System

Abstract

A system is provided.SOLUTION: A system comprising: means for transmitting a problem input to a terminal by a user to a server; means for passing problem data transmitted from the server to a natural language processing module and extracting main elements; means for transmitting a request for generating a solution to a multilateral viewpoint generation module based on the extracted elements; means for generating solutions from a plurality of viewpoints; means for passing the generated solutions to a logical verification module and evaluating an optimal solution; and means for transmitting the evaluated solution to the user terminal.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] There are situations where it is difficult to discover new solutions with an approach limited to a single specialty or cultural background. In modern society, there is a need to find solutions to diversifying issues and problems from multiple perspectives, but the overabundance of information makes it difficult to find appropriate solutions efficiently and quickly. This invention aims to integrate problem-solving approaches from different cultures and professions and present new solutions. [Means for solving the problem]

[0005] The solution of the present invention provides a means for transmitting a problem input by a user to a server. The server has means for passing the received problem data to a natural language processing module and extracting key elements. The server further has means for sending a solution generation request to a multi-perspective generation module based on the extracted elements, and includes means for generating solutions from multiple perspectives. The generated solutions are passed to a logical verification module and evaluated by means for evaluating the optimal solution. Finally, the server provides a system including means for transmitting the evaluated solutions to the user's terminal. Efficient and effective problem solving is achieved by obtaining information on different cultures, fields of expertise, and occupations from a database, generating solutions from each perspective, and having multiple AI expert modules conduct virtual discussions to evaluate the effectiveness and feasibility of each solution.

[0006] "User" refers to an individual or legal entity that utilizes the system to input problems and receive solutions.

[0007] "Terminal" refers to the electronic device used by the user to enter the challenge and view the solution sent from the server.

[0008] "Server" refers to a computer system that receives and analyzes problem data sent from user terminals, and generates and sends solutions.

[0009] "Natural language processing module" refers to a program or algorithm that analyzes the text data of the input assignment and extracts key elements.

[0010] A "multi-perspective generation module" refers to a program or algorithm that generates solutions from the perspectives of different cultures, fields of expertise, occupations, etc. based on the extracted elements.

[0011] "Solution generation request" refers to an instruction within the server to request the multi-perspective generation module to generate solutions based on the extracted elements.

[0012] "Logical Verification Module" refers to a program or algorithm for evaluating the validity and feasibility of generated solutions.

[0013] "AI Expert Module" refers to an artificial intelligence-based program or algorithm that virtually discusses and evaluates solutions.

[0014] "Database" refers to a system that stores information about different cultures, specialties, and occupations, and allows a server to retrieve the information as needed.

[0015] "Evaluated solution" refers to a solution whose effectiveness and feasibility have been confirmed by the logical verification module. [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] This invention is a system that supports efficient and effective problem solving by allowing a user to input any problem, and then having a server analyze it from multiple perspectives and generate a solution. This system includes a terminal, a server, a natural language processing module, a multiple perspective generation module, a logical verification module, an AI expert module, and a database.

[0038] System configuration and processing flow

[0039] 1. Assignment input

[0040] The user logs in to a terminal that has a problem input screen. The problem input screen has a text box where the user can freely enter the problem they want to solve. For example, "I want to think about how to enter a new market." Once the input is complete, the user clicks the send button and the problem data is sent to the server.

[0041] 2. Analysis of issue information

[0042] The server receives the assignment data sent from the user's device. A natural language processing (NLP) module in the server analyzes the assignment text and extracts key elements. For example, keywords such as "new market" and "entry method" are extracted.

[0043] 3. Solution generation from multiple perspectives

[0044] Based on the extracted elements, the server sends a request for solution generation to the multi-perspective generation module, which accesses the database to obtain relevant information from different cultures, fields of expertise, and occupations, and then generates solutions from each perspective.

[0045] Cultural perspective: Given the effectiveness of web marketing in specific cultural contexts, suggestions are made to strengthen social media advertising.

[0046] Specialist perspective: The technology sector suggests using online platforms to host webinars and promote products and services.

[0047] 4. Logical verification and solution selection

[0048] The server passes the generated solutions to a logical verification module, which collaborates with multiple AI expert modules to virtually discuss the effectiveness and feasibility of each solution, ultimately selecting the most effective solution.

[0049] 5. Providing a solution

[0050] The server sends the evaluated optimal solution to the user's device, which then displays the received solution in an easy-to-read format for the user. The user can then select an action based on the proposed solution.

[0051] Specific examples

[0052] 1. User input:

[0053] The user inputs the problem, "I want to think about how to enter a new market," and submits it.

[0054] 2. Analysis of assignment information:

[0055] The server's natural language processing module extracts "new markets" and "ways to enter the market."

[0056] 3. Solution generation from multiple perspectives:

[0057] The server's multifaceted perspective generation module generates solutions such as strengthening social media advertising (cultural perspective), strengthening market research (profession perspective), and holding web seminars (specialty perspective).

[0058] 4. Logical verification and solution selection:

[0059] The server's logical verification module virtually discusses the issue and determines that strengthening social media advertising and combining it with market research is optimal.

[0060] 5. Propose a solution:

[0061] The server sends the evaluated solutions to the device, which then displays the message on its screen: "Strengthen social media advertising and conduct thorough market research."

[0062] In this way, the system of the present invention analyzes the problem entered by the user from multiple perspectives and provides the optimal solution, thereby solving the problem efficiently and effectively.

[0063] The processing flow will be explained below.

[0064] Step 1:

[0065] The user logs in to the device and opens the task entry screen. They enter the task in the text box and click the submit button. For example, they might enter, "I want to think about how to enter a new market."

[0066] Step 2:

[0067] The terminal sends the assignment data entered by the user to the server in text format.

[0068] Step 3:

[0069] The server receives the submitted problem data and passes it to a natural language processing (NLP) module, which analyzes and extracts key elements. For example, "new market" and "entry method" are extracted.

[0070] Step 4:

[0071] The server sends a request for solution generation to the multi-perspective generation module based on the extracted elements.

[0072] Step 5:

[0073] The server's multi-perspective generation module accesses the database and starts generating solutions from different perspectives:

[0074] Cultural perspective: Solutions based on specific cultural backgrounds, such as "strengthening social media advertising"

[0075] Job-specific perspective: Solutions based on specific job roles, e.g., "strengthening market research"

[0076] Specialist perspective: Solutions based on a specific area of ​​expertise, e.g., "hosting a webinar"

[0077] Step 6:

[0078] The server passes the generated solutions to a logical validation module, which evaluates the effectiveness and feasibility of each solution.

[0079] Step 7:

[0080] The server uses an AI expert module to conduct a virtual discussion and select the optimal solution, for example, "strengthening social media advertising and combining it with market research."

[0081] Step 8:

[0082] The server sends the evaluated optimal solution to the user terminal, which displays the solution on a solution display screen.

[0083] Step 9:

[0084] The user can view the solutions displayed on the terminal, select the solution they think is appropriate, and implement it.

[0085] Example 1

[0086] 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."

[0087] Conventional problem-solving support systems often provide solutions based on a specific perspective or limited information, making it difficult to obtain solutions that reflect multiple perspectives or input from different fields of expertise. Furthermore, they lack the functionality to logically verify the effectiveness and feasibility of solutions, making it impossible to provide effective solutions for users. Therefore, there is a need for a system that allows users to efficiently and effectively obtain solutions from multiple perspectives.

[0088] 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.

[0089] In this invention, the server includes means for transmitting a problem input by a user to the server, means for the server to pass the received problem data to a natural language processing module and extract key elements, means for the server to send a request for solution generation to a multi-perspective generation module based on the extracted elements, means for the server to access a database and acquire related information from the perspectives of different cultures, fields of expertise, and occupations, means for the server to generate solutions from multiple perspectives based on the acquired information, means for the server to pass the generated solutions to a logical verification module and evaluate the optimal solution, means for the server to transmit the evaluated solution to the user terminal, and means for the user terminal to display the received solution. This enables the server to analyze from multiple perspectives and efficiently and effectively provide the user with an optimal solution that has been logically verified.

[0090] "User" refers to the entity that uses the system and inputs tasks.

[0091] "Terminal" refers to a device used by a user, which inputs and transmits tasks and displays solutions.

[0092] "Server" refers to a central processing unit that receives data sent from terminals, analyzes them, and generates and evaluates solutions.

[0093] "Natural language processing module" refers to a software component that analyzes received text data and extracts key elements.

[0094] The "multi-perspective generation module" refers to a software component that obtains relevant information from different cultural, professional, and occupational perspectives and generates solutions.

[0095] "Database" refers to a data storage system that stores information about different cultures, professions, and occupations and makes that information available when needed.

[0096] "Logical Verification Module" refers to a software component that evaluates the effectiveness and feasibility of generated solutions.

[0097] "Expert Module" refers to a software component that has expertise in a particular domain and virtually participates in the evaluation of solutions.

[0098] "Solution" refers to a specific approach or method to the problem entered by the user.

[0099] "Evaluation" refers to the process of examining the effectiveness and feasibility of the generated solutions and selecting the most suitable solution.

[0100] This invention is a system that analyzes a problem entered by a user from multiple perspectives and provides an effective and efficient solution. This system includes a terminal, a server, a natural language processing module, a multiple perspective generation module, a logical verification module, an expert module, and a database.

[0101] The user logs in to the device and enters the problem they want to solve in the text box on the problem input screen. Then, by clicking the send button, the problem data is sent to the server. For example, a user might enter "I want to think about how to enter a new market" and send it.

[0102] The server receives the problem data sent from the device and analyzes it using a natural language processing (NLP) module. This analysis extracts the main elements of the problem. For example, the keyword "new market" may be extracted.

[0103] Next, the server sends a solution generation request to the multi-perspective generation module based on the extracted elements. This module accesses a database to obtain relevant information from different cultural, professional, and occupational perspectives. It then generates solutions from each perspective. Specifically, the cultural perspective generates "proposals to enhance social media advertising in a specific cultural context."

[0104] The generated solutions are passed to the logical verification module by the server. This module collaborates with multiple expert modules to virtually discuss and evaluate the effectiveness and feasibility of each solution. As a result, the most effective solution is selected. For example, "combining strengthened social media advertising with market research" is evaluated as optimal.

[0105] The server sends the evaluated optimal solution to the user's terminal, which then displays the received solution to the user, who can then select an action based on the presented solution.

[0106] As an example of a specific prompt sentence, if a user inputs "I want to think about how to enter a new market," the server will receive and analyze it, retrieve information from the database, generate solutions from multiple perspectives, verify them logically, and send the optimal solution to the user's device.

[0107] This system allows users to efficiently obtain effective solutions that have been analyzed from multiple perspectives.

[0108] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0109] Step 1: Assignment entry

[0110] The user logs in to the device. The user enters the problem they want to solve in the text box displayed on the problem input screen. For example, the user might enter "I want to think about how to enter a new market." Once the input is complete, the user clicks the send button, and the problem data is sent to the server.

[0111] Input: Problem text such as "I want to think about how to enter a new market"

[0112] Output: Issue data sent to the server

[0113] Step 2: Analyze the issue information

[0114] The server receives the problem data sent from the device. It then passes the problem data to a natural language processing (NLP) module, which analyzes and extracts key elements. This process extracts keywords such as "new market" and "entry method."

[0115] Input: Assignment data received from the device

[0116] Output: Key elements analyzed (e.g., "New market" and "Entry method")

[0117] Step 3: Generate solutions from multiple perspectives

[0118] Based on the extracted elements, the server sends a request for solution generation to the multi-perspective generation module. The module accesses the database to obtain relevant information from the perspectives of different cultures, fields of expertise, and occupations. Solutions are generated from each perspective, and from the cultural perspective, for example, a specific solution such as "proposing strengthening social media advertising in a specific cultural context" is generated.

[0119] Input: Parsed key elements

[0120] Output: Multiple solutions generated from different perspectives (e.g., social media advertising reinforcement from a cultural perspective)

[0121] Step 4: Logical verification and solution selection

[0122] The server passes the generated solutions to the logical verification module, which collaborates with multiple expert modules to virtually discuss and evaluate the effectiveness and feasibility of each solution. For example, the optimal solution may be selected as "strengthening social media advertising and conducting market research."

[0123] Input: Multiple generated solutions

[0124] Output: Evaluated optimal solution (e.g., strengthening social media advertising and combining it with market research)

[0125] Step 5: Providing a solution

[0126] The server sends the evaluated optimal solution to the user's device. The device displays the received solution in an easy-to-read format for the user. The user can then choose an action based on the displayed solution. For example, the device screen might say, "Strengthen social media advertising and conduct thorough market research."

[0127] Input: Evaluated optimal solution

[0128] Output: Solution displayed in terminal

[0129] In this way, the system analyzes the problem entered by the user from multiple perspectives and efficiently provides the optimal solution.

[0130] (Application example 1)

[0131] 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."

[0132] Improving production efficiency and troubleshooting are important issues on factory floors, but it is often difficult to find effective solutions immediately on site. In particular, there are limited means to quickly obtain approaches from multiple fields of expertise and perspectives, which makes it difficult for on-site workers to make appropriate decisions. To solve this problem, a system that can quickly provide solutions from multiple perspectives through devices that can be easily used on-site is needed.

[0133] 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.

[0134] In this invention, the server includes means for transmitting a problem input by a user to the server, means for the server to pass the received problem data to a natural language processing module and extract key elements, means for the server to send a request for solution generation to a multi-perspective generation module based on the extracted elements, means for the server to generate solutions from multiple perspectives, means for the server to pass the generated solutions to a logical verification module and evaluate the optimal solution, means for the server to transmit the evaluated solutions to the user terminal, and means for inputting on-site problems using a wearable device or a mobile information terminal and displaying solutions from the server. This enables immediate on-site problem input and rapid presentation of solutions from multi-perspectives.

[0135] A "user terminal" is an electronic device that allows a user to input tasks, and includes smartphones, tablets, personal computers, etc.

[0136] A "server" is a central computer that receives assignment data sent from user terminals and analyzes and processes them.

[0137] The "natural language processing module" is a software module that analyzes the text of assignment data within the server and extracts key elements.

[0138] The "multi-perspective generation module" is a module that generates solutions from different perspectives and fields based on the extracted elements.

[0139] The "logical verification module" is a module for evaluating the effectiveness and feasibility of multiple generated solutions.

[0140] An "AI expert module" is an artificial intelligence module that has a knowledge base specialized in a specific field and virtually debates.

[0141] The "database" is a collection of information accessed by the multi-perspective generation module, and contains information on different cultures, fields of expertise, and occupations.

[0142] "Wearable devices" are electronic devices worn by field workers, including smart glasses and head-mounted displays.

[0143] A "personal digital assistant" is a portable electronic device, including a smartphone or tablet.

[0144] This invention is a system that supports efficient and effective problem-solving in factories by allowing users to input any problem and then having a server analyze it from multiple perspectives and generate solutions. This system includes a user terminal, a server, a natural language processing module, a multiple perspective generation module, a logical verification module, an AI expert module, and a database.

[0145] Components

[0146] 1. User Device

[0147] A user terminal is an electronic device that allows a user to input tasks, and includes a smartphone, tablet, PC, etc.

[0148] Field workers use wearable devices or mobile information terminals to input on-site problems, and solutions are displayed from the server.

[0149] 2. Server

[0150] The server is a central computer that receives the assignment data sent from the user terminal and analyzes and processes it.

[0151] 3. Natural Language Processing Module

[0152] The natural language processing module is a software module that analyzes the text of the assignment data on the server and extracts key elements. Specifically, it uses tools such as SpaCy and NLTK.

[0153] 4. Multi-perspective generation module

[0154] The multi-perspective generation module is a module that generates solutions from different perspectives and fields based on the extracted elements. An example of a generative AI model is GPT-3.

[0155] 5. Logical Verification Module

[0156] The logical verification module is a module for evaluating the effectiveness and feasibility of the generated solutions.

[0157] 6. AI Expert Module

[0158] An AI expert module is an artificial intelligence module that has a knowledge base specialized in a specific field and can hold virtual discussions.

[0159] 7. Database

[0160] The database is a collection of information that the multi-perspective generation module accesses, and contains information on different cultures, fields of expertise, and occupations.

[0161] System Operation Details

[0162] On-site users input their issues, such as "I want to solve the bottleneck on the production line," using a smartphone or head-mounted display. The input issue is sent to the server and analyzed by a natural language processing module. Here, key elements are extracted, and keywords such as "production line" and "bottleneck" are obtained.

[0163] Based on these keywords, the server sends a request for solution generation to the multi-perspective generation module. The multi-perspective generation module retrieves information on different cultures, fields of expertise, and occupations from a database and generates solutions using a generative AI model. For example, it may suggest "optimizing robot movements" or "introducing parallel work."

[0164] The generated solutions are evaluated by a logical verification module and multiple AI expert modules to select the most effective and feasible solution, which is then sent from the server to the user's device and presented to the on-site worker.

[0165] Examples and prompts

[0166] Example: A field worker voice-inputs, "I want to solve the bottleneck on the production line," and the solution to the problem is presented: "Optimize the robot's operation and introduce parallel work."

[0167] Example prompt sentence:

[0168] "X part of the production line is a bottleneck. Please suggest a solution to improve efficiency."

[0169] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0170] Step 1:

[0171] The user inputs the issue on-site.

[0172] Input: The user uses a smartphone or head-mounted display to input voice or text, such as "I want to solve the bottleneck on the production line."

[0173] Specific operation: The device receives the challenge and sends it to the server.

[0174] Step 2:

[0175] The terminal transmits the input assignment data to the server.

[0176] Input: User issue data.

[0177] Output: The issue data sent to the server.

[0178] Specific operation: The terminal sends the assignment data to the server as an HTTP request.

[0179] Step 3:

[0180] The server passes the received assignment data to a natural language processing module, which extracts key elements.

[0181] Input: The issue data sent to the server.

[0182] Output: Extracted key elements (e.g. "production line", "bottleneck").

[0183] How it works: The server uses natural language processing libraries such as SpaCy or NLTK to tokenize the issue data and extract key keywords.

[0184] Step 4:

[0185] The server sends a request for solution generation to the multi-perspective generation module based on the extracted elements.

[0186] Input: Extracted key elements.

[0187] Output: A request for solution generation.

[0188] Specific operation: The server sends a request including the extracted main elements to the multi-perspective generation module.

[0189] Step 5:

[0190] The multi-perspective generation module uses a generative AI model to generate solutions from multiple perspectives.

[0191] Input: Solution generation request.

[0192] Output: Multiple solutions (e.g., "optimize the robot's behavior," "introduce parallel work").

[0193] Specific operation: The multi-perspective generation module retrieves relevant information from the database and generates a solution using a generative AI model (e.g., GPT-3).

[0194] Step 6:

[0195] The server passes the generated solutions to a logical validation module to evaluate the best solution.

[0196] Input: Multiple solutions.

[0197] Output: The solution that is evaluated as optimal.

[0198] Specific operation: The logical verification module conducts a virtual discussion with the AI ​​expert module to select the optimal solution.

[0199] Step 7:

[0200] The server transmits the evaluated optimal solution to the user terminal.

[0201] Input: The solution that was evaluated as optimal.

[0202] Output: The solution sent to the user's device.

[0203] Specific operation: The server sends the optimal solution to the user terminal as an HTTP response.

[0204] 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.

[0205] This invention is a system in which a user inputs any problem, a server analyzes it from multiple perspectives, generates solutions, and then uses an emotion engine to recognize the user's emotions and present appropriate solutions. This system includes a terminal, a server, a natural language processing module, a multiple perspective generation module, a logical verification module, an AI expert module, a database, and an emotion engine.

[0206] System configuration and processing flow

[0207] 1. Assignment input

[0208] The user logs in to the device and opens the task input screen. They enter the task in the text box and click the submit button. For example, they might enter "I want to think about how to enter a new market." Once the input is complete, the emotion data is sent to the server along with the task data.

[0209] 2. Analysis of task information and emotion data

[0210] The server receives task data and emotion data sent from the user's device. A natural language processing (NLP) module analyzes the task text data and extracts key elements. For example, keywords such as "new market" and "entry methods" are extracted. At the same time, an emotion engine analyzes the sent emotion data and recognizes the user's current emotional state.

[0211] 3. Solution generation from multiple perspectives

[0212] Based on the extracted elements and emotion data, the server sends a request for solution generation to the multi-perspective generation module, which accesses a database to obtain relevant information from different cultures, fields of expertise, and occupations. It then generates solutions from each perspective.

[0213] Cultural perspective: Solutions based on specific cultural backgrounds, such as "strengthening social media advertising"

[0214] Specialist perspective: For example, "Hosting webinars" from the technology field

[0215] Job perspective: For example, "Strengthening market research" from the marketing field

[0216] 4. Adjusting the solution to take sentiment data into account

[0217] When generating solutions, the emotion engine adjusts the priority and content of proposed solutions based on the user's emotional state. For example, if the user is feeling anxious, more detailed and reassuring solutions will be given priority.

[0218] 5. Logical verification and solution selection

[0219] The server passes the generated solutions to a logical verification module, which, in collaboration with multiple AI expert modules, evaluates the effectiveness and feasibility of each solution, ultimately selecting the most effective solution.

[0220] 6. Providing a solution

[0221] The server sends the evaluated optimal solution to the user's terminal. The terminal displays the received solution on the solution display screen. The user can select an action based on the proposed solution.

[0222] Specific examples

[0223] 1. User input:

[0224] The user inputs a problem such as "I want to think about how to enter a new market" and submits it. At the same time, emotional data collected using cameras and sensors is also submitted.

[0225] 2. Analysis of task information and emotion data:

[0226] The server's natural language processing module extracts "new markets" and "entry methods." At the same time, the emotion engine analyzes the user's emotion as "anxiety."

[0227] 3. Solution generation from multiple perspectives:

[0228] The server's multifaceted perspective generation module generates the following: strengthening social media advertising (cultural perspective), hosting web seminars (professional field perspective), and strengthening market research (occupation perspective).

[0229] 4. Adjustments based on emotional data:

[0230] Because users feel "anxious," the priority is given to "strengthening market research," which is more detailed and gives a sense of security.

[0231] 5. Logical verification and solution selection:

[0232] The server's logical verification module virtually discusses the issue and concludes that the optimal solution is to "strengthen social media advertising and combine it with market research."

[0233] 6. Propose a solution:

[0234] The server sends the evaluated solutions to the device, which then displays the message "Strengthen social media advertising and conduct thorough market research." The user can then take action based on these solutions.

[0235] In this way, the system of the present invention analyzes the problem entered by the user from multiple perspectives and uses an emotion engine to provide an optimal solution that takes the user's emotions into consideration, thereby solving the problem efficiently and effectively.

[0236] The processing flow will be explained below.

[0237] Step 1:

[0238] The user logs in to the device and opens the task entry screen. They enter their task in the text box and click the submit button. For example, they enter, "I want to think about how to enter a new market." At the same time, emotion data collected by cameras and sensors is also collected on the device.

[0239] Step 2:

[0240] The device sends the task data and emotional data entered by the user to the server. The task data is sent in text format, and the emotional data is sent as sensor data such as facial expressions and voice tones.

[0241] Step 3:

[0242] The server receives the submitted problem data and emotion data. A natural language processing (NLP) module analyzes the text data of the problem and extracts key elements (e.g., "new market" and "entry method"), while an emotion engine analyzes the submitted emotion data and recognizes the user's current emotional state (e.g., "anxiety").

[0243] Step 4:

[0244] The server sends a request for solution generation to the multi-perspective generation module based on the extracted elements and emotion data. This request includes the main elements and the user's emotion information.

[0245] Step 5:

[0246] The server's multi-perspective generation module accesses the database and starts generating solutions from different perspectives:

[0247] Cultural perspective: Solutions based on specific cultural backgrounds, such as "strengthening social media advertising"

[0248] Specialist perspective: "Hosting a web seminar" from the technology field

[0249] Occupational perspective: "Strengthening market research" from the marketing field

[0250] Step 6:

[0251] The server's multifaceted perspective generation module takes into account the emotional data obtained from the emotion engine and adjusts the priority and content of the solution proposals. If the user feels "anxious," it will focus on "strengthening market research" to provide more reassurance.

[0252] Step 7:

[0253] The server passes the generated solutions to a logical verification module, which, in collaboration with multiple AI expert modules, evaluates the effectiveness and feasibility of each solution.

[0254] Step 8:

[0255] The server's logical verification module uses an AI expert module to conduct virtual discussions and select the optimal solution. For example, it may determine that "strengthening social media advertising and combining market research" is optimal.

[0256] Step 9:

[0257] The server sends the evaluated optimal solution to the user's device, which displays it on the solution display screen and presents the specific solution, "Strengthen social media advertising and conduct thorough market research."

[0258] Step 10:

[0259] Users can browse the solutions displayed on their device, select the ones they think are appropriate, and then implement them, such as strengthening market research and starting a social media advertising campaign.

[0260] Example 2

[0261] 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."

[0262] Modern society demands fast and accurate solutions to complex and diverse problems. However, the effectiveness of solutions is often limited due to the difficulty of responding flexibly to the emotions and circumstances of individual users. Another problem is a lack of resources and expertise to conduct analyses from multiple perspectives. To solve these problems, a system is needed that can approach users' problems from multiple perspectives and simultaneously provide optimized solutions that take the user's emotions into account.

[0263] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0264] In this invention, the server includes means for transmitting a problem input by a user to the server, means for the server to pass the received problem data to a natural language processing module and extract key elements, means for the server to send a request for solution generation to a multi-faceted perspective generation module based on the extracted elements, means for the server to send the extracted solution to an emotion engine for adjusting it taking into account emotion data, means for the server to pass the adjusted solution to a logical verification module and evaluate the optimal solution, and means for the server to send the evaluated solution to the user terminal. This makes it possible to provide an optimal solution that takes into account multi-faceted perspectives and the user's emotions.

[0265] "User" refers to an individual or organization that uses the system to enter challenges and receive solutions.

[0266] "Device" refers to the device (e.g., PC, smartphone, tablet) used by a user to enter a challenge and receive a solution.

[0267] "Server" refers to a computer system that receives data sent from users, analyzes the problem, generates, evaluates, and adjusts solutions using various modules, and finally sends the solutions to the user terminal.

[0268] "Natural language processing module" refers to a software module that has the function of analyzing the text data of assignments submitted by users and extracting key elements.

[0269] A "multi-perspective generation module" refers to a software module that has the function of generating solutions from the perspectives of different cultures, fields of expertise, occupations, etc. based on the extracted elements of the problem.

[0270] "Emotion engine" refers to a software module that has the function of analyzing a user's emotional data and using it to adjust the generated solution.

[0271] "Logical verification module" refers to a software module that has the function of evaluating the effectiveness and feasibility of the generated solution.

[0272] "AI Expert Module" refers to a software module that allows multiple virtual experts to discuss and participate in the evaluation of each solution.

[0273] "Database" refers to a data storage system that stores information about different cultures, fields of expertise, and occupations, and from which the multi-perspective generation module can retrieve information.

[0274] "Solution display screen" refers to an interface that displays solutions on a user terminal and allows the user to select an action based on the solutions.

[0275] This invention is a system in which a user inputs any problem, a server analyzes it from multiple perspectives, generates solutions, and then uses an emotion engine to recognize the user's emotions and present appropriate solutions. This system includes a terminal, a server, a natural language processing module, a multiple perspective generation module, a logical verification module, an AI expert module, a database, and an emotion engine.

[0276] First, the user logs in to the device and accesses the problem entry screen. There, they enter their problem in the text box and click the submit button. For example, they might enter, "I want to think about how to enter a new market." At this stage, the user's emotional data is also collected. The device then sends the problem data and emotional data to the server.

[0277] The server receives the task data and emotion data sent from the user's device. The server's natural language processing (NLP) module analyzes the task text data and extracts key elements. For example, keywords such as "new market" and "entry method" are extracted. At the same time, the emotion engine analyzes the emotion data and recognizes the user's current emotional state.

[0278] Based on the extracted elements and emotion data, the server sends a request for solution generation to the multi-perspective generation module. This module accesses a database to obtain relevant information from different cultures, fields of expertise, and occupations. It then generates solutions from each perspective. For example, solutions such as "strengthen social media advertising" from the cultural perspective, "host webinars" from the professional perspective, and "strengthen market research" from the occupation perspective may be generated.

[0279] The server's emotion engine adjusts the priority and content of generated solutions based on the user's emotional state. For example, if the user is feeling anxious, detailed and reassuring solutions will be prioritized. This provides the best solution for the user's situation.

[0280] The server passes the generated solutions to a logical verification module, which, in collaboration with multiple AI expert modules, evaluates the effectiveness and feasibility of each solution, ultimately selecting the most effective solution.

[0281] The server sends the evaluated optimal solution to the user's terminal, which displays it on the solution display screen. The user can then select an action based on the proposed solution.

[0282] Specific examples

[0283] User input:

[0284] The user inputs a problem such as "I want to think about how to enter a new market" and submits it. At the same time, emotional data collected using cameras and sensors is also submitted.

[0285] Task information and emotion data analysis:

[0286] The server's natural language processing module extracts "new markets" and "entry methods." At the same time, the emotion engine analyzes the user's emotion as "anxiety."

[0287] Multi-perspective solution generation:

[0288] The server's multifaceted perspective generation module generates the following: strengthening social media advertising (cultural perspective), hosting web seminars (professional field perspective), and strengthening market research (occupation perspective).

[0289] Adjustments based on sentiment data:

[0290] Because users feel "anxious," the priority is given to "strengthening market research," which is more detailed and gives a sense of security.

[0291] Logical verification and solution selection:

[0292] The server's logical verification module virtually discusses the issue and concludes that the optimal solution is to "strengthen social media advertising and combine it with market research."

[0293] Solution suggestion:

[0294] The server sends the evaluated solutions to the device, which then displays a message on the screen saying, "Strengthen social media advertising and conduct thorough market research." The user then begins to take action based on these solutions.

[0295] Prompt Sentence Examples

[0296] "I'd like to think about how to enter a new market. Currently, many members of my company are feeling uneasy about entering the market. Taking this situation into consideration, could you please tell me an effective way to do so?"

[0297] In this way, this system can solve problems efficiently and effectively by analyzing problems from multiple perspectives based on user input and providing optimal solutions that take emotions into account.

[0298] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0299] Step 1:

[0300] A user logs in to a device and opens the task input screen. The user enters the task in the text box and clicks the submit button. For example, the user might enter, "I want to think about how to enter a new market." The input data also includes the user's emotional data.

[0301] Specific behavior:

[0302] The user enters an issue.

[0303] The user clicks the submit button.

[0304] The device transmits the task data and emotion data to the server.

[0305] input:

[0306] Assignment text (e.g., "I want to think about how to enter a new market.")

[0307] Emotional data (user facial expressions, voice, etc.)

[0308] output:

[0309] The task data and emotion data are sent to the server.

[0310] Step 2:

[0311] The server receives the task data and emotion data sent from the user's device. A natural language processing (NLP) module analyzes the task text data and extracts key elements. For example, keywords such as "new market" and "entry methods" are extracted.

[0312] At the same time, the emotion engine analyzes the emotion data and recognizes the user's current emotional state.

[0313] Specific behavior:

[0314] The server receives the data.

[0315] The NLP module extracts keywords from the text data.

[0316] The emotion engine analyzes the emotion data and recognizes the emotional state.

[0317] input:

[0318] Issue data and emotion data.

[0319] output:

[0320] Extracted keywords.

[0321] The perceived emotional state of the user.

[0322] Step 3:

[0323] Based on the extracted elements and emotion data, the server sends a request for solution generation to the multi-perspective generation module, which accesses a database to obtain relevant information from different cultures, fields of expertise, and occupations. It then generates solutions from each perspective.

[0324] Specific behavior:

[0325] The server sends the request.

[0326] The multi-perspective generation module accesses the database and retrieves relevant information.

[0327] Generate solutions from each perspective.

[0328] input:

[0329] Extracted keywords.

[0330] The perceived emotional state of the user.

[0331] output:

[0332] Solutions from different perspectives (e.g., cultural perspective, disciplinary perspective, occupational perspective).

[0333] Step 4:

[0334] The server uses an emotion engine to tailor the generated solutions based on the user's emotional state: for example, if the user is feeling anxious, detailed and reassuring solutions are preferred.

[0335] Specific behavior:

[0336] The emotion engine reanalyzes the emotion data.

[0337] Adjust the priority and content of solutions.

[0338] input:

[0339] Generated solution.

[0340] The perceived emotional state of the user.

[0341] output:

[0342] Coordinated solutions.

[0343] Step 5:

[0344] The server passes the generated solutions to a logical verification module, which, in collaboration with multiple AI expert modules, evaluates the effectiveness and feasibility of each solution. As a result of the evaluation, the optimal solution is selected.

[0345] Specific behavior:

[0346] The logical verification module receives the solution.

[0347] An AI expert module evaluates each solution.

[0348] Select the best solution.

[0349] input:

[0350] Coordinated solutions.

[0351] output:

[0352] The best solution evaluated.

[0353] Step 6:

[0354] The server sends the evaluated optimal solution to the user's terminal, which displays the received solution on a solution display screen, allowing the user to select an action based on the proposed solution.

[0355] Specific behavior:

[0356] The server sends the best solution.

[0357] The device will display the solution.

[0358] The user chooses an action based on the solution.

[0359] input:

[0360] The best solution evaluated.

[0361] output:

[0362] The solution will be displayed on the device.

[0363] (Application example 2)

[0364] 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."

[0365] Currently, supervisors in the operation and management of factory robots often face complex challenges, making it difficult to find quick and accurate solutions. Furthermore, because the appropriate solution varies depending on the supervisor's emotions and the situation, flexible responses tailored to individual situations are required. This can lead to reduced labor efficiency and adversely affect productivity. The present invention aims to solve these problems and provide a system that allows supervisors to quickly find appropriate solutions in the operation and management of factory robots.

[0366] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0367] In this invention, the server includes means for transmitting a problem input by a user to a terminal to the server, means for the server to pass the received problem data to a natural language processing module and extract key elements, means for the server to send a request for solution generation to a multi-perspective generation module based on the extracted elements and emotion data, means for the server to generate solutions from multiple perspectives, means for the server to adjust the generated solutions in consideration of the emotion data, means for the server to adjust the solutions based on the emotion data and pass them to a logical verification module to evaluate the optimal solution, and means for the server to transmit the evaluated solutions to the user terminal. This makes it possible to provide supervisors with quick and appropriate solutions based on multi-perspectives and emotion data for complex problems they face.

[0368] "Tasks input by users to terminals" refers to problems or questions input to the terminal devices used by users.

[0369] "Means for sending to the server" refers to a device or program that has the function of transmitting the assignment entered by the user into the terminal to the server.

[0370] "Natural Language Processing Module" means software used to analyze submitted assignment data and extract key elements and keywords from the text.

[0371] "Key Elements" refers to the most important keywords or phrases in the submitted assignment.

[0372] "Emotion data" refers to information that identifies the user's emotional state and expresses it in a data format.

[0373] The "multi-perspective generation module" refers to software for generating solutions from different perspectives based on extracted key elements and emotional data.

[0374] "Solution generation request" refers to the act of the server sending a request to generate a solution to the multi-perspective generation module.

[0375] "Means for the server to generate solutions from multiple perspectives" refers to devices or programs that have the functionality to enable the server to generate solutions from the perspectives of different cultures, fields of expertise, occupations, etc.

[0376] "Means for adjusting by taking into account emotional data" refers to a device or program that has the function of adjusting the generated solution based on the emotional state of the user to make it optimal.

[0377] "Logical verification module" refers to software for evaluating the effectiveness and feasibility of generated solutions.

[0378] "AI Expert Module" means a module equipped with an artificial intelligence program with specific expertise.

[0379] The "means for transmitting to the user terminal" refers to a device or program having a function for transmitting the evaluated solution from the server to the terminal device used by the user.

[0380] "Database" means an information management system that stores relevant information and makes it accessible and available as needed.

[0381] The system for implementing this invention begins with a user inputting an operations management issue using a terminal. The server then receives the input issue data and extracts its main elements using a natural language processing module. At this time, an emotion engine analyzes the emotion data and recognizes the user's emotional state.

[0382] The server sends a solution generation request to the multi-perspective generation module based on key elements and emotional data. The multi-perspective generation module generates solutions from different cultural, disciplinary, and professional perspectives and adjusts these solutions based on emotional data. This adjustment may prioritize solutions that are more detailed and reassuring.

[0383] The generated solutions are evaluated for validity and feasibility by a logical verification module. Multiple AI expert modules virtually debate the solutions and ultimately select the optimal solution. This selected solution is then sent to the user's device and displayed.

[0384] Specifically, in the operation and management of factory robots, a supervisor inputs a problem such as "I want to identify the cause of a robot's failure" into a terminal and sends it. At this time, emotional data is also sent, and the server analyzes the data. A natural language processing module extracts keywords such as "robot," "failure," and "cause," and a multifaceted perspective generation module generates solutions. For example, this could include using software to analyze the robot's log data from a technology perspective, or having a specialist technician conduct an on-site inspection from an expert's perspective.

[0385] If the emotion engine recognizes the user's emotion as "anxiety," it prioritizes detailed and reassuring solutions. The logical verification module evaluates the effectiveness of the solutions and sends the optimal solution to the user's device.

[0386] This makes it possible to provide quick and appropriate solutions to the complex challenges faced by supervisors, based on multiple perspectives and emotional data.

[0387] Hardware and software used

[0388] Smartphone / Tablet: Used as an interface for users to enter assignments.

[0389] Server: Processes the issue data and sentiment data.

[0390] Natural Language Processing Module (NLPModule): Analyzes the text data of the assignment and extracts important elements.

[0391] Emotion Engine: Analyzes user emotional data.

[0392] PerspectiveModule: Generates solutions from cultural, disciplinary and professional perspectives and adjusts them based on emotional state.

[0393] Logic Validation Module: Evaluates the effectiveness and feasibility of each solution and selects the optimal solution.

[0394] Prompt Sentence Examples

[0395] "Based on the emotion data you have, propose the optimal solution to the problem input by the supervisor: 'I want to identify the cause of the robot's malfunction.' Consider solutions from the perspectives of culture, specialty, and job type, and provide prioritized solutions taking into account the user's anxieties."

[0396] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0397] Step 1:

[0398] The user inputs a task using the device. For example, the task might be "I want to identify the cause of a robot malfunction." The device then sends the input task data and emotion data acquired from sensors in use to the server.

[0399] Input: Task data, emotion data

[0400] Output: Issue data and sentiment data sent to the server

[0401] Step 2:

[0402] The server passes the received problem data to a natural language processing module, which extracts key elements. The natural language processing module performs text analysis and identifies important keywords and phrases. Key elements such as "robot," "fault," and "cause" are extracted.

[0403] Input: Issue data

[0404] Data processing: Text analysis using natural language processing

[0405] Output: Key Elements

[0406] Step 3:

[0407] The server uses an emotion engine to analyze the received emotion data and identify the user's emotion state, for example, recognizing an "anxiety" state from the emotion data.

[0408] Input: Emotion data

[0409] Data Computation: Emotional State Analysis with Emotion Engine

[0410] Output: User's emotional state

[0411] Step 4:

[0412] The server sends a solution generation request to the multi-perspective generation module based on the extracted key elements and sentiment data. The multi-perspective generation module generates solutions from the perspectives of different cultures, fields of expertise, and occupations, and creates a solution list. For example, it generates "analysis of log data" from the technology perspective and "on-site inspection by engineers" from the expert perspective.

[0413] Input: Primary element, emotional state

[0414] Data Computing: Generating Solutions from Multiple Perspectives

[0415] Output: Solution list

[0416] Step 5:

[0417] The server adjusts the list of solutions based on the emotion data: the emotion engine responds to the "anxiety" state and prioritizes detailed and quick solutions that put the user at ease.

[0418] Input: Solution list, emotional state

[0419] Data processing: Adjusting solution priorities based on sentiment data

[0420] Output: Reconciled solution list

[0421] Step 6:

[0422] The server passes the adjusted solution list to a logical verification module to evaluate its effectiveness and feasibility, and multiple AI expert modules virtually debate and select the optimal solution.

[0423] Input: Reconciled solution list

[0424] Data Computing: Assessing the Effectiveness and Feasibility of Solutions

[0425] Output: Optimal solution

[0426] Step 7:

[0427] The server sends the optimal solution to the user's device, which displays it, allowing the supervisor to take appropriate measures based on the presented solution.

[0428] Input: Optimal solution

[0429] Output: sent to and displayed on the user's terminal

[0430] 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.

[0431] 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.

[0432] 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.

[0433] [Second embodiment]

[0434] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0435] 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.

[0436] 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).

[0437] 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.

[0438] 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.

[0439] 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).

[0440] 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.

[0441] 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.

[0442] 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.

[0443] 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.

[0444] In the smart glasses 214, the 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.

[0445] 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."

[0446] This invention is a system that supports efficient and effective problem solving by allowing a user to input any problem, and then having a server analyze it from multiple perspectives and generate a solution. This system includes a terminal, a server, a natural language processing module, a multiple perspective generation module, a logical verification module, an AI expert module, and a database.

[0447] System configuration and processing flow

[0448] 1. Assignment input

[0449] The user logs in to a terminal that has a problem input screen. The problem input screen has a text box where the user can freely enter the problem they want to solve. For example, "I want to think about how to enter a new market." Once the input is complete, the user clicks the send button and the problem data is sent to the server.

[0450] 2. Analysis of issue information

[0451] The server receives the assignment data sent from the user's device. A natural language processing (NLP) module in the server analyzes the assignment text and extracts key elements. For example, keywords such as "new market" and "entry method" are extracted.

[0452] 3. Solution generation from multiple perspectives

[0453] Based on the extracted elements, the server sends a request for solution generation to the multi-perspective generation module, which accesses the database to obtain relevant information from different cultures, fields of expertise, and occupations, and then generates solutions from each perspective.

[0454] Cultural perspective: Given the effectiveness of web marketing in specific cultural contexts, suggestions are made to strengthen social media advertising.

[0455] Specialist perspective: The technology sector suggests using online platforms to host webinars and promote products and services.

[0456] 4. Logical verification and solution selection

[0457] The server passes the generated solutions to a logical verification module, which collaborates with multiple AI expert modules to virtually discuss the effectiveness and feasibility of each solution, ultimately selecting the most effective solution.

[0458] 5. Providing a solution

[0459] The server sends the evaluated optimal solution to the user's device, which then displays the received solution in an easy-to-read format for the user. The user can then select an action based on the proposed solution.

[0460] Specific examples

[0461] 1. User input:

[0462] The user inputs the problem, "I want to think about how to enter a new market," and submits it.

[0463] 2. Analysis of assignment information:

[0464] The server's natural language processing module extracts "new markets" and "ways to enter the market."

[0465] 3. Solution generation from multiple perspectives:

[0466] The server's multifaceted perspective generation module generates solutions such as strengthening social media advertising (cultural perspective), strengthening market research (profession perspective), and holding web seminars (specialty perspective).

[0467] 4. Logical verification and solution selection:

[0468] The server's logical verification module virtually discusses the issue and determines that strengthening social media advertising and combining it with market research is optimal.

[0469] 5. Propose a solution:

[0470] The server sends the evaluated solutions to the device, which then displays the message on its screen: "Strengthen social media advertising and conduct thorough market research."

[0471] In this way, the system of the present invention analyzes the problem entered by the user from multiple perspectives and provides the optimal solution, thereby solving the problem efficiently and effectively.

[0472] The processing flow will be explained below.

[0473] Step 1:

[0474] The user logs in to the device and opens the task entry screen. They enter the task in the text box and click the submit button. For example, they might enter, "I want to think about how to enter a new market."

[0475] Step 2:

[0476] The terminal sends the assignment data entered by the user to the server in text format.

[0477] Step 3:

[0478] The server receives the submitted problem data and passes it to a natural language processing (NLP) module, which analyzes and extracts key elements. For example, "new market" and "entry method" are extracted.

[0479] Step 4:

[0480] The server sends a request for solution generation to the multi-perspective generation module based on the extracted elements.

[0481] Step 5:

[0482] The server's multi-perspective generation module accesses the database and starts generating solutions from different perspectives:

[0483] Cultural perspective: Solutions based on specific cultural backgrounds, such as "strengthening social media advertising"

[0484] Job-specific perspective: Solutions based on specific job roles, e.g., "strengthening market research"

[0485] Specialist perspective: Solutions based on a specific area of ​​expertise, e.g., "hosting a webinar"

[0486] Step 6:

[0487] The server passes the generated solutions to a logical validation module, which evaluates the effectiveness and feasibility of each solution.

[0488] Step 7:

[0489] The server uses an AI expert module to conduct a virtual discussion and select the optimal solution, for example, "strengthening social media advertising and combining it with market research."

[0490] Step 8:

[0491] The server sends the evaluated optimal solution to the user terminal, which displays the solution on a solution display screen.

[0492] Step 9:

[0493] The user can view the solutions displayed on the terminal, select the solution they think is appropriate, and implement it.

[0494] Example 1

[0495] 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."

[0496] Conventional problem-solving support systems often provide solutions based on a specific perspective or limited information, making it difficult to obtain solutions that reflect multiple perspectives or input from different fields of expertise. Furthermore, they lack the functionality to logically verify the effectiveness and feasibility of solutions, making it impossible to provide effective solutions for users. Therefore, there is a need for a system that allows users to efficiently and effectively obtain solutions from multiple perspectives.

[0497] 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.

[0498] In this invention, the server includes means for transmitting a problem input by a user to the server, means for the server to pass the received problem data to a natural language processing module and extract key elements, means for the server to send a request for solution generation to a multi-perspective generation module based on the extracted elements, means for the server to access a database and acquire related information from the perspectives of different cultures, fields of expertise, and occupations, means for the server to generate solutions from multiple perspectives based on the acquired information, means for the server to pass the generated solutions to a logical verification module and evaluate the optimal solution, means for the server to transmit the evaluated solution to the user terminal, and means for the user terminal to display the received solution. This enables the server to analyze from multiple perspectives and efficiently and effectively provide the user with an optimal solution that has been logically verified.

[0499] "User" refers to the entity that uses the system and inputs tasks.

[0500] "Terminal" refers to a device used by a user, which inputs and transmits tasks and displays solutions.

[0501] "Server" refers to a central processing unit that receives data sent from terminals, analyzes them, and generates and evaluates solutions.

[0502] "Natural language processing module" refers to a software component that analyzes received text data and extracts key elements.

[0503] The "multi-perspective generation module" refers to a software component that obtains relevant information from different cultural, professional, and occupational perspectives and generates solutions.

[0504] "Database" refers to a data storage system that stores information about different cultures, professions, and occupations and makes that information available when needed.

[0505] "Logical Verification Module" refers to a software component that evaluates the effectiveness and feasibility of generated solutions.

[0506] "Expert Module" refers to a software component that has expertise in a particular domain and virtually participates in the evaluation of solutions.

[0507] "Solution" refers to a specific approach or method to the problem entered by the user.

[0508] "Evaluation" refers to the process of examining the effectiveness and feasibility of the generated solutions and selecting the most suitable solution.

[0509] This invention is a system that analyzes a problem entered by a user from multiple perspectives and provides an effective and efficient solution. This system includes a terminal, a server, a natural language processing module, a multiple perspective generation module, a logical verification module, an expert module, and a database.

[0510] The user logs in to the device and enters the problem they want to solve in the text box on the problem input screen. Then, by clicking the send button, the problem data is sent to the server. For example, a user might enter "I want to think about how to enter a new market" and send it.

[0511] The server receives the problem data sent from the device and analyzes it using a natural language processing (NLP) module. This analysis extracts the main elements of the problem. For example, the keyword "new market" may be extracted.

[0512] Next, the server sends a solution generation request to the multi-perspective generation module based on the extracted elements. This module accesses a database to obtain relevant information from different cultural, professional, and occupational perspectives. It then generates solutions from each perspective. Specifically, the cultural perspective generates "proposals to enhance social media advertising in a specific cultural context."

[0513] The generated solutions are passed to the logical verification module by the server. This module collaborates with multiple expert modules to virtually discuss and evaluate the effectiveness and feasibility of each solution. As a result, the most effective solution is selected. For example, "combining strengthened social media advertising with market research" is evaluated as optimal.

[0514] The server sends the evaluated optimal solution to the user's terminal, which then displays the received solution to the user, who can then select an action based on the presented solution.

[0515] As an example of a specific prompt sentence, if a user inputs "I want to think about how to enter a new market," the server will receive and analyze it, retrieve information from the database, generate solutions from multiple perspectives, verify them logically, and send the optimal solution to the user's device.

[0516] This system allows users to efficiently obtain effective solutions that have been analyzed from multiple perspectives.

[0517] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0518] Step 1: Assignment entry

[0519] The user logs in to the device. The user enters the problem they want to solve in the text box displayed on the problem input screen. For example, the user might enter "I want to think about how to enter a new market." Once the input is complete, the user clicks the send button, and the problem data is sent to the server.

[0520] Input: Problem text such as "I want to think about how to enter a new market"

[0521] Output: Issue data sent to the server

[0522] Step 2: Analyze the issue information

[0523] The server receives the problem data sent from the device. It then passes the problem data to a natural language processing (NLP) module, which analyzes and extracts key elements. This process extracts keywords such as "new market" and "entry method."

[0524] Input: Assignment data received from the device

[0525] Output: Key elements analyzed (e.g., "New market" and "Entry method")

[0526] Step 3: Generate solutions from multiple perspectives

[0527] Based on the extracted elements, the server sends a request for solution generation to the multi-perspective generation module. The module accesses the database to obtain relevant information from the perspectives of different cultures, fields of expertise, and occupations. Solutions are generated from each perspective, and from the cultural perspective, for example, a specific solution such as "proposing strengthening social media advertising in a specific cultural context" is generated.

[0528] Input: Parsed key elements

[0529] Output: Multiple solutions generated from different perspectives (e.g., social media advertising reinforcement from a cultural perspective)

[0530] Step 4: Logical verification and solution selection

[0531] The server passes the generated solutions to the logical verification module, which collaborates with multiple expert modules to virtually discuss and evaluate the effectiveness and feasibility of each solution. For example, the optimal solution may be selected as "strengthening social media advertising and conducting market research."

[0532] Input: Multiple generated solutions

[0533] Output: Evaluated optimal solution (e.g., strengthening social media advertising and combining it with market research)

[0534] Step 5: Providing a solution

[0535] The server sends the evaluated optimal solution to the user's device. The device displays the received solution in an easy-to-read format for the user. The user can then choose an action based on the displayed solution. For example, the device screen might say, "Strengthen social media advertising and conduct thorough market research."

[0536] Input: Evaluated optimal solution

[0537] Output: Solution displayed in terminal

[0538] In this way, the system analyzes the problem entered by the user from multiple perspectives and efficiently provides the optimal solution.

[0539] (Application example 1)

[0540] 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."

[0541] Improving production efficiency and troubleshooting are important issues on factory floors, but it is often difficult to find effective solutions immediately on site. In particular, there are limited means to quickly obtain approaches from multiple fields of expertise and perspectives, which makes it difficult for on-site workers to make appropriate decisions. To solve this problem, a system that can quickly provide solutions from multiple perspectives through devices that can be easily used on-site is needed.

[0542] 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.

[0543] In this invention, the server includes means for transmitting a problem input by a user to the server, means for the server to pass the received problem data to a natural language processing module and extract key elements, means for the server to send a request for solution generation to a multi-perspective generation module based on the extracted elements, means for the server to generate solutions from multiple perspectives, means for the server to pass the generated solutions to a logical verification module and evaluate the optimal solution, means for the server to transmit the evaluated solutions to the user terminal, and means for inputting on-site problems using a wearable device or a mobile information terminal and displaying solutions from the server. This enables immediate on-site problem input and rapid presentation of solutions from multi-perspectives.

[0544] A "user terminal" is an electronic device that allows a user to input tasks, and includes smartphones, tablets, personal computers, etc.

[0545] A "server" is a central computer that receives assignment data sent from user terminals and analyzes and processes them.

[0546] The "natural language processing module" is a software module that analyzes the text of assignment data within the server and extracts key elements.

[0547] The "multi-perspective generation module" is a module that generates solutions from different perspectives and fields based on the extracted elements.

[0548] The "logical verification module" is a module for evaluating the effectiveness and feasibility of multiple generated solutions.

[0549] An "AI expert module" is an artificial intelligence module that has a knowledge base specialized in a specific field and virtually debates.

[0550] The "database" is a collection of information accessed by the multi-perspective generation module, and contains information on different cultures, fields of expertise, and occupations.

[0551] "Wearable devices" are electronic devices worn by field workers, including smart glasses and head-mounted displays.

[0552] A "personal digital assistant" is a portable electronic device, including a smartphone or tablet.

[0553] This invention is a system that supports efficient and effective problem-solving in factories by allowing users to input any problem and then having a server analyze it from multiple perspectives and generate solutions. This system includes a user terminal, a server, a natural language processing module, a multiple perspective generation module, a logical verification module, an AI expert module, and a database.

[0554] Components

[0555] 1. User Device

[0556] A user terminal is an electronic device that allows a user to input tasks, and includes a smartphone, tablet, PC, etc.

[0557] Field workers use wearable devices or mobile information terminals to input on-site problems, and solutions are displayed from the server.

[0558] 2. Server

[0559] The server is a central computer that receives the assignment data sent from the user terminal and analyzes and processes it.

[0560] 3. Natural Language Processing Module

[0561] The natural language processing module is a software module that analyzes the text of the assignment data on the server and extracts key elements. Specifically, it uses tools such as SpaCy and NLTK.

[0562] 4. Multi-perspective generation module

[0563] The multi-perspective generation module is a module that generates solutions from different perspectives and fields based on the extracted elements. An example of a generative AI model is GPT-3.

[0564] 5. Logical Verification Module

[0565] The logical verification module is a module for evaluating the effectiveness and feasibility of the generated solutions.

[0566] 6. AI Expert Module

[0567] An AI expert module is an artificial intelligence module that has a knowledge base specialized in a specific field and can hold virtual discussions.

[0568] 7. Database

[0569] The database is a collection of information that the multi-perspective generation module accesses, and contains information on different cultures, fields of expertise, and occupations.

[0570] System Operation Details

[0571] On-site users input their issues, such as "I want to solve the bottleneck on the production line," using a smartphone or head-mounted display. The input issue is sent to the server and analyzed by a natural language processing module. Here, key elements are extracted, and keywords such as "production line" and "bottleneck" are obtained.

[0572] Based on these keywords, the server sends a request for solution generation to the multi-perspective generation module. The multi-perspective generation module retrieves information on different cultures, fields of expertise, and occupations from a database and generates solutions using a generative AI model. For example, it may suggest "optimizing robot movements" or "introducing parallel work."

[0573] The generated solutions are evaluated by a logical verification module and multiple AI expert modules to select the most effective and feasible solution, which is then sent from the server to the user's device and presented to the on-site worker.

[0574] Examples and prompts

[0575] Example: A field worker voice-inputs, "I want to solve the bottleneck on the production line," and the solution to the problem is presented: "Optimize the robot's operation and introduce parallel work."

[0576] Example prompt sentence:

[0577] "X part of the production line is a bottleneck. Please suggest a solution to improve efficiency."

[0578] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0579] Step 1:

[0580] The user inputs the issue on-site.

[0581] Input: The user uses a smartphone or head-mounted display to input voice or text, such as "I want to solve the bottleneck on the production line."

[0582] Specific operation: The device receives the challenge and sends it to the server.

[0583] Step 2:

[0584] The terminal transmits the input assignment data to the server.

[0585] Input: User issue data.

[0586] Output: The issue data sent to the server.

[0587] Specific operation: The terminal sends the assignment data to the server as an HTTP request.

[0588] Step 3:

[0589] The server passes the received assignment data to a natural language processing module, which extracts key elements.

[0590] Input: The issue data sent to the server.

[0591] Output: Extracted key elements (e.g. "production line", "bottleneck").

[0592] How it works: The server uses natural language processing libraries such as SpaCy or NLTK to tokenize the issue data and extract key keywords.

[0593] Step 4:

[0594] The server sends a request for solution generation to the multi-perspective generation module based on the extracted elements.

[0595] Input: Extracted key elements.

[0596] Output: A request for solution generation.

[0597] Specific operation: The server sends a request including the extracted main elements to the multi-perspective generation module.

[0598] Step 5:

[0599] The multi-perspective generation module uses a generative AI model to generate solutions from multiple perspectives.

[0600] Input: Solution generation request.

[0601] Output: Multiple solutions (e.g., "optimize the robot's behavior," "introduce parallel work").

[0602] Specific operation: The multi-perspective generation module retrieves relevant information from the database and generates a solution using a generative AI model (e.g., GPT-3).

[0603] Step 6:

[0604] The server passes the generated solutions to a logical validation module to evaluate the best solution.

[0605] Input: Multiple solutions.

[0606] Output: The solution that is evaluated as optimal.

[0607] Specific operation: The logical verification module conducts a virtual discussion with the AI ​​expert module to select the optimal solution.

[0608] Step 7:

[0609] The server transmits the evaluated optimal solution to the user terminal.

[0610] Input: The solution that was evaluated as optimal.

[0611] Output: The solution sent to the user's device.

[0612] Specific operation: The server sends the optimal solution to the user terminal as an HTTP response.

[0613] 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.

[0614] This invention is a system in which a user inputs any problem, a server analyzes it from multiple perspectives, generates solutions, and then uses an emotion engine to recognize the user's emotions and present appropriate solutions. This system includes a terminal, a server, a natural language processing module, a multiple perspective generation module, a logical verification module, an AI expert module, a database, and an emotion engine.

[0615] System configuration and processing flow

[0616] 1. Assignment input

[0617] The user logs in to the device and opens the task input screen. They enter the task in the text box and click the submit button. For example, they might enter "I want to think about how to enter a new market." Once the input is complete, the emotion data is sent to the server along with the task data.

[0618] 2. Analysis of task information and emotion data

[0619] The server receives task data and emotion data sent from the user's device. A natural language processing (NLP) module analyzes the task text data and extracts key elements. For example, keywords such as "new market" and "entry methods" are extracted. At the same time, an emotion engine analyzes the sent emotion data and recognizes the user's current emotional state.

[0620] 3. Solution generation from multiple perspectives

[0621] Based on the extracted elements and emotion data, the server sends a request for solution generation to the multi-perspective generation module, which accesses a database to obtain relevant information from different cultures, fields of expertise, and occupations. It then generates solutions from each perspective.

[0622] Cultural perspective: Solutions based on specific cultural backgrounds, such as "strengthening social media advertising"

[0623] Specialist perspective: For example, "Hosting webinars" from the technology field

[0624] Job perspective: For example, "Strengthening market research" from the marketing field

[0625] 4. Adjusting the solution to take sentiment data into account

[0626] When generating solutions, the emotion engine adjusts the priority and content of proposed solutions based on the user's emotional state. For example, if the user is feeling anxious, more detailed and reassuring solutions will be given priority.

[0627] 5. Logical verification and solution selection

[0628] The server passes the generated solutions to a logical verification module, which, in collaboration with multiple AI expert modules, evaluates the effectiveness and feasibility of each solution, ultimately selecting the most effective solution.

[0629] 6. Providing a solution

[0630] The server sends the evaluated optimal solution to the user's terminal. The terminal displays the received solution on the solution display screen. The user can select an action based on the proposed solution.

[0631] Specific examples

[0632] 1. User input:

[0633] The user inputs a problem such as "I want to think about how to enter a new market" and submits it. At the same time, emotional data collected using cameras and sensors is also submitted.

[0634] 2. Analysis of task information and emotion data:

[0635] The server's natural language processing module extracts "new markets" and "entry methods." At the same time, the emotion engine analyzes the user's emotion as "anxiety."

[0636] 3. Solution generation from multiple perspectives:

[0637] The server's multifaceted perspective generation module generates the following: strengthening social media advertising (cultural perspective), hosting web seminars (professional field perspective), and strengthening market research (occupation perspective).

[0638] 4. Adjustments based on emotional data:

[0639] Because users feel "anxious," the priority is given to "strengthening market research," which is more detailed and gives a sense of security.

[0640] 5. Logical verification and solution selection:

[0641] The server's logical verification module virtually discusses the issue and concludes that the optimal solution is to "strengthen social media advertising and combine it with market research."

[0642] 6. Propose a solution:

[0643] The server sends the evaluated solutions to the device, which then displays the message "Strengthen social media advertising and conduct thorough market research." The user can then take action based on these solutions.

[0644] In this way, the system of the present invention analyzes the problem entered by the user from multiple perspectives and uses an emotion engine to provide an optimal solution that takes the user's emotions into consideration, thereby solving the problem efficiently and effectively.

[0645] The processing flow will be explained below.

[0646] Step 1:

[0647] The user logs in to the device and opens the task entry screen. They enter their task in the text box and click the submit button. For example, they enter, "I want to think about how to enter a new market." At the same time, emotion data collected by cameras and sensors is also collected on the device.

[0648] Step 2:

[0649] The device sends the task data and emotional data entered by the user to the server. The task data is sent in text format, and the emotional data is sent as sensor data such as facial expressions and voice tones.

[0650] Step 3:

[0651] The server receives the submitted problem data and emotion data. A natural language processing (NLP) module analyzes the text data of the problem and extracts key elements (e.g., "new market" and "entry method"), while an emotion engine analyzes the submitted emotion data and recognizes the user's current emotional state (e.g., "anxiety").

[0652] Step 4:

[0653] The server sends a request for solution generation to the multi-perspective generation module based on the extracted elements and emotion data. This request includes the main elements and the user's emotion information.

[0654] Step 5:

[0655] The server's multi-perspective generation module accesses the database and starts generating solutions from different perspectives:

[0656] Cultural perspective: Solutions based on specific cultural backgrounds, such as "strengthening social media advertising"

[0657] Specialist perspective: "Hosting a web seminar" from the technology field

[0658] Occupational perspective: "Strengthening market research" from the marketing field

[0659] Step 6:

[0660] The server's multifaceted perspective generation module takes into account the emotional data obtained from the emotion engine and adjusts the priority and content of the solution proposals. If the user feels "anxious," it will focus on "strengthening market research" to provide more reassurance.

[0661] Step 7:

[0662] The server passes the generated solutions to a logical verification module, which, in collaboration with multiple AI expert modules, evaluates the effectiveness and feasibility of each solution.

[0663] Step 8:

[0664] The server's logical verification module uses an AI expert module to conduct virtual discussions and select the optimal solution. For example, it may determine that "strengthening social media advertising and combining market research" is optimal.

[0665] Step 9:

[0666] The server sends the evaluated optimal solution to the user's device, which displays it on the solution display screen and presents the specific solution, "Strengthen social media advertising and conduct thorough market research."

[0667] Step 10:

[0668] Users can browse the solutions displayed on their device, select the ones they think are appropriate, and then implement them, such as strengthening market research and starting a social media advertising campaign.

[0669] Example 2

[0670] 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."

[0671] Modern society demands fast and accurate solutions to complex and diverse problems. However, the effectiveness of solutions is often limited due to the difficulty of responding flexibly to the emotions and circumstances of individual users. Another problem is a lack of resources and expertise to conduct analyses from multiple perspectives. To solve these problems, a system is needed that can approach users' problems from multiple perspectives and simultaneously provide optimized solutions that take the user's emotions into account.

[0672] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0673] In this invention, the server includes means for transmitting a problem input by a user to the server, means for the server to pass the received problem data to a natural language processing module and extract key elements, means for the server to send a request for solution generation to a multi-faceted perspective generation module based on the extracted elements, means for the server to send the extracted solution to an emotion engine for adjusting it taking into account emotion data, means for the server to pass the adjusted solution to a logical verification module and evaluate the optimal solution, and means for the server to send the evaluated solution to the user terminal. This makes it possible to provide an optimal solution that takes into account multi-faceted perspectives and the user's emotions.

[0674] "User" refers to an individual or organization that uses the system to enter challenges and receive solutions.

[0675] "Device" refers to the device (e.g., PC, smartphone, tablet) used by a user to enter a challenge and receive a solution.

[0676] "Server" refers to a computer system that receives data sent from users, analyzes the problem, generates, evaluates, and adjusts solutions using various modules, and finally sends the solutions to the user terminal.

[0677] "Natural language processing module" refers to a software module that has the function of analyzing the text data of assignments submitted by users and extracting key elements.

[0678] A "multi-perspective generation module" refers to a software module that has the function of generating solutions from the perspectives of different cultures, fields of expertise, occupations, etc. based on the extracted elements of the problem.

[0679] "Emotion engine" refers to a software module that has the function of analyzing a user's emotional data and using it to adjust the generated solution.

[0680] "Logical verification module" refers to a software module that has the function of evaluating the effectiveness and feasibility of the generated solution.

[0681] "AI Expert Module" refers to a software module that allows multiple virtual experts to discuss and participate in the evaluation of each solution.

[0682] "Database" refers to a data storage system that stores information about different cultures, fields of expertise, and occupations, and from which the multi-perspective generation module can retrieve information.

[0683] "Solution display screen" refers to an interface that displays solutions on a user terminal and allows the user to select an action based on the solutions.

[0684] This invention is a system in which a user inputs any problem, a server analyzes it from multiple perspectives, generates solutions, and then uses an emotion engine to recognize the user's emotions and present appropriate solutions. This system includes a terminal, a server, a natural language processing module, a multiple perspective generation module, a logical verification module, an AI expert module, a database, and an emotion engine.

[0685] First, the user logs in to the device and accesses the problem entry screen. There, they enter their problem in the text box and click the submit button. For example, they might enter, "I want to think about how to enter a new market." At this stage, the user's emotional data is also collected. The device then sends the problem data and emotional data to the server.

[0686] The server receives the task data and emotion data sent from the user's device. The server's natural language processing (NLP) module analyzes the task text data and extracts key elements. For example, keywords such as "new market" and "entry method" are extracted. At the same time, the emotion engine analyzes the emotion data and recognizes the user's current emotional state.

[0687] Based on the extracted elements and emotion data, the server sends a request for solution generation to the multi-perspective generation module. This module accesses a database to obtain relevant information from different cultures, fields of expertise, and occupations. It then generates solutions from each perspective. For example, solutions such as "strengthen social media advertising" from the cultural perspective, "host webinars" from the professional perspective, and "strengthen market research" from the occupation perspective may be generated.

[0688] The server's emotion engine adjusts the priority and content of generated solutions based on the user's emotional state. For example, if the user is feeling anxious, detailed and reassuring solutions will be prioritized. This provides the best solution for the user's situation.

[0689] The server passes the generated solutions to a logical verification module, which, in collaboration with multiple AI expert modules, evaluates the effectiveness and feasibility of each solution, ultimately selecting the most effective solution.

[0690] The server sends the evaluated optimal solution to the user's terminal, which displays it on the solution display screen. The user can then select an action based on the proposed solution.

[0691] Specific examples

[0692] User input:

[0693] The user inputs a problem such as "I want to think about how to enter a new market" and submits it. At the same time, emotional data collected using cameras and sensors is also submitted.

[0694] Task information and emotion data analysis:

[0695] The server's natural language processing module extracts "new markets" and "entry methods." At the same time, the emotion engine analyzes the user's emotion as "anxiety."

[0696] Multi-perspective solution generation:

[0697] The server's multifaceted perspective generation module generates the following: strengthening social media advertising (cultural perspective), hosting web seminars (professional field perspective), and strengthening market research (occupation perspective).

[0698] Adjustments based on sentiment data:

[0699] Because users feel "anxious," the priority is given to "strengthening market research," which is more detailed and gives a sense of security.

[0700] Logical verification and solution selection:

[0701] The server's logical verification module virtually discusses the issue and concludes that the optimal solution is to "strengthen social media advertising and combine it with market research."

[0702] Solution suggestion:

[0703] The server sends the evaluated solutions to the device, which then displays a message on the screen saying, "Strengthen social media advertising and conduct thorough market research." The user then begins to take action based on these solutions.

[0704] Prompt Sentence Examples

[0705] "I'd like to think about how to enter a new market. Currently, many members of my company are feeling uneasy about entering the market. Taking this situation into consideration, could you please tell me an effective way to do so?"

[0706] In this way, this system can solve problems efficiently and effectively by analyzing problems from multiple perspectives based on user input and providing optimal solutions that take emotions into account.

[0707] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0708] Step 1:

[0709] A user logs in to a device and opens the task input screen. The user enters the task in the text box and clicks the submit button. For example, the user might enter, "I want to think about how to enter a new market." The input data also includes the user's emotional data.

[0710] Specific behavior:

[0711] The user enters an issue.

[0712] The user clicks the submit button.

[0713] The device transmits the task data and emotion data to the server.

[0714] input:

[0715] Assignment text (e.g., "I want to think about how to enter a new market.")

[0716] Emotional data (user facial expressions, voice, etc.)

[0717] output:

[0718] The task data and emotion data are sent to the server.

[0719] Step 2:

[0720] The server receives the task data and emotion data sent from the user's device. A natural language processing (NLP) module analyzes the task text data and extracts key elements. For example, keywords such as "new market" and "entry methods" are extracted.

[0721] At the same time, the emotion engine analyzes the emotion data and recognizes the user's current emotional state.

[0722] Specific behavior:

[0723] The server receives the data.

[0724] The NLP module extracts keywords from the text data.

[0725] The emotion engine analyzes the emotion data and recognizes the emotional state.

[0726] input:

[0727] Issue data and emotion data.

[0728] output:

[0729] Extracted keywords.

[0730] The perceived emotional state of the user.

[0731] Step 3:

[0732] Based on the extracted elements and emotion data, the server sends a request for solution generation to the multi-perspective generation module, which accesses a database to obtain relevant information from different cultures, fields of expertise, and occupations. It then generates solutions from each perspective.

[0733] Specific behavior:

[0734] The server sends the request.

[0735] The multi-perspective generation module accesses the database and retrieves relevant information.

[0736] Generate solutions from each perspective.

[0737] input:

[0738] Extracted keywords.

[0739] The perceived emotional state of the user.

[0740] output:

[0741] Solutions from different perspectives (e.g., cultural perspective, disciplinary perspective, occupational perspective).

[0742] Step 4:

[0743] The server uses an emotion engine to tailor the generated solutions based on the user's emotional state: for example, if the user is feeling anxious, detailed and reassuring solutions are preferred.

[0744] Specific behavior:

[0745] The emotion engine reanalyzes the emotion data.

[0746] Adjust the priority and content of solutions.

[0747] input:

[0748] Generated solution.

[0749] The perceived emotional state of the user.

[0750] output:

[0751] Coordinated solutions.

[0752] Step 5:

[0753] The server passes the generated solutions to a logical verification module, which, in collaboration with multiple AI expert modules, evaluates the effectiveness and feasibility of each solution. As a result of the evaluation, the optimal solution is selected.

[0754] Specific behavior:

[0755] The logical verification module receives the solution.

[0756] An AI expert module evaluates each solution.

[0757] Select the best solution.

[0758] input:

[0759] Coordinated solutions.

[0760] output:

[0761] The best solution evaluated.

[0762] Step 6:

[0763] The server sends the evaluated optimal solution to the user's terminal, which displays the received solution on a solution display screen, allowing the user to select an action based on the proposed solution.

[0764] Specific behavior:

[0765] The server sends the best solution.

[0766] The device will display the solution.

[0767] The user chooses an action based on the solution.

[0768] input:

[0769] The best solution evaluated.

[0770] output:

[0771] The solution will be displayed on the device.

[0772] (Application example 2)

[0773] 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."

[0774] Currently, supervisors in the operation and management of factory robots often face complex challenges, making it difficult to find quick and accurate solutions. Furthermore, because the appropriate solution varies depending on the supervisor's emotions and the situation, flexible responses tailored to individual situations are required. This can lead to reduced labor efficiency and adversely affect productivity. The present invention aims to solve these problems and provide a system that allows supervisors to quickly find appropriate solutions in the operation and management of factory robots.

[0775] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0776] In this invention, the server includes means for transmitting a problem input by a user to a terminal to the server, means for the server to pass the received problem data to a natural language processing module and extract key elements, means for the server to send a request for solution generation to a multi-perspective generation module based on the extracted elements and emotion data, means for the server to generate solutions from multiple perspectives, means for the server to adjust the generated solutions in consideration of the emotion data, means for the server to adjust the solutions based on the emotion data and pass them to a logical verification module to evaluate the optimal solution, and means for the server to transmit the evaluated solutions to the user terminal. This makes it possible to provide supervisors with quick and appropriate solutions based on multi-perspectives and emotion data for complex problems they face.

[0777] "Tasks input by users to terminals" refers to problems or questions input to the terminal devices used by users.

[0778] "Means for sending to the server" refers to a device or program that has the function of transmitting the assignment entered by the user into the terminal to the server.

[0779] "Natural Language Processing Module" means software used to analyze submitted assignment data and extract key elements and keywords from the text.

[0780] "Key Elements" refers to the most important keywords or phrases in the submitted assignment.

[0781] "Emotion data" refers to information that identifies the user's emotional state and expresses it in a data format.

[0782] The "multi-perspective generation module" refers to software for generating solutions from different perspectives based on extracted key elements and emotional data.

[0783] "Solution generation request" refers to the act of the server sending a request to generate a solution to the multi-perspective generation module.

[0784] "Means for the server to generate solutions from multiple perspectives" refers to devices or programs that have the functionality to enable the server to generate solutions from the perspectives of different cultures, fields of expertise, occupations, etc.

[0785] "Means for adjusting by taking into account emotional data" refers to a device or program that has the function of adjusting the generated solution based on the emotional state of the user to make it optimal.

[0786] "Logical verification module" refers to software for evaluating the effectiveness and feasibility of generated solutions.

[0787] "AI Expert Module" means a module equipped with an artificial intelligence program with specific expertise.

[0788] The "means for transmitting to the user terminal" refers to a device or program having a function for transmitting the evaluated solution from the server to the terminal device used by the user.

[0789] "Database" means an information management system that stores relevant information and makes it accessible and available as needed.

[0790] The system for implementing this invention begins with a user inputting an operations management issue using a terminal. The server then receives the input issue data and extracts its main elements using a natural language processing module. At this time, an emotion engine analyzes the emotion data and recognizes the user's emotional state.

[0791] The server sends a solution generation request to the multi-perspective generation module based on key elements and emotional data. The multi-perspective generation module generates solutions from different cultural, disciplinary, and professional perspectives and adjusts these solutions based on emotional data. This adjustment may prioritize solutions that are more detailed and reassuring.

[0792] The generated solutions are evaluated for validity and feasibility by a logical verification module. Multiple AI expert modules virtually debate the solutions and ultimately select the optimal solution. This selected solution is then sent to the user's device and displayed.

[0793] Specifically, in the operation and management of factory robots, a supervisor inputs a problem such as "I want to identify the cause of a robot's failure" into a terminal and sends it. At this time, emotional data is also sent, and the server analyzes the data. A natural language processing module extracts keywords such as "robot," "failure," and "cause," and a multifaceted perspective generation module generates solutions. For example, this could include using software to analyze the robot's log data from a technology perspective, or having a specialist technician conduct an on-site inspection from an expert's perspective.

[0794] If the emotion engine recognizes the user's emotion as "anxiety," it prioritizes detailed and reassuring solutions. The logical verification module evaluates the effectiveness of the solutions and sends the optimal solution to the user's device.

[0795] This makes it possible to provide quick and appropriate solutions to the complex challenges faced by supervisors, based on multiple perspectives and emotional data.

[0796] Hardware and software used

[0797] Smartphone / Tablet: Used as an interface for users to enter assignments.

[0798] Server: Processes the issue data and sentiment data.

[0799] Natural Language Processing Module (NLPModule): Analyzes the text data of the assignment and extracts important elements.

[0800] Emotion Engine: Analyzes user emotional data.

[0801] PerspectiveModule: Generates solutions from cultural, disciplinary and professional perspectives and adjusts them based on emotional state.

[0802] Logic Validation Module: Evaluates the effectiveness and feasibility of each solution and selects the optimal solution.

[0803] Prompt Sentence Examples

[0804] "Based on the emotion data you have, propose the optimal solution to the problem input by the supervisor: 'I want to identify the cause of the robot's malfunction.' Consider solutions from the perspectives of culture, specialty, and job type, and provide prioritized solutions taking into account the user's anxieties."

[0805] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0806] Step 1:

[0807] The user inputs a task using the device. For example, the task might be "I want to identify the cause of a robot malfunction." The device then sends the input task data and emotion data acquired from sensors in use to the server.

[0808] Input: Task data, emotion data

[0809] Output: Issue data and sentiment data sent to the server

[0810] Step 2:

[0811] The server passes the received problem data to a natural language processing module, which extracts key elements. The natural language processing module performs text analysis and identifies important keywords and phrases. Key elements such as "robot," "fault," and "cause" are extracted.

[0812] Input: Issue data

[0813] Data processing: Text analysis using natural language processing

[0814] Output: Key Elements

[0815] Step 3:

[0816] The server uses an emotion engine to analyze the received emotion data and identify the user's emotion state, for example, recognizing an "anxiety" state from the emotion data.

[0817] Input: Emotion data

[0818] Data Computation: Emotional State Analysis with Emotion Engine

[0819] Output: User's emotional state

[0820] Step 4:

[0821] The server sends a solution generation request to the multi-perspective generation module based on the extracted key elements and sentiment data. The multi-perspective generation module generates solutions from the perspectives of different cultures, fields of expertise, and occupations, and creates a solution list. For example, it generates "analysis of log data" from the technology perspective and "on-site inspection by engineers" from the expert perspective.

[0822] Input: Primary element, emotional state

[0823] Data Computing: Generating Solutions from Multiple Perspectives

[0824] Output: Solution list

[0825] Step 5:

[0826] The server adjusts the list of solutions based on the emotion data: the emotion engine responds to the "anxiety" state and prioritizes detailed and quick solutions that put the user at ease.

[0827] Input: Solution list, emotional state

[0828] Data processing: Adjusting solution priorities based on sentiment data

[0829] Output: Reconciled solution list

[0830] Step 6:

[0831] The server passes the adjusted solution list to a logical verification module to evaluate its effectiveness and feasibility, and multiple AI expert modules virtually debate and select the optimal solution.

[0832] Input: Reconciled solution list

[0833] Data Computing: Assessing the Effectiveness and Feasibility of Solutions

[0834] Output: Optimal solution

[0835] Step 7:

[0836] The server sends the optimal solution to the user's device, which displays it, allowing the supervisor to take appropriate measures based on the presented solution.

[0837] Input: Optimal solution

[0838] Output: sent to and displayed on the user's terminal

[0839] 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.

[0840] 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.

[0841] 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.

[0842] [Third embodiment]

[0843] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0844] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0845] 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).

[0846] 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.

[0847] 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.

[0848] 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).

[0849] 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.

[0850] 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.

[0851] 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.

[0852] 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.

[0853] 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.

[0854] 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."

[0855] This invention is a system that supports efficient and effective problem solving by allowing a user to input any problem, and then having a server analyze it from multiple perspectives and generate a solution. This system includes a terminal, a server, a natural language processing module, a multiple perspective generation module, a logical verification module, an AI expert module, and a database.

[0856] System configuration and processing flow

[0857] 1. Assignment input

[0858] The user logs in to a terminal that has a problem input screen. The problem input screen has a text box where the user can freely enter the problem they want to solve. For example, "I want to think about how to enter a new market." Once the input is complete, the user clicks the send button and the problem data is sent to the server.

[0859] 2. Analysis of issue information

[0860] The server receives the assignment data sent from the user's device. A natural language processing (NLP) module in the server analyzes the assignment text and extracts key elements. For example, keywords such as "new market" and "entry method" are extracted.

[0861] 3. Solution generation from multiple perspectives

[0862] Based on the extracted elements, the server sends a request for solution generation to the multi-perspective generation module, which accesses the database to obtain relevant information from different cultures, fields of expertise, and occupations, and then generates solutions from each perspective.

[0863] Cultural perspective: Given the effectiveness of web marketing in specific cultural contexts, suggestions are made to strengthen social media advertising.

[0864] Specialist perspective: The technology sector suggests using online platforms to host webinars and promote products and services.

[0865] 4. Logical verification and solution selection

[0866] The server passes the generated solutions to a logical verification module, which collaborates with multiple AI expert modules to virtually discuss the effectiveness and feasibility of each solution, ultimately selecting the most effective solution.

[0867] 5. Providing a solution

[0868] The server sends the evaluated optimal solution to the user's device, which then displays the received solution in an easy-to-read format for the user. The user can then select an action based on the proposed solution.

[0869] Specific examples

[0870] 1. User input:

[0871] The user inputs the problem, "I want to think about how to enter a new market," and submits it.

[0872] 2. Analysis of assignment information:

[0873] The server's natural language processing module extracts "new markets" and "ways to enter the market."

[0874] 3. Solution generation from multiple perspectives:

[0875] The server's multifaceted perspective generation module generates solutions such as strengthening social media advertising (cultural perspective), strengthening market research (profession perspective), and holding web seminars (specialty perspective).

[0876] 4. Logical verification and solution selection:

[0877] The server's logical verification module virtually discusses the issue and determines that strengthening social media advertising and combining it with market research is optimal.

[0878] 5. Propose a solution:

[0879] The server sends the evaluated solutions to the device, which then displays the message on its screen: "Strengthen social media advertising and conduct thorough market research."

[0880] In this way, the system of the present invention analyzes the problem entered by the user from multiple perspectives and provides the optimal solution, thereby solving the problem efficiently and effectively.

[0881] The processing flow will be explained below.

[0882] Step 1:

[0883] The user logs in to the device and opens the task entry screen. They enter the task in the text box and click the submit button. For example, they might enter, "I want to think about how to enter a new market."

[0884] Step 2:

[0885] The terminal sends the assignment data entered by the user to the server in text format.

[0886] Step 3:

[0887] The server receives the submitted problem data and passes it to a natural language processing (NLP) module, which analyzes and extracts key elements. For example, "new market" and "entry method" are extracted.

[0888] Step 4:

[0889] The server sends a request for solution generation to the multi-perspective generation module based on the extracted elements.

[0890] Step 5:

[0891] The server's multi-perspective generation module accesses the database and starts generating solutions from different perspectives:

[0892] Cultural perspective: Solutions based on specific cultural backgrounds, such as "strengthening social media advertising"

[0893] Job-specific perspective: Solutions based on specific job roles, e.g., "strengthening market research"

[0894] Specialist perspective: Solutions based on a specific area of ​​expertise, e.g., "hosting a webinar"

[0895] Step 6:

[0896] The server passes the generated solutions to a logical validation module, which evaluates the effectiveness and feasibility of each solution.

[0897] Step 7:

[0898] The server uses an AI expert module to conduct a virtual discussion and select the optimal solution, for example, "strengthening social media advertising and combining it with market research."

[0899] Step 8:

[0900] The server sends the evaluated optimal solution to the user terminal, which displays the solution on a solution display screen.

[0901] Step 9:

[0902] The user can view the solutions displayed on the terminal, select the solution they think is appropriate, and implement it.

[0903] Example 1

[0904] 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."

[0905] Conventional problem-solving support systems often provide solutions based on a specific perspective or limited information, making it difficult to obtain solutions that reflect multiple perspectives or input from different fields of expertise. Furthermore, they lack the functionality to logically verify the effectiveness and feasibility of solutions, making it impossible to provide effective solutions for users. Therefore, there is a need for a system that allows users to efficiently and effectively obtain solutions from multiple perspectives.

[0906] 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.

[0907] In this invention, the server includes means for transmitting a problem input by a user to the server, means for the server to pass the received problem data to a natural language processing module and extract key elements, means for the server to send a request for solution generation to a multi-perspective generation module based on the extracted elements, means for the server to access a database and acquire related information from the perspectives of different cultures, fields of expertise, and occupations, means for the server to generate solutions from multiple perspectives based on the acquired information, means for the server to pass the generated solutions to a logical verification module and evaluate the optimal solution, means for the server to transmit the evaluated solution to the user terminal, and means for the user terminal to display the received solution. This enables the server to analyze from multiple perspectives and efficiently and effectively provide the user with an optimal solution that has been logically verified.

[0908] "User" refers to the entity that uses the system and inputs tasks.

[0909] "Terminal" refers to a device used by a user, which inputs and transmits tasks and displays solutions.

[0910] "Server" refers to a central processing unit that receives data sent from terminals, analyzes them, and generates and evaluates solutions.

[0911] "Natural language processing module" refers to a software component that analyzes received text data and extracts key elements.

[0912] The "multi-perspective generation module" refers to a software component that obtains relevant information from different cultural, professional, and occupational perspectives and generates solutions.

[0913] "Database" refers to a data storage system that stores information about different cultures, professions, and occupations and makes that information available when needed.

[0914] "Logical Verification Module" refers to a software component that evaluates the effectiveness and feasibility of generated solutions.

[0915] "Expert Module" refers to a software component that has expertise in a particular domain and virtually participates in the evaluation of solutions.

[0916] "Solution" refers to a specific approach or method to the problem entered by the user.

[0917] "Evaluation" refers to the process of examining the effectiveness and feasibility of the generated solutions and selecting the most suitable solution.

[0918] This invention is a system that analyzes a problem entered by a user from multiple perspectives and provides an effective and efficient solution. This system includes a terminal, a server, a natural language processing module, a multiple perspective generation module, a logical verification module, an expert module, and a database.

[0919] The user logs in to the device and enters the problem they want to solve in the text box on the problem input screen. Then, by clicking the send button, the problem data is sent to the server. For example, a user might enter "I want to think about how to enter a new market" and send it.

[0920] The server receives the problem data sent from the device and analyzes it using a natural language processing (NLP) module. This analysis extracts the main elements of the problem. For example, the keyword "new market" may be extracted.

[0921] Next, the server sends a solution generation request to the multi-perspective generation module based on the extracted elements. This module accesses a database to obtain relevant information from different cultural, professional, and occupational perspectives. It then generates solutions from each perspective. Specifically, the cultural perspective generates "proposals to enhance social media advertising in a specific cultural context."

[0922] The generated solutions are passed to the logical verification module by the server. This module collaborates with multiple expert modules to virtually discuss and evaluate the effectiveness and feasibility of each solution. As a result, the most effective solution is selected. For example, "combining strengthened social media advertising with market research" is evaluated as optimal.

[0923] The server sends the evaluated optimal solution to the user's terminal, which then displays the received solution to the user, who can then select an action based on the presented solution.

[0924] As an example of a specific prompt sentence, if a user inputs "I want to think about how to enter a new market," the server will receive and analyze it, retrieve information from the database, generate solutions from multiple perspectives, verify them logically, and send the optimal solution to the user's device.

[0925] This system allows users to efficiently obtain effective solutions that have been analyzed from multiple perspectives.

[0926] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0927] Step 1: Assignment entry

[0928] The user logs in to the device. The user enters the problem they want to solve in the text box displayed on the problem input screen. For example, the user might enter "I want to think about how to enter a new market." Once the input is complete, the user clicks the send button, and the problem data is sent to the server.

[0929] Input: Problem text such as "I want to think about how to enter a new market"

[0930] Output: Issue data sent to the server

[0931] Step 2: Analyze the issue information

[0932] The server receives the problem data sent from the device. It then passes the problem data to a natural language processing (NLP) module, which analyzes and extracts key elements. This process extracts keywords such as "new market" and "entry method."

[0933] Input: Assignment data received from the device

[0934] Output: Key elements analyzed (e.g., "New market" and "Entry method")

[0935] Step 3: Generate solutions from multiple perspectives

[0936] Based on the extracted elements, the server sends a request for solution generation to the multi-perspective generation module. The module accesses the database to obtain relevant information from the perspectives of different cultures, fields of expertise, and occupations. Solutions are generated from each perspective, and from the cultural perspective, for example, a specific solution such as "proposing strengthening social media advertising in a specific cultural context" is generated.

[0937] Input: Parsed key elements

[0938] Output: Multiple solutions generated from different perspectives (e.g., social media advertising reinforcement from a cultural perspective)

[0939] Step 4: Logical verification and solution selection

[0940] The server passes the generated solutions to the logical verification module, which collaborates with multiple expert modules to virtually discuss and evaluate the effectiveness and feasibility of each solution. For example, the optimal solution may be selected as "strengthening social media advertising and conducting market research."

[0941] Input: Multiple generated solutions

[0942] Output: Evaluated optimal solution (e.g., strengthening social media advertising and combining it with market research)

[0943] Step 5: Providing a solution

[0944] The server sends the evaluated optimal solution to the user's device. The device displays the received solution in an easy-to-read format for the user. The user can then choose an action based on the displayed solution. For example, the device screen might say, "Strengthen social media advertising and conduct thorough market research."

[0945] Input: Evaluated optimal solution

[0946] Output: Solution displayed in terminal

[0947] In this way, the system analyzes the problem entered by the user from multiple perspectives and efficiently provides the optimal solution.

[0948] (Application example 1)

[0949] 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."

[0950] Improving production efficiency and troubleshooting are important issues on factory floors, but it is often difficult to find effective solutions immediately on site. In particular, there are limited means to quickly obtain approaches from multiple fields of expertise and perspectives, which makes it difficult for on-site workers to make appropriate decisions. To solve this problem, a system that can quickly provide solutions from multiple perspectives through devices that can be easily used on-site is needed.

[0951] 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.

[0952] In this invention, the server includes means for transmitting a problem input by a user to the server, means for the server to pass the received problem data to a natural language processing module and extract key elements, means for the server to send a request for solution generation to a multi-perspective generation module based on the extracted elements, means for the server to generate solutions from multiple perspectives, means for the server to pass the generated solutions to a logical verification module and evaluate the optimal solution, means for the server to transmit the evaluated solutions to the user terminal, and means for inputting on-site problems using a wearable device or a mobile information terminal and displaying solutions from the server. This enables immediate on-site problem input and rapid presentation of solutions from multi-perspectives.

[0953] A "user terminal" is an electronic device that allows a user to input tasks, and includes smartphones, tablets, personal computers, etc.

[0954] A "server" is a central computer that receives assignment data sent from user terminals and analyzes and processes them.

[0955] The "natural language processing module" is a software module that analyzes the text of assignment data within the server and extracts key elements.

[0956] The "multi-perspective generation module" is a module that generates solutions from different perspectives and fields based on the extracted elements.

[0957] The "logical verification module" is a module for evaluating the effectiveness and feasibility of multiple generated solutions.

[0958] An "AI expert module" is an artificial intelligence module that has a knowledge base specialized in a specific field and virtually debates.

[0959] The "database" is a collection of information accessed by the multi-perspective generation module, and contains information on different cultures, fields of expertise, and occupations.

[0960] "Wearable devices" are electronic devices worn by field workers, including smart glasses and head-mounted displays.

[0961] A "personal digital assistant" is a portable electronic device, including a smartphone or tablet.

[0962] This invention is a system that supports efficient and effective problem-solving in factories by allowing users to input any problem and then having a server analyze it from multiple perspectives and generate solutions. This system includes a user terminal, a server, a natural language processing module, a multiple perspective generation module, a logical verification module, an AI expert module, and a database.

[0963] Components

[0964] 1. User Device

[0965] A user terminal is an electronic device that allows a user to input tasks, and includes a smartphone, tablet, PC, etc.

[0966] Field workers use wearable devices or mobile information terminals to input on-site problems, and solutions are displayed from the server.

[0967] 2. Server

[0968] The server is a central computer that receives the assignment data sent from the user terminal and analyzes and processes it.

[0969] 3. Natural Language Processing Module

[0970] The natural language processing module is a software module that analyzes the text of the assignment data on the server and extracts key elements. Specifically, it uses tools such as SpaCy and NLTK.

[0971] 4. Multi-perspective generation module

[0972] The multi-perspective generation module is a module that generates solutions from different perspectives and fields based on the extracted elements. An example of a generative AI model is GPT-3.

[0973] 5. Logical Verification Module

[0974] The logical verification module is a module for evaluating the effectiveness and feasibility of the generated solutions.

[0975] 6. AI Expert Module

[0976] An AI expert module is an artificial intelligence module that has a knowledge base specialized in a specific field and can hold virtual discussions.

[0977] 7. Database

[0978] The database is a collection of information that the multi-perspective generation module accesses, and contains information on different cultures, fields of expertise, and occupations.

[0979] System Operation Details

[0980] On-site users input their issues, such as "I want to solve the bottleneck on the production line," using a smartphone or head-mounted display. The input issue is sent to the server and analyzed by a natural language processing module. Here, key elements are extracted, and keywords such as "production line" and "bottleneck" are obtained.

[0981] Based on these keywords, the server sends a request for solution generation to the multi-perspective generation module. The multi-perspective generation module retrieves information on different cultures, fields of expertise, and occupations from a database and generates solutions using a generative AI model. For example, it may suggest "optimizing robot movements" or "introducing parallel work."

[0982] The generated solutions are evaluated by a logical verification module and multiple AI expert modules to select the most effective and feasible solution, which is then sent from the server to the user's device and presented to the on-site worker.

[0983] Examples and prompts

[0984] Example: A field worker voice-inputs, "I want to solve the bottleneck on the production line," and the solution to the problem is presented: "Optimize the robot's operation and introduce parallel work."

[0985] Example prompt sentence:

[0986] "X part of the production line is a bottleneck. Please suggest a solution to improve efficiency."

[0987] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0988] Step 1:

[0989] The user inputs the issue on-site.

[0990] Input: The user uses a smartphone or head-mounted display to input voice or text, such as "I want to solve the bottleneck on the production line."

[0991] Specific operation: The device receives the challenge and sends it to the server.

[0992] Step 2:

[0993] The terminal transmits the input assignment data to the server.

[0994] Input: User issue data.

[0995] Output: The issue data sent to the server.

[0996] Specific operation: The terminal sends the assignment data to the server as an HTTP request.

[0997] Step 3:

[0998] The server passes the received assignment data to a natural language processing module, which extracts key elements.

[0999] Input: The issue data sent to the server.

[1000] Output: Extracted key elements (e.g. "production line", "bottleneck").

[1001] How it works: The server uses natural language processing libraries such as SpaCy or NLTK to tokenize the issue data and extract key keywords.

[1002] Step 4:

[1003] The server sends a request for solution generation to the multi-perspective generation module based on the extracted elements.

[1004] Input: Extracted key elements.

[1005] Output: A request for solution generation.

[1006] Specific operation: The server sends a request including the extracted main elements to the multi-perspective generation module.

[1007] Step 5:

[1008] The multi-perspective generation module uses a generative AI model to generate solutions from multiple perspectives.

[1009] Input: Solution generation request.

[1010] Output: Multiple solutions (e.g., "optimize the robot's behavior," "introduce parallel work").

[1011] Specific operation: The multi-perspective generation module retrieves relevant information from the database and generates a solution using a generative AI model (e.g., GPT-3).

[1012] Step 6:

[1013] The server passes the generated solutions to a logical validation module to evaluate the best solution.

[1014] Input: Multiple solutions.

[1015] Output: The solution that is evaluated as optimal.

[1016] Specific operation: The logical verification module conducts a virtual discussion with the AI ​​expert module to select the optimal solution.

[1017] Step 7:

[1018] The server transmits the evaluated optimal solution to the user terminal.

[1019] Input: The solution that was evaluated as optimal.

[1020] Output: The solution sent to the user's device.

[1021] Specific operation: The server sends the optimal solution to the user terminal as an HTTP response.

[1022] 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.

[1023] This invention is a system in which a user inputs any problem, a server analyzes it from multiple perspectives, generates solutions, and then uses an emotion engine to recognize the user's emotions and present appropriate solutions. This system includes a terminal, a server, a natural language processing module, a multiple perspective generation module, a logical verification module, an AI expert module, a database, and an emotion engine.

[1024] System configuration and processing flow

[1025] 1. Assignment input

[1026] The user logs in to the device and opens the task input screen. They enter the task in the text box and click the submit button. For example, they might enter "I want to think about how to enter a new market." Once the input is complete, the emotion data is sent to the server along with the task data.

[1027] 2. Analysis of task information and emotion data

[1028] The server receives task data and emotion data sent from the user's device. A natural language processing (NLP) module analyzes the task text data and extracts key elements. For example, keywords such as "new market" and "entry methods" are extracted. At the same time, an emotion engine analyzes the sent emotion data and recognizes the user's current emotional state.

[1029] 3. Solution generation from multiple perspectives

[1030] Based on the extracted elements and emotion data, the server sends a request for solution generation to the multi-perspective generation module, which accesses a database to obtain relevant information from different cultures, fields of expertise, and occupations. It then generates solutions from each perspective.

[1031] Cultural perspective: Solutions based on specific cultural backgrounds, such as "strengthening social media advertising"

[1032] Specialist perspective: For example, "Hosting webinars" from the technology field

[1033] Job perspective: For example, "Strengthening market research" from the marketing field

[1034] 4. Adjusting the solution to take sentiment data into account

[1035] When generating solutions, the emotion engine adjusts the priority and content of proposed solutions based on the user's emotional state. For example, if the user is feeling anxious, more detailed and reassuring solutions will be given priority.

[1036] 5. Logical verification and solution selection

[1037] The server passes the generated solutions to a logical verification module, which, in collaboration with multiple AI expert modules, evaluates the effectiveness and feasibility of each solution, ultimately selecting the most effective solution.

[1038] 6. Providing a solution

[1039] The server sends the evaluated optimal solution to the user's terminal. The terminal displays the received solution on the solution display screen. The user can select an action based on the proposed solution.

[1040] Specific examples

[1041] 1. User input:

[1042] The user inputs a problem such as "I want to think about how to enter a new market" and submits it. At the same time, emotional data collected using cameras and sensors is also submitted.

[1043] 2. Analysis of task information and emotion data:

[1044] The server's natural language processing module extracts "new markets" and "entry methods." At the same time, the emotion engine analyzes the user's emotion as "anxiety."

[1045] 3. Solution generation from multiple perspectives:

[1046] The server's multifaceted perspective generation module generates the following: strengthening social media advertising (cultural perspective), hosting web seminars (professional field perspective), and strengthening market research (occupation perspective).

[1047] 4. Adjustments based on emotional data:

[1048] Because users feel "anxious," the priority is given to "strengthening market research," which is more detailed and gives a sense of security.

[1049] 5. Logical verification and solution selection:

[1050] The server's logical verification module virtually discusses the issue and concludes that the optimal solution is to "strengthen social media advertising and combine it with market research."

[1051] 6. Propose a solution:

[1052] The server sends the evaluated solutions to the device, which then displays the message "Strengthen social media advertising and conduct thorough market research." The user can then take action based on these solutions.

[1053] In this way, the system of the present invention analyzes the problem entered by the user from multiple perspectives and uses an emotion engine to provide an optimal solution that takes the user's emotions into consideration, thereby solving the problem efficiently and effectively.

[1054] The processing flow will be explained below.

[1055] Step 1:

[1056] The user logs in to the device and opens the task entry screen. They enter their task in the text box and click the submit button. For example, they enter, "I want to think about how to enter a new market." At the same time, emotion data collected by cameras and sensors is also collected on the device.

[1057] Step 2:

[1058] The device sends the task data and emotional data entered by the user to the server. The task data is sent in text format, and the emotional data is sent as sensor data such as facial expressions and voice tones.

[1059] Step 3:

[1060] The server receives the submitted problem data and emotion data. A natural language processing (NLP) module analyzes the text data of the problem and extracts key elements (e.g., "new market" and "entry method"), while an emotion engine analyzes the submitted emotion data and recognizes the user's current emotional state (e.g., "anxiety").

[1061] Step 4:

[1062] The server sends a request for solution generation to the multi-perspective generation module based on the extracted elements and emotion data. This request includes the main elements and the user's emotion information.

[1063] Step 5:

[1064] The server's multi-perspective generation module accesses the database and starts generating solutions from different perspectives:

[1065] Cultural perspective: Solutions based on specific cultural backgrounds, such as "strengthening social media advertising"

[1066] Specialist perspective: "Hosting a web seminar" from the technology field

[1067] Occupational perspective: "Strengthening market research" from the marketing field

[1068] Step 6:

[1069] The server's multifaceted perspective generation module takes into account the emotional data obtained from the emotion engine and adjusts the priority and content of the solution proposals. If the user feels "anxious," it will focus on "strengthening market research" to provide more reassurance.

[1070] Step 7:

[1071] The server passes the generated solutions to a logical verification module, which, in collaboration with multiple AI expert modules, evaluates the effectiveness and feasibility of each solution.

[1072] Step 8:

[1073] The server's logical verification module uses an AI expert module to conduct virtual discussions and select the optimal solution. For example, it may determine that "strengthening social media advertising and combining market research" is optimal.

[1074] Step 9:

[1075] The server sends the evaluated optimal solution to the user's device, which displays it on the solution display screen and presents the specific solution, "Strengthen social media advertising and conduct thorough market research."

[1076] Step 10:

[1077] Users can browse the solutions displayed on their device, select the ones they think are appropriate, and then implement them, such as strengthening market research and starting a social media advertising campaign.

[1078] Example 2

[1079] 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."

[1080] Modern society demands fast and accurate solutions to complex and diverse problems. However, the effectiveness of solutions is often limited due to the difficulty of responding flexibly to the emotions and circumstances of individual users. Another problem is a lack of resources and expertise to conduct analyses from multiple perspectives. To solve these problems, a system is needed that can approach users' problems from multiple perspectives and simultaneously provide optimized solutions that take the user's emotions into account.

[1081] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1082] In this invention, the server includes means for transmitting a problem input by a user to the server, means for the server to pass the received problem data to a natural language processing module and extract key elements, means for the server to send a request for solution generation to a multi-faceted perspective generation module based on the extracted elements, means for the server to send the extracted solution to an emotion engine for adjusting it taking into account emotion data, means for the server to pass the adjusted solution to a logical verification module and evaluate the optimal solution, and means for the server to send the evaluated solution to the user terminal. This makes it possible to provide an optimal solution that takes into account multi-faceted perspectives and the user's emotions.

[1083] "User" refers to an individual or organization that uses the system to enter challenges and receive solutions.

[1084] "Device" refers to the device (e.g., PC, smartphone, tablet) used by a user to enter a challenge and receive a solution.

[1085] "Server" refers to a computer system that receives data sent from users, analyzes the problem, generates, evaluates, and adjusts solutions using various modules, and finally sends the solutions to the user terminal.

[1086] "Natural language processing module" refers to a software module that has the function of analyzing the text data of assignments submitted by users and extracting key elements.

[1087] A "multi-perspective generation module" refers to a software module that has the function of generating solutions from the perspectives of different cultures, fields of expertise, occupations, etc. based on the extracted elements of the problem.

[1088] "Emotion engine" refers to a software module that has the function of analyzing a user's emotional data and using it to adjust the generated solution.

[1089] "Logical verification module" refers to a software module that has the function of evaluating the effectiveness and feasibility of the generated solution.

[1090] "AI Expert Module" refers to a software module that allows multiple virtual experts to discuss and participate in the evaluation of each solution.

[1091] "Database" refers to a data storage system that stores information about different cultures, fields of expertise, and occupations, and from which the multi-perspective generation module can retrieve information.

[1092] "Solution display screen" refers to an interface that displays solutions on a user terminal and allows the user to select an action based on the solutions.

[1093] This invention is a system in which a user inputs any problem, a server analyzes it from multiple perspectives, generates solutions, and then uses an emotion engine to recognize the user's emotions and present appropriate solutions. This system includes a terminal, a server, a natural language processing module, a multiple perspective generation module, a logical verification module, an AI expert module, a database, and an emotion engine.

[1094] First, the user logs in to the device and accesses the problem entry screen. There, they enter their problem in the text box and click the submit button. For example, they might enter, "I want to think about how to enter a new market." At this stage, the user's emotional data is also collected. The device then sends the problem data and emotional data to the server.

[1095] The server receives the task data and emotion data sent from the user's device. The server's natural language processing (NLP) module analyzes the task text data and extracts key elements. For example, keywords such as "new market" and "entry method" are extracted. At the same time, the emotion engine analyzes the emotion data and recognizes the user's current emotional state.

[1096] Based on the extracted elements and emotion data, the server sends a request for solution generation to the multi-perspective generation module. This module accesses a database to obtain relevant information from different cultures, fields of expertise, and occupations. It then generates solutions from each perspective. For example, solutions such as "strengthen social media advertising" from the cultural perspective, "host webinars" from the professional perspective, and "strengthen market research" from the occupation perspective may be generated.

[1097] The server's emotion engine adjusts the priority and content of generated solutions based on the user's emotional state. For example, if the user is feeling anxious, detailed and reassuring solutions will be prioritized. This provides the best solution for the user's situation.

[1098] The server passes the generated solutions to a logical verification module, which, in collaboration with multiple AI expert modules, evaluates the effectiveness and feasibility of each solution, ultimately selecting the most effective solution.

[1099] The server sends the evaluated optimal solution to the user's terminal, which displays it on the solution display screen. The user can then select an action based on the proposed solution.

[1100] Specific examples

[1101] User input:

[1102] The user inputs a problem such as "I want to think about how to enter a new market" and submits it. At the same time, emotional data collected using cameras and sensors is also submitted.

[1103] Task information and emotion data analysis:

[1104] The server's natural language processing module extracts "new markets" and "entry methods." At the same time, the emotion engine analyzes the user's emotion as "anxiety."

[1105] Multi-perspective solution generation:

[1106] The server's multifaceted perspective generation module generates the following: strengthening social media advertising (cultural perspective), hosting web seminars (professional field perspective), and strengthening market research (occupation perspective).

[1107] Adjustments based on sentiment data:

[1108] Because users feel "anxious," the priority is given to "strengthening market research," which is more detailed and gives a sense of security.

[1109] Logical verification and solution selection:

[1110] The server's logical verification module virtually discusses the issue and concludes that the optimal solution is to "strengthen social media advertising and combine it with market research."

[1111] Solution suggestion:

[1112] The server sends the evaluated solutions to the device, which then displays a message on the screen saying, "Strengthen social media advertising and conduct thorough market research." The user then begins to take action based on these solutions.

[1113] Prompt Sentence Examples

[1114] "I'd like to think about how to enter a new market. Currently, many members of my company are feeling uneasy about entering the market. Taking this situation into consideration, could you please tell me an effective way to do so?"

[1115] In this way, this system can solve problems efficiently and effectively by analyzing problems from multiple perspectives based on user input and providing optimal solutions that take emotions into account.

[1116] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1117] Step 1:

[1118] A user logs in to a device and opens the task input screen. The user enters the task in the text box and clicks the submit button. For example, the user might enter, "I want to think about how to enter a new market." The input data also includes the user's emotional data.

[1119] Specific behavior:

[1120] The user enters an issue.

[1121] The user clicks the submit button.

[1122] The device transmits the task data and emotion data to the server.

[1123] input:

[1124] Assignment text (e.g., "I want to think about how to enter a new market.")

[1125] Emotional data (user facial expressions, voice, etc.)

[1126] output:

[1127] The task data and emotion data are sent to the server.

[1128] Step 2:

[1129] The server receives the task data and emotion data sent from the user's device. A natural language processing (NLP) module analyzes the task text data and extracts key elements. For example, keywords such as "new market" and "entry methods" are extracted.

[1130] At the same time, the emotion engine analyzes the emotion data and recognizes the user's current emotional state.

[1131] Specific behavior:

[1132] The server receives the data.

[1133] The NLP module extracts keywords from the text data.

[1134] The emotion engine analyzes the emotion data and recognizes the emotional state.

[1135] input:

[1136] Issue data and emotion data.

[1137] output:

[1138] Extracted keywords.

[1139] The perceived emotional state of the user.

[1140] Step 3:

[1141] Based on the extracted elements and emotion data, the server sends a request for solution generation to the multi-perspective generation module, which accesses a database to obtain relevant information from different cultures, fields of expertise, and occupations. It then generates solutions from each perspective.

[1142] Specific behavior:

[1143] The server sends the request.

[1144] The multi-perspective generation module accesses the database and retrieves relevant information.

[1145] Generate solutions from each perspective.

[1146] input:

[1147] Extracted keywords.

[1148] The perceived emotional state of the user.

[1149] output:

[1150] Solutions from different perspectives (e.g., cultural perspective, disciplinary perspective, occupational perspective).

[1151] Step 4:

[1152] The server uses an emotion engine to tailor the generated solutions based on the user's emotional state: for example, if the user is feeling anxious, detailed and reassuring solutions are preferred.

[1153] Specific behavior:

[1154] The emotion engine reanalyzes the emotion data.

[1155] Adjust the priority and content of solutions.

[1156] input:

[1157] Generated solution.

[1158] The perceived emotional state of the user.

[1159] output:

[1160] Coordinated solutions.

[1161] Step 5:

[1162] The server passes the generated solutions to a logical verification module, which, in collaboration with multiple AI expert modules, evaluates the effectiveness and feasibility of each solution. As a result of the evaluation, the optimal solution is selected.

[1163] Specific behavior:

[1164] The logical verification module receives the solution.

[1165] An AI expert module evaluates each solution.

[1166] Select the best solution.

[1167] input:

[1168] Coordinated solutions.

[1169] output:

[1170] The best solution evaluated.

[1171] Step 6:

[1172] The server sends the evaluated optimal solution to the user's terminal, which displays the received solution on a solution display screen, allowing the user to select an action based on the proposed solution.

[1173] Specific behavior:

[1174] The server sends the best solution.

[1175] The device will display the solution.

[1176] The user chooses an action based on the solution.

[1177] input:

[1178] The best solution evaluated.

[1179] output:

[1180] The solution will be displayed on the device.

[1181] (Application example 2)

[1182] 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."

[1183] Currently, supervisors in the operation and management of factory robots often face complex challenges, making it difficult to find quick and accurate solutions. Furthermore, because the appropriate solution varies depending on the supervisor's emotions and the situation, flexible responses tailored to individual situations are required. This can lead to reduced labor efficiency and adversely affect productivity. The present invention aims to solve these problems and provide a system that allows supervisors to quickly find appropriate solutions in the operation and management of factory robots.

[1184] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1185] In this invention, the server includes means for transmitting a problem input by a user to a terminal to the server, means for the server to pass the received problem data to a natural language processing module and extract key elements, means for the server to send a request for solution generation to a multi-perspective generation module based on the extracted elements and emotion data, means for the server to generate solutions from multiple perspectives, means for the server to adjust the generated solutions in consideration of the emotion data, means for the server to adjust the solutions based on the emotion data and pass them to a logical verification module to evaluate the optimal solution, and means for the server to transmit the evaluated solutions to the user terminal. This makes it possible to provide supervisors with quick and appropriate solutions based on multi-perspectives and emotion data for complex problems they face.

[1186] "Tasks input by users to terminals" refers to problems or questions input to the terminal devices used by users.

[1187] "Means for sending to the server" refers to a device or program that has the function of transmitting the assignment entered by the user into the terminal to the server.

[1188] "Natural Language Processing Module" means software used to analyze submitted assignment data and extract key elements and keywords from the text.

[1189] "Key Elements" refers to the most important keywords or phrases in the submitted assignment.

[1190] "Emotion data" refers to information that identifies the user's emotional state and expresses it in a data format.

[1191] The "multi-perspective generation module" refers to software for generating solutions from different perspectives based on extracted key elements and emotional data.

[1192] "Solution generation request" refers to the act of the server sending a request to generate a solution to the multi-perspective generation module.

[1193] "Means for the server to generate solutions from multiple perspectives" refers to devices or programs that have the functionality to enable the server to generate solutions from the perspectives of different cultures, fields of expertise, occupations, etc.

[1194] "Means for adjusting by taking into account emotional data" refers to a device or program that has the function of adjusting the generated solution based on the emotional state of the user to make it optimal.

[1195] "Logical verification module" refers to software for evaluating the effectiveness and feasibility of generated solutions.

[1196] "AI Expert Module" means a module equipped with an artificial intelligence program with specific expertise.

[1197] The "means for transmitting to the user terminal" refers to a device or program having a function for transmitting the evaluated solution from the server to the terminal device used by the user.

[1198] "Database" means an information management system that stores relevant information and makes it accessible and available as needed.

[1199] The system for implementing this invention begins with a user inputting an operations management issue using a terminal. The server then receives the input issue data and extracts its main elements using a natural language processing module. At this time, an emotion engine analyzes the emotion data and recognizes the user's emotional state.

[1200] The server sends a solution generation request to the multi-perspective generation module based on key elements and emotional data. The multi-perspective generation module generates solutions from different cultural, disciplinary, and professional perspectives and adjusts these solutions based on emotional data. This adjustment may prioritize solutions that are more detailed and reassuring.

[1201] The generated solutions are evaluated for validity and feasibility by a logical verification module. Multiple AI expert modules virtually debate the solutions and ultimately select the optimal solution. This selected solution is then sent to the user's device and displayed.

[1202] Specifically, in the operation and management of factory robots, a supervisor inputs a problem such as "I want to identify the cause of a robot's failure" into a terminal and sends it. At this time, emotional data is also sent, and the server analyzes the data. A natural language processing module extracts keywords such as "robot," "failure," and "cause," and a multifaceted perspective generation module generates solutions. For example, this could include using software to analyze the robot's log data from a technology perspective, or having a specialist technician conduct an on-site inspection from an expert's perspective.

[1203] If the emotion engine recognizes the user's emotion as "anxiety," it prioritizes detailed and reassuring solutions. The logical verification module evaluates the effectiveness of the solutions and sends the optimal solution to the user's device.

[1204] This makes it possible to provide quick and appropriate solutions to the complex challenges faced by supervisors, based on multiple perspectives and emotional data.

[1205] Hardware and software used

[1206] Smartphone / Tablet: Used as an interface for users to enter assignments.

[1207] Server: Processes the issue data and sentiment data.

[1208] Natural Language Processing Module (NLPModule): Analyzes the text data of the assignment and extracts important elements.

[1209] Emotion Engine: Analyzes user emotional data.

[1210] PerspectiveModule: Generates solutions from cultural, disciplinary and professional perspectives and adjusts them based on emotional state.

[1211] Logic Validation Module: Evaluates the effectiveness and feasibility of each solution and selects the optimal solution.

[1212] Prompt Sentence Examples

[1213] "Based on the emotion data you have, propose the optimal solution to the problem input by the supervisor: 'I want to identify the cause of the robot's malfunction.' Consider solutions from the perspectives of culture, specialty, and job type, and provide prioritized solutions taking into account the user's anxieties."

[1214] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1215] Step 1:

[1216] The user inputs a task using the device. For example, the task might be "I want to identify the cause of a robot malfunction." The device then sends the input task data and emotion data acquired from sensors in use to the server.

[1217] Input: Task data, emotion data

[1218] Output: Issue data and sentiment data sent to the server

[1219] Step 2:

[1220] The server passes the received problem data to a natural language processing module, which extracts key elements. The natural language processing module performs text analysis and identifies important keywords and phrases. Key elements such as "robot," "fault," and "cause" are extracted.

[1221] Input: Issue data

[1222] Data processing: Text analysis using natural language processing

[1223] Output: Key Elements

[1224] Step 3:

[1225] The server uses an emotion engine to analyze the received emotion data and identify the user's emotion state, for example, recognizing an "anxiety" state from the emotion data.

[1226] Input: Emotion data

[1227] Data Computation: Emotional State Analysis with Emotion Engine

[1228] Output: User's emotional state

[1229] Step 4:

[1230] The server sends a solution generation request to the multi-perspective generation module based on the extracted key elements and sentiment data. The multi-perspective generation module generates solutions from the perspectives of different cultures, fields of expertise, and occupations, and creates a solution list. For example, it generates "analysis of log data" from the technology perspective and "on-site inspection by engineers" from the expert perspective.

[1231] Input: Primary element, emotional state

[1232] Data Computing: Generating Solutions from Multiple Perspectives

[1233] Output: Solution list

[1234] Step 5:

[1235] The server adjusts the list of solutions based on the emotion data: the emotion engine responds to the "anxiety" state and prioritizes detailed and quick solutions that put the user at ease.

[1236] Input: Solution list, emotional state

[1237] Data processing: Adjusting solution priorities based on sentiment data

[1238] Output: Reconciled solution list

[1239] Step 6:

[1240] The server passes the adjusted solution list to a logical verification module to evaluate its effectiveness and feasibility, and multiple AI expert modules virtually debate and select the optimal solution.

[1241] Input: Reconciled solution list

[1242] Data Computing: Assessing the Effectiveness and Feasibility of Solutions

[1243] Output: Optimal solution

[1244] Step 7:

[1245] The server sends the optimal solution to the user's device, which displays it, allowing the supervisor to take appropriate measures based on the presented solution.

[1246] Input: Optimal solution

[1247] Output: sent to and displayed on the user's terminal

[1248] 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.

[1249] 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.

[1250] 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.

[1251] [Fourth embodiment]

[1252] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1253] 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.

[1254] 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).

[1255] 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.

[1256] 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.

[1257] 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).

[1258] 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.

[1259] 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.

[1260] 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.

[1261] 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.

[1262] 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.

[1263] 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.

[1264] 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."

[1265] This invention is a system that supports efficient and effective problem solving by allowing a user to input any problem, and then having a server analyze it from multiple perspectives and generate a solution. This system includes a terminal, a server, a natural language processing module, a multiple perspective generation module, a logical verification module, an AI expert module, and a database.

[1266] System configuration and processing flow

[1267] 1. Assignment input

[1268] The user logs in to a terminal that has a problem input screen. The problem input screen has a text box where the user can freely enter the problem they want to solve. For example, "I want to think about how to enter a new market." Once the input is complete, the user clicks the send button and the problem data is sent to the server.

[1269] 2. Analysis of issue information

[1270] The server receives the assignment data sent from the user's device. A natural language processing (NLP) module in the server analyzes the assignment text and extracts key elements. For example, keywords such as "new market" and "entry method" are extracted.

[1271] 3. Solution generation from multiple perspectives

[1272] Based on the extracted elements, the server sends a request for solution generation to the multi-perspective generation module, which accesses the database to obtain relevant information from different cultures, fields of expertise, and occupations, and then generates solutions from each perspective.

[1273] Cultural perspective: Given the effectiveness of web marketing in specific cultural contexts, suggestions are made to strengthen social media advertising.

[1274] Specialist perspective: The technology sector suggests using online platforms to host webinars and promote products and services.

[1275] 4. Logical verification and solution selection

[1276] The server passes the generated solutions to a logical verification module, which collaborates with multiple AI expert modules to virtually discuss the effectiveness and feasibility of each solution, ultimately selecting the most effective solution.

[1277] 5. Providing a solution

[1278] The server sends the evaluated optimal solution to the user's device, which then displays the received solution in an easy-to-read format for the user. The user can then select an action based on the proposed solution.

[1279] Specific examples

[1280] 1. User input:

[1281] The user inputs the problem, "I want to think about how to enter a new market," and submits it.

[1282] 2. Analysis of assignment information:

[1283] The server's natural language processing module extracts "new markets" and "ways to enter the market."

[1284] 3. Solution generation from multiple perspectives:

[1285] The server's multifaceted perspective generation module generates solutions such as strengthening social media advertising (cultural perspective), strengthening market research (profession perspective), and holding web seminars (specialty perspective).

[1286] 4. Logical verification and solution selection:

[1287] The server's logical verification module virtually discusses the issue and determines that strengthening social media advertising and combining it with market research is optimal.

[1288] 5. Propose a solution:

[1289] The server sends the evaluated solutions to the device, which then displays the message on its screen: "Strengthen social media advertising and conduct thorough market research."

[1290] In this way, the system of the present invention analyzes the problem entered by the user from multiple perspectives and provides the optimal solution, thereby solving the problem efficiently and effectively.

[1291] The processing flow will be explained below.

[1292] Step 1:

[1293] The user logs in to the device and opens the task entry screen. They enter the task in the text box and click the submit button. For example, they might enter, "I want to think about how to enter a new market."

[1294] Step 2:

[1295] The terminal sends the assignment data entered by the user to the server in text format.

[1296] Step 3:

[1297] The server receives the submitted problem data and passes it to a natural language processing (NLP) module, which analyzes and extracts key elements. For example, "new market" and "entry method" are extracted.

[1298] Step 4:

[1299] The server sends a request for solution generation to the multi-perspective generation module based on the extracted elements.

[1300] Step 5:

[1301] The server's multi-perspective generation module accesses the database and starts generating solutions from different perspectives:

[1302] Cultural perspective: Solutions based on specific cultural backgrounds, such as "strengthening social media advertising"

[1303] Job-specific perspective: Solutions based on specific job roles, e.g., "strengthening market research"

[1304] Specialist perspective: Solutions based on a specific area of ​​expertise, e.g., "hosting a webinar"

[1305] Step 6:

[1306] The server passes the generated solutions to a logical validation module, which evaluates the effectiveness and feasibility of each solution.

[1307] Step 7:

[1308] The server uses an AI expert module to conduct a virtual discussion and select the optimal solution, for example, "strengthening social media advertising and combining it with market research."

[1309] Step 8:

[1310] The server sends the evaluated optimal solution to the user terminal, which displays the solution on a solution display screen.

[1311] Step 9:

[1312] The user can view the solutions displayed on the terminal, select the solution they think is appropriate, and implement it.

[1313] Example 1

[1314] 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."

[1315] Conventional problem-solving support systems often provide solutions based on a specific perspective or limited information, making it difficult to obtain solutions that reflect multiple perspectives or input from different fields of expertise. Furthermore, they lack the functionality to logically verify the effectiveness and feasibility of solutions, making it impossible to provide effective solutions for users. Therefore, there is a need for a system that allows users to efficiently and effectively obtain solutions from multiple perspectives.

[1316] 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.

[1317] In this invention, the server includes means for transmitting a problem input by a user to the server, means for the server to pass the received problem data to a natural language processing module and extract key elements, means for the server to send a request for solution generation to a multi-perspective generation module based on the extracted elements, means for the server to access a database and acquire related information from the perspectives of different cultures, fields of expertise, and occupations, means for the server to generate solutions from multiple perspectives based on the acquired information, means for the server to pass the generated solutions to a logical verification module and evaluate the optimal solution, means for the server to transmit the evaluated solution to the user terminal, and means for the user terminal to display the received solution. This enables the server to analyze from multiple perspectives and efficiently and effectively provide the user with an optimal solution that has been logically verified.

[1318] "User" refers to the entity that uses the system and inputs tasks.

[1319] "Terminal" refers to a device used by a user, which inputs and transmits tasks and displays solutions.

[1320] "Server" refers to a central processing unit that receives data sent from terminals, analyzes them, and generates and evaluates solutions.

[1321] "Natural language processing module" refers to a software component that analyzes received text data and extracts key elements.

[1322] The "multi-perspective generation module" refers to a software component that obtains relevant information from different cultural, professional, and occupational perspectives and generates solutions.

[1323] "Database" refers to a data storage system that stores information about different cultures, professions, and occupations and makes that information available when needed.

[1324] "Logical Verification Module" refers to a software component that evaluates the effectiveness and feasibility of generated solutions.

[1325] "Expert Module" refers to a software component that has expertise in a particular domain and virtually participates in the evaluation of solutions.

[1326] "Solution" refers to a specific approach or method to the problem entered by the user.

[1327] "Evaluation" refers to the process of examining the effectiveness and feasibility of the generated solutions and selecting the most suitable solution.

[1328] This invention is a system that analyzes a problem entered by a user from multiple perspectives and provides an effective and efficient solution. This system includes a terminal, a server, a natural language processing module, a multiple perspective generation module, a logical verification module, an expert module, and a database.

[1329] The user logs in to the device and enters the problem they want to solve in the text box on the problem input screen. Then, by clicking the send button, the problem data is sent to the server. For example, a user might enter "I want to think about how to enter a new market" and send it.

[1330] The server receives the problem data sent from the device and analyzes it using a natural language processing (NLP) module. This analysis extracts the main elements of the problem. For example, the keyword "new market" may be extracted.

[1331] Next, the server sends a solution generation request to the multi-perspective generation module based on the extracted elements. This module accesses a database to obtain relevant information from different cultural, professional, and occupational perspectives. It then generates solutions from each perspective. Specifically, the cultural perspective generates "proposals to enhance social media advertising in a specific cultural context."

[1332] The generated solutions are passed to the logical verification module by the server. This module collaborates with multiple expert modules to virtually discuss and evaluate the effectiveness and feasibility of each solution. As a result, the most effective solution is selected. For example, "combining strengthened social media advertising with market research" is evaluated as optimal.

[1333] The server sends the evaluated optimal solution to the user's terminal, which then displays the received solution to the user, who can then select an action based on the presented solution.

[1334] As an example of a specific prompt sentence, if a user inputs "I want to think about how to enter a new market," the server will receive and analyze it, retrieve information from the database, generate solutions from multiple perspectives, verify them logically, and send the optimal solution to the user's device.

[1335] This system allows users to efficiently obtain effective solutions that have been analyzed from multiple perspectives.

[1336] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1337] Step 1: Assignment entry

[1338] The user logs in to the device. The user enters the problem they want to solve in the text box displayed on the problem input screen. For example, the user might enter "I want to think about how to enter a new market." Once the input is complete, the user clicks the send button, and the problem data is sent to the server.

[1339] Input: Problem text such as "I want to think about how to enter a new market"

[1340] Output: Issue data sent to the server

[1341] Step 2: Analyze the issue information

[1342] The server receives the problem data sent from the device. It then passes the problem data to a natural language processing (NLP) module, which analyzes and extracts key elements. This process extracts keywords such as "new market" and "entry method."

[1343] Input: Assignment data received from the device

[1344] Output: Key elements analyzed (e.g., "New market" and "Entry method")

[1345] Step 3: Generate solutions from multiple perspectives

[1346] Based on the extracted elements, the server sends a request for solution generation to the multi-perspective generation module. The module accesses the database to obtain relevant information from the perspectives of different cultures, fields of expertise, and occupations. Solutions are generated from each perspective, and from the cultural perspective, for example, a specific solution such as "proposing strengthening social media advertising in a specific cultural context" is generated.

[1347] Input: Parsed key elements

[1348] Output: Multiple solutions generated from different perspectives (e.g., social media advertising reinforcement from a cultural perspective)

[1349] Step 4: Logical verification and solution selection

[1350] The server passes the generated solutions to the logical verification module, which collaborates with multiple expert modules to virtually discuss and evaluate the effectiveness and feasibility of each solution. For example, the optimal solution may be selected as "strengthening social media advertising and conducting market research."

[1351] Input: Multiple generated solutions

[1352] Output: Evaluated optimal solution (e.g., strengthening social media advertising and combining it with market research)

[1353] Step 5: Providing a solution

[1354] The server sends the evaluated optimal solution to the user's device. The device displays the received solution in an easy-to-read format for the user. The user can then choose an action based on the displayed solution. For example, the device screen might say, "Strengthen social media advertising and conduct thorough market research."

[1355] Input: Evaluated optimal solution

[1356] Output: Solution displayed in terminal

[1357] In this way, the system analyzes the problem entered by the user from multiple perspectives and efficiently provides the optimal solution.

[1358] (Application example 1)

[1359] 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."

[1360] Improving production efficiency and troubleshooting are important issues on factory floors, but it is often difficult to find effective solutions immediately on site. In particular, there are limited means to quickly obtain approaches from multiple fields of expertise and perspectives, which makes it difficult for on-site workers to make appropriate decisions. To solve this problem, a system that can quickly provide solutions from multiple perspectives through devices that can be easily used on-site is needed.

[1361] 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.

[1362] In this invention, the server includes means for transmitting a problem input by a user to the server, means for the server to pass the received problem data to a natural language processing module and extract key elements, means for the server to send a request for solution generation to a multi-perspective generation module based on the extracted elements, means for the server to generate solutions from multiple perspectives, means for the server to pass the generated solutions to a logical verification module and evaluate the optimal solution, means for the server to transmit the evaluated solutions to the user terminal, and means for inputting on-site problems using a wearable device or a mobile information terminal and displaying solutions from the server. This enables immediate on-site problem input and rapid presentation of solutions from multi-perspectives.

[1363] A "user terminal" is an electronic device that allows a user to input tasks, and includes smartphones, tablets, personal computers, etc.

[1364] A "server" is a central computer that receives assignment data sent from user terminals and analyzes and processes them.

[1365] The "natural language processing module" is a software module that analyzes the text of assignment data within the server and extracts key elements.

[1366] The "multi-perspective generation module" is a module that generates solutions from different perspectives and fields based on the extracted elements.

[1367] The "logical verification module" is a module for evaluating the effectiveness and feasibility of multiple generated solutions.

[1368] An "AI expert module" is an artificial intelligence module that has a knowledge base specialized in a specific field and virtually debates.

[1369] The "database" is a collection of information accessed by the multi-perspective generation module, and contains information on different cultures, fields of expertise, and occupations.

[1370] "Wearable devices" are electronic devices worn by field workers, including smart glasses and head-mounted displays.

[1371] A "personal digital assistant" is a portable electronic device, including a smartphone or tablet.

[1372] This invention is a system that supports efficient and effective problem-solving in factories by allowing users to input any problem and then having a server analyze it from multiple perspectives and generate solutions. This system includes a user terminal, a server, a natural language processing module, a multiple perspective generation module, a logical verification module, an AI expert module, and a database.

[1373] Components

[1374] 1. User Device

[1375] A user terminal is an electronic device that allows a user to input tasks, and includes a smartphone, tablet, PC, etc.

[1376] Field workers use wearable devices or mobile information terminals to input on-site problems, and solutions are displayed from the server.

[1377] 2. Server

[1378] The server is a central computer that receives the assignment data sent from the user terminal and analyzes and processes it.

[1379] 3. Natural Language Processing Module

[1380] The natural language processing module is a software module that analyzes the text of the assignment data on the server and extracts key elements. Specifically, it uses tools such as SpaCy and NLTK.

[1381] 4. Multi-perspective generation module

[1382] The multi-perspective generation module is a module that generates solutions from different perspectives and fields based on the extracted elements. An example of a generative AI model is GPT-3.

[1383] 5. Logical Verification Module

[1384] The logical verification module is a module for evaluating the effectiveness and feasibility of the generated solutions.

[1385] 6. AI Expert Module

[1386] An AI expert module is an artificial intelligence module that has a knowledge base specialized in a specific field and can hold virtual discussions.

[1387] 7. Database

[1388] The database is a collection of information that the multi-perspective generation module accesses, and contains information on different cultures, fields of expertise, and occupations.

[1389] System Operation Details

[1390] On-site users input their issues, such as "I want to solve the bottleneck on the production line," using a smartphone or head-mounted display. The input issue is sent to the server and analyzed by a natural language processing module. Here, key elements are extracted, and keywords such as "production line" and "bottleneck" are obtained.

[1391] Based on these keywords, the server sends a request for solution generation to the multi-perspective generation module. The multi-perspective generation module retrieves information on different cultures, fields of expertise, and occupations from a database and generates solutions using a generative AI model. For example, it may suggest "optimizing robot movements" or "introducing parallel work."

[1392] The generated solutions are evaluated by a logical verification module and multiple AI expert modules to select the most effective and feasible solution, which is then sent from the server to the user's device and presented to the on-site worker.

[1393] Examples and prompts

[1394] Example: A field worker voice-inputs, "I want to solve the bottleneck on the production line," and the solution to the problem is presented: "Optimize the robot's operation and introduce parallel work."

[1395] Example prompt sentence:

[1396] "X part of the production line is a bottleneck. Please suggest a solution to improve efficiency."

[1397] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1398] Step 1:

[1399] The user inputs the issue on-site.

[1400] Input: The user uses a smartphone or head-mounted display to input voice or text, such as "I want to solve the bottleneck on the production line."

[1401] Specific operation: The device receives the challenge and sends it to the server.

[1402] Step 2:

[1403] The terminal transmits the input assignment data to the server.

[1404] Input: User issue data.

[1405] Output: The issue data sent to the server.

[1406] Specific operation: The terminal sends the assignment data to the server as an HTTP request.

[1407] Step 3:

[1408] The server passes the received assignment data to a natural language processing module, which extracts key elements.

[1409] Input: The issue data sent to the server.

[1410] Output: Extracted key elements (e.g. "production line", "bottleneck").

[1411] How it works: The server uses natural language processing libraries such as SpaCy or NLTK to tokenize the issue data and extract key keywords.

[1412] Step 4:

[1413] The server sends a request for solution generation to the multi-perspective generation module based on the extracted elements.

[1414] Input: Extracted key elements.

[1415] Output: A request for solution generation.

[1416] Specific operation: The server sends a request including the extracted main elements to the multi-perspective generation module.

[1417] Step 5:

[1418] The multi-perspective generation module uses a generative AI model to generate solutions from multiple perspectives.

[1419] Input: Solution generation request.

[1420] Output: Multiple solutions (e.g., "optimize the robot's behavior," "introduce parallel work").

[1421] Specific operation: The multi-perspective generation module retrieves relevant information from the database and generates a solution using a generative AI model (e.g., GPT-3).

[1422] Step 6:

[1423] The server passes the generated solutions to a logical validation module to evaluate the best solution.

[1424] Input: Multiple solutions.

[1425] Output: The solution that is evaluated as optimal.

[1426] Specific operation: The logical verification module conducts a virtual discussion with the AI ​​expert module to select the optimal solution.

[1427] Step 7:

[1428] The server transmits the evaluated optimal solution to the user terminal.

[1429] Input: The solution that was evaluated as optimal.

[1430] Output: The solution sent to the user's device.

[1431] Specific operation: The server sends the optimal solution to the user terminal as an HTTP response.

[1432] 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.

[1433] This invention is a system in which a user inputs any problem, a server analyzes it from multiple perspectives, generates solutions, and then uses an emotion engine to recognize the user's emotions and present appropriate solutions. This system includes a terminal, a server, a natural language processing module, a multiple perspective generation module, a logical verification module, an AI expert module, a database, and an emotion engine.

[1434] System configuration and processing flow

[1435] 1. Assignment input

[1436] The user logs in to the device and opens the task input screen. They enter the task in the text box and click the submit button. For example, they might enter "I want to think about how to enter a new market." Once the input is complete, the emotion data is sent to the server along with the task data.

[1437] 2. Analysis of task information and emotion data

[1438] The server receives task data and emotion data sent from the user's device. A natural language processing (NLP) module analyzes the task text data and extracts key elements. For example, keywords such as "new market" and "entry methods" are extracted. At the same time, an emotion engine analyzes the sent emotion data and recognizes the user's current emotional state.

[1439] 3. Solution generation from multiple perspectives

[1440] Based on the extracted elements and emotion data, the server sends a request for solution generation to the multi-perspective generation module, which accesses a database to obtain relevant information from different cultures, fields of expertise, and occupations. It then generates solutions from each perspective.

[1441] Cultural perspective: Solutions based on specific cultural backgrounds, such as "strengthening social media advertising"

[1442] Specialist perspective: For example, "Hosting webinars" from the technology field

[1443] Job perspective: For example, "Strengthening market research" from the marketing field

[1444] 4. Adjusting the solution to take sentiment data into account

[1445] When generating solutions, the emotion engine adjusts the priority and content of proposed solutions based on the user's emotional state. For example, if the user is feeling anxious, more detailed and reassuring solutions will be given priority.

[1446] 5. Logical verification and solution selection

[1447] The server passes the generated solutions to a logical verification module, which, in collaboration with multiple AI expert modules, evaluates the effectiveness and feasibility of each solution, ultimately selecting the most effective solution.

[1448] 6. Providing a solution

[1449] The server sends the evaluated optimal solution to the user's terminal. The terminal displays the received solution on the solution display screen. The user can select an action based on the proposed solution.

[1450] Specific examples

[1451] 1. User input:

[1452] The user inputs a problem such as "I want to think about how to enter a new market" and submits it. At the same time, emotional data collected using cameras and sensors is also submitted.

[1453] 2. Analysis of task information and emotion data:

[1454] The server's natural language processing module extracts "new markets" and "entry methods." At the same time, the emotion engine analyzes the user's emotion as "anxiety."

[1455] 3. Solution generation from multiple perspectives:

[1456] The server's multifaceted perspective generation module generates the following: strengthening social media advertising (cultural perspective), hosting web seminars (professional field perspective), and strengthening market research (occupation perspective).

[1457] 4. Adjustments based on emotional data:

[1458] Because users feel "anxious," the priority is given to "strengthening market research," which is more detailed and gives a sense of security.

[1459] 5. Logical verification and solution selection:

[1460] The server's logical verification module virtually discusses the issue and concludes that the optimal solution is to "strengthen social media advertising and combine it with market research."

[1461] 6. Propose a solution:

[1462] The server sends the evaluated solutions to the device, which then displays the message "Strengthen social media advertising and conduct thorough market research." The user can then take action based on these solutions.

[1463] In this way, the system of the present invention analyzes the problem entered by the user from multiple perspectives and uses an emotion engine to provide an optimal solution that takes the user's emotions into consideration, thereby solving the problem efficiently and effectively.

[1464] The processing flow will be explained below.

[1465] Step 1:

[1466] The user logs in to the device and opens the task entry screen. They enter their task in the text box and click the submit button. For example, they enter, "I want to think about how to enter a new market." At the same time, emotion data collected by cameras and sensors is also collected on the device.

[1467] Step 2:

[1468] The device sends the task data and emotional data entered by the user to the server. The task data is sent in text format, and the emotional data is sent as sensor data such as facial expressions and voice tones.

[1469] Step 3:

[1470] The server receives the submitted problem data and emotion data. A natural language processing (NLP) module analyzes the text data of the problem and extracts key elements (e.g., "new market" and "entry method"), while an emotion engine analyzes the submitted emotion data and recognizes the user's current emotional state (e.g., "anxiety").

[1471] Step 4:

[1472] The server sends a request for solution generation to the multi-perspective generation module based on the extracted elements and emotion data. This request includes the main elements and the user's emotion information.

[1473] Step 5:

[1474] The server's multi-perspective generation module accesses the database and starts generating solutions from different perspectives:

[1475] Cultural perspective: Solutions based on specific cultural backgrounds, such as "strengthening social media advertising"

[1476] Specialist perspective: "Hosting a web seminar" from the technology field

[1477] Occupational perspective: "Strengthening market research" from the marketing field

[1478] Step 6:

[1479] The server's multifaceted perspective generation module takes into account the emotional data obtained from the emotion engine and adjusts the priority and content of the solution proposals. If the user feels "anxious," it will focus on "strengthening market research" to provide more reassurance.

[1480] Step 7:

[1481] The server passes the generated solutions to a logical verification module, which, in collaboration with multiple AI expert modules, evaluates the effectiveness and feasibility of each solution.

[1482] Step 8:

[1483] The server's logical verification module uses an AI expert module to conduct virtual discussions and select the optimal solution. For example, it may determine that "strengthening social media advertising and combining market research" is optimal.

[1484] Step 9:

[1485] The server sends the evaluated optimal solution to the user's device, which displays it on the solution display screen and presents the specific solution, "Strengthen social media advertising and conduct thorough market research."

[1486] Step 10:

[1487] Users can browse the solutions displayed on their device, select the ones they think are appropriate, and then implement them, such as strengthening market research and starting a social media advertising campaign.

[1488] Example 2

[1489] 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."

[1490] Modern society demands fast and accurate solutions to complex and diverse problems. However, the effectiveness of solutions is often limited due to the difficulty of responding flexibly to the emotions and circumstances of individual users. Another problem is a lack of resources and expertise to conduct analyses from multiple perspectives. To solve these problems, a system is needed that can approach users' problems from multiple perspectives and simultaneously provide optimized solutions that take the user's emotions into account.

[1491] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1492] In this invention, the server includes means for transmitting a problem input by a user to the server, means for the server to pass the received problem data to a natural language processing module and extract key elements, means for the server to send a request for solution generation to a multi-faceted perspective generation module based on the extracted elements, means for the server to send the extracted solution to an emotion engine for adjusting it taking into account emotion data, means for the server to pass the adjusted solution to a logical verification module and evaluate the optimal solution, and means for the server to send the evaluated solution to the user terminal. This makes it possible to provide an optimal solution that takes into account multi-faceted perspectives and the user's emotions.

[1493] "User" refers to an individual or organization that uses the system to enter challenges and receive solutions.

[1494] "Device" refers to the device (e.g., PC, smartphone, tablet) used by a user to enter a challenge and receive a solution.

[1495] "Server" refers to a computer system that receives data sent from users, analyzes the problem, generates, evaluates, and adjusts solutions using various modules, and finally sends the solutions to the user terminal.

[1496] "Natural language processing module" refers to a software module that has the function of analyzing the text data of assignments submitted by users and extracting key elements.

[1497] A "multi-perspective generation module" refers to a software module that has the function of generating solutions from the perspectives of different cultures, fields of expertise, occupations, etc. based on the extracted elements of the problem.

[1498] "Emotion engine" refers to a software module that has the function of analyzing a user's emotional data and using it to adjust the generated solution.

[1499] "Logical verification module" refers to a software module that has the function of evaluating the effectiveness and feasibility of the generated solution.

[1500] "AI Expert Module" refers to a software module that allows multiple virtual experts to discuss and participate in the evaluation of each solution.

[1501] "Database" refers to a data storage system that stores information about different cultures, fields of expertise, and occupations, and from which the multi-perspective generation module can retrieve information.

[1502] "Solution display screen" refers to an interface that displays solutions on a user terminal and allows the user to select an action based on the solutions.

[1503] This invention is a system in which a user inputs any problem, a server analyzes it from multiple perspectives, generates solutions, and then uses an emotion engine to recognize the user's emotions and present appropriate solutions. This system includes a terminal, a server, a natural language processing module, a multiple perspective generation module, a logical verification module, an AI expert module, a database, and an emotion engine.

[1504] First, the user logs in to the device and accesses the problem entry screen. There, they enter their problem in the text box and click the submit button. For example, they might enter, "I want to think about how to enter a new market." At this stage, the user's emotional data is also collected. The device then sends the problem data and emotional data to the server.

[1505] The server receives the task data and emotion data sent from the user's device. The server's natural language processing (NLP) module analyzes the task text data and extracts key elements. For example, keywords such as "new market" and "entry method" are extracted. At the same time, the emotion engine analyzes the emotion data and recognizes the user's current emotional state.

[1506] Based on the extracted elements and emotion data, the server sends a request for solution generation to the multi-perspective generation module. This module accesses a database to obtain relevant information from different cultures, fields of expertise, and occupations. It then generates solutions from each perspective. For example, solutions such as "strengthen social media advertising" from the cultural perspective, "host webinars" from the professional perspective, and "strengthen market research" from the occupation perspective may be generated.

[1507] The server's emotion engine adjusts the priority and content of generated solutions based on the user's emotional state. For example, if the user is feeling anxious, detailed and reassuring solutions will be prioritized. This provides the best solution for the user's situation.

[1508] The server passes the generated solutions to a logical verification module, which, in collaboration with multiple AI expert modules, evaluates the effectiveness and feasibility of each solution, ultimately selecting the most effective solution.

[1509] The server sends the evaluated optimal solution to the user's terminal, which displays it on the solution display screen. The user can then select an action based on the proposed solution.

[1510] Specific examples

[1511] User input:

[1512] The user inputs a problem such as "I want to think about how to enter a new market" and submits it. At the same time, emotional data collected using cameras and sensors is also submitted.

[1513] Task information and emotion data analysis:

[1514] The server's natural language processing module extracts "new markets" and "entry methods." At the same time, the emotion engine analyzes the user's emotion as "anxiety."

[1515] Multi-perspective solution generation:

[1516] The server's multifaceted perspective generation module generates the following: strengthening social media advertising (cultural perspective), hosting web seminars (professional field perspective), and strengthening market research (occupation perspective).

[1517] Adjustments based on sentiment data:

[1518] Because users feel "anxious," the priority is given to "strengthening market research," which is more detailed and gives a sense of security.

[1519] Logical verification and solution selection:

[1520] The server's logical verification module virtually discusses the issue and concludes that the optimal solution is to "strengthen social media advertising and combine it with market research."

[1521] Solution suggestion:

[1522] The server sends the evaluated solutions to the device, which then displays a message on the screen saying, "Strengthen social media advertising and conduct thorough market research." The user then begins to take action based on these solutions.

[1523] Prompt Sentence Examples

[1524] "I'd like to think about how to enter a new market. Currently, many members of my company are feeling uneasy about entering the market. Taking this situation into consideration, could you please tell me an effective way to do so?"

[1525] In this way, this system can solve problems efficiently and effectively by analyzing problems from multiple perspectives based on user input and providing optimal solutions that take emotions into account.

[1526] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1527] Step 1:

[1528] A user logs in to a device and opens the task input screen. The user enters the task in the text box and clicks the submit button. For example, the user might enter, "I want to think about how to enter a new market." The input data also includes the user's emotional data.

[1529] Specific behavior:

[1530] The user enters an issue.

[1531] The user clicks the submit button.

[1532] The device transmits the task data and emotion data to the server.

[1533] input:

[1534] Assignment text (e.g., "I want to think about how to enter a new market.")

[1535] Emotional data (user facial expressions, voice, etc.)

[1536] output:

[1537] The task data and emotion data are sent to the server.

[1538] Step 2:

[1539] The server receives the task data and emotion data sent from the user's device. A natural language processing (NLP) module analyzes the task text data and extracts key elements. For example, keywords such as "new market" and "entry methods" are extracted.

[1540] At the same time, the emotion engine analyzes the emotion data and recognizes the user's current emotional state.

[1541] Specific behavior:

[1542] The server receives the data.

[1543] The NLP module extracts keywords from the text data.

[1544] The emotion engine analyzes the emotion data and recognizes the emotional state.

[1545] input:

[1546] Issue data and emotion data.

[1547] output:

[1548] Extracted keywords.

[1549] The perceived emotional state of the user.

[1550] Step 3:

[1551] Based on the extracted elements and emotion data, the server sends a request for solution generation to the multi-perspective generation module, which accesses a database to obtain relevant information from different cultures, fields of expertise, and occupations. It then generates solutions from each perspective.

[1552] Specific behavior:

[1553] The server sends the request.

[1554] The multi-perspective generation module accesses the database and retrieves relevant information.

[1555] Generate solutions from each perspective.

[1556] input:

[1557] Extracted keywords.

[1558] The perceived emotional state of the user.

[1559] output:

[1560] Solutions from different perspectives (e.g., cultural perspective, disciplinary perspective, occupational perspective).

[1561] Step 4:

[1562] The server uses an emotion engine to tailor the generated solutions based on the user's emotional state: for example, if the user is feeling anxious, detailed and reassuring solutions are preferred.

[1563] Specific behavior:

[1564] The emotion engine reanalyzes the emotion data.

[1565] Adjust the priority and content of solutions.

[1566] input:

[1567] Generated solution.

[1568] The perceived emotional state of the user.

[1569] output:

[1570] Coordinated solutions.

[1571] Step 5:

[1572] The server passes the generated solutions to a logical verification module, which, in collaboration with multiple AI expert modules, evaluates the effectiveness and feasibility of each solution. As a result of the evaluation, the optimal solution is selected.

[1573] Specific behavior:

[1574] The logical verification module receives the solution.

[1575] An AI expert module evaluates each solution.

[1576] Select the best solution.

[1577] input:

[1578] Coordinated solutions.

[1579] output:

[1580] The best solution evaluated.

[1581] Step 6:

[1582] The server sends the evaluated optimal solution to the user's terminal, which displays the received solution on a solution display screen, allowing the user to select an action based on the proposed solution.

[1583] Specific behavior:

[1584] The server sends the best solution.

[1585] The device will display the solution.

[1586] The user chooses an action based on the solution.

[1587] input:

[1588] The best solution evaluated.

[1589] output:

[1590] The solution will be displayed on the device.

[1591] (Application example 2)

[1592] 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."

[1593] Currently, supervisors in the operation and management of factory robots often face complex challenges, making it difficult to find quick and accurate solutions. Furthermore, because the appropriate solution varies depending on the supervisor's emotions and the situation, flexible responses tailored to individual situations are required. This can lead to reduced labor efficiency and adversely affect productivity. The present invention aims to solve these problems and provide a system that allows supervisors to quickly find appropriate solutions in the operation and management of factory robots.

[1594] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1595] In this invention, the server includes means for transmitting a problem input by a user to a terminal to the server, means for the server to pass the received problem data to a natural language processing module and extract key elements, means for the server to send a request for solution generation to a multi-perspective generation module based on the extracted elements and emotion data, means for the server to generate solutions from multiple perspectives, means for the server to adjust the generated solutions in consideration of the emotion data, means for the server to adjust the solutions based on the emotion data and pass them to a logical verification module to evaluate the optimal solution, and means for the server to transmit the evaluated solutions to the user terminal. This makes it possible to provide supervisors with quick and appropriate solutions based on multi-perspectives and emotion data for complex problems they face.

[1596] "Tasks input by users to terminals" refers to problems or questions input to the terminal devices used by users.

[1597] "Means for sending to the server" refers to a device or program that has the function of transmitting the assignment entered by the user into the terminal to the server.

[1598] "Natural Language Processing Module" means software used to analyze submitted assignment data and extract key elements and keywords from the text.

[1599] "Key Elements" refers to the most important keywords or phrases in the submitted assignment.

[1600] "Emotion data" refers to information that identifies the user's emotional state and expresses it in a data format.

[1601] The "multi-perspective generation module" refers to software for generating solutions from different perspectives based on extracted key elements and emotional data.

[1602] "Solution generation request" refers to the act of the server sending a request to generate a solution to the multi-perspective generation module.

[1603] "Means for the server to generate solutions from multiple perspectives" refers to devices or programs that have the functionality to enable the server to generate solutions from the perspectives of different cultures, fields of expertise, occupations, etc.

[1604] "Means for adjusting by taking into account emotional data" refers to a device or program that has the function of adjusting the generated solution based on the emotional state of the user to make it optimal.

[1605] "Logical verification module" refers to software for evaluating the effectiveness and feasibility of generated solutions.

[1606] "AI Expert Module" means a module equipped with an artificial intelligence program with specific expertise.

[1607] The "means for transmitting to the user terminal" refers to a device or program having a function for transmitting the evaluated solution from the server to the terminal device used by the user.

[1608] "Database" means an information management system that stores relevant information and makes it accessible and available as needed.

[1609] The system for implementing this invention begins with a user inputting an operations management issue using a terminal. The server then receives the input issue data and extracts its main elements using a natural language processing module. At this time, an emotion engine analyzes the emotion data and recognizes the user's emotional state.

[1610] The server sends a solution generation request to the multi-perspective generation module based on key elements and emotional data. The multi-perspective generation module generates solutions from different cultural, disciplinary, and professional perspectives and adjusts these solutions based on emotional data. This adjustment may prioritize solutions that are more detailed and reassuring.

[1611] The generated solutions are evaluated for validity and feasibility by a logical verification module. Multiple AI expert modules virtually debate the solutions and ultimately select the optimal solution. This selected solution is then sent to the user's device and displayed.

[1612] Specifically, in the operation and management of factory robots, a supervisor inputs a problem such as "I want to identify the cause of a robot's failure" into a terminal and sends it. At this time, emotional data is also sent, and the server analyzes the data. A natural language processing module extracts keywords such as "robot," "failure," and "cause," and a multifaceted perspective generation module generates solutions. For example, this could include using software to analyze the robot's log data from a technology perspective, or having a specialist technician conduct an on-site inspection from an expert's perspective.

[1613] If the emotion engine recognizes the user's emotion as "anxiety," it prioritizes detailed and reassuring solutions. The logical verification module evaluates the effectiveness of the solutions and sends the optimal solution to the user's device.

[1614] This makes it possible to provide quick and appropriate solutions to the complex challenges faced by supervisors, based on multiple perspectives and emotional data.

[1615] Hardware and software used

[1616] Smartphone / Tablet: Used as an interface for users to enter assignments.

[1617] Server: Processes the issue data and sentiment data.

[1618] Natural Language Processing Module (NLPModule): Analyzes the text data of the assignment and extracts important elements.

[1619] Emotion Engine: Analyzes user emotional data.

[1620] PerspectiveModule: Generates solutions from cultural, disciplinary and professional perspectives and adjusts them based on emotional state.

[1621] Logic Validation Module: Evaluates the effectiveness and feasibility of each solution and selects the optimal solution.

[1622] Prompt Sentence Examples

[1623] "Based on the emotion data you have, propose the optimal solution to the problem input by the supervisor: 'I want to identify the cause of the robot's malfunction.' Consider solutions from the perspectives of culture, specialty, and job type, and provide prioritized solutions taking into account the user's anxieties."

[1624] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1625] Step 1:

[1626] The user inputs a task using the device. For example, the task might be "I want to identify the cause of a robot malfunction." The device then sends the input task data and emotion data acquired from sensors in use to the server.

[1627] Input: Task data, emotion data

[1628] Output: Issue data and sentiment data sent to the server

[1629] Step 2:

[1630] The server passes the received problem data to a natural language processing module, which extracts key elements. The natural language processing module performs text analysis and identifies important keywords and phrases. Key elements such as "robot," "fault," and "cause" are extracted.

[1631] Input: Issue data

[1632] Data processing: Text analysis using natural language processing

[1633] Output: Key Elements

[1634] Step 3:

[1635] The server uses an emotion engine to analyze the received emotion data and identify the user's emotion state, for example, recognizing an "anxiety" state from the emotion data.

[1636] Input: Emotion data

[1637] Data Computation: Emotional State Analysis with Emotion Engine

[1638] Output: User's emotional state

[1639] Step 4:

[1640] The server sends a solution generation request to the multi-perspective generation module based on the extracted key elements and sentiment data. The multi-perspective generation module generates solutions from the perspectives of different cultures, fields of expertise, and occupations, and creates a solution list. For example, it generates "analysis of log data" from the technology perspective and "on-site inspection by engineers" from the expert perspective.

[1641] Input: Primary element, emotional state

[1642] Data Computing: Generating Solutions from Multiple Perspectives

[1643] Output: Solution list

[1644] Step 5:

[1645] The server adjusts the list of solutions based on the emotion data: the emotion engine responds to the "anxiety" state and prioritizes detailed and quick solutions that put the user at ease.

[1646] Input: Solution list, emotional state

[1647] Data processing: Adjusting solution priorities based on sentiment data

[1648] Output: Reconciled solution list

[1649] Step 6:

[1650] The server passes the adjusted solution list to a logical verification module to evaluate its effectiveness and feasibility, and multiple AI expert modules virtually debate and select the optimal solution.

[1651] Input: Reconciled solution list

[1652] Data Computing: Assessing the Effectiveness and Feasibility of Solutions

[1653] Output: Optimal solution

[1654] Step 7:

[1655] The server sends the optimal solution to the user's device, which displays it, allowing the supervisor to take appropriate measures based on the presented solution.

[1656] Input: Optimal solution

[1657] Output: sent to and displayed on the user's terminal

[1658] 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.

[1659] 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.

[1660] 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 robot 414.

[1661] 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.

[1662] 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.

[1663] 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.

[1664] 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).

[1665] 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.

[1666] 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."

[1667] 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.

[1668] 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).

[1669] 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.

[1670] 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.

[1671] 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.

[1672] 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.

[1673] 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.

[1674] 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.

[1675] 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.

[1676] 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.

[1677] 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.

[1678] 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.

[1679] The following is further disclosed regarding the above embodiment.

[1680] (Claim 1)

[1681] means for transmitting a task input by a user to a terminal to a server;

[1682] The server passes the received assignment data to a natural language processing module to extract key elements;

[1683] a means for the server to send a request for solution generation to the multi-perspective generation module based on the extracted elements;

[1684] a means for the server to generate solutions from multiple perspectives;

[1685] a means for the server to pass the generated solutions to a logical validation module to evaluate the optimal solution;

[1686] means for the server to transmit the evaluated solution to a user terminal;

[1687] A system including:

[1688] (Claim 2)

[1689] The system according to claim 1, wherein information on different cultures, specialties, and occupations is obtained from a database, and solutions are generated from each perspective.

[1690] (Claim 3)

[1691] 10. The system of claim 1, wherein multiple AI expert modules virtually debate and evaluate the effectiveness and feasibility of each solution.

[1692] "Example 1"

[1693] (Claim 1)

[1694] means for transmitting a task input by a user to a terminal to a server;

[1695] The server passes the received assignment data to a natural language processing module to extract key elements;

[1696] a means for the server to send a request for solution generation to the multi-perspective generation module based on the extracted elements;

[1697] a means for the server to access the database to retrieve relevant information from different cultural, professional and occupational perspectives;

[1698] A means for the server to generate solutions from multiple perspectives based on the acquired information;

[1699] a means for the server to pass the generated solutions to a logical validation module to evaluate the optimal solution;

[1700] means for the server to transmit the evaluated solution to a user terminal;

[1701] means for displaying the received solution at the user terminal;

[1702] A system including:

[1703] (Claim 2)

[1704] The system according to claim 1, wherein information on different cultures, specialties, and occupations is obtained from a database, and solutions are generated from each perspective.

[1705] (Claim 3)

[1706] 10. The system of claim 1, wherein a plurality of expert modules virtually discuss and evaluate the effectiveness and feasibility of each solution.

[1707] "Application Example 1"

[1708] (Claim 1)

[1709] means for transmitting a task input by a user to a terminal to a server;

[1710] The server passes the received assignment data to a natural language processing module to extract key elements;

[1711] a means for the server to send a request for solution generation to the multi-perspective generation module based on the extracted elements;

[1712] a means for the server to generate solutions from multiple perspectives;

[1713] a means for the server to pass the generated solutions to a logical validation module to evaluate the optimal solution;

[1714] means for the server to transmit the evaluated solution to a user terminal;

[1715] a means for inputting on-site problems using a wearable device or a mobile information terminal and displaying solutions from a server;

[1716] A system including:

[1717] (Claim 2)

[1718] The system according to claim 1, wherein information on different cultures, specialties, and occupations is obtained from a database, and solutions are generated from each perspective.

[1719] (Claim 3)

[1720] 10. The system of claim 1, wherein multiple AI expert modules virtually debate and evaluate the effectiveness and feasibility of each solution.

[1721] "Example 2: Combining Emotion Engines"

[1722] (Claim 1)

[1723] means for transmitting a task input by a user to a terminal to a server;

[1724] The server passes the received assignment data to a natural language processing module to extract key elements;

[1725] a means for the server to send a request for solution generation to the multi-perspective generation module based on the extracted elements;

[1726] a means for the server to generate solutions from multiple perspectives;

[1727] means for the server to send the generated solution to an emotion engine for adjusting the solution in consideration of the emotion data;

[1728] a means for the server to pass the adjusted solutions to a logical validation module to evaluate the optimal solution;

[1729] means for the server to transmit the evaluated solution to a user terminal;

[1730] A system including:

[1731] (Claim 2)

[1732] The system according to claim 1, wherein information on different cultures, specialties, and occupations is obtained from a database, and solutions are generated from each perspective.

[1733] (Claim 3)

[1734] 10. The system of claim 1, wherein multiple AI expert modules virtually debate and evaluate the effectiveness and feasibility of each solution.

[1735] "Application example 2 when combining emotion engines"

[1736] (Claim 1)

[1737] means for transmitting a task input by a user to a terminal to a server;

[1738] The server passes the received assignment data to a natural language processing module to extract key elements;

[1739] a means for the server to send a request for solution generation to the multi-perspective generation module based on the extracted elements and emotion data;

[1740] a means for the server to generate solutions from multiple perspectives;

[1741] means for the server to adjust the generated solutions by taking into account the emotion data;

[1742] The server adjusts the solution based on the emotion data and passes it to the logical validation module to evaluate the optimal solution.

[1743] means for the server to transmit the evaluated solution to a user terminal;

[1744] A system including:

[1745] (Claim 2)

[1746] The system according to claim 1, which obtains information about different cultures, specialties, and occupations from a database and adjusts the priority and content of solutions based on emotional data.

[1747] (Claim 3)

[1748] The system of claim 1, wherein multiple AI expert modules virtually debate, evaluate the effectiveness and feasibility of each solution, and select the optimal solution based on emotional data. [Explanation of symbols]

[1749] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for transmitting a task input by a user to a terminal to a server; The server passes the received assignment data to a natural language processing module to extract key elements; a means for the server to send a request for solution generation to the multi-perspective generation module based on the extracted elements; a means for the server to generate solutions from multiple perspectives; a means for the server to pass the generated solutions to a logical validation module to evaluate the optimal solution; means for the server to transmit the evaluated solution to a user terminal; A system including:

2. The system according to claim 1, wherein information on different cultures, specialties, and occupations is obtained from a database, and solutions are generated from each of the perspectives.

3. 10. The system of claim 1, wherein a plurality of AI expert modules virtually debate and evaluate the effectiveness and feasibility of each solution.

Images