereby significantly improving customer satisfaction in physical stores.

[0909] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0910] Program processing flow

[0911] Step 1:

[0912] Users input their customer's problem by voice or text using a smartphone or tablet, and the input voice data is converted into text using voice recognition software.

[0913] Input: Customer voice or text input

[0914] How it works: Uses speech recognition software (Google Speech Recognition API) to convert speech to text.

[0915] Output: Text data

[0916] Step 2:

[0917] The user's device sends the converted text data to the server, which also uses an emotion recognition engine to analyze the customer's emotions and sends the results to the server.

[0918] Input: Text data and customer sentiment data obtained in Step 1

[0919] How it works: Analyzes emotions using an emotion recognition engine (Hugging Face's Transformers library). Sends the data to the server.

[0920] Output: Text data and emotion data

[0921] Step 3:

[0922] The server receives the question text data and emotion data from the user's terminal and stores them.

[0923] Input: Text data and emotion data sent in Step 2

[0924] Action: Save to database.

[0925] Output: Saved text data and emotion data

[0926] Step 4:

[0927] The server analyzes the stored problem data using a natural language processing model (such as TextBlob), removes specific information, and abstracts it into a generalized problem.

[0928] Input: Saved text data

[0929] How it works: Analyzes data using a natural language processing model, filtering out and abstracting specific information.

[0930] Output: Abstracted problem data

[0931] Step 5:

[0932] Based on the abstracted problem, the server uses AI means to generate concrete fictitious cases and shares them with community members and autonomous AI.

[0933] Input: Abstracted problem data

[0934] How it works: Generate fictional cases using AI tools. Share the fictional cases with the community.

[0935] Output: fictional example

[0936] Step 6:

[0937] Solutions proposed by community members and autonomous AIs are collected on a server using an online platform.

[0938] Input: Solutions from community members and autonomous AI

[0939] How it works: Collect suggestions through an online platform.

[0940] Output: Collected solutions

[0941] Step 7:

[0942] The collected solutions are summarized on the server using a summarization model (from the Transformers library in Hugging Face).

[0943] Input: Collected solutions

[0944] What it does: Summarize the solution using a summary model.

[0945] Output: Summarized solution

[0946] Step 8:

[0947] The summarized solution is translated using a multilingual translation model, using the opus-mt-en-jp model from Helsinki-NLP.

[0948] Input: Abridged solution

[0949] What it does: Translates the solution using a translation model.

[0950] Output: Translated solution

[0951] Step 9:

[0952] The server provides the translated solutions to the user, who then selects the best solution. Furthermore, the server rewards the proposer who provides the best solution based on the evaluation.

[0953] Input: translated solution

[0954] Behavior: Show the translated solution to the user. Reward the user based on their choice and rating.

[0955] Output: Selected solution and evaluation results

[0956] In this way, a system is created that can quickly resolve customer problems in brick-and-mortar stores and respond in an emotionally sensitive manner.

[0957] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0958] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0959] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0960] [Third embodiment]

[0961] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0962] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0963] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0964] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0965] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0966] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0967] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0968] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0969] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0970] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0971] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0972] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0973] The embodiment of the present invention is a system in which a user inputs a problem and solicits solutions from a wide range of sources. This system is composed of a terminal, a server, and an AI means. The specific roles and processing flow of each element are explained below.

[0974] User's device

[0975] The user's terminal provides an interface for inputting problems. The user inputs specific problems they are facing in their hobbies or work in text format through the terminal. The input problem is sent from the user's terminal to the server.

[0976] Server Processing

[0977] The server centrally processes the problems received from the user's terminal and provides the means to proceed to the next step.

[0978] 1. Receiving the problem:

[0979] The server receives the question sent from the terminal.

[0980] 2. Problem Abstraction:

[0981] The received problem is analyzed by AI means on the server and abstracted to eliminate sensitive information. This abstracted problem is then reconstructed as a fictional case that hides the real problem.

[0982] 3. Generating fictitious cases:

[0983] The server uses AI tools to generate fictitious cases based on abstracted problems, which are constructed as generalized and widely applicable problems.

[0984] 4. Sharing fictional stories:

[0985] The generated fictional cases are shared with the community via the server, which consists of other users and autonomous AIs participating in the system.

[0986] Community members and autonomous AI proposals

[0987] Community members can propose solutions to published fictitious cases. The autonomous AI can also propose solutions based on its prior knowledge. These proposals are sent to the server for further processing.

[0988] Solution Processing

[0989] 1. Solution Summary:

[0990] The server uses AI summarization to concisely summarize the proposed solutions, providing a clear overview of each solution.

[0991] 2. Solution Translation:

[0992] The server translates the summarized solution using a multilingual translation means, making it easier for users around the world to understand the solution.

[0993] User Choice and Rewards

[0994] Users can review a list of solutions provided by the server, complete with summaries and translations, and select the most suitable solution. Based on this selection, they can obtain specific measures to adapt to their own problems. Furthermore, users can reward community members who propose the most useful solutions.

[0995] Specific examples

[0996] Example 1: Engineer's Concerns

[0997] 1. User problem input:

[0998] A user (engineer) enters a problem: "I don't know how to optimize the performance of a project in a specific programming language."

[0999] 2. Server processing:

[1000] The server receives this problem and uses AI means to convert it into a fictional case study titled "General methods for improving the performance of software systems."

[1001] 3. Community Suggestions:

[1002] Community members and autonomous AI propose solutions such as cache optimization, code refactoring, and algorithm improvements.

[1003] 4. Solution summary and translation:

[1004] The proposed solutions are summarized by the server and translated into multiple languages.

[1005] 5. User Choice and Action:

[1006] Users can choose the best solution and apply it to their own projects, and members who make the best suggestions are rewarded.

[1007] Example 2: Gardening problems

[1008] 1. User problem input:

[1009] The user (gardener) inputs the problem, "I don't know the cause of a certain plant dying and what to do about it."

[1010] 2. Server processing:

[1011] The server receives this problem and uses AI tools to convert it into a fictional case study called "General methods for plant health management."

[1012] 3. Community Suggestions:

[1013] Community members and autonomous AI will suggest solutions such as soil improvement, watering timing, and proper sunlight.

[1014] 4. Solution summary and translation:

[1015] The proposed solutions are summarized by the server and translated into multiple languages.

[1016] 5. User Choice and Action:

[1017] Users can choose the best solution and apply it to their own gardening activities, and members who make the best suggestions will be rewarded.

[1018] With this configuration, the present invention provides a system that can solve a user's problem from various perspectives while maintaining anonymity.

[1019] The processing flow will be explained below.

[1020] Step 1: User enters problem

[1021] Users log in to the IdeaQuest app from their device and enter the specific problem they are facing into a text box.

[1022] For example: "I don't know how to optimize the performance of my project in a specific programming language."

[1023] Step 2: The server receives the problem

[1024] The server receives the problem data sent from the terminal, including the specific problem text entered by the user.

[1025] Step 3: Abstract the problem using AI tools

[1026] An AI tool on the server analyzes the received problem and converts it into a fictitious case so as not to extract sensitive information.

[1027] Example: Remove information about specific programming languages ​​and abstract it as "a general method for improving the performance of software systems."

[1028] Step 4: Generate fictitious cases

[1029] The server generates specific fictitious cases based on the content abstracted by the AI.

[1030] For example, a hypothetical case study generated might be: "What techniques or approaches are effective in a situation where a software system is performing poorly?"

[1031] Step 5: Share your fictional story with the community

[1032] The server makes the generated fictitious cases public to all users and autonomous AIs in the community.

[1033] Step 6: Community members propose solutions

[1034] Community members come up with solutions to the fictitious cases that are published and post their solutions from their own devices.

[1035] For example: cache optimization, code refactoring, algorithm improvements, etc.

[1036] Step 7: Autonomous AI proposes a solution

[1037] The autonomous AI also analyzes fictitious cases provided to it and generates and proposes solutions based on its prior knowledge.

[1038] Step 8: The server summarizes the solution

[1039] The server uses an AI summary model to summarize multiple solutions proposed by community members and autonomous AIs, concisely summarizing the key points of each solution.

[1040] Step 9: Server translates the solution

[1041] The server translates the summarized solution using a multilingual translation model, allowing users around the world to understand the solution across language barriers.

[1042] Step 10: User selects optimal solution

[1043] The user reviews a list of solutions provided by the server, complete with summaries and translations, and selects the solution that seems most useful.

[1044] Step 11: User Gives Reward

[1045] Users can show their appreciation by rewarding community members who propose optimal solutions, either in the form of points in the system or actual rewards.

[1046] Through the above processing steps, the "IdeaQuest" system abstracts the user's specific problem, gathers solutions from a variety of perspectives, and presents them in an easy-to-understand format.

[1047] Example 1

[1048] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1049] Conventional problem-solving systems have difficulty providing direct solutions to problems entered by users, and sharing problems while maintaining user privacy. Furthermore, their proposed solutions lack multilingual support, making it difficult for users of different languages ​​to communicate with each other. To solve these problems, a system is needed that protects privacy by anonymizing and abstracting users' problems, and that also allows for multilingual solution proposals.

[1050] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1051] In this invention, the server includes means for a user to input a problem, means for receiving a problem, artificial intelligence means for abstracting the received problem and converting it into a fictitious case, means for generating a fictitious case based on the abstracted problem, means for publishing the generated fictitious case to the community, means for community members and the autonomous artificial intelligence to propose solutions, means for summarizing the proposed solutions, means for translating the proposed solutions, means for a user to select a solution, and means for providing a reward. This makes it possible to share problems while maintaining user privacy, and makes it easier for users of different languages ​​to obtain solutions.

[1052] "User" means a person or entity that uses the System to enter a problem and request a solution.

[1053] "Input means" refers to an interface or device that allows a user to input and submit a question in text format.

[1054] "Server" refers to a central management system that receives and processes problems submitted by users.

[1055] "Means for receiving" refers to a function that allows the server to receive questions sent by users in real time.

[1056] "Abstraction" refers to the process of removing sensitive information from an incoming problem and reconstructing it into a generalized problem.

[1057] "Artificial intelligence tools" refers to machine learning models and algorithms used to analyze problems, abstract, and generate fictitious cases.

[1058] "Fictional cases" refer to general and broadly applicable problems that are generated based on abstract problems.

[1059] "Community" refers to a group of other users and autonomous artificial intelligences participating in the system.

[1060] "Means for sharing" refers to a method for communicating the generated fictional cases to community members and autonomous artificial intelligence.

[1061] "Community Members" refers to other users who use the system to propose solutions.

[1062] "Autonomous artificial intelligence" refers to an AI system that uses pre-trained models to generate solutions independently.

[1063] "Solution" refers to a specific method of dealing with a hypothetical case.

[1064] "Means for Proposing" refers to the methods by which community members and autonomous artificial intelligences submit solutions to the server.

[1065] "Means for summarizing" refers to a function for concisely summarizing multiple proposed solutions.

[1066] "Means for translation" refers to the functionality for translating the summarized solution into multiple languages.

[1067] "Means of selection" refers to the interface and functionality that allows users to choose the optimal solution.

[1068] "Reward mechanisms" refers to a feature that provides rewards to community members who propose good solutions.

[1069] The system mainly consists of a user terminal, a server, and an artificial intelligence means. The user inputs the problem using the terminal, and the system then executes the process of proposing a solution.

[1070] User's device

[1071] The user's device refers to an input device such as a general personal computer or smartphone. The user inputs a problem in the form of text input through the device's interface. For example, the user inputs a problem such as "I don't know how to optimize the performance of a project in a specific programming language." After inputting the problem, the device sends it to the server. This transmission requires an internet connection.

[1072] Server Processing

[1073] The server receives the questions sent from the user's terminal and performs the following process to proceed to the next step.

[1074] 1. Receiving the Problem

[1075] The server receives the user's problem via a REST API and temporarily stores it in a database, ensuring that the problem content is preserved.

[1076] 2. Problem Abstraction

[1077] The server analyzes the received problem using artificial intelligence means (e.g., a machine learning model). Specifically, it uses a generative AI model and invokes the AI ​​with the prompt, "Abstract the input problem and reconstruct it into a general problem." The problem is then converted into a generalized problem that does not contain sensitive information.

[1078] 3. Generating fictional cases

[1079] The server uses a generative AI model to generate fictitious cases based on the abstract problem. The prompt is "Generate specific fictitious cases based on the abstract problem." For example, the server generates a generalized problem called "improving the performance of a software system" as "a method for improving the performance of a large-scale data processing system."

[1080] 4. Sharing fictional stories

[1081] The generated fictional cases are shared with the community via a server, using messaging protocols and SNS APIs.

[1082] Community members and autonomous AI proposals

[1083] Community members (other users) and the autonomous AI propose solutions based on fictitious cases shared by the server. Community members input solutions from their own devices and send them to the server. The autonomous AI generates solutions using a pre-trained model and sends them to the server.

[1084] Solution Processing

[1085] 1. Solution Summary

[1086] The server uses a generative AI model to summarize the proposed solutions. It invokes the AI ​​with the prompt "Please briefly summarize these solutions" to generate a concise solution.

[1087] 2. Translation of the solution

[1088] The summarized solution is translated using a multilingual translation means. The server uses the prompt sentence "Please translate from English to Japanese" and runs a machine translation model.

[1089] User Choice and Rewards

[1090] Users can view a list of solutions with abridged translations on their device, choose the best solution, and adopt it to solve their problem. Community members who propose particularly good solutions can be rewarded using a points system or virtual currency.

[1091] Examples of specific examples and prompts

[1092] As a concrete example, suppose a user inputs a problem such as "I don't know the cause of a particular plant dying and what to do about it." This problem is sent to the server, which uses artificial intelligence to abstract it into the form of "general methods for plant health management." Then, a generative AI model is used to generate fictitious examples such as "improving the soil, watering at the right time, and providing adequate sunlight." After the problem is shared, community members and autonomous AI propose solutions, which the server then summarizes and translates.

[1093] Examples of prompts include:

[1094] "Abstract the input problem and reconstruct it into a general problem."

[1095] "Generate concrete, fictional cases based on abstract problems."

[1096] Please briefly summarize these multiple solutions.

[1097] Please translate from English to Japanese.

[1098] Thus, the present invention provides a system for efficient, multilingual management and resolution of user problems while preserving their anonymity.

[1099] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1100] The flow of this system's program processing

[1101] Step 1: User Problem Input

[1102] The user enters the problem on their device. Specifically, the user writes the problem in text format in the input form on the device and presses the submit button. For example, the user might enter, "I don't know how to optimize the performance of a project in a specific programming language."

[1103] Input: Problem text

[1104] Output: The problem request sent to the server

[1105] Step 2: The server receives the problem

[1106] The server receives the problem sent by the user using the REST API and saves the problem in the database. This is to temporarily store the problem content and ensure subsequent processing.

[1107] Input: User submitted text question

[1108] Output: Saved problem data

[1109] Step 3: Abstract the problem

[1110] The server analyzes and abstracts the received problem using artificial intelligence. It passes the prompt "Abstract the input problem and reconstruct it into a general problem" to the generative AI model. The AI ​​analyzes the problem, removes sensitive information, and generalizes it.

[1111] Input: Saved problem data

[1112] Output: Abstracted problem

[1113] Step 4: Generate fictional cases

[1114] The server uses a generative AI model to generate a fictitious case based on the abstracted problem. The prompt is "Generate a concrete fictitious case based on the abstracted problem." For example, it could be described as "How to improve the performance of a software system."

[1115] Input: Abstracted problem

[1116] Output: fictitious example

[1117] Step 5: Share a fictional example

[1118] The server shares the generated fictional cases with the community. The server uses messaging protocols and SNS APIs to send the cases to community members and autonomous AI.

[1119] Input: fictional case

[1120] Output: Share the case study with the community

[1121] Step 6: Community members and autonomous AI proposals

[1122] Community members and the autonomous AI propose solutions based on shared fictional cases. Members input and submit solutions on their own devices, and the autonomous AI generates solutions using a pre-trained model. The server receives the proposed solutions.

[1123] Input: Solution proposals from community members and autonomous AI

[1124] Output: Proposal data stored on the server

[1125] Step 7: Solution Summary

[1126] The server summarizes the proposed solutions using a generative AI model. The AI ​​is invoked with the prompt "Please briefly summarize these solutions" to generate a concise summary.

[1127] Input: Proposal data

[1128] Output: Summarized solution

[1129] Step 8: Translating the solution

[1130] The server translates the summarized solution using a multilingual translation means. The server uses the prompt "Please translate from English to Japanese" and executes a machine translation service.

[1131] Input: Abridged solution

[1132] Output: Translated solution

[1133] Step 9: User Choice and Reward

[1134] The user reviews the translated list of solutions on their device, selects the best solution, and rewards the proposer of the selected solution using a points system or virtual currency.

[1135] Input: translated solution list, user selection

[1136] Output: Selected solution, reward given

[1137] This allows users to solve problems while maintaining their privacy, and creates a system that can be used by users of different languages.

[1138] (Application example 1)

[1139] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1140] In modern factories, it is important to find a quick and accurate solution when an abnormality or problem occurs. However, many current solution methods require human effort and time, and are inefficient. In addition, it is difficult to identify and abstract the problem, making it difficult for workers without specialized knowledge to deal with it. In such situations, there is a risk of reduced productivity and increased costs.

[1141] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1142] In this invention, the server includes: a means for a user to input a problem; a server means for receiving the problem; an AI means for abstracting the received problem and converting it into a fictitious case; a means for sharing the abstracted problem with the community; a means for community members and the autonomous AI to propose solutions; a means for summarizing the proposed solutions; a means for a user to select a solution and a means for providing a reward; a means for a factory robot to detect anomalies; a means including a sensor and a camera for describing anomalies in text format; and a means for automatically collecting and processing the proposed solutions. This enables rapid detection of anomalies in factories and the proposal and selection of solutions.

[1143] The "means for the user to input a question" refers to a device or software that provides an interface for the user to input a specific question in text format.

[1144] The "server means for receiving questions" is a central server for receiving and managing questions sent by users.

[1145] "AI means for abstracting received problems and converting them into fictional cases" refers to an artificial intelligence algorithm for generalizing received specific problems and removing sensitive information.

[1146] "Means for sharing abstracted problems with the community" refers to the means by which abstracted problems can be sent to other users and AI models in the system to broadly solicit solutions.

[1147] "Means for community members and autonomous AIs to propose solutions" refers to the means by which other users participating in the system and autonomous AIs with previously learned knowledge can make proposals.

[1148] A "means for summarizing proposed solutions" is a summarization algorithm for concisely summarizing multiple proposed solutions.

[1149] A "means for translating the proposed solution" is a translation algorithm or API that translates the summarized solution into other languages ​​so that it can be understood by multilingual users.

[1150] The "means for users to select solutions and provide rewards" is a mechanism by which users can select the best solution from the proposed solutions and provide a reward to the person who proposed it.

[1151] "Means for factory robots to detect abnormalities" refers to devices such as sensors and cameras used to detect abnormalities within the factory.

[1152] "Means including a sensor and a camera for describing anomalies in text form" refers to a device for describing information on detected anomalies in text form and software that supports it.

[1153] "Means for automatically collecting and processing proposed solutions" means a system for automatically collecting, analyzing, and processing proposed solutions from the community.

[1154] Specifically, an embodiment of the present invention is realized as a system that detects anomalies using factory robots and widely solicits solutions to the anomalies. The system includes: means for a user to input a problem; a server means for receiving the problem; an AI means for abstracting the received problem and converting it into a fictitious case; means for sharing the abstracted problem with a community; means for community members and autonomous AIs to propose solutions; means for summarizing the proposed solutions; means for a user to select a solution and provide a reward; means for a factory robot to detect anomalies; means including a sensor and a camera for describing the anomaly in text form; and means for automatically collecting and processing the proposed solutions.

[1155] First, we will explain how factory robots detect abnormalities. Factory robots are equipped with hardware such as temperature sensors, pressure sensors, and cameras, which detect abnormalities. For example, if a conveyor belt stops during transportation, the cameras and sensors detect the abnormality and record the information in text format. This text data is sent to a server.

[1156] The server then abstracts the received text data. Specifically, it uses a Transformer-based AI model such as BERT to generalize the specific content of the anomaly and remove sensitive information. The abstracted problem is reconstructed as a fictitious example that hides the real problem. This allows it to be shared as useful information for other users with similar problems.

[1157] The abstracted problems are then shared with the community through a web application. Users can submit solutions using their own PCs or smartphones. The proposed solutions are collected on a server, where they are summarized and translated. The translation is done using the Google Translate API, and the summarization is done using generative AI models such as GPT-3. This allows the proposed solutions to be understood in other languages.

[1158] Finally, users select the best solution from the list and apply it to their own system. Community members who make excellent suggestions are rewarded. This process quickly detects abnormalities in factories and effectively derives solutions.

[1159] Specific examples

[1160] For example, consider the case where a conveyor belt in a factory suddenly stops. The factory robot's cameras and sensors detect the abnormality and input the problem into the system in text format. This problem is described as "the conveyor belt stops." The server receives this problem and abstracts it into a "general conveyor system stoppage problem." After it is shared with the community, other users and AI can make suggestions such as "motor failure" or "abnormal belt stretch." These suggestions are summarized and translated into multiple languages ​​and provided to users.

[1161] Prompt Sentence Examples

[1162] User: "The conveyor belt in our factory suddenly stopped. I don't know what caused it or what to do about it."

[1163] System: "Abstracting the problem..."

[1164] AI model: "What are some common problems that cause conveyor belts to stop?"

[1165] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1166] Now, the processing flow of the program of the system that realizes the application example will be explained in detail, broken down into steps.

[1167] Step 1:

[1168] Factory robots detect abnormalities. Sensors (temperature sensors, pressure sensors, etc.) and cameras installed on the factory robots are activated to detect abnormalities. For example, abnormal events such as a stopped conveyor belt, a motor failure, or an abnormal rise in temperature are detected. This abnormality detection data is obtained as numerical data or image data.

[1169] Step 2:

[1170] Anomaly detection data is converted into text format. A terminal inside the robot receives data from the sensors and cameras and describes the anomaly in text format. For example, abnormal temperature data obtained from a temperature sensor is converted into text such as "The temperature has exceeded the set value." This generates specific information about the anomaly as text data.

[1171] Step 3:

[1172] The server receives the text data. The central server receives the text data sent from the factory robot. The input is text data, and the received text data becomes the input for the next step.

[1173] Step 4:

[1174] The received problem is abstracted and converted into a fictitious case. The received text data is abstracted using AI means (e.g., the BERT model) installed on a central server. This process converts concrete information into a general problem. The input is the received text data, and the output is an abstracted problem such as "a general problem of a conveyor belt stopping." This data conversion generalizes the data to make it easier to find a solution while hiding specific anomaly information.

[1175] Step 5:

[1176] The abstracted problem is shared with the community. The server publishes the abstracted problem to the community through a web front end (for example, an application using React). The input is the abstracted problem, and the output is information shared with all members of the community. This sharing process makes it possible to solicit solution proposals from a wide range of users.

[1177] Step 6:

[1178] Community members and autonomous AI propose solutions. Other users participating in the community and autonomous AI models propose solutions to abstracted problems. The input is the abstracted problem, and the output is multiple proposed solutions. This behavior is achieved by users directly entering the solution on the web application, or by the AI ​​automatically generating the solution.

[1179] Step 7:

[1180] Summarize proposed solutions and translate them into multiple languages. Multiple proposed solutions are concisely summarized on the server using an AI summarization tool (e.g., GPT-3). Furthermore, the solutions are translated into other languages ​​using a multilingual translation tool such as the Google Translate API. The input is the proposed solution, and the output is the summarized and translated solution. This makes the solution easily understandable to users around the world.

[1181] Step 8:

[1182] The user selects the best solution and is rewarded. The user reviews the summarized and translated solution list provided by the server and selects the best solution. After selection, the community member who made the best proposal is rewarded. The input is the summarized and translated solution list, and the output is the selected solution and reward information. This operation allows the user to obtain a concrete means to solve the problem, and provides appropriate incentives to the contributing members.

[1183] In this way, the entire system works together to efficiently support anomaly detection and problem resolution within the factory.

[1184] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1185] The embodiment of the present invention is a system in which a user inputs a problem and solicits solutions from a wide range of people, and is combined with an emotion engine that recognizes the user's emotions. This system is composed of a terminal, a server, an AI means, and an emotion engine, and the specific roles and processing flow of each element are explained below.

[1186] User's device

[1187] The user's device provides an interface for inputting problems and communicating emotions. The user inputs specific problems they are facing in their hobbies or work through the device. The system also provides a function for reading emotions from the user's input and interactions. This input information is sent from the user's device to the server.

[1188] Server Processing

[1189] The server centrally processes the data received from the user's device about the problem and emotions and provides the means to take the next step.

[1190] 1. Receiving the problem and recognizing emotions:

[1191] The server receives the problem data and emotion data sent from the device, which includes emotions analyzed from the user's input and interactions.

[1192] 2. Problem Abstraction:

[1193] The received problem is analyzed by AI means on the server, and abstracted without sensitive information, referring to the data from the emotion engine. This abstracted problem is reconstructed as a fictional case that hides the real problem.

[1194] 3. Generating fictitious cases:

[1195] The server uses AI tools to generate concrete fictional cases based on abstractions, which are constructed as generalized and widely applicable problems.

[1196] 4. Sharing fictional stories:

[1197] The generated fictitious cases are made public to all users and autonomous AIs in the community via the server.

[1198] Community members and autonomous AI proposals

[1199] Community members can propose solutions to published fictitious cases. The autonomous AI can also propose solutions based on its pre-trained knowledge. These proposals are filtered by the emotion engine to match the user's emotions and sent to the server.

[1200] Solution Processing

[1201] 1. Solution Summary:

[1202] The server uses an AI summary model to concisely summarize multiple solutions proposed by community members and autonomous AIs. This summary concisely summarizes the key points of each solution.

[1203] 2. Solution Translation:

[1204] The server translates the summarized solution using a multilingual translation model, making the solution easier to understand for users around the world.

[1205] User Choice and Rewards

[1206] Users can review a list of solutions with summaries and translations provided by the server, and select the most useful one from the solutions filtered by the emotion engine. Based on this selection, they can obtain specific measures to apply to their own problem. Furthermore, users can reward community members who propose the most useful solutions.

[1207] Specific examples

[1208] Example 1: Engineer's Concerns

[1209] 1. User problem input and emotion recognition:

[1210] The user (engineer) enters a problem such as "I don't know how to optimize the performance of a project in a specific programming language," and expresses the stress and confusion they feel at the time.

[1211] 2. Server processing:

[1212] The server receives the problem and user sentiment data and uses AI means to convert it into a fictional case study of "general methods for improving the performance of software systems."

[1213] 3. Community Suggestions and Sentiment Filtering:

[1214] Community members and autonomous AI suggest solutions such as cache optimization, code refactoring, and algorithm improvements, and an emotion engine filters them in a tone that reduces user stress.

[1215] 4. Solution summary and translation:

[1216] The proposed solutions are summarized by the server and translated into multiple languages.

[1217] 5. User Choice and Action:

[1218] Users can choose the best solution and apply it to their own projects, and members who make the best suggestions are rewarded.

[1219] Example 2: Gardening problems

[1220] 1. User problem input and emotion recognition:

[1221] The user (gardener) inputs the problem, "I don't know why a certain plant is dying and what to do about it," and expresses the sadness and concern he or she feels at the time.

[1222] 2. Server processing:

[1223] The server receives the problem and the user's emotional data and converts it into a fictional case study called "General methods for plant health management" using AI means.

[1224] 3. Community Suggestions and Sentiment Filtering:

[1225] Community members and autonomous AI suggest solutions such as soil improvement, watering times, and proper sunlight, and an emotion engine filters them with a tone that alleviates the user's concerns.

[1226] 4. Solution summary and translation:

[1227] The proposed solutions are summarized by the server and translated into multiple languages.

[1228] 5. User Choice and Action:

[1229] Users can choose the best solution and apply it to their own gardening activities, and members who make the best suggestions will be rewarded.

[1230] With this configuration, the present invention provides a system that can solve a user's problem in a way that takes into consideration their emotions while maintaining anonymity, and can obtain suggestions from a variety of perspectives.

[1231] The processing flow will be explained below.

[1232] Step 1: User enters problem

[1233] Users log in to the "IdeaQuest" app using their own devices and enter specific problems in text format.

[1234] For example: "I don't know how to optimize the performance of my project in a specific programming language."

[1235] Step 2: Enter user emotions

[1236] The user selects or describes their own emotion when entering a question. The terminal provides an option for entering emotions.

[1237] For example, enter emotions such as confusion, anxiety, or tension.

[1238] Step 3: Server receives the problem and sentiment

[1239] The server receives the question text data and emotion data sent from the user terminal.

[1240] Step 4: Abstract the problem

[1241] An AI means on the server analyzes the received problem and generalizes the problem while excluding sensitive information.

[1242] Example: Remove information about specific programming languages ​​and abstract it as a "general method for improving the performance of software systems."

[1243] Step 5: Generate fictional cases

[1244] The server generates fictitious cases based on problems abstracted using AI means.

[1245] For example, a fictitious case study was generated: "What techniques or approaches are effective in a situation where a software system is performing poorly?"

[1246] Step 6: Share your fictional story with the community

[1247] The server shares the generated fictional cases with all users and autonomous AIs in the community.

[1248] Step 7: Community members propose solutions

[1249] Community members can think of solutions to the fictitious cases that are published and post their suggestions from their own devices.

[1250] For example: cache optimization, code refactoring, algorithm improvements, etc.

[1251] Step 8: Autonomous AI proposes a solution

[1252] The autonomous AI also proposes solutions to fictitious cases that are made public based on knowledge it has learned in advance.

[1253] Step 9: Filtering solutions with the emotion engine

[1254] The emotion engine on the server filters the proposed solutions according to the user's emotion. The solution is selected in a tone that matches the user's emotion and is presented in a way that is less stressful for the user.

[1255] Step 10: Solution Summary

[1256] The server summarizes the solutions filtered by the emotion engine, using an AI summarization model to concisely summarize each solution.

[1257] Step 11: Translating the Solution

[1258] The server translates the summarized solutions into multiple languages, using a multilingual translation model to provide appropriate translations for each language.

[1259] Step 12: User selects optimal solution

[1260] The user reviews the list of translated solutions provided by the server and selects the solution that seems most useful.

[1261] Step 13: User Gives Reward

[1262] Users can show their appreciation and reward community members who propose optimal solutions, either in the form of points in the system or real money.

[1263] Through the above processing steps, the "IdeaQuest" system abstracts the user's specific problem, gathers solutions from various perspectives, and provides the solutions according to the user's feelings.

[1264] Example 2

[1265] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1266] Conventional problem-solving systems have been unable to properly recognize users' emotions and provide filtered solutions. This makes it difficult for users to receive suggestions that are appropriate for their emotions, resulting in reduced problem-solving efficiency. Furthermore, the proposed solutions are not multilingual, making it difficult for global users to efficiently utilize the system.

[1267] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes emotion recognition means for analyzing user emotion data, means for analyzing the user emotion using an emotion engine, and means for filtering proposed solutions through the emotion engine. This allows the system to provide solutions suited to the user's emotions, and the system's multilingual support enables users around the world to efficiently use the system.

[1268] A "user" is a person or entity that utilizes the system to enter their problem and receive a solution.

[1269] A "terminal" is a device that provides an interface for users to input questions and communicate their feelings.

[1270] A "server" is a central system that receives data sent from terminals and analyzes and processes it.

[1271] The "means for receiving questions" is a function by which the server receives question data sent from the user's terminal.

[1272] "Problem abstraction" is the process of generalizing the problem received from the user by excluding sensitive information.

[1273] "AI means for converting into fictional cases" is an artificial intelligence technology that reconstructs abstract problems into concrete fictional cases.

[1274] "Emotion recognition means" is a technology that analyzes and recognizes emotions from user input and interactions.

[1275] The "emotion engine" is a system that analyzes user emotions, filters proposed solutions, and analyzes emotional data.

[1276] "Sharing means" is the process of making abstracted problems available to other users and autonomous AIs.

[1277] "Community members" are multiple users who participate in the system and propose solutions.

[1278] "Independent AI" is artificial intelligence that proposes solutions based on its own learning data.

[1279] "Filtering" is the process of sorting proposed solutions in a way that is appropriate to the user's emotions.

[1280] "Means to summarize" is a function that succinctly summarizes the proposed solution.

[1281] "Translation means" is a technique for translating summarized solutions into multiple languages.

[1282] "Selection" is the process by which a user chooses the most beneficial solution from those offered.

[1283] "Rewarding" is a feature that provides rewards to community members who propose the most beneficial solutions.

[1284] A "multilingual translation model" is an artificial intelligence model designed to handle different languages.

[1285] This invention is a system in which a user inputs a problem, analyzes and abstracts the problem, and solicits solutions from a broad community. This system achieves more effective problem solving by combining it with an emotion engine that recognizes the user's emotions and proposes appropriate solutions. A specific embodiment of this system is described below.

[1286] User's device

[1287] The user's device provides an interface for inputting problems and communicating emotions. Users input specific problems they are facing in their hobbies or work through the device. The system also provides a function for reading emotions from the user's input and interactions. This function uses a natural language processing (NLP) engine and a facial recognition system. This input information is sent from the user's device to a server.

[1288] Server Processing

[1289] The server centrally processes the data received from the user's device about the problem and emotions and provides the means to take the next step.

[1290] Problem reception and emotion recognition:

[1291] The server receives the problem data and emotion data sent from the device, which includes emotions analyzed from the user's input and interactions.

[1292] Problem Abstraction:

[1293] The AI ​​means on the server analyzes the received problem data and abstracts the problem by removing sensitive information based on the data from the emotion engine. This converts the user's specific problem into a generalized form such as "a general method for improving the performance of software systems."

[1294] Fictional Case Generation:

[1295] The server generates concrete fictitious examples based on the abstracted content using AI means. The technology used is a generative AI model (e.g., GPT-3, GPT-4, etc.). These examples are created in a general-purpose format that can be applied to many situations.

[1296] Sharing a fictional example:

[1297] The generated fictitious cases are made public via the server to all users and autonomous AIs in the community. After the cases are made public, users and autonomous AIs can propose solutions to new cases.

[1298] Community members and autonomous AI proposals

[1299] Community members propose solutions to fictitious cases that have been published. The autonomous AI also proposes solutions based on its pre-trained knowledge. These proposals are filtered by the emotion engine to match the user's emotions and sent to the server.

[1300] Solution Processing

[1301] Solution Summary:

[1302] The server uses an AI summary model to concisely summarize multiple solutions proposed by community members and autonomous AIs. This summary concisely summarizes the key points of each solution.

[1303] Solution translation:

[1304] The server translates the summarized solution using a multilingual translation model, making the solution easier to understand for users around the world.

[1305] User Choice and Rewards

[1306] Users review a list of solutions with summaries and translations provided by the server, and select the most useful one from the solutions filtered by the emotion engine. Users then apply the selected solution to their own problem. Community members who propose the most useful solution can also be rewarded.

[1307] Specific examples

[1308] Engineer's Concerns

[1309] User problem input and emotion recognition:

[1310] The user (engineer) enters a problem such as "I don't know how to optimize the performance of a project in a specific programming language," and expresses the stress and confusion they feel at the time.

[1311] Server Action:

[1312] The server receives the problem and user sentiment data and uses AI means to convert it into a fictional case study of "general methods for improving the performance of software systems."

[1313] Community Suggestions and Sentiment Filtering:

[1314] Community members and autonomous AI suggest solutions such as cache optimization, code refactoring, and algorithm improvements, and an emotion engine filters them in a tone that reduces user stress.

[1315] Solution summary and translation:

[1316] The proposed solutions are summarized by the server and translated into multiple languages.

[1317] User selection and execution:

[1318] Users choose the best solution and apply it to their own projects, and members who make the best suggestions are rewarded.

[1319] Example prompt: "An engineer is struggling and frustrated with how to optimize the performance of a project in a specific programming language. Please provide some generally applicable advice to solve this problem."

[1320] In this way, the present invention provides a system that can solve individual user problems in a way that takes into consideration emotions while maintaining anonymity, and can obtain suggestions from a variety of perspectives.

[1321] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1322] System program processing flow

[1323] Step 1:

[1324] The user uses the device to input their specific problem. They can also input their emotions or communicate them through emotion recognition. The device's NLP engine and facial recognition system analyze the user's input and interactions to extract emotion data. The input data is in the form of "I don't know how to optimize the performance of a project in a specific programming language," and the output data is the analysis result (e.g., emotion = stress, confusion).

[1325] Step 2:

[1326] The server receives the problem and emotion data sent from the device. The received data includes the user's specific problem and the emotion they felt at the time. The server's program analyzes this data and provides feedback to the emotion engine. The input data is the received user problem and emotion data, and the output data is the analyzed emotion information.

[1327] Step 3:

[1328] The AI ​​means on the server analyzes the received problem data and abstracts the problem while removing sensitive information using the emotion engine data as a reference. Specifically, NLP engines and data mining techniques are used. For example, the problem "I don't know how to optimize the performance of a project in a specific programming language" is abstracted into "general methods for improving the performance of software systems." The input data of this step is specific problem information, and the output data is abstracted problem information.

[1329] Step 4:

[1330] The server uses AI means to generate specific fictitious cases based on abstracted problem data. Generative AI models (e.g., GPT-3, GPT-4) are used for generation. These cases are constructed in a general form that can be applied to many situations. For example, they are reconstructed as "general methods for improving the performance of software systems." The input data is the abstracted problem, and the output data is the generated fictitious case.

[1331] Step 5:

[1332] The server publishes the generated fictitious cases to all users and autonomous AIs in the community. After the cases are published, users and autonomous AIs use them as prompts to propose solutions for new cases. The input data is the generated fictitious case, and the output data is the published case.

[1333] Step 6:

[1334] Community members and autonomous AI propose solutions to fictitious cases. These proposals are filtered by an emotion engine to match the user's emotions and sent to the server. The input data are the solutions for each proposal, and the output data are the solutions filtered by the emotion engine.

[1335] Step 7:

[1336] The server summarizes the proposed solutions concisely using an AI summarization model. This summary concisely extracts the key points of each solution. The summarized solutions are then translated using a multilingual translation model. The input data for this step are the filtered solutions for each proposal, and the output data are the summarized solutions and their translations.

[1337] Step 8:

[1338] The user reviews a list of solutions with summaries and translations provided by the server. The user selects the most useful solution from the solutions filtered by the emotion engine and applies it to solving their own problem. The user can also award a reward to the community member who proposes the most useful solution. The input data is the summarized solution list, and the output data is the selected optimal solution and reward data.

[1339] (Application example 2)

[1340] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1341] Customer service in traditional brick-and-mortar stores has been heavily dependent on the experience and skills of staff, resulting in inconsistent quality of service. It has also been difficult to properly recognize customer emotions and respond accordingly. The objective of this invention is to provide a system that solves these problems, quickly resolves customer problems, and provides emotionally sensitive service.

[1342] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for a user to input a problem; server means for receiving the problem; AI means for abstracting the received problem and converting it into a fictitious case; means for sharing the abstracted problem with the community; means for community members and autonomous AI to propose solutions; means for summarizing the proposed solution; means for translating the proposed solution; means for a user to select a solution and provide a reward; means for inputting a problem from the voice or text of a customer in a physical store and recognizing their emotions; and means for generating suggestions based on the customer's emotions and providing an optimal solution. This makes it possible to solve customer problems quickly and in a manner that takes their emotions into consideration.

[1343] Key Word Definitions

[1344] The "means for users to input problems" refers to a means for providing an interface for users to input problems such as questions or concerns by text or voice.

[1345] The "server means for receiving questions" is a server device for receiving and processing question information sent from a user.

[1346] "AI means for abstracting received problems and converting them into fictional cases" refers to artificial intelligence means for analyzing received problems, excluding specific information, and reconstructing them in a generalized form as fictional cases.

[1347] A "means for sharing abstract problems with the community" is a means for publishing abstract problems to an online community so that they can be widely viewed and suggested.

[1348] "Means for community members and autonomous AI to propose solutions" means means that enable community members and autonomous AI to propose solutions to specified problems.

[1349] A "means for summarizing proposed solutions" is a means for concisely summarizing multiple solutions provided and extracting their main points.

[1350] A "means for translating the proposed solution" is a means for translating the summarized solution into other languages.

[1351] The "means for users to select a solution and to give a reward" refers to a means by which a user can select the most suitable solution from among the solutions provided and send a reward to the proposer of the solution.

[1352] "Means for inputting problems and recognizing emotions from voices and texts of customers in physical stores" refers to a means for analyzing the voices uttered by customers and the texts they input in physical stores and identifying their emotions from them.

[1353] The "means for generating proposals based on customer emotions and providing optimal solutions" is a means for taking into account the recognized emotions of a customer and generating and providing a solution that is appropriate for the customer.

[1354] An embodiment of the present invention will be described in detail below. This embodiment is a system for quickly resolving customer problems and responding in an emotionally sensitive manner in order to improve the quality of customer service in brick-and-mortar stores.

[1355] User's device

[1356] The user device is a device such as a smartphone or tablet. The user can use this device to input customer problems or questions by voice or text. The device converts speech to text using speech recognition software (such as the Google Speech Recognition API). It also includes an emotion recognition engine (such as the Hugging Face Transformers library) to recognize emotions from the customer's facial expressions and tone of voice.

[1357] Server Processing

[1358] The server receives the questions and emotion data sent from the user's terminal and performs the following processing.

[1359] 1. Problem Abstraction:

[1360] The server analyzes the received data using AI (such as TextBlob or a custom natural language processing model) and abstracts it into a generalized problem, excluding specific information.

[1361] 2. Generating fictitious cases:

[1362] Generate concrete fictitious cases based on abstract problems and share them with the community.

[1363] 3. Share with the community:

[1364] We provide an environment where community members (other store staff, related parties, etc.) and autonomous AI can propose solutions to this fictional case.

[1365] 4. Summary and translation of the proposed solution:

[1366] The proposed solution is summarized using an AI summarization model (such as Hugging Face's Transformers library) and translated using a multilingual translation model (such as Helsinki-NLP's opus-mt-en-jp).

[1367] Specific processing flow example

[1368] The following example shows a specific processing flow.

[1369] Example 1: "Product not found"

[1370] The user voice-inputs the customer's problem into their smartphone, saying, "I can't find the product."

[1371] The server converts the voice into text and uses an emotion recognition engine to recognize the customer's "confusion" emotion.

[1372] AI abstracts the problem into "optimizing product information" and generates solutions such as "providing product layout diagrams" and "direct guidance by staff."

[1373] The solutions are summarized and translated into other languages ​​(e.g., English) using a multilingual translation model.

[1374] Example prompt sentence:

[1375] "A customer has expressed difficulty finding a particular product. They seem confused. How should I respond?"

[1376] As shown in this specific example, the present invention is a system that can solve customer problems quickly and in an emotionally sensitive manner, thereby significantly improving customer satisfaction in physical stores.

[1377] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1378] Program processing flow

[1379] Step 1:

[1380] Users input their customer's problem by voice or text using a smartphone or tablet, and the input voice data is converted into text using voice recognition software.

[1381] Input: Customer voice or text input

[1382] How it works: Uses speech recognition software (Google Speech Recognition API) to convert speech to text.

[1383] Output: Text data

[1384] Step 2:

[1385] The user's device sends the converted text data to the server, which also uses an emotion recognition engine to analyze the customer's emotions and sends the results to the server.

[1386] Input: Text data and customer sentiment data obtained in Step 1

[1387] How it works: Analyzes emotions using an emotion recognition engine (Hugging Face's Transformers library). Sends the data to the server.

[1388] Output: Text data and emotion data

[1389] Step 3:

[1390] The server receives the question text data and emotion data from the user's terminal and stores them.

[1391] Input: Text data and emotion data sent in Step 2

[1392] Action: Save to database.

[1393] Output: Saved text data and emotion data

[1394] Step 4:

[1395] The server analyzes the stored problem data using a natural language processing model (such as TextBlob), removes specific information, and abstracts it into a generalized problem.

[1396] Input: Saved text data

[1397] How it works: Analyzes data using a natural language processing model, filtering out and abstracting specific information.

[1398] Output: Abstracted problem data

[1399] Step 5:

[1400] Based on the abstracted problem, the server uses AI means to generate concrete fictitious cases and shares them with community members and autonomous AI.

[1401] Input: Abstracted problem data

[1402] How it works: Generate fictional cases using AI tools. Share the fictional cases with the community.

[1403] Output: fictional example

[1404] Step 6:

[1405] Solutions proposed by community members and autonomous AIs are collected on a server using an online platform.

[1406] Input: Solutions from community members and autonomous AI

[1407] How it works: Collect suggestions through an online platform.

[1408] Output: Collected solutions

[1409] Step 7:

[1410] The collected solutions are summarized on the server using a summarization model (from the Transformers library in Hugging Face).

[1411] Input: Collected solutions

[1412] What it does: Summarize the solution using a summary model.

[1413] Output: Summarized solution

[1414] Step 8:

[1415] The summarized solution is translated using a multilingual translation model, using the opus-mt-en-jp model from Helsinki-NLP.

[1416] Input: Abridged solution

[1417] What it does: Translates the solution using a translation model.

[1418] Output: Translated solution

[1419] Step 9:

[1420] The server provides the translated solutions to the user, who then selects the best solution. Furthermore, the server rewards the proposer who provides the best solution based on the evaluation.

[1421] Input: translated solution

[1422] Behavior: Show the translated solution to the user. Reward the user based on their choice and rating.

[1423] Output: Selected solution and evaluation results

[1424] In this way, a system is created that can quickly resolve customer problems in brick-and-mortar stores and respond in an emotionally sensitive manner.

[1425] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1426] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1427] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1428] [Fourth embodiment]

[1429] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1430] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1431] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1432] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1433] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1434] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1435] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1436] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1437] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1438] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1439] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1440] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1441] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1442] The embodiment of the present invention is a system in which a user inputs a problem and solicits solutions from a wide range of sources. This system is composed of a terminal, a server, and an AI means. The specific roles and processing flow of each element are explained below.

[1443] User's device

[1444] The user's terminal provides an interface for inputting problems. The user inputs specific problems they are facing in their hobbies or work in text format through the terminal. The input problem is sent from the user's terminal to the server.

[1445] Server Processing

[1446] The server centrally processes the problems received from the user's terminal and provides the means to proceed to the next step.

[1447] 1. Receiving the problem:

[1448] The server receives the question sent from the terminal.

[1449] 2. Problem Abstraction:

[1450] The received problem is analyzed by AI means on the server and abstracted to eliminate sensitive information. This abstracted problem is then reconstructed as a fictional case that hides the real problem.

[1451] 3. Generating fictitious cases:

[1452] The server uses AI tools to generate fictitious cases based on abstracted problems, which are constructed as generalized and widely applicable problems.

[1453] 4. Sharing fictional stories:

[1454] The generated fictional cases are shared with the community via the server, which consists of other users and autonomous AIs participating in the system.

[1455] Community members and autonomous AI proposals

[1456] Community members can propose solutions to published fictitious cases. The autonomous AI can also propose solutions based on its prior knowledge. These proposals are sent to the server for further processing.

[1457] Solution Processing

[1458] 1. Solution Summary:

[1459] The server uses AI summarization to concisely summarize the proposed solutions, providing a clear overview of each solution.

[1460] 2. Solution Translation:

[1461] The server translates the summarized solution using a multilingual translation means, making it easier for users around the world to understand the solution.

[1462] User Choice and Rewards

[1463] Users can review a list of solutions provided by the server, complete with summaries and translations, and select the most suitable solution. Based on this selection, they can obtain specific measures to adapt to their own problems. Furthermore, users can reward community members who propose the most useful solutions.

[1464] Specific examples

[1465] Example 1: Engineer's Concerns

[1466] 1. User problem input:

[1467] A user (engineer) enters a problem: "I don't know how to optimize the performance of a project in a specific programming language."

[1468] 2. Server processing:

[1469] The server receives this problem and uses AI means to convert it into a fictional case study titled "General methods for improving the performance of software systems."

[1470] 3. Community Suggestions:

[1471] Community members and autonomous AI propose solutions such as cache optimization, code refactoring, and algorithm improvements.

[1472] 4. Solution summary and translation:

[1473] The proposed solutions are summarized by the server and translated into multiple languages.

[1474] 5. User Choice and Action:

[1475] Users can choose the best solution and apply it to their own projects, and members who make the best suggestions are rewarded.

[1476] Example 2: Gardening problems

[1477] 1. User problem input:

[1478] The user (gardener) inputs the problem, "I don't know the cause of a certain plant dying and what to do about it."

[1479] 2. Server processing:

[1480] The server receives this problem and uses AI tools to convert it into a fictional case study called "General methods for plant health management."

[1481] 3. Community Suggestions:

[1482] Community members and autonomous AI will suggest solutions such as soil improvement, watering timing, and proper sunlight.

[1483] 4. Solution summary and translation:

[1484] The proposed solutions are summarized by the server and translated into multiple languages.

[1485] 5. User Choice and Action:

[1486] Users can choose the best solution and apply it to their own gardening activities, and members who make the best suggestions will be rewarded.

[1487] With this configuration, the present invention provides a system that can solve a user's problem from various perspectives while maintaining anonymity.

[1488] The processing flow will be explained below.

[1489] Step 1: User enters problem

[1490] Users log in to the IdeaQuest app from their device and enter the specific problem they are facing into a text box.

[1491] For example: "I don't know how to optimize the performance of my project in a specific programming language."

[1492] Step 2: The server receives the problem

[1493] The server receives the problem data sent from the terminal, including the specific problem text entered by the user.

[1494] Step 3: Abstract the problem using AI tools

[1495] An AI tool on the server analyzes the received problem and converts it into a fictitious case so as not to extract sensitive information.

[1496] Example: Remove information about specific programming languages ​​and abstract it as "a general method for improving the performance of software systems."

[1497] Step 4: Generate fictitious cases

[1498] The server generates specific fictitious cases based on the content abstracted by the AI.

[1499] For example, a hypothetical case study generated might be: "What techniques or approaches are effective in a situation where a software system is performing poorly?"

[1500] Step 5: Share your fictional story with the community

[1501] The server makes the generated fictitious cases public to all users and autonomous AIs in the community.

[1502] Step 6: Community members propose solutions

[1503] Community members come up with solutions to the fictitious cases that are published and post their solutions from their own devices.

[1504] For example: cache optimization, code refactoring, algorithm improvements, etc.

[1505] Step 7: Autonomous AI proposes a solution

[1506] The autonomous AI also analyzes fictitious cases provided to it and generates and proposes solutions based on its prior knowledge.

[1507] Step 8: The server summarizes the solution

[1508] The server uses an AI summary model to summarize multiple solutions proposed by community members and autonomous AIs, concisely summarizing the key points of each solution.

[1509] Step 9: Server translates the solution

[1510] The server translates the summarized solution using a multilingual translation model, allowing users around the world to understand the solution across language barriers.

[1511] Step 10: User selects optimal solution

[1512] The user reviews a list of solutions provided by the server, complete with summaries and translations, and selects the solution that seems most useful.

[1513] Step 11: User Gives Reward

[1514] Users can show their appreciation by rewarding community members who propose optimal solutions, either in the form of points in the system or actual rewards.

[1515] Through the above processing steps, the "IdeaQuest" system abstracts the user's specific problem, gathers solutions from a variety of perspectives, and presents them in an easy-to-understand format.

[1516] Example 1

[1517] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1518] Conventional problem-solving systems have difficulty providing direct solutions to problems entered by users, and sharing problems while maintaining user privacy. Furthermore, their proposed solutions lack multilingual support, making it difficult for users of different languages ​​to communicate with each other. To solve these problems, a system is needed that protects privacy by anonymizing and abstracting users' problems, and that also allows for multilingual solution proposals.

[1519] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1520] In this invention, the server includes means for a user to input a problem, means for receiving a problem, artificial intelligence means for abstracting the received problem and converting it into a fictitious case, means for generating a fictitious case based on the abstracted problem, means for publishing the generated fictitious case to the community, means for community members and the autonomous artificial intelligence to propose solutions, means for summarizing the proposed solutions, means for translating the proposed solutions, means for a user to select a solution, and means for providing a reward. This makes it possible to share problems while maintaining user privacy, and makes it easier for users of different languages ​​to obtain solutions.

[1521] "User" means a person or entity that uses the System to enter a problem and request a solution.

[1522] "Input means" refers to an interface or device that allows a user to input and submit a question in text format.

[1523] "Server" refers to a central management system that receives and processes problems submitted by users.

[1524] "Means for receiving" refers to a function that allows the server to receive questions sent by users in real time.

[1525] "Abstraction" refers to the process of removing sensitive information from an incoming problem and reconstructing it into a generalized problem.

[1526] "Artificial intelligence tools" refers to machine learning models and algorithms used to analyze problems, abstract, and generate fictitious cases.

[1527] "Fictional cases" refer to general and broadly applicable problems that are generated based on abstract problems.

[1528] "Community" refers to a group of other users and autonomous artificial intelligences participating in the system.

[1529] "Means for sharing" refers to a method for communicating the generated fictional cases to community members and autonomous artificial intelligence.

[1530] "Community Members" refers to other users who use the system to propose solutions.

[1531] "Autonomous artificial intelligence" refers to an AI system that uses pre-trained models to generate solutions independently.

[1532] "Solution" refers to a specific method of dealing with a hypothetical case.

[1533] "Means for Proposing" refers to the methods by which community members and autonomous artificial intelligences submit solutions to the server.

[1534] "Means for summarizing" refers to a function for concisely summarizing multiple proposed solutions.

[1535] "Means for translation" refers to the functionality for translating the summarized solution into multiple languages.

[1536] "Means of selection" refers to the interface and functionality that allows users to choose the optimal solution.

[1537] "Reward mechanisms" refers to a feature that provides rewards to community members who propose good solutions.

[1538] The system mainly consists of a user terminal, a server, and an artificial intelligence means. The user inputs the problem using the terminal, and the system then executes the process of proposing a solution.

[1539] User's device

[1540] The user's device refers to an input device such as a general personal computer or smartphone. The user inputs a problem in the form of text input through the device's interface. For example, the user inputs a problem such as "I don't know how to optimize the performance of a project in a specific programming language." After inputting the problem, the device sends it to the server. This transmission requires an internet connection.

[1541] Server Processing

[1542] The server receives the questions sent from the user's terminal and performs the following process to proceed to the next step.

[1543] 1. Receiving the Problem

[1544] The server receives the user's problem via a REST API and temporarily stores it in a database, ensuring that the problem content is preserved.

[1545] 2. Problem Abstraction

[1546] The server analyzes the received problem using artificial intelligence means (e.g., a machine learning model). Specifically, it uses a generative AI model and invokes the AI ​​with the prompt, "Abstract the input problem and reconstruct it into a general problem." The problem is then converted into a generalized problem that does not contain sensitive information.

[1547] 3. Generating fictional cases

[1548] The server uses a generative AI model to generate fictitious cases based on the abstract problem. The prompt is "Generate specific fictitious cases based on the abstract problem." For example, the server generates a generalized problem called "improving the performance of a software system" as "a method for improving the performance of a large-scale data processing system."

[1549] 4. Sharing fictional stories

[1550] The generated fictional cases are shared with the community via a server, using messaging protocols and SNS APIs.

[1551] Community members and autonomous AI proposals

[1552] Community members (other users) and the autonomous AI propose solutions based on fictitious cases shared by the server. Community members input solutions from their own devices and send them to the server. The autonomous AI generates solutions using a pre-trained model and sends them to the server.

[1553] Solution Processing

[1554] 1. Solution Summary

[1555] The server uses a generative AI model to summarize the proposed solutions. It invokes the AI ​​with the prompt "Please briefly summarize these solutions" to generate a concise solution.

[1556] 2. Translation of the solution

[1557] The summarized solution is translated using a multilingual translation means. The server uses the prompt sentence "Please translate from English to Japanese" and runs a machine translation model.

[1558] User Choice and Rewards

[1559] Users can view a list of solutions with abridged translations on their device, choose the best solution, and adopt it to solve their problem. Community members who propose particularly good solutions can be rewarded using a points system or virtual currency.

[1560] Examples of specific examples and prompts

[1561] As a concrete example, suppose a user inputs a problem such as "I don't know the cause of a particular plant dying and what to do about it." This problem is sent to the server, which uses artificial intelligence to abstract it into the form of "general methods for plant health management." Then, a generative AI model is used to generate fictitious examples such as "improving the soil, watering at the right time, and providing adequate sunlight." After the problem is shared, community members and autonomous AI propose solutions, which the server then summarizes and translates.

[1562] Examples of prompts include:

[1563] "Abstract the input problem and reconstruct it into a general problem."

[1564] "Generate concrete, fictional cases based on abstract problems."

[1565] Please briefly summarize these multiple solutions.

[1566] Please translate from English to Japanese.

[1567] Thus, the present invention provides a system for efficient, multilingual management and resolution of user problems while preserving their anonymity.

[1568] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1569] The flow of this system's program processing

[1570] Step 1: User Problem Input

[1571] The user enters the problem on their device. Specifically, the user writes the problem in text format in the input form on the device and presses the submit button. For example, the user might enter, "I don't know how to optimize the performance of a project in a specific programming language."

[1572] Input: Problem text

[1573] Output: The problem request sent to the server

[1574] Step 2: The server receives the problem

[1575] The server receives the problem sent by the user using the REST API and saves the problem in the database. This is to temporarily store the problem content and ensure subsequent processing.

[1576] Input: User submitted text question

[1577] Output: Saved problem data

[1578] Step 3: Abstract the problem

[1579] The server analyzes and abstracts the received problem using artificial intelligence. It passes the prompt "Abstract the input problem and reconstruct it into a general problem" to the generative AI model. The AI ​​analyzes the problem, removes sensitive information, and generalizes it.

[1580] Input: Saved problem data

[1581] Output: Abstracted problem

[1582] Step 4: Generate fictional cases

[1583] The server uses a generative AI model to generate a fictitious case based on the abstracted problem. The prompt is "Generate a concrete fictitious case based on the abstracted problem." For example, it could be described as "How to improve the performance of a software system."

[1584] Input: Abstracted problem

[1585] Output: fictitious example

[1586] Step 5: Share a fictional example

[1587] The server shares the generated fictional cases with the community. The server uses messaging protocols and SNS APIs to send the cases to community members and autonomous AI.

[1588] Input: fictional case

[1589] Output: Share the case study with the community

[1590] Step 6: Community members and autonomous AI proposals

[1591] Community members and the autonomous AI propose solutions based on shared fictional cases. Members input and submit solutions on their own devices, and the autonomous AI generates solutions using a pre-trained model. The server receives the proposed solutions.

[1592] Input: Solution proposals from community members and autonomous AI

[1593] Output: Proposal data stored on the server

[1594] Step 7: Solution Summary

[1595] The server summarizes the proposed solutions using a generative AI model. The AI ​​is invoked with the prompt "Please briefly summarize these solutions" to generate a concise summary.

[1596] Input: Proposal data

[1597] Output: Summarized solution

[1598] Step 8: Translating the solution

[1599] The server translates the summarized solution using a multilingual translation means. The server uses the prompt "Please translate from English to Japanese" and executes a machine translation service.

[1600] Input: Abridged solution

[1601] Output: Translated solution

[1602] Step 9: User Choice and Reward

[1603] The user reviews the translated list of solutions on their device, selects the best solution, and rewards the proposer of the selected solution using a points system or virtual currency.

[1604] Input: translated solution list, user selection

[1605] Output: Selected solution, reward given

[1606] This allows users to solve problems while maintaining their privacy, and creates a system that can be used by users of different languages.

[1607] (Application example 1)

[1608] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1609] In modern factories, it is important to find a quick and accurate solution when an abnormality or problem occurs. However, many current solution methods require human effort and time, and are inefficient. In addition, it is difficult to identify and abstract the problem, making it difficult for workers without specialized knowledge to deal with it. In such situations, there is a risk of reduced productivity and increased costs.

[1610] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1611] In this invention, the server includes: a means for a user to input a problem; a server means for receiving the problem; an AI means for abstracting the received problem and converting it into a fictitious case; a means for sharing the abstracted problem with the community; a means for community members and the autonomous AI to propose solutions; a means for summarizing the proposed solutions; a means for a user to select a solution and a means for providing a reward; a means for a factory robot to detect anomalies; a means including a sensor and a camera for describing anomalies in text format; and a means for automatically collecting and processing the proposed solutions. This enables rapid detection of anomalies in factories and the proposal and selection of solutions.

[1612] The "means for the user to input a question" refers to a device or software that provides an interface for the user to input a specific question in text format.

[1613] The "server means for receiving questions" is a central server for receiving and managing questions sent by users.

[1614] "AI means for abstracting received problems and converting them into fictional cases" refers to an artificial intelligence algorithm for generalizing received specific problems and removing sensitive information.

[1615] "Means for sharing abstracted problems with the community" refers to the means by which abstracted problems can be sent to other users and AI models in the system to broadly solicit solutions.

[1616] "Means for community members and autonomous AIs to propose solutions" refers to the means by which other users participating in the system and autonomous AIs with previously learned knowledge can make proposals.

[1617] A "means for summarizing proposed solutions" is a summarization algorithm for concisely summarizing multiple proposed solutions.

[1618] A "means for translating the proposed solution" is a translation algorithm or API that translates the summarized solution into other languages ​​so that it can be understood by multilingual users.

[1619] The "means for users to select solutions and provide rewards" is a mechanism by which users can select the best solution from the proposed solutions and provide a reward to the person who proposed it.

[1620] "Means for factory robots to detect abnormalities" refers to devices such as sensors and cameras used to detect abnormalities within the factory.

[1621] "Means including a sensor and a camera for describing anomalies in text form" refers to a device for describing information on detected anomalies in text form and software that supports it.

[1622] "Means for automatically collecting and processing proposed solutions" means a system for automatically collecting, analyzing, and processing proposed solutions from the community.

[1623] Specifically, an embodiment of the present invention is realized as a system that detects anomalies using factory robots and widely solicits solutions to the anomalies. The system includes: means for a user to input a problem; a server means for receiving the problem; an AI means for abstracting the received problem and converting it into a fictitious case; means for sharing the abstracted problem with a community; means for community members and autonomous AIs to propose solutions; means for summarizing the proposed solutions; means for a user to select a solution and provide a reward; means for a factory robot to detect anomalies; means including a sensor and a camera for describing the anomaly in text form; and means for automatically collecting and processing the proposed solutions.

[1624] First, we will explain how factory robots detect abnormalities. Factory robots are equipped with hardware such as temperature sensors, pressure sensors, and cameras, which detect abnormalities. For example, if a conveyor belt stops during transportation, the cameras and sensors detect the abnormality and record the information in text format. This text data is sent to a server.

[1625] The server then abstracts the received text data. Specifically, it uses a Transformer-based AI model such as BERT to generalize the specific content of the anomaly and remove sensitive information. The abstracted problem is reconstructed as a fictitious example that hides the real problem. This allows it to be shared as useful information for other users with similar problems.

[1626] The abstracted problems are then shared with the community through a web application. Users can submit solutions using their own PCs or smartphones. The proposed solutions are collected on a server, where they are summarized and translated. The translation is done using the Google Translate API, and the summarization is done using generative AI models such as GPT-3. This allows the proposed solutions to be understood in other languages.

[1627] Finally, users select the best solution from the list and apply it to their own system. Community members who make excellent suggestions are rewarded. This process quickly detects abnormalities in factories and effectively derives solutions.

[1628] Specific examples

[1629] For example, consider the case where a conveyor belt in a factory suddenly stops. The factory robot's cameras and sensors detect the abnormality and input the problem into the system in text format. This problem is described as "the conveyor belt stops." The server receives this problem and abstracts it into a "general conveyor system stoppage problem." After it is shared with the community, other users and AI can make suggestions such as "motor failure" or "abnormal belt stretch." These suggestions are summarized and translated into multiple languages ​​and provided to users.

[1630] Prompt Sentence Examples

[1631] User: "The conveyor belt in our factory suddenly stopped. I don't know what caused it or what to do about it."

[1632] System: "Abstracting the problem..."

[1633] AI model: "What are some common problems that cause conveyor belts to stop?"

[1634] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1635] Now, the processing flow of the program of the system that realizes the application example will be explained in detail, broken down into steps.

[1636] Step 1:

[1637] Factory robots detect abnormalities. Sensors (temperature sensors, pressure sensors, etc.) and cameras installed on the factory robots are activated to detect abnormalities. For example, abnormal events such as a stopped conveyor belt, a motor failure, or an abnormal rise in temperature are detected. This abnormality detection data is obtained as numerical data or image data.

[1638] Step 2:

[1639] Anomaly detection data is converted into text format. A terminal inside the robot receives data from the sensors and cameras and describes the anomaly in text format. For example, abnormal temperature data obtained from a temperature sensor is converted into text such as "The temperature has exceeded the set value." This generates specific information about the anomaly as text data.

[1640] Step 3:

[1641] The server receives the text data. The central server receives the text data sent from the factory robot. The input is text data, and the received text data becomes the input for the next step.

[1642] Step 4:

[1643] The received problem is abstracted and converted into a fictitious case. The received text data is abstracted using AI means (e.g., the BERT model) installed on a central server. This process converts concrete information into a general problem. The input is the received text data, and the output is an abstracted problem such as "a general problem of a conveyor belt stopping." This data conversion generalizes the data to make it easier to find a solution while hiding specific anomaly information.

[1644] Step 5:

[1645] The abstracted problem is shared with the community. The server publishes the abstracted problem to the community through a web front end (for example, an application using React). The input is the abstracted problem, and the output is information shared with all members of the community. This sharing process makes it possible to solicit solution proposals from a wide range of users.

[1646] Step 6:

[1647] Community members and autonomous AI propose solutions. Other users participating in the community and autonomous AI models propose solutions to abstracted problems. The input is the abstracted problem, and the output is multiple proposed solutions. This behavior is achieved by users directly entering the solution on the web application, or by the AI ​​automatically generating the solution.

[1648] Step 7:

[1649] Summarize proposed solutions and translate them into multiple languages. Multiple proposed solutions are concisely summarized on the server using an AI summarization tool (e.g., GPT-3). Furthermore, the solutions are translated into other languages ​​using a multilingual translation tool such as the Google Translate API. The input is the proposed solution, and the output is the summarized and translated solution. This makes the solution easily understandable to users around the world.

[1650] Step 8:

[1651] The user selects the best solution and is rewarded. The user reviews the summarized and translated solution list provided by the server and selects the best solution. After selection, the community member who made the best proposal is rewarded. The input is the summarized and translated solution list, and the output is the selected solution and reward information. This operation allows the user to obtain a concrete means to solve the problem, and provides appropriate incentives to the contributing members.

[1652] In this way, the entire system works together to efficiently support anomaly detection and problem resolution within the factory.

[1653] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1654] The embodiment of the present invention is a system in which a user inputs a problem and solicits solutions from a wide range of people, and is combined with an emotion engine that recognizes the user's emotions. This system is composed of a terminal, a server, an AI means, and an emotion engine, and the specific roles and processing flow of each element are explained below.

[1655] User's device

[1656] The user's device provides an interface for inputting problems and communicating emotions. The user inputs specific problems they are facing in their hobbies or work through the device. The system also provides a function for reading emotions from the user's input and interactions. This input information is sent from the user's device to the server.

[1657] Server Processing

[1658] The server centrally processes the data received from the user's device about the problem and emotions and provides the means to take the next step.

[1659] 1. Receiving the problem and recognizing emotions:

[1660] The server receives the problem data and emotion data sent from the device, which includes emotions analyzed from the user's input and interactions.

[1661] 2. Problem Abstraction:

[1662] The received problem is analyzed by AI means on the server, and abstracted without sensitive information, referring to the data from the emotion engine. This abstracted problem is reconstructed as a fictional case that hides the real problem.

[1663] 3. Generating fictitious cases:

[1664] The server uses AI tools to generate concrete fictional cases based on abstractions, which are constructed as generalized and widely applicable problems.

[1665] 4. Sharing fictional stories:

[1666] The generated fictitious cases are made public to all users and autonomous AIs in the community via the server.

[1667] Community members and autonomous AI proposals

[1668] Community members can propose solutions to published fictitious cases. The autonomous AI can also propose solutions based on its pre-trained knowledge. These proposals are filtered by the emotion engine to match the user's emotions and sent to the server.

[1669] Solution Processing

[1670] 1. Solution Summary:

[1671] The server uses an AI summary model to concisely summarize multiple solutions proposed by community members and autonomous AIs. This summary concisely summarizes the key points of each solution.

[1672] 2. Solution Translation:

[1673] The server translates the summarized solution using a multilingual translation model, making the solution easier to understand for users around the world.

[1674] User Choice and Rewards

[1675] Users can review a list of solutions with summaries and translations provided by the server, and select the most useful one from the solutions filtered by the emotion engine. Based on this selection, they can obtain specific measures to apply to their own problem. Furthermore, users can reward community members who propose the most useful solutions.

[1676] Specific examples

[1677] Example 1: Engineer's Concerns

[1678] 1. User problem input and emotion recognition:

[1679] The user (engineer) enters a problem such as "I don't know how to optimize the performance of a project in a specific programming language," and expresses the stress and confusion they feel at the time.

[1680] 2. Server processing:

[1681] The server receives the problem and user sentiment data and uses AI means to convert it into a fictional case study of "general methods for improving the performance of software systems."

[1682] 3. Community Suggestions and Sentiment Filtering:

[1683] Community members and autonomous AI suggest solutions such as cache optimization, code refactoring, and algorithm improvements, and an emotion engine filters them in a tone that reduces user stress.

[1684] 4. Solution summary and translation:

[1685] The proposed solutions are summarized by the server and translated into multiple languages.

[1686] 5. User Choice and Action:

[1687] Users can choose the best solution and apply it to their own projects, and members who make the best suggestions are rewarded.

[1688] Example 2: Gardening problems

[1689] 1. User problem input and emotion recognition:

[1690] The user (gardener) inputs the problem, "I don't know why a certain plant is dying and what to do about it," and expresses the sadness and concern he or she feels at the time.

[1691] 2. Server processing:

[1692] The server receives the problem and the user's emotional data and converts it into a fictional case study called "General methods for plant health management" using AI means.

[1693] 3. Community Suggestions and Sentiment Filtering:

[1694] Community members and autonomous AI suggest solutions such as soil improvement, watering times, and proper sunlight, and an emotion engine filters them with a tone that alleviates the user's concerns.

[1695] 4. Solution summary and translation:

[1696] The proposed solutions are summarized by the server and translated into multiple languages.

[1697] 5. User Choice and Action:

[1698] Users can choose the best solution and apply it to their own gardening activities, and members who make the best suggestions will be rewarded.

[1699] With this configuration, the present invention provides a system that can solve a user's problem in a way that takes into consideration their emotions while maintaining anonymity, and can obtain suggestions from a variety of perspectives.

[1700] The processing flow will be explained below.

[1701] Step 1: User enters problem

[1702] Users log in to the "IdeaQuest" app using their own devices and enter specific problems in text format.

[1703] For example: "I don't know how to optimize the performance of my project in a specific programming language."

[1704] Step 2: Enter user emotions

[1705] The user selects or describes their own emotion when entering a question. The terminal provides an option for entering emotions.

[1706] For example, enter emotions such as confusion, anxiety, or tension.

[1707] Step 3: Server receives the problem and sentiment

[1708] The server receives the question text data and emotion data sent from the user terminal.

[1709] Step 4: Abstract the problem

[1710] An AI means on the server analyzes the received problem and generalizes the problem while excluding sensitive information.

[1711] Example: Remove information about specific programming languages ​​and abstract it as a "general method for improving the performance of software systems."

[1712] Step 5: Generate fictional cases

[1713] The server generates fictitious cases based on problems abstracted using AI means.

[1714] For example, a fictitious case study was generated: "What techniques or approaches are effective in a situation where a software system is performing poorly?"

[1715] Step 6: Share your fictional story with the community

[1716] The server shares the generated fictional cases with all users and autonomous AIs in the community.

[1717] Step 7: Community members propose solutions

[1718] Community members can think of solutions to the fictitious cases that are published and post their suggestions from their own devices.

[1719] For example: cache optimization, code refactoring, algorithm improvements, etc.

[1720] Step 8: Autonomous AI proposes a solution

[1721] The autonomous AI also proposes solutions to fictitious cases that are made public based on knowledge it has learned in advance.

[1722] Step 9: Filtering solutions with the emotion engine

[1723] The emotion engine on the server filters the proposed solutions according to the user's emotion. The solution is selected in a tone that matches the user's emotion and is presented in a way that is less stressful for the user.

[1724] Step 10: Solution Summary

[1725] The server summarizes the solutions filtered by the emotion engine, using an AI summarization model to concisely summarize each solution.

[1726] Step 11: Translating the Solution

[1727] The server translates the summarized solutions into multiple languages, using a multilingual translation model to provide appropriate translations for each language.

[1728] Step 12: User selects optimal solution

[1729] The user reviews the list of translated solutions provided by the server and selects the solution that seems most useful.

[1730] Step 13: User Gives Reward

[1731] Users can show their appreciation and reward community members who propose optimal solutions, either in the form of points in the system or real money.

[1732] Through the above processing steps, the "IdeaQuest" system abstracts the user's specific problem, gathers solutions from various perspectives, and provides the solutions according to the user's feelings.

[1733] Example 2

[1734] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1735] Conventional problem-solving systems have been unable to properly recognize users' emotions and provide filtered solutions. This makes it difficult for users to receive suggestions that are appropriate for their emotions, resulting in reduced problem-solving efficiency. Furthermore, the proposed solutions are not multilingual, making it difficult for global users to efficiently utilize the system.

[1736] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes emotion recognition means for analyzing user emotion data, means for analyzing the user emotion using an emotion engine, and means for filtering proposed solutions through the emotion engine. This allows the system to provide solutions suited to the user's emotions, and the system's multilingual support enables users around the world to efficiently use the system.

[1737] A "user" is a person or entity that utilizes the system to enter their problem and receive a solution.

[1738] A "terminal" is a device that provides an interface for users to input questions and communicate their feelings.

[1739] A "server" is a central system that receives data sent from terminals and analyzes and processes it.

[1740] The "means for receiving questions" is a function by which the server receives question data sent from the user's terminal.

[1741] "Problem abstraction" is the process of generalizing the problem received from the user by excluding sensitive information.

[1742] "AI means for converting into fictional cases" is an artificial intelligence technology that reconstructs abstract problems into concrete fictional cases.

[1743] "Emotion recognition means" is a technology that analyzes and recognizes emotions from user input and interactions.

[1744] The "emotion engine" is a system that analyzes user emotions, filters proposed solutions, and analyzes emotional data.

[1745] "Sharing means" is the process of making abstracted problems available to other users and autonomous AIs.

[1746] "Community members" are multiple users who participate in the system and propose solutions.

[1747] "Independent AI" is artificial intelligence that proposes solutions based on its own learning data.

[1748] "Filtering" is the process of sorting proposed solutions in a way that is appropriate to the user's emotions.

[1749] "Means to summarize" is a function that succinctly summarizes the proposed solution.

[1750] "Translation means" is a technique for translating summarized solutions into multiple languages.

[1751] "Selection" is the process by which a user chooses the most beneficial solution from those offered.

[1752] "Rewarding" is a feature that provides rewards to community members who propose the most beneficial solutions.

[1753] A "multilingual translation model" is an artificial intelligence model designed to handle different languages.

[1754] This invention is a system in which a user inputs a problem, analyzes and abstracts the problem, and solicits solutions from a broad community. This system achieves more effective problem solving by combining it with an emotion engine that recognizes the user's emotions and proposes appropriate solutions. A specific embodiment of this system is described below.

[1755] User's device

[1756] The user's device provides an interface for inputting problems and communicating emotions. Users input specific problems they are facing in their hobbies or work through the device. The system also provides a function for reading emotions from the user's input and interactions. This function uses a natural language processing (NLP) engine and a facial recognition system. This input information is sent from the user's device to a server.

[1757] Server Processing

[1758] The server centrally processes the data received from the user's device about the problem and emotions and provides the means to take the next step.

[1759] Problem reception and emotion recognition:

[1760] The server receives the problem data and emotion data sent from the device, which includes emotions analyzed from the user's input and interactions.

[1761] Problem Abstraction:

[1762] The AI ​​means on the server analyzes the received problem data and abstracts the problem by removing sensitive information based on the data from the emotion engine. This converts the user's specific problem into a generalized form such as "a general method for improving the performance of software systems."

[1763] Fictional Case Generation:

[1764] The server generates concrete fictitious examples based on the abstracted content using AI means. The technology used is a generative AI model (e.g., GPT-3, GPT-4, etc.). These examples are created in a general-purpose format that can be applied to many situations.

[1765] Sharing a fictional example:

[1766] The generated fictitious cases are made public via the server to all users and autonomous AIs in the community. After the cases are made public, users and autonomous AIs can propose solutions to new cases.

[1767] Community members and autonomous AI proposals

[1768] Community members propose solutions to fictitious cases that have been published. The autonomous AI also proposes solutions based on its pre-trained knowledge. These proposals are filtered by the emotion engine to match the user's emotions and sent to the server.

[1769] Solution Processing

[1770] Solution Summary:

[1771] The server uses an AI summary model to concisely summarize multiple solutions proposed by community members and autonomous AIs. This summary concisely summarizes the key points of each solution.

[1772] Solution translation:

[1773] The server translates the summarized solution using a multilingual translation model, making the solution easier to understand for users around the world.

[1774] User Choice and Rewards

[1775] Users review a list of solutions with summaries and translations provided by the server, and select the most useful one from the solutions filtered by the emotion engine. Users then apply the selected solution to their own problem. Community members who propose the most useful solution can also be rewarded.

[1776] Specific examples

[1777] Engineer's Concerns

[1778] User problem input and emotion recognition:

[1779] The user (engineer) enters a problem such as "I don't know how to optimize the performance of a project in a specific programming language," and expresses the stress and confusion they feel at the time.

[1780] Server Action:

[1781] The server receives the problem and user sentiment data and uses AI means to convert it into a fictional case study of "general methods for improving the performance of software systems."

[1782] Community Suggestions and Sentiment Filtering:

[1783] Community members and autonomous AI suggest solutions such as cache optimization, code refactoring, and algorithm improvements, and an emotion engine filters them in a tone that reduces user stress.

[1784] Solution summary and translation:

[1785] The proposed solutions are summarized by the server and translated into multiple languages.

[1786] User selection and execution:

[1787] Users choose the best solution and apply it to their own projects, and members who make the best suggestions are rewarded.

[1788] Example prompt: "An engineer is struggling and frustrated with how to optimize the performance of a project in a specific programming language. Please provide some generally applicable advice to solve this problem."

[1789] In this way, the present invention provides a system that can solve individual user problems in a way that takes into consideration emotions while maintaining anonymity, and can obtain suggestions from a variety of perspectives.

[1790] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1791] System program processing flow

[1792] Step 1:

[1793] The user uses the device to input their specific problem. They can also input their emotions or communicate them through emotion recognition. The device's NLP engine and facial recognition system analyze the user's input and interactions to extract emotion data. The input data is in the form of "I don't know how to optimize the performance of a project in a specific programming language," and the output data is the analysis result (e.g., emotion = stress, confusion).

[1794] Step 2:

[1795] The server receives the problem and emotion data sent from the device. The received data includes the user's specific problem and the emotion they felt at the time. The server's program analyzes this data and provides feedback to the emotion engine. The input data is the received user problem and emotion data, and the output data is the analyzed emotion information.

[1796] Step 3:

[1797] The AI ​​means on the server analyzes the received problem data and abstracts the problem while removing sensitive information using the emotion engine data as a reference. Specifically, NLP engines and data mining techniques are used. For example, the problem "I don't know how to optimize the performance of a project in a specific programming language" is abstracted into "general methods for improving the performance of software systems." The input data of this step is specific problem information, and the output data is abstracted problem information.

[1798] Step 4:

[1799] The server uses AI means to generate specific fictitious cases based on abstracted problem data. Generative AI models (e.g., GPT-3, GPT-4) are used for generation. These cases are constructed in a general form that can be applied to many situations. For example, they are reconstructed as "general methods for improving the performance of software systems." The input data is the abstracted problem, and the output data is the generated fictitious case.

[1800] Step 5:

[1801] The server publishes the generated fictitious cases to all users and autonomous AIs in the community. After the cases are published, users and autonomous AIs use them as prompts to propose solutions for new cases. The input data is the generated fictitious case, and the output data is the published case.

[1802] Step 6:

[1803] Community members and autonomous AI propose solutions to fictitious cases. These proposals are filtered by an emotion engine to match the user's emotions and sent to the server. The input data are the solutions for each proposal, and the output data are the solutions filtered by the emotion engine.

[1804] Step 7:

[1805] The server summarizes the proposed solutions concisely using an AI summarization model. This summary concisely extracts the key points of each solution. The summarized solutions are then translated using a multilingual translation model. The input data for this step are the filtered solutions for each proposal, and the output data are the summarized solutions and their translations.

[1806] Step 8:

[1807] The user reviews a list of solutions with summaries and translations provided by the server. The user selects the most useful solution from the solutions filtered by the emotion engine and applies it to solving their own problem. The user can also award a reward to the community member who proposes the most useful solution. The input data is the summarized solution list, and the output data is the selected optimal solution and reward data.

[1808] (Application example 2)

[1809] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1810] Customer service in traditional brick-and-mortar stores has been heavily dependent on the experience and skills of staff, resulting in inconsistent quality of service. It has also been difficult to properly recognize customer emotions and respond accordingly. The objective of this invention is to provide a system that solves these problems, quickly resolves customer problems, and provides emotionally sensitive service.

[1811] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for a user to input a problem; server means for receiving the problem; AI means for abstracting the received problem and converting it into a fictitious case; means for sharing the abstracted problem with the community; means for community members and autonomous AI to propose solutions; means for summarizing the proposed solution; means for translating the proposed solution; means for a user to select a solution and provide a reward; means for inputting a problem from the voice or text of a customer in a physical store and recognizing their emotions; and means for generating suggestions based on the customer's emotions and providing an optimal solution. This makes it possible to solve customer problems quickly and in a manner that takes their emotions into consideration.

[1812] Key Word Definitions

[1813] The "means for users to input problems" refers to a means for providing an interface for users to input problems such as questions or concerns by text or voice.

[1814] The "server means for receiving questions" is a server device for receiving and processing question information sent from a user.

[1815] "AI means for abstracting received problems and converting them into fictional cases" refers to artificial intelligence means for analyzing received problems, excluding specific information, and reconstructing them in a generalized form as fictional cases.

[1816] A "means for sharing abstract problems with the community" is a means for publishing abstract problems to an online community so that they can be widely viewed and suggested.

[1817] "Means for community members and autonomous AI to propose solutions" means means that enable community members and autonomous AI to propose solutions to specified problems.

[1818] A "means for summarizing proposed solutions" is a means for concisely summarizing multiple solutions provided and extracting their main points.

[1819] A "means for translating the proposed solution" is a means for translating the summarized solution into other languages.

[1820] The "means for users to select a solution and to give a reward" refers to a means by which a user can select the most suitable solution from among the solutions provided and send a reward to the proposer of the solution.

[1821] "Means for inputting problems and recognizing emotions from voices and texts of customers in physical stores" refers to a means for analyzing the voices uttered by customers and the texts they input in physical stores and identifying their emotions from them.

[1822] The "means for generating proposals based on customer emotions and providing optimal solutions" is a means for taking into account the recognized emotions of a customer and generating and providing a solution that is appropriate for the customer.

[1823] An embodiment of the present invention will be described in detail below. This embodiment is a system for quickly resolving customer problems and responding in an emotionally sensitive manner in order to improve the quality of customer service in brick-and-mortar stores.

[1824] User's device

[1825] The user device is a device such as a smartphone or tablet. The user can use this device to input customer problems or questions by voice or text. The device converts speech to text using speech recognition software (such as the Google Speech Recognition API). It also includes an emotion recognition engine (such as the Hugging Face Transformers library) to recognize emotions from the customer's facial expressions and tone of voice.

[1826] Server Processing

[1827] The server receives the questions and emotion data sent from the user's terminal and performs the following processing.

[1828] 1. Problem Abstraction:

[1829] The server analyzes the received data using AI (such as TextBlob or a custom natural language processing model) and abstracts it into a generalized problem, excluding specific information.

[1830] 2. Generating fictitious cases:

[1831] Generate concrete fictitious cases based on abstract problems and share them with the community.

[1832] 3. Share with the community:

[1833] We provide an environment where community members (other store staff, related parties, etc.) and autonomous AI can propose solutions to this fictional case.

[1834] 4. Summary and translation of the proposed solution:

[1835] The proposed solution is summarized using an AI summarization model (such as Hugging Face's Transformers library) and translated using a multilingual translation model (such as Helsinki-NLP's opus-mt-en-jp).

[1836] Specific processing flow example

[1837] The following example shows a specific processing flow.

[1838] Example 1: "Product not found"

[1839] The user voice-inputs the customer's problem into their smartphone, saying, "I can't find the product."

[1840] The server converts the voice into text and uses an emotion recognition engine to recognize the customer's "confusion" emotion.

[1841] AI abstracts the problem into "optimizing product information" and generates solutions such as "providing product layout diagrams" and "direct guidance by staff."

[1842] The solutions are summarized and translated into other languages ​​(e.g., English) using a multilingual translation model.

[1843] Example prompt sentence:

[1844] "A customer has expressed difficulty finding a particular product. They seem confused. How should I respond?"

[1845] As shown in this specific example, the present invention is a system that can solve customer problems quickly and in an emotionally sensitive manner, thereby significantly improving customer satisfaction in physical stores.

[1846] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1847] Program processing flow

[1848] Step 1:

[1849] Users input their customer's problem by voice or text using a smartphone or tablet, and the input voice data is converted into text using voice recognition software.

[1850] Input: Customer voice or text input

[1851] How it works: Uses speech recognition software (Google Speech Recognition API) to convert speech to text.

[1852] Output: Text data

[1853] Step 2:

[1854] The user's device sends the converted text data to the server, which also uses an emotion recognition engine to analyze the customer's emotions and sends the results to the server.

[1855] Input: Text data and customer sentiment data obtained in Step 1

[1856] How it works: Analyzes emotions using an emotion recognition engine (Hugging Face's Transformers library). Sends the data to the server.

[1857] Output: Text data and emotion data

[1858] Step 3:

[1859] The server receives the question text data and emotion data from the user's terminal and stores them.

[1860] Input: Text data and emotion data sent in Step 2

[1861] Action: Save to database.

[1862] Output: Saved text data and emotion data

[1863] Step 4:

[1864] The server analyzes the stored problem data using a natural language processing model (such as TextBlob), removes specific information, and abstracts it into a generalized problem.

[1865] Input: Saved text data

[1866] How it works: Analyzes data using a natural language processing model, filtering out and abstracting specific information.

[1867] Output: Abstracted problem data

[1868] Step 5:

[1869] Based on the abstracted problem, the server uses AI means to generate concrete fictitious cases and shares them with community members and autonomous AI.

[1870] Input: Abstracted problem data

[1871] How it works: Generate fictional cases using AI tools. Share the fictional cases with the community.

[1872] Output: fictional example

[1873] Step 6:

[1874] Solutions proposed by community members and autonomous AIs are collected on a server using an online platform.

[1875] Input: Solutions from community members and autonomous AI

[1876] How it works: Collect suggestions through an online platform.

[1877] Output: Collected solutions

[1878] Step 7:

[1879] The collected solutions are summarized on the server using a summarization model (from the Transformers library in Hugging Face).

[1880] Input: Collected solutions

[1881] What it does: Summarize the solution using a summary model.

[1882] Output: Summarized solution

[1883] Step 8:

[1884] The summarized solution is translated using a multilingual translation model, using the opus-mt-en-jp model from Helsinki-NLP.

[1885] Input: Abridged solution

[1886] What it does: Translates the solution using a translation model.

[1887] Output: Translated solution

[1888] Step 9:

[1889] The server provides the translated solutions to the user, who then selects the best solution. Furthermore, the server rewards the proposer who provides the best solution based on the evaluation.

[1890] Input: translated solution

[1891] Behavior: Show the translated solution to the user. Reward the user based on their choice and rating.

[1892] Output: Selected solution and evaluation results

[1893] In this way, a system is created that can quickly resolve customer problems in brick-and-mortar stores and respond in an emotionally sensitive manner.

[1894] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1895] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1896] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1897] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1898] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1899] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1900] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1901] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1902] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1903] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1904] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1905] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1906] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1907] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1908] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1909] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1910] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1911] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1912] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1913] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1914] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1915] The following is further disclosed regarding the above embodiment.

[1916] (Claim 1)

[1917] a means for a user to input a question;

[1918] server means for receiving questions;

[1919] AI means to abstract received problems and convert them into fictional cases;

[1920] A means to share abstracted problems with the community,

[1921] A means for community members and autonomous AI to propose solutions;

[1922] a means of summarizing the proposed solution;

[1923] a means of translating the proposed solution;

[1924] means for users to select solutions and to provide rewards;

[1925] A system including:

[1926] (Claim 2)

[1927] a means for generating an abstract problem;

[1928] A means to publish generated issues to the community;

[1929] 10. The system of claim 1, comprising:

[1930] (Claim 3)

[1931] a means for summarizing and translating the proposed solution;

[1932] A means to enable multilingual understanding;

[1933] 10. The system of claim 1, comprising:

[1934] "Example 1"

[1935] (Claim 1)

[1936] a means for a user to input a question;

[1937] server means for receiving questions;

[1938] an artificial intelligence means for abstracting received problems and converting them into fictional cases;

[1939] A means to share abstracted problems with the community,

[1940] A means for community members and autonomous AI to propose solutions;

[1941] a means of summarizing the proposed solution;

[1942] a means of translating the proposed solution;

[1943] means for users to select solutions and to provide rewards;

[1944] A system including:

[1945] (Claim 2)

[1946] A means of generating fictitious cases based on abstract problems;

[1947] A means to publish the generated fictional cases to the community; and

[1948] 10. The system of claim 1, comprising:

[1949] (Claim 3)

[1950] a means for summarizing and translating the proposed solution;

[1951] A means to enable multilingual understanding;

[1952] 10. The system of claim 1, comprising:

[1953] "Application Example 1"

[1954] (Claim 1)

[1955] a means for a user to input a question;

[1956] server means for receiving questions;

[1957] AI means to abstract received problems and convert them into fictional cases;

[1958] A means to share abstracted problems with the community,

[1959] A means for community members and autonomous AI to propose solutions;

[1960] a means of summarizing the proposed solution;

[1961] a means of translating the proposed solution;

[1962] a means for a user to select a solution and a means for providing a reward;

[1963] A means for factory robots to detect abnormalities;

[1964] means including a sensor and a camera for describing the anomaly in text form;

[1965] means for automatically collecting and processing proposed solutions;

[1966] A system including:

[1967] (Claim 2)

[1968] a means for generating an abstract problem;

[1969] A means to publish generated issues to the community;

[1970] a means of abstracting the reported anomalies; and

[1971] a means for sharing the information with the community via a user terminal;

[1972] a means of collecting and summarizing suggestions for solving the problem;

[1973] 10. The system of claim 1, comprising:

[1974] (Claim 3)

[1975] a means of summarizing and translating the proposed solution;

[1976] A means to enable multilingual understanding;

[1977] a means for using a translation API and a summarization API to summarize and translate the proposed solution;

[1978] 10. The system of claim 1, comprising: ...

Claims

1. a means for a user to input a question; server means for receiving questions; AI means to abstract received problems and convert them into fictional cases; A means to share abstracted problems with the community, A means for community members and autonomous AI to propose solutions; a means of summarizing the proposed solution; a means of translating the proposed solution; means for users to select solutions and to provide rewards; A system including:

2. a means for generating an abstract problem; A means to publish generated issues to the community; 10. The system of claim 1, comprising:

3. a means for summarizing and translating the proposed solution; A means to enable multilingual understanding; 10. The system of claim 1, comprising:

Images