system

Abstract

Provide a system. An input means for a user to input his / her own knowledge and background information; a transmitting means for transmitting the data acquired from the input means to a server; an analysis means for analyzing the data received by the server and identifying background information and areas of interest of the user; instruction generation means for generating custom instructions for the generative AI based on the information identified by the analysis means; a transmitting means for transmitting the custom instruction to a user terminal; an application means for applying the custom instruction to a generative AI; A system including:

Description

[Technical Field]

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

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

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

[0004] In recent years, the use of generative AI has rapidly spread, but its effective use requires custom instructions based on the user's background information. However, conventional generative AI systems have difficulty responding to individual user needs based on their expertise and interests, and have the problem of only being able to provide general answers. As a result, even if a user has specialized knowledge, the answers provided by the AI ​​are often insufficient and useless. There is a growing demand for systems that can solve this issue and provide optimal answers based on the user's expertise and interests. [Means for solving the problem]

[0005] The present invention provides an input means through which a user inputs their own knowledge and background information. It also provides a transmission means for transmitting data acquired from the input means to a server. The server further includes an analysis means for analyzing the data received and identifying the user's background information and areas of interest. It also provides an instruction generation means for generating custom instructions for the generative AI based on the information identified by the analysis means. It also provides a system including a transmission means for transmitting the custom instructions to a user terminal and an application means for applying the custom instructions to the generative AI. This means enables users to obtain optimal answers from the generative AI based on their expertise and interests.

[0006] A "user" is an individual or organization that uses the system and is the entity that inputs their own knowledge and background information.

[0007] "Input means" refers to an interface through which a user inputs their own knowledge and background information, and includes a keyboard, mouse, touch screen, etc.

[0008] The "transmission means" refers to a communication means for transmitting data acquired from the input means to the server, and includes protocols that utilize wired or wireless networks.

[0009] A "server" is a computer system that receives data sent from a user, analyzes it, and performs processing such as generating instructions.

[0010] "Analysis means" refers to algorithms or software that analyze the data received by the server and identify the user's background information and areas of interest.

[0011] "Natural language processing algorithms" are technologies for analyzing input natural language data and understanding its content and meaning, and include text mining, morphological analysis, and semantic analysis.

[0012] The "instruction generation means" is a function that generates custom instructions to be applied to the generative AI based on the information identified by the analysis means.

[0013] "Generative AI" is an artificial intelligence system that generates answers in natural language in response to user questions or requests.

[0014] "Custom instructions" are instructions that allow a generative AI to generate answers in a specific format and content based on the user's background information and areas of interest.

[0015] "Means of application" refers to the method or means for applying the generated custom instructions to the generative AI, including updating configuration files and calling APIs.

[0016] A "user terminal" is a device through which a user interacts with the system, and includes a personal computer, smartphone, tablet, etc. [Brief explanation of the drawings]

[0017] [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

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] 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).

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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."

[0038] The present invention is a system that generates custom instructions for a generative AI based on the user's background information, thereby providing the optimal answer the user desires. Specifically, this system uses the following means.

[0039] System Overview

[0040] 1. Input Method

[0041] User: Accesses the system and enters their knowledge and background information through a dedicated input interface. This interface can be a web form, an application UI, etc. For example, a user who is an educator might enter, "I have over 10 years of teaching experience and would like to learn more about the latest educational technologies."

[0042] 2. Transmission Method

[0043] Terminal: User-entered information is encrypted as JSON data and sent to the server using a secure communication protocol (e.g., HTTPS). This transmission method is built into the client-side application code.

[0044] 3. Data Reception and Analysis

[0045] Server: The received data is decoded and stored in a database. The stored data is then analyzed using natural language processing (NLP) algorithms. Specifically, text mining techniques are used to extract information such as the user's occupation, years of experience, and areas of interest, and a user profile is generated based on the analysis results.

[0046] 4. Instruction Generation

[0047] Server: Automatically generates custom instructions for the generative AI based on user information identified through analytical methods. For example, for a user with extensive teaching experience, the server might generate instructions such as "provide a detailed explanation of the latest educational technologies and examples of their practical applications."

[0048] 5. Sending generation instructions

[0049] Server: The generated custom instructions are re-encrypted and sent to the device via the API.

[0050] 6. Applying Custom Instructions

[0051] Device: The user device applies the received custom instructions to the generative AI and saves them in an instruction configuration file or applies them immediately via an API call.

[0052] 7. User Response

[0053] Generative AI: Generates optimal answers to user questions based on custom instructions. For example, if a user asks, "What are the latest trends in educational technology?", the AI ​​can provide a specific answer such as, "The latest trends in educational technology include personalized learning using AI, virtual classrooms using VR, and the use of gamification."

[0054] 8. Results display

[0055] Terminal: The generated answers are presented visually to the user, either in a web browser or in an application, in the form of text, graphs, charts, etc.

[0056] 9. Feedback Processing

[0057] User: Enters feedback on the provided answer and submits it to the server again. The feedback includes specific comments such as "This information was helpful" or "I would like more information."

[0058] Server: Analyzes the received feedback and helps optimize the custom instructions for the generative AI.

[0059] Through this system, users will be able to effectively obtain information tailored to their own expertise and interests, greatly increasing the utility of generative AI.

[0060] The processing flow will be explained below.

[0061] Step 1:

[0062] User: Accesses the system's website or application and enters their knowledge and background information through a dedicated input interface, for example, "I am a doctor and have been working for five years. I would like to learn more about the latest treatments."

[0063] Step 2:

[0064] Terminal: User-entered information is packaged in JSON format, encrypted as an HTTP POST request, and sent to the server using a security protocol (e.g., HTTPS).

[0065] Step 3:

[0066] Server: Receives the transmitted data, decodes it, and stores it in a database. For security reasons, the data is encrypted before storage. It also operates a monitoring system to detect unauthorized access.

[0067] Step 4:

[0068] Server: Analyzes the user's information stored in the database using a natural language processing (NLP) algorithm. This analysis identifies the user's occupation, years of experience, and specific areas of interest. For example, the following data is extracted: "Occupation: Doctor," "Years of experience: 5 years," and "Area of ​​interest: Latest treatments."

[0069] Step 5:

[0070] Server: Automatically generates custom instructions for the generative AI based on the analysis results. Instructions can be set in the form of, for example, "Provide answers that include detailed explanations and the latest research findings in the medical field."

[0071] Step 6:

[0072] Server: The generated custom instructions are packaged again in JSON format, encrypted, and sent to the device. This process also uses a secure communication protocol.

[0073] Step 7:

[0074] Terminal: Decodes the received custom instructions and applies them to the generative AI, either by updating the configuration file or through API calls.

[0075] Step 8:

[0076] User: Asks a question to the generative AI with custom instructions applied, such as "Please tell me more about the latest anti-cancer drug treatments."

[0077] Step 9:

[0078] Generative AI: Generates optimal answers to user questions based on custom instructions. For example, it generates answers that include expert explanations such as, "New anti-cancer drug treatments include molecular targeted therapy and immunotherapy. Details of each are as follows..."

[0079] Step 10:

[0080] Terminal: The generated answers are displayed on the user's screen, not only in text format but also visually using graphs and charts as needed.

[0081] Step 11:

[0082] Users: Enter feedback on the answers provided. Feedback can be specific, such as "This answer was very helpful" or "I need more information."

[0083] Step 12:

[0084] Server: Re-analyzes the feedback sent by the user and uses it to improve the custom instructions for the generative AI. Based on the feedback, the instruction generation algorithm is adjusted to improve the accuracy of answers in the future.

[0085] This series of processes enables users to efficiently obtain information optimized according to their expertise and interests.

[0086] Example 1

[0087] 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."

[0088] Currently, systems that use generative AI to provide answers to users have difficulty generating customized answers based on the user's background information and areas of interest. Additionally, they lack the ability to optimize system performance based on user feedback, making it difficult to provide information that satisfies users.

[0089] 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.

[0090] In this invention, the server includes input means for a user to input their own knowledge and background information, transmission means for transmitting data acquired from the input means to the server, analysis means for analyzing the data received by the server and identifying the user's background information and areas of interest, instruction generation means for generating custom instructions for the generative AI based on the information identified by the analysis means, transmission means for transmitting the custom instructions to a user terminal, application means for applying the custom instructions to the generative AI, response means for a user to input a question for the generative AI and generate an optimal answer based on the question, display means for visually displaying the generated answer to the user, feedback transmission means for acquiring user feedback and transmitting the feedback to the server, and feedback analysis means for analyzing the feedback and optimizing the custom instructions for the generative AI. This enables users to accurately acquire information based on their own expertise and areas of interest, improving the recognition accuracy and utility value of the entire system.

[0091] A "user" is an individual or entity that accesses the system and inputs their knowledge and background information.

[0092] "Input means" refers to an interface through which a user inputs their own knowledge and background information, such as a web form or an application UI.

[0093] The "transmission means" is a means for transmitting the data entered by the user to the server, and uses data encryption and a secure communication protocol such as HTTP.

[0094] A "server" is a computer system that receives data sent by a user, analyzes it, and performs the necessary processing.

[0095] "Analysis means" refers to algorithms or techniques that analyze the data received by the server and identify the user's background information and areas of interest.

[0096] "Database" means a relational database or other data storage system used by the server to store data received by the server.

[0097] A "natural language processing (NLP) algorithm" is a technology that uses text mining technology and other techniques to analyze user input data and understand its meaning and intent.

[0098] The "instruction generation means" is a function that automatically generates custom instructions for the generative AI based on the user information identified by the analysis means.

[0099] "Generative AI" is an artificial intelligence model that generates optimal answers to user questions based on custom instructions.

[0100] A "response means" is a means by which a generative AI generates the optimal answer to a user's question.

[0101] The "display means" is a means for visually displaying the generated answers to the user, and may be displayed in the form of text, graphs, charts, or the like.

[0102] The "feedback sending means" is a means by which a user inputs feedback on a provided answer and sends it to the server.

[0103] "Feedback analysis means" is a technology that analyzes the feedback received by the server and optimizes the custom instructions of the generative AI.

[0104] A "secure communication protocol" is a protocol for ensuring security when sending and receiving data, and an example of this is HTTPS.

[0105] "Custom instructions" are specialized instructions for generative AI that are automatically generated based on the user's background information.

[0106] The present invention provides a system that generates custom instructions for a generative AI based on a user's background information and provides optimal answers. A specific embodiment of this system will be described in detail below.

[0107] System Overview

[0108] Enter user information

[0109] Users enter their knowledge and background information through a dedicated input interface (web form or application UI). This interface is built using HTML and CSS, and the front-end uses JavaScript® to process user input. For example, an educator might enter, "I have over 10 years of teaching experience. I would like to learn more about the latest educational technologies."

[0110] Sending data

[0111] The terminal encrypts the information entered by the user as JSON format data, uses a standard encryption library, and sends the encrypted data to the server using a secure communication protocol such as HTTPS. This process is implemented using JavaScript or Python coding.

[0112] Receiving and storing data

[0113] The server receives data sent from the terminal, decodes the received data, and stores it in a database. Specifically, it uses a relational database such as MySQL (registered trademark) or PostgreSQL to efficiently manage the received data.

[0114] Data analysis

[0115] The server analyzes the stored data using natural language processing (NLP) algorithms, using Python libraries such as nltk and spaCy, and employs text mining techniques to extract information such as the user's occupation, years of experience, and areas of interest, and then generates a user profile.

[0116] Custom Instruction Generation

[0117] The server automatically generates custom instructions for the generative AI based on the analyzed user information. For example, for a user with extensive teaching experience, the server might generate instructions such as "Provide a detailed explanation of the latest educational technologies and examples of their practical applications." This generation is performed using a generative AI model (e.g., GPT-3 (registered trademark)).

[0118] Sending instructions

[0119] The server then re-encrypts the generated custom instructions and sends them to the device. This process is performed through an API, which uses a standard REST API and can be implemented using a web framework such as Flask or Django.

[0120] Applying the Instructions

[0121] The device applies the received custom instructions to the generative AI. The instructions are stored in a configuration file or applied immediately via API calls, which can include updating a JSON file or making requests to an API endpoint.

[0122] Responding to user questions

[0123] Generative AI generates optimal answers to user questions based on custom instructions. For example, if a user asks, "What are the latest trends in educational technology?", generative AI can provide a specific answer such as, "The latest trends in educational technology include personalized learning using AI, virtual classrooms using VR, and the use of gamification."

[0124] Displaying the results

[0125] The device visually displays the generated answers to the user in the form of text, graphs, charts, etc., delivered in a web browser or application using HTML, CSS, and JavaScript.

[0126] Obtaining and analyzing feedback

[0127] The user inputs feedback on the provided answers and sends it to the server. The feedback sending means is a function for collecting user comments and ratings. The server analyzes the received feedback and uses the feedback analysis means to optimize the custom instructions of the generative AI.

[0128] Examples and prompts

[0129] Specific examples

[0130] User types, "I have over 10 years of teaching experience and would like to learn more about the latest educational technologies."

[0131] The device encrypts the information and sends it to the server via HTTPS.

[0132] The server analyzes the information and identifies the following: "Teaching experience: 10+ years, Area of ​​interest: Educational technology."

[0133] The server generates custom instructions such as "Detailed explanation of the latest educational technologies and their practical applications."

[0134] The server sends these instructions to the terminal, which then applies them to the generative AI.

[0135] When a user asks, "Tell me about the latest trends in education technology," generative AI provides a specific answer.

[0136] Prompt Sentence Examples

[0137] For Educators

[0138] "Write detailed instruction for users with 10+ years of teaching experience about the latest educational technologies and their practical applications."

[0139] For general users

[0140] "Create instructions that take a user's expert background information and generate the best answer based on that information."

[0141] The above is an embodiment of the present invention, which allows a user to accurately obtain information based on their own specialized knowledge or areas of interest.

[0142] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0143] Step 1:

[0144] Users input their knowledge and background information through a dedicated input interface. The input is in text format, for example, "I have more than 10 years of teaching experience. I would like to learn more about the latest educational technologies."

[0145] Input: Text data entered by a user into an input interface.

[0146] Output: The input text data is sent to the next processing step.

[0147] Step 2:

[0148] The device converts the information entered by the user into JSON format data and encrypts it using a standard encryption library to keep the data secure.

[0149] Input: Text data entered by the user.

[0150] Output: Encrypted data in JSON format.

[0151] Step 3:

[0152] The device sends the encrypted data to the server using a secure communication protocol such as HTTPS. The sending process is implemented by program code on the device.

[0153] Input: Encrypted JSON formatted data.

[0154] Output: The encrypted data sent to the server.

[0155] Step 4:

[0156] The server receives the encrypted data and decodes it. The decoded data is then stored in a database, typically a relational database such as MySQL or PostgreSQL.

[0157] Input: Encrypted data.

[0158] Output: The decoded data is stored in the database.

[0159] Step 5:

[0160] The server analyzes the received data using natural language processing (NLP) algorithms. Specifically, it uses Python libraries (nltk, spaCy) to extract the user's occupation, years of experience, and areas of interest.

[0161] Input: Decoded user text data.

[0162] Output: User profile information (occupation, years of experience, areas of interest).

[0163] Step 6:

[0164] The server automatically generates custom instructions for the generative AI based on the analyzed user information. This generation uses a generative AI model (e.g., GPT-3).

[0165] Input: User profile information.

[0166] Output: Custom instructions (e.g., "Describe the latest educational technologies and their practical applications").

[0167] Step 7:

[0168] The server re-encrypts the generated custom instructions and sends them to the device via an API.

[0169] Input: Custom instructions.

[0170] Output: Encrypted custom instructions are sent to the terminal.

[0171] Step 8:

[0172] The device applies the custom instructions it receives to the generative AI, either stored in an instruction configuration file or via an API call.

[0173] Input: Encrypted custom instructions.

[0174] Output: Applied to the generative AI via an instruction configuration file or API calls.

[0175] Step 9:

[0176] The user inputs a question into the generative AI, for example, "Tell me about the latest trends in educational technology."

[0177] Input: The user's question.

[0178] Output: The question is sent to the generative AI.

[0179] Step 10:

[0180] Generative AI generates optimal answers based on custom instructions. For example, it can provide specific answers such as, "The latest trends in educational technology include personalized learning using AI, virtual classrooms using VR, and the use of gamification."

[0181] Input: User questions and custom instructions.

[0182] Output: The best answer generated.

[0183] Step 11:

[0184] The device visually displays the generated answers to the user in the form of text, graphs, charts, etc., within a web browser or application.

[0185] Input: The generated answer.

[0186] Output: The visual information that is displayed to the user.

[0187] Step 12:

[0188] The user inputs feedback for the provided answer and sends it to the server. The user's feedback includes specific comments such as "This information was helpful" or "I would like more information."

[0189] Input: User feedback.

[0190] Output: The feedback data is sent to the server.

[0191] Step 13:

[0192] The server analyzes the received feedback and uses it to optimize the generative AI's custom instructions. Text mining technology is used to analyze the feedback, extracting information to generate more accurate instructions.

[0193] Input: User feedback data.

[0194] Output: Optimized custom instructions.

[0195] (Application example 1)

[0196] 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."

[0197] Existing factory robot systems are difficult to customize based on the skill level and background information of operators, making it difficult to provide efficient instructions or troubleshoot. This problem is particularly pronounced between new employees and experienced operators, and if appropriate information is not provided to both parties, it can have a negative impact on the efficiency and quality of the production process.

[0198] 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.

[0199] In this invention, the server includes an input means for a user to input their own knowledge and background information, a transmission means for transmitting data acquired from the input means, an analysis means for analyzing the data received by the server and identifying the user's background information and areas of interest, an instruction generation means for generating custom instructions for the generative AI based on the information identified by the analysis means, a transmission means for transmitting the custom instructions to a user terminal, an application means for applying the custom instructions to the generative AI, a means installed in a factory robot that manages an industrial process and provides individually customized operating instructions and troubleshooting guides based on the operator's background information, and a feedback processing means for the factory robot to collect and analyze operator feedback and optimize the custom instructions for the generative AI. This enables efficient instruction provision and troubleshooting that corresponds to the individual skill level and background information of the operator.

[0200] The "input means for the user to input his / her own knowledge and background information" is an interface device for the operator to input his / her own skill level, experience, and area of ​​interest.

[0201] The "transmission means for transmitting data acquired from the input means to a server" is a system for transmitting information collected from the input means to a server using a secure communication protocol.

[0202] The "analysis means for analyzing data received by the server and identifying the user's background information and areas of interest" is a system that analyzes data received within the server and identifies the operator's skill level, experience, and areas of interest using natural language processing technology.

[0203] "Instruction generation means for generating custom instructions for the generative AI based on the information identified by the analysis means" refers to a system that creates individual instructions and troubleshooting guides that the generative AI provides to the operator based on the analyzed information.

[0204] The "transmission means for transmitting the custom instructions to the user terminal" is a system that transfers the generated custom instructions to the operator's terminal.

[0205] The "means for applying the custom instructions to the generative AI" is a system that reflects the custom instructions in the settings and commands of the generative AI.

[0206] "A means for installing on a factory robot that manages an industrial process and providing individually customized operating instructions and troubleshooting guides based on the operator's background information" is a system that is installed on a factory robot and provides instructions and guides according to the operator's skills and experience.

[0207] The "feedback processing means for the factory robot to collect and analyze operator feedback to optimize the generative AI's custom instructions" is a system that collects feedback from operators and optimizes the generative AI's instructions based on the results of the analysis.

[0208] This invention is a system that provides factory robots with custom instructions based on background information and generates optimal guides according to the skills and experience of operators. This system aims to improve production efficiency by automatically customizing instructions based on information input by operators.

[0209] System Configuration

[0210] 1. Input Method

[0211] Operators use devices such as tablets and smartphones to input their own operating experience and areas of interest. For example, they input information such as, "I'm a beginner at robot operation. Please teach me the basic operations." through a dedicated user interface.

[0212] 2. Transmission Method

[0213] The entered information is encrypted in JSON format and sent securely to the cloud server using the HTTPS protocol, ensuring the safety of the data.

[0214] 3. Data Analysis

[0215] The server decodes the received data and uses a natural language processing (NLP) engine (e.g., NLTK, SpaCy) to analyze the operator's background information and areas of interest, and then generates an operator profile based on the results. Specifically, it uses keyword extraction and classification techniques to identify the operator's skill level and experience.

[0216] 4. Instruction Generation

[0217] The server generates custom instructions for the generative AI (e.g., GPT-3.5) from the analyzed data. For example, it generates a "step-by-step guide for basic operations" for newcomers with little experience, and a "troubleshooting optimization method" for veterans.

[0218] 5. Sending instructions

[0219] The generated custom instructions are then re-encrypted via an API and sent to the operator's terminal, which provides a user interface to display the received instructions and collect operator feedback.

[0220] 6. Feedback Processing

[0221] Feedback from operators is sent to a cloud server where it is analyzed and used to optimize instructions by the generative AI. For example, specific comments such as "This information was helpful" or "I would like more information" are analyzed.

[0222] Hardware and software used

[0223] Hardware:

[0224] Tablets, smartphones: Devices used by operators to input data about operations and provide feedback.

[0225] Cloud server: Infrastructure for receiving data, analyzing it, and generating instructions.

[0226] software:

[0227] Natural language processing engines: NLTK, SpaCy

[0228] Generative AI models: GPT-3.5, etc.

[0229] Data transmission protocol: HTTPS, JSON format

[0230] Specific examples

[0231] The operator uses a tablet to input and send the message, "I'm a beginner at robot operation. Please teach me the basic operations." The server analyzes the received information and generates custom instructions such as "Step-by-step guide for basic operations: 1. Turn on the power 2. Basic movement operations 3. How to use the sensors," and sends them to the terminal. The operator operates the robot according to the custom instructions and then provides feedback.

[0232] Prompt Sentence Examples

[0233] "Basic Robot Operation Guide: 1. Turning on the power 2. Basic movement operations 3. How to use the sensors"

[0234] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0235] Step 1:

[0236] The user uses a tablet or smartphone to input their own operating experience and areas of interest. At this time, the user enters information such as "I am a beginner at robot operation. Please tell me the basic operations." through a dedicated user interface. The input information is parsed into JSON format.

[0237] input:

[0238] Text data about user experience and areas of interest entered into a tablet or smartphone by the user.

[0239] output:

[0240] Parsed data in JSON format.

[0241] Step 2:

[0242] The terminal transmits the data acquired from the input means to the cloud server in encrypted JSON format using the HTTPS protocol, thereby ensuring the security of the data.

[0243] input:

[0244] Parsed JSON format data.

[0245] output:

[0246] The encrypted data is sent to the cloud server using the HTTPS protocol.

[0247] Step 3:

[0248] The server decodes the received data and uses a natural language processing (NLP) engine to analyze the operator's background information and areas of interest, specifically using NLP tools such as NLTK and SpaCy to perform keyword extraction and classification to identify the operator's skill level and experience.

[0249] input:

[0250] Encrypted JSON formatted data.

[0251] output:

[0252] Operator profile information (skill level, experience, etc.).

[0253] Step 4:

[0254] The server generates custom instructions for the generative AI (e.g., GPT-3.5) from the analyzed data, generating a "step-by-step guide to basic operations" for newcomers with little experience, and a "troubleshooting optimization method" for veterans.

[0255] input:

[0256] Operator profile information.

[0257] output:

[0258] Custom instructions (e.g., "Step-by-step guide to basic operations").

[0259] Step 5:

[0260] The server re-encrypts the generated custom instructions via API and sends them to the operator's device, where the operator displays the received instructions and performs operations based on their content.

[0261] input:

[0262] Custom instructions.

[0263] output:

[0264] Encrypted custom instructions are sent to the operator's terminal.

[0265] Step 6:

[0266] The user operates the robot by following custom instructions displayed, for example, a "step-by-step guide to basic operations."

[0267] input:

[0268] Custom instructions.

[0269] output:

[0270] User control of the robot.

[0271] Step 7:

[0272] After completing the operation, the user inputs feedback into the device. For example, they input comments such as "This information was helpful" or "I would like more detailed information." The device then sends this feedback to the server in JSON format using the transmission method.

[0273] input:

[0274] Text data of user feedback.

[0275] output:

[0276] The feedback data is parsed in JSON format and sent to the server.

[0277] Step 8:

[0278] The server decodes and analyzes the feedback data and uses it to optimize the generative AI's custom instructions, resulting in more accurate instructions for future iterations.

[0279] input:

[0280] Feedback data.

[0281] output:

[0282] Optimized custom instructions.

[0283] 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.

[0284] This invention is a system that generates custom instructions for generative AI based on the user's background information and emotional state, thereby providing the optimal answer the user desires. In particular, this invention achieves more personalized responses by combining an emotion engine that recognizes the user's emotions.

[0285] System Overview

[0286] 1. Input Method

[0287] User: Accesses the system and enters their knowledge and background information through a dedicated input interface, which may include text boxes and voice input options. For example, they might enter, "I'm an engineer with over 10 years of experience. I'm looking for detailed technical information."

[0288] 2. Transmission Method

[0289] Terminal: User-entered information is packaged in JSON format and sent to the server using a secure protocol.

[0290] 3. Data Reception and Analysis

[0291] Server: Decodes the received data, stores it in a specialized database, and analyzes it. Natural language processing (NLP) algorithms are used to identify the user's background information and areas of interest. For example, information such as "Occupation: Engineer," "Years of experience: 10 years," and "Area of ​​interest: Technical details" can be extracted.

[0292] 4. Emotion recognition

[0293] Device: Operates an emotion engine to recognize emotions from the voice and text data input by the user. It uses voice analysis, facial recognition, or text analysis to identify the user's emotional state. For example, it obtains information such as "The user is excited" or "The user is feeling stressed."

[0294] 5. Instruction Generation

[0295] Server: Automatically generates custom instructions for the generative AI based on the background information acquired by the analytical means and the emotional state recognized by the emotion engine. For example, if the user is feeling stressed, the server adds an instruction such as "answer with kindness."

[0296] 6. Sending generation instructions

[0297] Server: Packages the generated custom instructions in JSON format, encrypts them, and sends them to the device.

[0298] 7. Applying Custom Instructions

[0299] Terminal: Decodes the received custom instructions and applies them to the generative AI, either by updating the configuration file or through API calls.

[0300] 8. User Questions

[0301] User: Asks a question to the generative AI with custom instructions applied, for example, "Tell me about the latest trends in AI technology."

[0302] 9. Generative AI Responses

[0303] Generative AI: Generates optimal answers to user questions based on custom instructions. Provides detailed answers based on the user's technical background and emotional state. For example, it generates specific answers such as, "The latest AI technology trends include deep learning, reinforcement learning, and natural language processing. These technologies are..."

[0304] 10. Results display

[0305] Terminal: Generated answers are displayed on the user's screen, often in the form of text, graphs, charts, or other visual aids.

[0306] 11. Feedback Processing

[0307] User: Enter feedback on the answer provided. For example, "This information was very helpful" or "I'd like to see more specific examples."

[0308] Server: Analyzes user feedback and uses it to improve the custom instructions for the generative AI. Based on the feedback, the instruction generation algorithm is adjusted to improve the accuracy of answers in future.

[0309] Through this system, users can efficiently obtain responses optimized for their technical background and emotional state.

[0310] The processing flow will be explained below.

[0311] Step 1:

[0312] User: Accesses the system's website or application and enters their knowledge and background information through a dedicated input interface, for example, "I am a software engineer with over 10 years of experience. I would like to learn more about the latest AI technologies."

[0313] Step 2:

[0314] Terminal: The information entered by the user is packaged in JSON format, encrypted using HTTPS, and sent to the server.

[0315] Step 3:

[0316] Server: Receives the data, decodes it from JSON format, and stores it in a database, which stores the user's background information, occupation, years of experience, areas of interest, etc.

[0317] Step 4:

[0318] Server: Analyzes the stored data using natural language processing (NLP) algorithms, for example, to determine that the user is a software engineer, has more than 10 years of experience, and is interested in AI technology.

[0319] Step 5:

[0320] On the device: Run an emotion engine to recognize emotions from the user's voice and text data. Use voice analysis, facial recognition, or text analysis techniques to identify the user's emotional state. For example, determine whether the user is excited or stressed.

[0321] Step 6:

[0322] Server: Generates custom instructions based on the analyzed background information and emotional state. For example, if the user is excited, the instructions are set to respond in a detailed and positive tone.

[0323] Step 7:

[0324] Server: Repackage the generated custom instructions in JSON format, re-encrypt them, and send them to the device.

[0325] Step 8:

[0326] Terminal: Decodes the received custom instructions and applies them to the generative AI by updating the AI's configuration file or by using an API call to reflect the instructions.

[0327] Step 9:

[0328] User: Asks a question to the generative AI with custom instructions applied, for example, "Tell me about the latest trends in AI technology."

[0329] Step 10:

[0330] Generative AI: Generates optimal answers to user questions based on custom instructions. For example, it provides specific and detailed answers such as, "The latest AI technology trends include deep learning, reinforcement learning, and natural language processing. Each technology is..."

[0331] Step 11:

[0332] Terminal: Generated answers are displayed on the user's screen, and can be visually interpreted in the form of text, graphs, charts, etc.

[0333] Step 12:

[0334] User: Enter feedback on the answer provided. For example, "This information was very helpful. I'd like to see more specific examples."

[0335] Step 13:

[0336] Server: Re-analyzes the feedback sent by the user and uses it to improve the custom instructions for the generative AI. Based on the feedback, the instruction generation algorithm is adjusted to improve the accuracy of answers in the future.

[0337] This allows users to efficiently receive responses that are optimized for their own technical background and emotional state.

[0338] Example 2

[0339] 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."

[0340] Conventional generative AI systems generate answers by taking into account only the user's background information, which means they are unable to provide personalized responses that reflect the user's emotional state. This reduces user satisfaction and makes it difficult to use the system effectively.

[0341] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an input means through which a user inputs their own knowledge and background information, a transmission means for transmitting data acquired from the input means to the server, an analysis means for analyzing the data received by the server and identifying the user's background information and areas of interest, an instruction generation means for generating custom instructions for the generative AI based on information acquired by the analysis means and the emotion recognition means, a transmission means for transmitting the custom instructions to the user terminal, and an application means for applying the custom instructions to the generative AI. This makes it possible to provide an optimal response according to the user's technical background and emotional state.

[0342] "User" refers to an individual or organization that uses the system.

[0343] "Knowledge" is a general term for specialized fields and general information that a user possesses.

[0344] "Background information" refers to personal information such as the user's occupation, years of experience, and areas of interest.

[0345] "Input means" refers to an interface that allows a user to input information through text, voice, or the like.

[0346] The "transmission means" refers to a means for sending data acquired through the input means to the server.

[0347] "Server" refers to a computer system that receives data via the Internet, analyzes it, and performs the necessary processing.

[0348] "Analysis means" refers to the methods and algorithms used by the server to interpret the data received and identify the user's background information and areas of interest.

[0349] "Emotion recognition means" refers to an engine or algorithm for identifying a user's emotional state from their voice or text data.

[0350] "Instruction generation means" refers to a means for automatically generating custom instructions for the generative AI based on information obtained by the analysis means and emotion recognition means.

[0351] "Custom instructions" refers to special instructions or settings that a generative AI needs to generate the best answer to a user's question.

[0352] "Means of application" refers to the means for applying custom instructions to generative AI.

[0353] "Generative AI" refers to models and systems that use artificial intelligence techniques to generate responses in natural language.

[0354] "Natural language processing algorithms" refer to computational methods for understanding and analyzing text data.

[0355] This invention is a system that generates custom instructions for a generative AI based on the user's background information and emotional state, and provides the optimal answer the user desires. This system is specifically designed to achieve more personalized responses by combining an emotion engine that recognizes the user's emotions.

[0356] First, a user logs into the system and enters their knowledge and background information through a dedicated input interface. This interface includes text boxes and voice input options. For example, a user might enter, "I'm an engineer with over 10 years of experience. I'm looking for detailed technical information." This information is packaged in JSON format and sent to the server using a secure protocol (e.g., HTTPS).

[0357] The server decodes the received data, stores it in a specialized database (e.g., MySQL, NoSQL), and then uses natural language processing (NLP) algorithms (e.g., SpaCy, NLTK) to identify the user's background information and areas of interest. The extracted information might be "Occupation: Engineer," "Years of experience: 10 years," or "Area of ​​interest: Technical details."

[0358] Next, the device recognizes emotions from the user's input data. It uses an emotion engine (e.g., IBM Watson® Tone Analyzer, Microsoft® Azure® Emotion API) to identify the user's emotional state using voice analysis, facial recognition, or text analysis. For example, if a user inputs, "I'm very tired from my recent project, but I'd like to learn more about new technologies," the device can obtain an emotional state such as, "The user is feeling tired."

[0359] The server automatically generates custom instructions for the generative AI (e.g., GPT series) based on the background information acquired by the analysis means and the emotional state recognized by the emotion engine. This can include instructions such as "focus on technical details and provide helpful answers." The generated custom instructions are again packaged in JSON format, encrypted, and sent to the device.

[0360] The device that receives the custom instructions decodes them and applies them to the generative AI through configuration file updates or API calls. When a user inputs a question such as, "Please tell me about the latest trends in AI technology," the generative AI generates the optimal answer based on the custom instructions. For example, a specific answer such as, "The latest trends in AI technology include deep learning, reinforcement learning, and natural language processing. These technologies are..." can be obtained.

[0361] Finally, the device displays the generated answer on the user's screen. The display format can be text, graphs, charts, etc. For example, if the user provides feedback on the provided answer, such as "This information was very helpful" or "I'd like to know more specific examples," the server analyzes that feedback and uses it to improve the generative AI's instruction generation algorithm. This allows for improved answer accuracy in future answers.

[0362] This allows users to efficiently obtain responses that are optimized for their technical background and emotional state.

[0363] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0364] Step 1:

[0365] The user enters their knowledge and background information through an input interface. This input can be done using text boxes or voice input options. For example, they might enter information like, "I'm an engineer with over 10 years of experience. I'm looking for detailed technical information." The input data is packaged in JSON format.

[0366] Input: User text / voice input of knowledge and background information

[0367] Output: JSON formatted data package

[0368] Step 2:

[0369] The terminal sends the information entered by the user to the server using a secure protocol (such as HTTPS). Specifically, it is sent as an HTTP POST request. The communication at this time is encrypted, so the safety of the input data is maintained.

[0370] Input: JSON format data package

[0371] Output: HTTP POST request to the server

[0372] Step 3:

[0373] The server decodes the received data and stores it in a specialized database (e.g., MySQL or NoSQL). Next, it uses natural language processing (NLP) algorithms (e.g., SpaCy or NLTK) to identify the user's background information and areas of interest. For example, information such as "Occupation: Engineer," "Years of experience: 10 years," and "Area of ​​interest: Technical details" can be extracted.

[0374] Input: JSON formatted data received as an HTTP POST request to the server

[0375] Output: Decoded user background information and regions of interest

[0376] Step 4:

[0377] The device runs an emotion engine to recognize the user's emotional state from input data. This is done using emotion recognition tools such as IBM Watson Tone Analyzer and Microsoft Azure Emotion API. Through voice analysis, facial recognition, or text analysis, the device identifies the user's emotional state, such as excitement or fatigue.

[0378] Input: JSON formatted text / audio data

[0379] Output: User's emotional state (e.g., excited, tired)

[0380] Step 5:

[0381] The server automatically generates custom instructions for the generative AI based on the analyzed background information and the identified emotional state. For example, if the user is feeling stressed, the server adds an instruction such as "Respond with kindness." The instructions are packaged in JSON format.

[0382] Input: User background information and emotional state

[0383] Output: Custom instructions (JSON format)

[0384] Step 6:

[0385] The server then packages the generated custom instructions in JSON format, encrypts them, and sends them to the device using a secure protocol (such as SSL / TLS).

[0386] Input: Custom instructions (JSON format)

[0387] Output: Encrypted custom instructions (sent to the terminal)

[0388] Step 7:

[0389] The device decodes the received custom instructions and applies them to the generative AI, either through configuration file updates or API calls, allowing the generative AI to generate optimal responses based on the user's information.

[0390] Input: Received custom instructions (JSON format)

[0391] Output: Applied instructions to the generative AI

[0392] Step 8:

[0393] Users can then ask questions to the generative AI with custom instructions applied, for example, by typing, "Tell me about the latest trends in AI technology."

[0394] Input: User question (text input)

[0395] Output: Question data (JSON format)

[0396] Step 9:

[0397] Generative AI generates the best answer to a user's question based on custom instructions. For example, it can provide a specific answer such as, "The latest trends in AI technology include deep learning, reinforcement learning, and natural language processing. These technologies are..."

[0398] Input: User question data (JSON format)

[0399] Output: Best answer (text format)

[0400] Step 10:

[0401] The terminal displays the generated answers on the user screen. The display format can be text, graphs, charts, etc. For example, if you need a graph to visually explain the latest technology trends, you can display it using an appropriate library (e.g., D3.js or Chart.js).

[0402] Input: Generated answer (text format)

[0403] Output: Answer displayed to the user

[0404] Step 11:

[0405] The user can input feedback for the provided answer, such as "This information was very helpful" or "I would like to know more specific examples."

[0406] Input: User feedback (text input)

[0407] Output: Feedback data (JSON format)

[0408] The server analyzes user feedback and uses it to improve the custom instructions of the generative AI. The feedback data is fed back to a new custom instruction generation algorithm to improve the accuracy of answers from the next time onwards.

[0409] Input: Feedback data (JSON format)

[0410] Output: Improved custom instruction generation algorithm

[0411] (Application example 2)

[0412] 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."

[0413] When a user searches for or purchases products in a virtual store, there is a need for a system that automatically provides optimal product suggestions and information based on the user's emotional state and background information. However, while conventional systems can generate responses based on the user's background information, they cannot generate responses that take the user's emotional state into account. As a result, optimal suggestions are not made based on the user's emotions when searching for products, which can lead to a decrease in satisfaction and a decrease in purchasing motivation.

[0414] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes an input means through which a user inputs their own knowledge and background information, a transmission means for transmitting data acquired from the input means to the server, an analysis means for analyzing the data received by the server and identifying the user's background information and areas of interest, an instruction generation means for generating custom instructions for the generative AI based on the information identified by the analysis means, a transmission means for transmitting the custom instructions to the user terminal, an application means for applying the custom instructions to the generative AI, an emotion recognition means for recognizing the user's emotional state from the user's input, and a suggestion means for suggesting optimal products and providing information in a virtual store based on the user's background information and emotional state. This enables suggestions and answers optimized for the user's technical background and emotional state.

[0415] A "user" is an entity that accesses the system and inputs their knowledge and background information.

[0416] "Background information" is personal information such as the user's occupation, years of experience, areas of interest, etc.

[0417] "Input means" refers to an interface through which a user inputs their own knowledge and background information.

[0418] The "transmission means" is a means for transmitting data acquired from the input means to the server.

[0419] The "server" is the central processing unit of the system that analyzes the received data and generates optimal instructions for the user.

[0420] The "analysis means" is a means for analyzing the data received by the server and identifying the user's background information and areas of interest.

[0421] The "instruction generation means" is a means for generating custom instructions for the generative AI based on the information identified by the analysis means.

[0422] "Custom instructions" are specific instructions to a generative AI that are generated based on the user's background information and emotional state.

[0423] The "application means" is a means for applying the generated custom instructions to the generative AI.

[0424] "Emotion recognition means" is a means for recognizing an emotional state from a user's input.

[0425] The "suggestion means" is a means for suggesting optimal products and providing information within the virtual store based on the user's background information and emotional state.

[0426] "Generative AI" is artificial intelligence that generates optimal responses and suggestions based on the user's background information and emotional state.

[0427] A "virtual store" is a virtual store set up on the Internet to offer products and services.

[0428] The system of the present invention is a solution for virtual stores that provides optimal product suggestions and information to users based on their background information and emotional state. This system provides support for users to efficiently search for and purchase products in stores.

[0429] System Overview

[0430] The system consists of the following components:

[0431] 1. User Device

[0432] The user device provides an interface for users to input their background information and emotional state. Specifically, a smartphone or a head-mounted display (HMD) is used.

[0433] 2. Server

[0434] The server receives and analyzes data sent from the user's device. It is equipped with a natural language processing engine (NLPProcessor) and an emotion recognition engine (EmotionRecognition).

[0435] 3. Generative AI

[0436] Generative AI (Custom AI) provides optimal product suggestions and information to users based on custom instructions received from the server.

[0437] User terminal processing

[0438] The user terminal is equipped with a text box and / or voice input options for the user to enter information, such as "I am a designer with over 5 years of experience." This information is then sent to the server via a security protocol.

[0439] Server Processing

[0440] The server analyzes the received data using a natural language processing engine (NLPProcessor) to identify the user's background information and emotional state. For example, information such as "Occupation: Designer," "Years of Experience: 5 years," and "Emotion: Excited" may be analyzed. The custom instructions constructed based on this information include instructions for the generative AI on how to respond.

[0441] emotion recognition

[0442] The EmotionRecognition engine recognizes the emotional state of a user from their input data. It uses techniques from speech analysis, facial recognition, and text analysis. For example, if a user's input includes "I'm super excited about the new design tool," the EmotionRecognition engine will identify the emotional state as "excited."

[0443] Custom Instruction Generation

[0444] The server generates custom instructions based on the analysis results, such as "Since the user is a designer and is excited, kindly provide detailed information about the latest design tools." This custom instruction is sent to the AI ​​generator, which then provides optimal product suggestions and information.

[0445] Generative AI response

[0446] The generative AI responds to the user according to the custom instructions it receives. For example, in response to a user question, "Tell me about new design tools," it generates a specific answer such as, "CAD software X is a cutting-edge design tool. Using this..."

[0447] Feedback Processing

[0448] Users can enter feedback on the answers provided, which is sent to the server to help improve the generated AI's custom instructions.

[0449] Specific examples

[0450] For example, if a user enters, "I'm a designer and I'm looking for the latest design tools," and then asks, "Tell me about new design tools," the system will suggest the latest design software and examples of its use based on the user's background information and emotional state.

[0451] Prompt Sentence Examples

[0452] "I'm a designer with over 5 years of experience."

[0453] "Tell me about the latest design tools."

[0454] In this way, users can receive personalized suggestions and answers that are optimized for their background information and emotional state, making their shopping experience in the virtual store more efficient and satisfying.

[0455] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0456] Step 1:

[0457] Enter the user's background information. The user enters their background information and areas of interest through a text box or voice input interface. For example, they might enter information such as, "I'm a designer with over 5 years of experience." This becomes the initial input data for the system.

[0458] Step 2:

[0459] The device sends the entered data to the server. The obtained user background information is packaged in JSON format and sent to the server using a security protocol (e.g., HTTPS). At this time, the data is formatted and validated to prevent unauthorized data entry.

[0460] input:

[0461] User-supplied background information (e.g., "I'm a designer with over 5 years of experience.")

[0462] output:

[0463] JSON format data (e.g., "{"Occupation": "Designer", "Experience": "5+ years"}")

[0464] Step 3:

[0465] The server analyzes the received data. The server decodes the received JSON format data and analyzes it using a natural language processing engine (NLPProcessor). For example, information such as "Occupation: Designer" and "Years of experience: 5 years" is extracted and stored in a database.

[0466] input:

[0467] User data in JSON format

[0468] output:

[0469] Analyzed background information (e.g., "Occupation: Designer" and "Years of experience: 5 years")

[0470] Step 4:

[0471] Emotional states are identified using emotion recognition means. The emotion engine (EmotionRecognition) recognizes emotional states based on the voice and text data entered by the user. Using voice analysis and text analysis techniques, emotional states such as "the user is excited" are identified.

[0472] input:

[0473] User-entered text and voice data

[0474] output:

[0475] Perceived emotional state (e.g., "I'm excited")

[0476] Step 5:

[0477] The server generates custom instructions. Based on the background information and emotional state identified by the analysis means, the instruction generation means generates custom instructions containing specific instructions for the generative AI, such as "provide a friendly description of the latest tools for designers."

[0478] input:

[0479] Background information and emotional state

[0480] output:

[0481] Custom instructions (e.g., "Helpful instructions on the latest tools for designers")

[0482] Step 6:

[0483] The custom instructions are sent to the user device. The server packages the generated custom instructions in JSON format and sends them to the user device using a security protocol. The user device decodes the received custom instructions.

[0484] input:

[0485] Generated Custom Instructions

[0486] output:

[0487] Custom instructions in JSON format sent to the user device

[0488] Step 7:

[0489] Apply custom instructions to the generative AI. Custom instructions received on the user's device are applied to the generative AI (CustomAI). This is done by updating the configuration file or by calling the API.

[0490] input:

[0491] Decoded Custom Instructions

[0492] output:

[0493] New instructions set for generative AI

[0494] Step 8:

[0495] A user asks a generative AI a question, for example, "Tell me about a new design tool." The generative AI generates the best answer based on custom instructions.

[0496] input:

[0497] User questions (e.g., "Tell me about the new design tool.")

[0498] output:

[0499] Generative AI answers (e.g., "The latest design tool is CAD software X. Using this...")

[0500] Step 9:

[0501] The terminal displays the generated answer to the user, and the generated answer is displayed on the user's screen in a visually easy-to-understand format such as text or a graph.

[0502] input:

[0503] Generative AI answers

[0504] output:

[0505] The answer displayed on the user's device (e.g., "CAD software X is a cutting-edge design tool. Using this...")

[0506] Step 10:

[0507] Feedback processing is performed. The user enters feedback on the provided answers. For example, they enter their impressions, such as "This information was very helpful." This feedback is sent to the server and used to improve the generative AI.

[0508] input:

[0509] User feedback (e.g., "This information was very helpful")

[0510] output:

[0511] Generative AI improvement data

[0512] In this way, a personalized purchasing experience based on the user's technological background and emotional state is achieved.

[0513] 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.

[0514] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0515] 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.

[0516] [Second embodiment]

[0517] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0518] 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.

[0519] 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).

[0520] 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.

[0521] 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.

[0522] 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).

[0523] 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.

[0524] 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.

[0525] 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.

[0526] 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.

[0527] 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.

[0528] 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."

[0529] The present invention is a system that generates custom instructions for a generative AI based on the user's background information, thereby providing the optimal answer the user desires. Specifically, this system uses the following means.

[0530] System Overview

[0531] 1. Input Method

[0532] User: Accesses the system and enters their knowledge and background information through a dedicated input interface. This interface can be a web form, an application UI, etc. For example, a user who is an educator might enter, "I have over 10 years of teaching experience and would like to learn more about the latest educational technologies."

[0533] 2. Transmission Method

[0534] Terminal: User-entered information is encrypted as JSON data and sent to the server using a secure communication protocol (e.g., HTTPS). This transmission method is built into the client-side application code.

[0535] 3. Data Reception and Analysis

[0536] Server: The received data is decoded and stored in a database. The stored data is then analyzed using natural language processing (NLP) algorithms. Specifically, text mining techniques are used to extract information such as the user's occupation, years of experience, and areas of interest, and a user profile is generated based on the analysis results.

[0537] 4. Instruction Generation

[0538] Server: Automatically generates custom instructions for the generative AI based on user information identified through analytical methods. For example, for a user with extensive teaching experience, the server might generate instructions such as "provide a detailed explanation of the latest educational technologies and examples of their practical applications."

[0539] 5. Sending generation instructions

[0540] Server: The generated custom instructions are re-encrypted and sent to the device via the API.

[0541] 6. Applying Custom Instructions

[0542] Device: The user device applies the received custom instructions to the generative AI and saves them in an instruction configuration file or applies them immediately via an API call.

[0543] 7. User Response

[0544] Generative AI: Generates optimal answers to user questions based on custom instructions. For example, if a user asks, "What are the latest trends in educational technology?", the AI ​​can provide a specific answer such as, "The latest trends in educational technology include personalized learning using AI, virtual classrooms using VR, and the use of gamification."

[0545] 8. Results display

[0546] Terminal: The generated answers are presented visually to the user, either in a web browser or in an application, in the form of text, graphs, charts, etc.

[0547] 9. Feedback Processing

[0548] User: Enters feedback on the provided answer and submits it to the server again. The feedback includes specific comments such as "This information was helpful" or "I would like more information."

[0549] Server: Analyzes the received feedback and helps optimize the custom instructions for the generative AI.

[0550] Through this system, users will be able to effectively obtain information tailored to their own expertise and interests, greatly increasing the utility of generative AI.

[0551] The processing flow will be explained below.

[0552] Step 1:

[0553] User: Accesses the system's website or application and enters their knowledge and background information through a dedicated input interface, for example, "I am a doctor and have been working for five years. I would like to learn more about the latest treatments."

[0554] Step 2:

[0555] Terminal: User-entered information is packaged in JSON format, encrypted as an HTTP POST request, and sent to the server using a security protocol (e.g., HTTPS).

[0556] Step 3:

[0557] Server: Receives the transmitted data, decodes it, and stores it in a database. For security reasons, the data is encrypted before storage. It also operates a monitoring system to detect unauthorized access.

[0558] Step 4:

[0559] Server: Analyzes the user's information stored in the database using a natural language processing (NLP) algorithm. This analysis identifies the user's occupation, years of experience, and specific areas of interest. For example, the following data is extracted: "Occupation: Doctor," "Years of experience: 5 years," and "Area of ​​interest: Latest treatments."

[0560] Step 5:

[0561] Server: Automatically generates custom instructions for the generative AI based on the analysis results. Instructions can be set in the form of, for example, "Provide answers that include detailed explanations and the latest research findings in the medical field."

[0562] Step 6:

[0563] Server: The generated custom instructions are packaged again in JSON format, encrypted, and sent to the device. This process also uses a secure communication protocol.

[0564] Step 7:

[0565] Terminal: Decodes the received custom instructions and applies them to the generative AI, either by updating the configuration file or through API calls.

[0566] Step 8:

[0567] User: Asks a question to the generative AI with custom instructions applied, such as "Please tell me more about the latest anti-cancer drug treatments."

[0568] Step 9:

[0569] Generative AI: Generates optimal answers to user questions based on custom instructions. For example, it generates answers that include expert explanations such as, "New anti-cancer drug treatments include molecular targeted therapy and immunotherapy. Details of each are as follows..."

[0570] Step 10:

[0571] Terminal: The generated answers are displayed on the user's screen, not only in text format but also visually using graphs and charts as needed.

[0572] Step 11:

[0573] Users: Enter feedback on the answers provided. Feedback can be specific, such as "This answer was very helpful" or "I need more information."

[0574] Step 12:

[0575] Server: Re-analyzes the feedback sent by the user and uses it to improve the custom instructions for the generative AI. Based on the feedback, the instruction generation algorithm is adjusted to improve the accuracy of answers in the future.

[0576] This series of processes enables users to efficiently obtain information optimized according to their expertise and interests.

[0577] Example 1

[0578] 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."

[0579] Currently, systems that use generative AI to provide answers to users have difficulty generating customized answers based on the user's background information and areas of interest. Additionally, they lack the ability to optimize system performance based on user feedback, making it difficult to provide information that satisfies users.

[0580] 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.

[0581] In this invention, the server includes input means for a user to input their own knowledge and background information, transmission means for transmitting data acquired from the input means to the server, analysis means for analyzing the data received by the server and identifying the user's background information and areas of interest, instruction generation means for generating custom instructions for the generative AI based on the information identified by the analysis means, transmission means for transmitting the custom instructions to a user terminal, application means for applying the custom instructions to the generative AI, response means for a user to input a question for the generative AI and generate an optimal answer based on the question, display means for visually displaying the generated answer to the user, feedback transmission means for acquiring user feedback and transmitting the feedback to the server, and feedback analysis means for analyzing the feedback and optimizing the custom instructions for the generative AI. This enables users to accurately acquire information based on their own expertise and areas of interest, improving the recognition accuracy and utility value of the entire system.

[0582] A "user" is an individual or entity that accesses the system and inputs their knowledge and background information.

[0583] "Input means" refers to an interface through which a user inputs their own knowledge and background information, such as a web form or an application UI.

[0584] The "transmission means" is a means for transmitting the data entered by the user to the server, and uses data encryption and a secure communication protocol such as HTTP.

[0585] A "server" is a computer system that receives data sent by a user, analyzes it, and performs the necessary processing.

[0586] "Analysis means" refers to algorithms or techniques that analyze the data received by the server and identify the user's background information and areas of interest.

[0587] "Database" means a relational database or other data storage system used by the server to store data received by the server.

[0588] A "natural language processing (NLP) algorithm" is a technology that uses text mining technology and other techniques to analyze user input data and understand its meaning and intent.

[0589] The "instruction generation means" is a function that automatically generates custom instructions for the generative AI based on the user information identified by the analysis means.

[0590] "Generative AI" is an artificial intelligence model that generates optimal answers to user questions based on custom instructions.

[0591] A "response means" is a means by which a generative AI generates the optimal answer to a user's question.

[0592] The "display means" is a means for visually displaying the generated answers to the user, and may be displayed in the form of text, graphs, charts, or the like.

[0593] The "feedback sending means" is a means by which a user inputs feedback on a provided answer and sends it to the server.

[0594] "Feedback analysis means" is a technology that analyzes the feedback received by the server and optimizes the custom instructions of the generative AI.

[0595] A "secure communication protocol" is a protocol for ensuring security when sending and receiving data, and an example of this is HTTPS.

[0596] "Custom instructions" are specialized instructions for generative AI that are automatically generated based on the user's background information.

[0597] The present invention provides a system that generates custom instructions for a generative AI based on a user's background information and provides optimal answers. A specific embodiment of this system will be described in detail below.

[0598] System Overview

[0599] Enter user information

[0600] Users enter their knowledge and background information through a dedicated input interface (web form or application UI). This interface is built using HTML and CSS, and the front-end uses JavaScript to process user input. For example, an educator might enter, "I have over 10 years of teaching experience and would like to learn more about the latest educational technologies."

[0601] Sending data

[0602] The terminal encrypts the information entered by the user as JSON format data, uses a standard encryption library, and sends the encrypted data to the server using a secure communication protocol such as HTTPS. This process is implemented using JavaScript or Python coding.

[0603] Receiving and storing data

[0604] The server receives the data sent from the device, decodes it, and stores it in a database. Specifically, it uses a relational database such as MySQL or PostgreSQL to efficiently manage the received data.

[0605] Data analysis

[0606] The server analyzes the stored data using natural language processing (NLP) algorithms, using Python libraries such as nltk and spaCy, and employs text mining techniques to extract information such as the user's occupation, years of experience, and areas of interest, and then generates a user profile.

[0607] Custom Instruction Generation

[0608] The server automatically generates custom instructions for the generative AI based on the analyzed user information. For example, for a user with extensive teaching experience, the server might generate instructions such as "Provide a detailed explanation of the latest educational technologies and examples of their practical applications." This generation is performed using a generative AI model (e.g., GPT-3).

[0609] Sending instructions

[0610] The server then re-encrypts the generated custom instructions and sends them to the device. This process is performed through an API, which uses a standard REST API and can be implemented using a web framework such as Flask or Django.

[0611] Applying the Instructions

[0612] The device applies the received custom instructions to the generative AI. The instructions are stored in a configuration file or applied immediately via API calls, which can include updating a JSON file or making requests to an API endpoint.

[0613] Responding to user questions

[0614] Generative AI generates optimal answers to user questions based on custom instructions. For example, if a user asks, "What are the latest trends in educational technology?", generative AI can provide a specific answer such as, "The latest trends in educational technology include personalized learning using AI, virtual classrooms using VR, and the use of gamification."

[0615] Displaying the results

[0616] The device visually displays the generated answers to the user in the form of text, graphs, charts, etc., delivered in a web browser or application using HTML, CSS, and JavaScript.

[0617] Obtaining and analyzing feedback

[0618] The user inputs feedback on the provided answers and sends it to the server. The feedback sending means is a function for collecting user comments and ratings. The server analyzes the received feedback and uses the feedback analysis means to optimize the custom instructions of the generative AI.

[0619] Examples and prompts

[0620] Specific examples

[0621] User types, "I have over 10 years of teaching experience and would like to learn more about the latest educational technologies."

[0622] The device encrypts the information and sends it to the server via HTTPS.

[0623] The server analyzes the information and identifies the following: "Teaching experience: 10+ years, Area of ​​interest: Educational technology."

[0624] The server generates custom instructions such as "Detailed explanation of the latest educational technologies and their practical applications."

[0625] The server sends these instructions to the terminal, which then applies them to the generative AI.

[0626] When a user asks, "Tell me about the latest trends in education technology," generative AI provides a specific answer.

[0627] Prompt Sentence Examples

[0628] For Educators

[0629] "Write detailed instruction for users with 10+ years of teaching experience about the latest educational technologies and their practical applications."

[0630] For general users

[0631] "Create instructions that take a user's expert background information and generate the best answer based on that information."

[0632] The above is an embodiment of the present invention, which allows a user to accurately obtain information based on their own specialized knowledge or areas of interest.

[0633] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0634] Step 1:

[0635] Users input their knowledge and background information through a dedicated input interface. The input is in text format, for example, "I have more than 10 years of teaching experience. I would like to learn more about the latest educational technologies."

[0636] Input: Text data entered by a user into an input interface.

[0637] Output: The input text data is sent to the next processing step.

[0638] Step 2:

[0639] The device converts the information entered by the user into JSON format data and encrypts it using a standard encryption library to keep the data secure.

[0640] Input: Text data entered by the user.

[0641] Output: Encrypted data in JSON format.

[0642] Step 3:

[0643] The device sends the encrypted data to the server using a secure communication protocol such as HTTPS. The sending process is implemented by program code on the device.

[0644] Input: Encrypted JSON formatted data.

[0645] Output: The encrypted data sent to the server.

[0646] Step 4:

[0647] The server receives the encrypted data and decodes it. The decoded data is then stored in a database, typically a relational database such as MySQL or PostgreSQL.

[0648] Input: Encrypted data.

[0649] Output: The decoded data is stored in the database.

[0650] Step 5:

[0651] The server analyzes the received data using natural language processing (NLP) algorithms. Specifically, it uses Python libraries (nltk, spaCy) to extract the user's occupation, years of experience, and areas of interest.

[0652] Input: Decoded user text data.

[0653] Output: User profile information (occupation, years of experience, areas of interest).

[0654] Step 6:

[0655] The server automatically generates custom instructions for the generative AI based on the analyzed user information. This generation uses a generative AI model (e.g., GPT-3).

[0656] Input: User profile information.

[0657] Output: Custom instructions (e.g., "Describe the latest educational technologies and their practical applications").

[0658] Step 7:

[0659] The server re-encrypts the generated custom instructions and sends them to the device via an API.

[0660] Input: Custom instructions.

[0661] Output: Encrypted custom instructions are sent to the terminal.

[0662] Step 8:

[0663] The device applies the custom instructions it receives to the generative AI, either stored in an instruction configuration file or via an API call.

[0664] Input: Encrypted custom instructions.

[0665] Output: Applied to the generative AI via an instruction configuration file or API calls.

[0666] Step 9:

[0667] The user inputs a question into the generative AI, for example, "Tell me about the latest trends in educational technology."

[0668] Input: The user's question.

[0669] Output: The question is sent to the generative AI.

[0670] Step 10:

[0671] Generative AI generates optimal answers based on custom instructions. For example, it can provide specific answers such as, "The latest trends in educational technology include personalized learning using AI, virtual classrooms using VR, and the use of gamification."

[0672] Input: User questions and custom instructions.

[0673] Output: The best answer generated.

[0674] Step 11:

[0675] The device visually displays the generated answers to the user in the form of text, graphs, charts, etc., within a web browser or application.

[0676] Input: The generated answer.

[0677] Output: The visual information that is displayed to the user.

[0678] Step 12:

[0679] The user inputs feedback for the provided answer and sends it to the server. The user's feedback includes specific comments such as "This information was helpful" or "I would like more information."

[0680] Input: User feedback.

[0681] Output: The feedback data is sent to the server.

[0682] Step 13:

[0683] The server analyzes the received feedback and uses it to optimize the generative AI's custom instructions. Text mining technology is used to analyze the feedback, extracting information to generate more accurate instructions.

[0684] Input: User feedback data.

[0685] Output: Optimized custom instructions.

[0686] (Application example 1)

[0687] 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."

[0688] Existing factory robot systems are difficult to customize based on the skill level and background information of operators, making it difficult to provide efficient instructions or troubleshoot. This problem is particularly pronounced between new employees and experienced operators, and if appropriate information is not provided to both parties, it can have a negative impact on the efficiency and quality of the production process.

[0689] 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.

[0690] In this invention, the server includes an input means for a user to input their own knowledge and background information, a transmission means for transmitting data acquired from the input means, an analysis means for analyzing the data received by the server and identifying the user's background information and areas of interest, an instruction generation means for generating custom instructions for the generative AI based on the information identified by the analysis means, a transmission means for transmitting the custom instructions to a user terminal, an application means for applying the custom instructions to the generative AI, a means installed in a factory robot that manages an industrial process and provides individually customized operating instructions and troubleshooting guides based on the operator's background information, and a feedback processing means for the factory robot to collect and analyze operator feedback and optimize the custom instructions for the generative AI. This enables efficient instruction provision and troubleshooting that corresponds to the individual skill level and background information of the operator.

[0691] The "input means for the user to input his / her own knowledge and background information" is an interface device for the operator to input his / her own skill level, experience, and area of ​​interest.

[0692] The "transmission means for transmitting data acquired from the input means to a server" is a system for transmitting information collected from the input means to a server using a secure communication protocol.

[0693] The "analysis means for analyzing data received by the server and identifying the user's background information and areas of interest" is a system that analyzes data received within the server and identifies the operator's skill level, experience, and areas of interest using natural language processing technology.

[0694] "Instruction generation means for generating custom instructions for the generative AI based on the information identified by the analysis means" refers to a system that creates individual instructions and troubleshooting guides that the generative AI provides to the operator based on the analyzed information.

[0695] The "transmission means for transmitting the custom instructions to the user terminal" is a system that transfers the generated custom instructions to the operator's terminal.

[0696] The "means for applying the custom instructions to the generative AI" is a system that reflects the custom instructions in the settings and commands of the generative AI.

[0697] "A means for installing on a factory robot that manages an industrial process and providing individually customized operating instructions and troubleshooting guides based on the operator's background information" is a system that is installed on a factory robot and provides instructions and guides according to the operator's skills and experience.

[0698] The "feedback processing means for the factory robot to collect and analyze operator feedback to optimize the generative AI's custom instructions" is a system that collects feedback from operators and optimizes the generative AI's instructions based on the results of the analysis.

[0699] This invention is a system that provides factory robots with custom instructions based on background information and generates optimal guides according to the skills and experience of operators. This system aims to improve production efficiency by automatically customizing instructions based on information input by operators.

[0700] System Configuration

[0701] 1. Input Method

[0702] Operators use devices such as tablets and smartphones to input their own operating experience and areas of interest. For example, they input information such as, "I'm a beginner at robot operation. Please teach me the basic operations." through a dedicated user interface.

[0703] 2. Transmission Method

[0704] The entered information is encrypted in JSON format and sent securely to the cloud server using the HTTPS protocol, ensuring the safety of the data.

[0705] 3. Data Analysis

[0706] The server decodes the received data and uses a natural language processing (NLP) engine (e.g., NLTK, SpaCy) to analyze the operator's background information and areas of interest, and then generates an operator profile based on the results. Specifically, it uses keyword extraction and classification techniques to identify the operator's skill level and experience.

[0707] 4. Instruction Generation

[0708] The server generates custom instructions for the generative AI (e.g., GPT-3.5) from the analyzed data. For example, it generates a "step-by-step guide for basic operations" for newcomers with little experience, and a "troubleshooting optimization method" for veterans.

[0709] 5. Sending instructions

[0710] The generated custom instructions are then re-encrypted via an API and sent to the operator's terminal, which provides a user interface to display the received instructions and collect operator feedback.

[0711] 6. Feedback Processing

[0712] Feedback from operators is sent to a cloud server where it is analyzed and used to optimize instructions by the generative AI. For example, specific comments such as "This information was helpful" or "I would like more information" are analyzed.

[0713] Hardware and software used

[0714] Hardware:

[0715] Tablets, smartphones: Devices used by operators to input data about operations and provide feedback.

[0716] Cloud server: Infrastructure for receiving data, analyzing it, and generating instructions.

[0717] software:

[0718] Natural language processing engines: NLTK, SpaCy

[0719] Generative AI models: GPT-3.5, etc.

[0720] Data transmission protocol: HTTPS, JSON format

[0721] Specific examples

[0722] The operator uses a tablet to input and send the message, "I'm a beginner at robot operation. Please teach me the basic operations." The server analyzes the received information and generates custom instructions such as "Step-by-step guide for basic operations: 1. Turn on the power 2. Basic movement operations 3. How to use the sensors," and sends them to the terminal. The operator operates the robot according to the custom instructions and then provides feedback.

[0723] Prompt Sentence Examples

[0724] "Basic Robot Operation Guide: 1. Turning on the power 2. Basic movement operations 3. How to use the sensors"

[0725] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0726] Step 1:

[0727] The user uses a tablet or smartphone to input their own operating experience and areas of interest. At this time, the user enters information such as "I am a beginner at robot operation. Please tell me the basic operations." through a dedicated user interface. The input information is parsed into JSON format.

[0728] input:

[0729] Text data about user experience and areas of interest entered into a tablet or smartphone by the user.

[0730] output:

[0731] Parsed data in JSON format.

[0732] Step 2:

[0733] The terminal transmits the data acquired from the input means to the cloud server in encrypted JSON format using the HTTPS protocol, thereby ensuring the security of the data.

[0734] input:

[0735] Parsed JSON format data.

[0736] output:

[0737] The encrypted data is sent to the cloud server using the HTTPS protocol.

[0738] Step 3:

[0739] The server decodes the received data and uses a natural language processing (NLP) engine to analyze the operator's background information and areas of interest, specifically using NLP tools such as NLTK and SpaCy to perform keyword extraction and classification to identify the operator's skill level and experience.

[0740] input:

[0741] Encrypted JSON formatted data.

[0742] output:

[0743] Operator profile information (skill level, experience, etc.).

[0744] Step 4:

[0745] The server generates custom instructions for the generative AI (e.g., GPT-3.5) from the analyzed data, generating a "step-by-step guide to basic operations" for newcomers with little experience, and a "troubleshooting optimization method" for veterans.

[0746] input:

[0747] Operator profile information.

[0748] output:

[0749] Custom instructions (e.g., "Step-by-step guide to basic operations").

[0750] Step 5:

[0751] The server re-encrypts the generated custom instructions via API and sends them to the operator's device, where the operator displays the received instructions and performs operations based on their content.

[0752] input:

[0753] Custom instructions.

[0754] output:

[0755] Encrypted custom instructions are sent to the operator's terminal.

[0756] Step 6:

[0757] The user operates the robot by following custom instructions displayed, for example, a "step-by-step guide to basic operations."

[0758] input:

[0759] Custom instructions.

[0760] output:

[0761] User control of the robot.

[0762] Step 7:

[0763] After completing the operation, the user inputs feedback into the device. For example, they input comments such as "This information was helpful" or "I would like more detailed information." The device then sends this feedback to the server in JSON format using the transmission method.

[0764] input:

[0765] Text data of user feedback.

[0766] output:

[0767] The feedback data is parsed in JSON format and sent to the server.

[0768] Step 8:

[0769] The server decodes and analyzes the feedback data and uses it to optimize the generative AI's custom instructions, resulting in more accurate instructions for future iterations.

[0770] input:

[0771] Feedback data.

[0772] output:

[0773] Optimized custom instructions.

[0774] 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.

[0775] This invention is a system that generates custom instructions for generative AI based on the user's background information and emotional state, thereby providing the optimal answer the user desires. In particular, this invention achieves more personalized responses by combining an emotion engine that recognizes the user's emotions.

[0776] System Overview

[0777] 1. Input Method

[0778] User: Accesses the system and enters their knowledge and background information through a dedicated input interface, which may include text boxes and voice input options. For example, they might enter, "I'm an engineer with over 10 years of experience. I'm looking for detailed technical information."

[0779] 2. Transmission Method

[0780] Terminal: User-entered information is packaged in JSON format and sent to the server using a secure protocol.

[0781] 3. Data Reception and Analysis

[0782] Server: Decodes the received data, stores it in a specialized database, and analyzes it. Natural language processing (NLP) algorithms are used to identify the user's background information and areas of interest. For example, information such as "Occupation: Engineer," "Years of experience: 10 years," and "Area of ​​interest: Technical details" can be extracted.

[0783] 4. Emotion recognition

[0784] Device: Operates an emotion engine to recognize emotions from the voice and text data input by the user. It uses voice analysis, facial recognition, or text analysis to identify the user's emotional state. For example, it obtains information such as "The user is excited" or "The user is feeling stressed."

[0785] 5. Instruction Generation

[0786] Server: Automatically generates custom instructions for the generative AI based on the background information acquired by the analytical means and the emotional state recognized by the emotion engine. For example, if the user is feeling stressed, the server adds an instruction such as "answer with kindness."

[0787] 6. Sending generation instructions

[0788] Server: Packages the generated custom instructions in JSON format, encrypts them, and sends them to the device.

[0789] 7. Applying Custom Instructions

[0790] Terminal: Decodes the received custom instructions and applies them to the generative AI, either by updating the configuration file or through API calls.

[0791] 8. User Questions

[0792] User: Asks a question to the generative AI with custom instructions applied, for example, "Tell me about the latest trends in AI technology."

[0793] 9. Generative AI Responses

[0794] Generative AI: Generates optimal answers to user questions based on custom instructions. Provides detailed answers based on the user's technical background and emotional state. For example, it generates specific answers such as, "The latest AI technology trends include deep learning, reinforcement learning, and natural language processing. These technologies are..."

[0795] 10. Results display

[0796] Terminal: Generated answers are displayed on the user's screen, often in the form of text, graphs, charts, or other visual aids.

[0797] 11. Feedback Processing

[0798] User: Enter feedback on the answer provided. For example, "This information was very helpful" or "I'd like to see more specific examples."

[0799] Server: Analyzes user feedback and uses it to improve the custom instructions for the generative AI. Based on the feedback, the instruction generation algorithm is adjusted to improve the accuracy of answers in future.

[0800] Through this system, users can efficiently obtain responses optimized for their technical background and emotional state.

[0801] The processing flow will be explained below.

[0802] Step 1:

[0803] User: Accesses the system's website or application and enters their knowledge and background information through a dedicated input interface, for example, "I am a software engineer with over 10 years of experience. I would like to learn more about the latest AI technologies."

[0804] Step 2:

[0805] Terminal: The information entered by the user is packaged in JSON format, encrypted using HTTPS, and sent to the server.

[0806] Step 3:

[0807] Server: Receives the data, decodes it from JSON format, and stores it in a database, which stores the user's background information, occupation, years of experience, areas of interest, etc.

[0808] Step 4:

[0809] Server: Analyzes the stored data using natural language processing (NLP) algorithms, for example, to determine that the user is a software engineer, has more than 10 years of experience, and is interested in AI technology.

[0810] Step 5:

[0811] On the device: Run an emotion engine to recognize emotions from the user's voice and text data. Use voice analysis, facial recognition, or text analysis techniques to identify the user's emotional state. For example, determine whether the user is excited or stressed.

[0812] Step 6:

[0813] Server: Generates custom instructions based on the analyzed background information and emotional state. For example, if the user is excited, the instructions are set to respond in a detailed and positive tone.

[0814] Step 7:

[0815] Server: Repackage the generated custom instructions in JSON format, re-encrypt them, and send them to the device.

[0816] Step 8:

[0817] Terminal: Decodes the received custom instructions and applies them to the generative AI by updating the AI's configuration file or by using an API call to reflect the instructions.

[0818] Step 9:

[0819] User: Asks a question to the generative AI with custom instructions applied, for example, "Tell me about the latest trends in AI technology."

[0820] Step 10:

[0821] Generative AI: Generates optimal answers to user questions based on custom instructions. For example, it provides specific and detailed answers such as, "The latest AI technology trends include deep learning, reinforcement learning, and natural language processing. Each technology is..."

[0822] Step 11:

[0823] Terminal: Generated answers are displayed on the user's screen, and can be visually interpreted in the form of text, graphs, charts, etc.

[0824] Step 12:

[0825] User: Enter feedback on the answer provided. For example, "This information was very helpful. I'd like to see more specific examples."

[0826] Step 13:

[0827] Server: Re-analyzes the feedback sent by the user and uses it to improve the custom instructions for the generative AI. Based on the feedback, the instruction generation algorithm is adjusted to improve the accuracy of answers in the future.

[0828] This allows users to efficiently receive responses that are optimized for their own technical background and emotional state.

[0829] Example 2

[0830] 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."

[0831] Conventional generative AI systems generate answers by taking into account only the user's background information, which means they are unable to provide personalized responses that reflect the user's emotional state. This reduces user satisfaction and makes it difficult to use the system effectively.

[0832] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an input means through which a user inputs their own knowledge and background information, a transmission means for transmitting data acquired from the input means to the server, an analysis means for analyzing the data received by the server and identifying the user's background information and areas of interest, an instruction generation means for generating custom instructions for the generative AI based on information acquired by the analysis means and the emotion recognition means, a transmission means for transmitting the custom instructions to the user terminal, and an application means for applying the custom instructions to the generative AI. This makes it possible to provide an optimal response according to the user's technical background and emotional state.

[0833] "User" refers to an individual or organization that uses the system.

[0834] "Knowledge" is a general term for specialized fields and general information that a user possesses.

[0835] "Background information" refers to personal information such as the user's occupation, years of experience, and areas of interest.

[0836] "Input means" refers to an interface that allows a user to input information through text, voice, or the like.

[0837] The "transmission means" refers to a means for sending data acquired through the input means to the server.

[0838] "Server" refers to a computer system that receives data via the Internet, analyzes it, and performs the necessary processing.

[0839] "Analysis means" refers to the methods and algorithms used by the server to interpret the data received and identify the user's background information and areas of interest.

[0840] "Emotion recognition means" refers to an engine or algorithm for identifying a user's emotional state from their voice or text data.

[0841] "Instruction generation means" refers to a means for automatically generating custom instructions for the generative AI based on information obtained by the analysis means and emotion recognition means.

[0842] "Custom instructions" refers to special instructions or settings that a generative AI needs to generate the best answer to a user's question.

[0843] "Means of application" refers to the means for applying custom instructions to generative AI.

[0844] "Generative AI" refers to models and systems that use artificial intelligence techniques to generate responses in natural language.

[0845] "Natural language processing algorithms" refer to computational methods for understanding and analyzing text data.

[0846] This invention is a system that generates custom instructions for a generative AI based on the user's background information and emotional state, and provides the optimal answer the user desires. This system is specifically designed to achieve more personalized responses by combining an emotion engine that recognizes the user's emotions.

[0847] First, a user logs into the system and enters their knowledge and background information through a dedicated input interface. This interface includes text boxes and voice input options. For example, a user might enter, "I'm an engineer with over 10 years of experience. I'm looking for detailed technical information." This information is packaged in JSON format and sent to the server using a secure protocol (e.g., HTTPS).

[0848] The server decodes the received data, stores it in a specialized database (e.g., MySQL, NoSQL), and then uses natural language processing (NLP) algorithms (e.g., SpaCy, NLTK) to identify the user's background information and areas of interest. The extracted information might be "Occupation: Engineer," "Years of experience: 10 years," or "Area of ​​interest: Technical details."

[0849] Next, the device recognizes emotions from the user's input data. It uses an emotion engine (e.g., IBM Watson Tone Analyzer, Microsoft Azure Emotion API) to identify the user's emotional state using voice analysis, facial recognition, or text analysis. For example, if a user inputs, "I'm very tired from my recent project, but I'd like to learn more about new technologies," the device can obtain an emotional state such as, "The user is feeling tired."

[0850] The server automatically generates custom instructions for the generative AI (e.g., GPT series) based on the background information acquired by the analysis means and the emotional state recognized by the emotion engine. This can include instructions such as "focus on technical details and provide helpful answers." The generated custom instructions are again packaged in JSON format, encrypted, and sent to the device.

[0851] The device that receives the custom instructions decodes them and applies them to the generative AI through configuration file updates or API calls. When a user inputs a question such as, "Please tell me about the latest trends in AI technology," the generative AI generates the optimal answer based on the custom instructions. For example, a specific answer such as, "The latest trends in AI technology include deep learning, reinforcement learning, and natural language processing. These technologies are..." can be obtained.

[0852] Finally, the device displays the generated answer on the user's screen. The display format can be text, graphs, charts, etc. For example, if the user provides feedback on the provided answer, such as "This information was very helpful" or "I'd like to know more specific examples," the server analyzes that feedback and uses it to improve the generative AI's instruction generation algorithm. This allows for improved answer accuracy in future answers.

[0853] This allows users to efficiently obtain responses that are optimized for their technical background and emotional state.

[0854] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0855] Step 1:

[0856] The user enters their knowledge and background information through an input interface. This input can be done using text boxes or voice input options. For example, they might enter information like, "I'm an engineer with over 10 years of experience. I'm looking for detailed technical information." The input data is packaged in JSON format.

[0857] Input: User text / voice input of knowledge and background information

[0858] Output: JSON formatted data package

[0859] Step 2:

[0860] The terminal sends the information entered by the user to the server using a secure protocol (such as HTTPS). Specifically, it is sent as an HTTP POST request. The communication at this time is encrypted, so the safety of the input data is maintained.

[0861] Input: JSON format data package

[0862] Output: HTTP POST request to the server

[0863] Step 3:

[0864] The server decodes the received data and stores it in a specialized database (e.g., MySQL or NoSQL). Next, it uses natural language processing (NLP) algorithms (e.g., SpaCy or NLTK) to identify the user's background information and areas of interest. For example, information such as "Occupation: Engineer," "Years of experience: 10 years," and "Area of ​​interest: Technical details" can be extracted.

[0865] Input: JSON formatted data received as an HTTP POST request to the server

[0866] Output: Decoded user background information and regions of interest

[0867] Step 4:

[0868] The device runs an emotion engine to recognize the user's emotional state from input data. This is done using emotion recognition tools such as IBM Watson Tone Analyzer and Microsoft Azure Emotion API. Through voice analysis, facial recognition, or text analysis, the device identifies the user's emotional state, such as excitement or fatigue.

[0869] Input: JSON formatted text / audio data

[0870] Output: User's emotional state (e.g., excited, tired)

[0871] Step 5:

[0872] The server automatically generates custom instructions for the generative AI based on the analyzed background information and the identified emotional state. For example, if the user is feeling stressed, the server adds an instruction such as "Respond with kindness." The instructions are packaged in JSON format.

[0873] Input: User background information and emotional state

[0874] Output: Custom instructions (JSON format)

[0875] Step 6:

[0876] The server then packages the generated custom instructions in JSON format, encrypts them, and sends them to the device using a secure protocol (such as SSL / TLS).

[0877] Input: Custom instructions (JSON format)

[0878] Output: Encrypted custom instructions (sent to the terminal)

[0879] Step 7:

[0880] The device decodes the received custom instructions and applies them to the generative AI, either through configuration file updates or API calls, allowing the generative AI to generate optimal responses based on the user's information.

[0881] Input: Received custom instructions (JSON format)

[0882] Output: Applied instructions to the generative AI

[0883] Step 8:

[0884] Users can then ask questions to the generative AI with custom instructions applied, for example, by typing, "Tell me about the latest trends in AI technology."

[0885] Input: User question (text input)

[0886] Output: Question data (JSON format)

[0887] Step 9:

[0888] Generative AI generates the best answer to a user's question based on custom instructions. For example, it can provide a specific answer such as, "The latest trends in AI technology include deep learning, reinforcement learning, and natural language processing. These technologies are..."

[0889] Input: User question data (JSON format)

[0890] Output: Best answer (text format)

[0891] Step 10:

[0892] The terminal displays the generated answers on the user screen. The display format can be text, graphs, charts, etc. For example, if you need a graph to visually explain the latest technology trends, you can display it using an appropriate library (e.g., D3.js or Chart.js).

[0893] Input: Generated answer (text format)

[0894] Output: Answer displayed to the user

[0895] Step 11:

[0896] The user can input feedback for the provided answer, such as "This information was very helpful" or "I would like to know more specific examples."

[0897] Input: User feedback (text input)

[0898] Output: Feedback data (JSON format)

[0899] The server analyzes user feedback and uses it to improve the custom instructions of the generative AI. The feedback data is fed back to a new custom instruction generation algorithm to improve the accuracy of answers from the next time onwards.

[0900] Input: Feedback data (JSON format)

[0901] Output: Improved custom instruction generation algorithm

[0902] (Application example 2)

[0903] 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."

[0904] When a user searches for or purchases products in a virtual store, there is a need for a system that automatically provides optimal product suggestions and information based on the user's emotional state and background information. However, while conventional systems can generate responses based on the user's background information, they cannot generate responses that take the user's emotional state into account. As a result, optimal suggestions are not made based on the user's emotions when searching for products, which can lead to a decrease in satisfaction and a decrease in purchasing motivation.

[0905] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes an input means through which a user inputs their own knowledge and background information, a transmission means for transmitting data acquired from the input means to the server, an analysis means for analyzing the data received by the server and identifying the user's background information and areas of interest, an instruction generation means for generating custom instructions for the generative AI based on the information identified by the analysis means, a transmission means for transmitting the custom instructions to the user terminal, an application means for applying the custom instructions to the generative AI, an emotion recognition means for recognizing the user's emotional state from the user's input, and a suggestion means for suggesting optimal products and providing information in a virtual store based on the user's background information and emotional state. This enables suggestions and answers optimized for the user's technical background and emotional state.

[0906] A "user" is an entity that accesses the system and inputs their knowledge and background information.

[0907] "Background information" is personal information such as the user's occupation, years of experience, areas of interest, etc.

[0908] "Input means" refers to an interface through which a user inputs their own knowledge and background information.

[0909] The "transmission means" is a means for transmitting data acquired from the input means to the server.

[0910] The "server" is the central processing unit of the system that analyzes the received data and generates optimal instructions for the user.

[0911] The "analysis means" is a means for analyzing the data received by the server and identifying the user's background information and areas of interest.

[0912] The "instruction generation means" is a means for generating custom instructions for the generative AI based on the information identified by the analysis means.

[0913] "Custom instructions" are specific instructions to a generative AI that are generated based on the user's background information and emotional state.

[0914] The "application means" is a means for applying the generated custom instructions to the generative AI.

[0915] "Emotion recognition means" is a means for recognizing an emotional state from a user's input.

[0916] The "suggestion means" is a means for suggesting optimal products and providing information within the virtual store based on the user's background information and emotional state.

[0917] "Generative AI" is artificial intelligence that generates optimal responses and suggestions based on the user's background information and emotional state.

[0918] A "virtual store" is a virtual store set up on the Internet to offer products and services.

[0919] The system of the present invention is a solution for virtual stores that provides optimal product suggestions and information to users based on their background information and emotional state. This system provides support for users to efficiently search for and purchase products in stores.

[0920] System Overview

[0921] The system consists of the following components:

[0922] 1. User Device

[0923] The user device provides an interface for users to input their background information and emotional state. Specifically, a smartphone or a head-mounted display (HMD) is used.

[0924] 2. Server

[0925] The server receives and analyzes data sent from the user's device. It is equipped with a natural language processing engine (NLPProcessor) and an emotion recognition engine (EmotionRecognition).

[0926] 3. Generative AI

[0927] Generative AI (Custom AI) provides optimal product suggestions and information to users based on custom instructions received from the server.

[0928] User terminal processing

[0929] The user terminal is equipped with a text box and / or voice input options for the user to enter information, such as "I am a designer with over 5 years of experience." This information is then sent to the server via a security protocol.

[0930] Server Processing

[0931] The server analyzes the received data using a natural language processing engine (NLPProcessor) to identify the user's background information and emotional state. For example, information such as "Occupation: Designer," "Years of Experience: 5 years," and "Emotion: Excited" may be analyzed. The custom instructions constructed based on this information include instructions for the generative AI on how to respond.

[0932] emotion recognition

[0933] The EmotionRecognition engine recognizes the emotional state of a user from their input data. It uses techniques from speech analysis, facial recognition, and text analysis. For example, if a user's input includes "I'm super excited about the new design tool," the EmotionRecognition engine will identify the emotional state as "excited."

[0934] Custom Instruction Generation

[0935] The server generates custom instructions based on the analysis results, such as "Since the user is a designer and is excited, kindly provide detailed information about the latest design tools." This custom instruction is sent to the AI ​​generator, which then provides optimal product suggestions and information.

[0936] Generative AI response

[0937] The generative AI responds to the user according to the custom instructions it receives. For example, in response to a user question, "Tell me about new design tools," it generates a specific answer such as, "CAD software X is a cutting-edge design tool. Using this..."

[0938] Feedback Processing

[0939] Users can enter feedback on the answers provided, which is sent to the server to help improve the generated AI's custom instructions.

[0940] Specific examples

[0941] For example, if a user enters, "I'm a designer and I'm looking for the latest design tools," and then asks, "Tell me about new design tools," the system will suggest the latest design software and examples of its use based on the user's background information and emotional state.

[0942] Prompt Sentence Examples

[0943] "I'm a designer with over 5 years of experience."

[0944] "Tell me about the latest design tools."

[0945] In this way, users can receive personalized suggestions and answers that are optimized for their background information and emotional state, making their shopping experience in the virtual store more efficient and satisfying.

[0946] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0947] Step 1:

[0948] Enter the user's background information. The user enters their background information and areas of interest through a text box or voice input interface. For example, they might enter information such as, "I'm a designer with over 5 years of experience." This becomes the initial input data for the system.

[0949] Step 2:

[0950] The device sends the entered data to the server. The obtained user background information is packaged in JSON format and sent to the server using a security protocol (e.g., HTTPS). At this time, the data is formatted and validated to prevent unauthorized data entry.

[0951] input:

[0952] User-supplied background information (e.g., "I'm a designer with over 5 years of experience.")

[0953] output:

[0954] JSON format data (e.g., "{"Occupation": "Designer", "Experience": "5+ years"}")

[0955] Step 3:

[0956] The server analyzes the received data. The server decodes the received JSON format data and analyzes it using a natural language processing engine (NLPProcessor). For example, information such as "Occupation: Designer" and "Years of experience: 5 years" is extracted and stored in a database.

[0957] input:

[0958] User data in JSON format

[0959] output:

[0960] Analyzed background information (e.g., "Occupation: Designer" and "Years of experience: 5 years")

[0961] Step 4:

[0962] Emotional states are identified using emotion recognition means. The emotion engine (EmotionRecognition) recognizes emotional states based on the voice and text data entered by the user. Using voice analysis and text analysis techniques, emotional states such as "the user is excited" are identified.

[0963] input:

[0964] User-entered text and voice data

[0965] output:

[0966] Perceived emotional state (e.g., "I'm excited")

[0967] Step 5:

[0968] The server generates custom instructions. Based on the background information and emotional state identified by the analysis means, the instruction generation means generates custom instructions containing specific instructions for the generative AI, such as "provide a friendly description of the latest tools for designers."

[0969] input:

[0970] Background information and emotional state

[0971] output:

[0972] Custom instructions (e.g., "Helpful instructions on the latest tools for designers")

[0973] Step 6:

[0974] The custom instructions are sent to the user device. The server packages the generated custom instructions in JSON format and sends them to the user device using a security protocol. The user device decodes the received custom instructions.

[0975] input:

[0976] Generated Custom Instructions

[0977] output:

[0978] Custom instructions in JSON format sent to the user device

[0979] Step 7:

[0980] Apply custom instructions to the generative AI. Custom instructions received on the user's device are applied to the generative AI (CustomAI). This is done by updating the configuration file or by calling the API.

[0981] input:

[0982] Decoded Custom Instructions

[0983] output:

[0984] New instructions set for generative AI

[0985] Step 8:

[0986] A user asks a generative AI a question, for example, "Tell me about a new design tool." The generative AI generates the best answer based on custom instructions.

[0987] input:

[0988] User questions (e.g., "Tell me about the new design tool.")

[0989] output:

[0990] Generative AI answers (e.g., "The latest design tool is CAD software X. Using this...")

[0991] Step 9:

[0992] The terminal displays the generated answer to the user, and the generated answer is displayed on the user's screen in a visually easy-to-understand format such as text or a graph.

[0993] input:

[0994] Generative AI answers

[0995] output:

[0996] The answer displayed on the user's device (e.g., "CAD software X is a cutting-edge design tool. Using this...")

[0997] Step 10:

[0998] Feedback processing is performed. The user enters feedback on the provided answers. For example, they enter their impressions, such as "This information was very helpful." This feedback is sent to the server and used to improve the generative AI.

[0999] input:

[1000] User feedback (e.g., "This information was very helpful")

[1001] output:

[1002] Generative AI improvement data

[1003] In this way, a personalized purchasing experience based on the user's technological background and emotional state is achieved.

[1004] 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.

[1005] 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.

[1006] 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.

[1007] [Third embodiment]

[1008] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1009] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1010] 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).

[1011] 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.

[1012] 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.

[1013] 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).

[1014] 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.

[1015] 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.

[1016] 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.

[1017] 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.

[1018] 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.

[1019] 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."

[1020] The present invention is a system that generates custom instructions for a generative AI based on the user's background information, thereby providing the optimal answer the user desires. Specifically, this system uses the following means.

[1021] System Overview

[1022] 1. Input Method

[1023] User: Accesses the system and enters their knowledge and background information through a dedicated input interface. This interface can be a web form, an application UI, etc. For example, a user who is an educator might enter, "I have over 10 years of teaching experience and would like to learn more about the latest educational technologies."

[1024] 2. Transmission Method

[1025] Terminal: User-entered information is encrypted as JSON data and sent to the server using a secure communication protocol (e.g., HTTPS). This transmission method is built into the client-side application code.

[1026] 3. Data Reception and Analysis

[1027] Server: The received data is decoded and stored in a database. The stored data is then analyzed using natural language processing (NLP) algorithms. Specifically, text mining techniques are used to extract information such as the user's occupation, years of experience, and areas of interest, and a user profile is generated based on the analysis results.

[1028] 4. Instruction Generation

[1029] Server: Automatically generates custom instructions for the generative AI based on user information identified through analytical methods. For example, for a user with extensive teaching experience, the server might generate instructions such as "provide a detailed explanation of the latest educational technologies and examples of their practical applications."

[1030] 5. Sending generation instructions

[1031] Server: The generated custom instructions are re-encrypted and sent to the device via the API.

[1032] 6. Applying Custom Instructions

[1033] Device: The user device applies the received custom instructions to the generative AI and saves them in an instruction configuration file or applies them immediately via an API call.

[1034] 7. User Response

[1035] Generative AI: Generates optimal answers to user questions based on custom instructions. For example, if a user asks, "What are the latest trends in educational technology?", the AI ​​can provide a specific answer such as, "The latest trends in educational technology include personalized learning using AI, virtual classrooms using VR, and the use of gamification."

[1036] 8. Results display

[1037] Terminal: The generated answers are presented visually to the user, either in a web browser or in an application, in the form of text, graphs, charts, etc.

[1038] 9. Feedback Processing

[1039] User: Enters feedback on the provided answer and submits it to the server again. The feedback includes specific comments such as "This information was helpful" or "I would like more information."

[1040] Server: Analyzes the received feedback and helps optimize the custom instructions for the generative AI.

[1041] Through this system, users will be able to effectively obtain information tailored to their own expertise and interests, greatly increasing the utility of generative AI.

[1042] The processing flow will be explained below.

[1043] Step 1:

[1044] User: Accesses the system's website or application and enters their knowledge and background information through a dedicated input interface, for example, "I am a doctor and have been working for five years. I would like to learn more about the latest treatments."

[1045] Step 2:

[1046] Terminal: User-entered information is packaged in JSON format, encrypted as an HTTP POST request, and sent to the server using a security protocol (e.g., HTTPS).

[1047] Step 3:

[1048] Server: Receives the transmitted data, decodes it, and stores it in a database. For security reasons, the data is encrypted before storage. It also operates a monitoring system to detect unauthorized access.

[1049] Step 4:

[1050] Server: Analyzes the user's information stored in the database using a natural language processing (NLP) algorithm. This analysis identifies the user's occupation, years of experience, and specific areas of interest. For example, the following data is extracted: "Occupation: Doctor," "Years of experience: 5 years," and "Area of ​​interest: Latest treatments."

[1051] Step 5:

[1052] Server: Automatically generates custom instructions for the generative AI based on the analysis results. Instructions can be set in the form of, for example, "Provide answers that include detailed explanations and the latest research findings in the medical field."

[1053] Step 6:

[1054] Server: The generated custom instructions are packaged again in JSON format, encrypted, and sent to the device. This process also uses a secure communication protocol.

[1055] Step 7:

[1056] Terminal: Decodes the received custom instructions and applies them to the generative AI, either by updating the configuration file or through API calls.

[1057] Step 8:

[1058] User: Asks a question to the generative AI with custom instructions applied, such as "Please tell me more about the latest anti-cancer drug treatments."

[1059] Step 9:

[1060] Generative AI: Generates optimal answers to user questions based on custom instructions. For example, it generates answers that include expert explanations such as, "New anti-cancer drug treatments include molecular targeted therapy and immunotherapy. Details of each are as follows..."

[1061] Step 10:

[1062] Terminal: The generated answers are displayed on the user's screen, not only in text format but also visually using graphs and charts as needed.

[1063] Step 11:

[1064] Users: Enter feedback on the answers provided. Feedback can be specific, such as "This answer was very helpful" or "I need more information."

[1065] Step 12:

[1066] Server: Re-analyzes the feedback sent by the user and uses it to improve the custom instructions for the generative AI. Based on the feedback, the instruction generation algorithm is adjusted to improve the accuracy of answers in the future.

[1067] This series of processes enables users to efficiently obtain information optimized according to their expertise and interests.

[1068] Example 1

[1069] 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."

[1070] Currently, systems that use generative AI to provide answers to users have difficulty generating customized answers based on the user's background information and areas of interest. Additionally, they lack the ability to optimize system performance based on user feedback, making it difficult to provide information that satisfies users.

[1071] 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.

[1072] In this invention, the server includes input means for a user to input their own knowledge and background information, transmission means for transmitting data acquired from the input means to the server, analysis means for analyzing the data received by the server and identifying the user's background information and areas of interest, instruction generation means for generating custom instructions for the generative AI based on the information identified by the analysis means, transmission means for transmitting the custom instructions to a user terminal, application means for applying the custom instructions to the generative AI, response means for a user to input a question for the generative AI and generate an optimal answer based on the question, display means for visually displaying the generated answer to the user, feedback transmission means for acquiring user feedback and transmitting the feedback to the server, and feedback analysis means for analyzing the feedback and optimizing the custom instructions for the generative AI. This enables users to accurately acquire information based on their own expertise and areas of interest, improving the recognition accuracy and utility value of the entire system.

[1073] A "user" is an individual or entity that accesses the system and inputs their knowledge and background information.

[1074] "Input means" refers to an interface through which a user inputs their own knowledge and background information, such as a web form or an application UI.

[1075] The "transmission means" is a means for transmitting the data entered by the user to the server, and uses data encryption and a secure communication protocol such as HTTP.

[1076] A "server" is a computer system that receives data sent by a user, analyzes it, and performs the necessary processing.

[1077] "Analysis means" refers to algorithms or techniques that analyze the data received by the server and identify the user's background information and areas of interest.

[1078] "Database" means a relational database or other data storage system used by the server to store data received by the server.

[1079] A "natural language processing (NLP) algorithm" is a technology that uses text mining technology and other techniques to analyze user input data and understand its meaning and intent.

[1080] The "instruction generation means" is a function that automatically generates custom instructions for the generative AI based on the user information identified by the analysis means.

[1081] "Generative AI" is an artificial intelligence model that generates optimal answers to user questions based on custom instructions.

[1082] A "response means" is a means by which a generative AI generates the optimal answer to a user's question.

[1083] The "display means" is a means for visually displaying the generated answers to the user, and may be displayed in the form of text, graphs, charts, or the like.

[1084] The "feedback sending means" is a means by which a user inputs feedback on a provided answer and sends it to the server.

[1085] "Feedback analysis means" is a technology that analyzes the feedback received by the server and optimizes the custom instructions of the generative AI.

[1086] A "secure communication protocol" is a protocol for ensuring security when sending and receiving data, and an example of this is HTTPS.

[1087] "Custom instructions" are specialized instructions for generative AI that are automatically generated based on the user's background information.

[1088] The present invention provides a system that generates custom instructions for a generative AI based on a user's background information and provides optimal answers. A specific embodiment of this system will be described in detail below.

[1089] System Overview

[1090] Enter user information

[1091] Users enter their knowledge and background information through a dedicated input interface (web form or application UI). This interface is built using HTML and CSS, and the front-end uses JavaScript to process user input. For example, an educator might enter, "I have over 10 years of teaching experience and would like to learn more about the latest educational technologies."

[1092] Sending data

[1093] The terminal encrypts the information entered by the user as JSON format data, uses a standard encryption library, and sends the encrypted data to the server using a secure communication protocol such as HTTPS. This process is implemented using JavaScript or Python coding.

[1094] Receiving and storing data

[1095] The server receives the data sent from the device, decodes it, and stores it in a database. Specifically, it uses a relational database such as MySQL or PostgreSQL to efficiently manage the received data.

[1096] Data analysis

[1097] The server analyzes the stored data using natural language processing (NLP) algorithms, using Python libraries such as nltk and spaCy, and employs text mining techniques to extract information such as the user's occupation, years of experience, and areas of interest, and then generates a user profile.

[1098] Custom Instruction Generation

[1099] The server automatically generates custom instructions for the generative AI based on the analyzed user information. For example, for a user with extensive teaching experience, the server might generate instructions such as "Provide a detailed explanation of the latest educational technologies and examples of their practical applications." This generation is performed using a generative AI model (e.g., GPT-3).

[1100] Sending instructions

[1101] The server then re-encrypts the generated custom instructions and sends them to the device. This process is performed through an API, which uses a standard REST API and can be implemented using a web framework such as Flask or Django.

[1102] Applying the Instructions

[1103] The device applies the received custom instructions to the generative AI. The instructions are stored in a configuration file or applied immediately via API calls, which can include updating a JSON file or making requests to an API endpoint.

[1104] Responding to user questions

[1105] Generative AI generates optimal answers to user questions based on custom instructions. For example, if a user asks, "What are the latest trends in educational technology?", generative AI can provide a specific answer such as, "The latest trends in educational technology include personalized learning using AI, virtual classrooms using VR, and the use of gamification."

[1106] Displaying the results

[1107] The device visually displays the generated answers to the user in the form of text, graphs, charts, etc., delivered in a web browser or application using HTML, CSS, and JavaScript.

[1108] Obtaining and analyzing feedback

[1109] The user inputs feedback on the provided answers and sends it to the server. The feedback sending means is a function for collecting user comments and ratings. The server analyzes the received feedback and uses the feedback analysis means to optimize the custom instructions of the generative AI.

[1110] Examples and prompts

[1111] Specific examples

[1112] User types, "I have over 10 years of teaching experience and would like to learn more about the latest educational technologies."

[1113] The device encrypts the information and sends it to the server via HTTPS.

[1114] The server analyzes the information and identifies the following: "Teaching experience: 10+ years, Area of ​​interest: Educational technology."

[1115] The server generates custom instructions such as "Detailed explanation of the latest educational technologies and their practical applications."

[1116] The server sends these instructions to the terminal, which then applies them to the generative AI.

[1117] When a user asks, "Tell me about the latest trends in education technology," generative AI provides a specific answer.

[1118] Prompt Sentence Examples

[1119] For Educators

[1120] "Write detailed instruction for users with 10+ years of teaching experience about the latest educational technologies and their practical applications."

[1121] For general users

[1122] "Create instructions that take a user's expert background information and generate the best answer based on that information."

[1123] The above is an embodiment of the present invention, which allows a user to accurately obtain information based on their own specialized knowledge or areas of interest.

[1124] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1125] Step 1:

[1126] Users input their knowledge and background information through a dedicated input interface. The input is in text format, for example, "I have more than 10 years of teaching experience. I would like to learn more about the latest educational technologies."

[1127] Input: Text data entered by a user into an input interface.

[1128] Output: The input text data is sent to the next processing step.

[1129] Step 2:

[1130] The device converts the information entered by the user into JSON format data and encrypts it using a standard encryption library to keep the data secure.

[1131] Input: Text data entered by the user.

[1132] Output: Encrypted data in JSON format.

[1133] Step 3:

[1134] The device sends the encrypted data to the server using a secure communication protocol such as HTTPS. The sending process is implemented by program code on the device.

[1135] Input: Encrypted JSON formatted data.

[1136] Output: The encrypted data sent to the server.

[1137] Step 4:

[1138] The server receives the encrypted data and decodes it. The decoded data is then stored in a database, typically a relational database such as MySQL or PostgreSQL.

[1139] Input: Encrypted data.

[1140] Output: The decoded data is stored in the database.

[1141] Step 5:

[1142] The server analyzes the received data using natural language processing (NLP) algorithms. Specifically, it uses Python libraries (nltk, spaCy) to extract the user's occupation, years of experience, and areas of interest.

[1143] Input: Decoded user text data.

[1144] Output: User profile information (occupation, years of experience, areas of interest).

[1145] Step 6:

[1146] The server automatically generates custom instructions for the generative AI based on the analyzed user information. This generation uses a generative AI model (e.g., GPT-3).

[1147] Input: User profile information.

[1148] Output: Custom instructions (e.g., "Describe the latest educational technologies and their practical applications").

[1149] Step 7:

[1150] The server re-encrypts the generated custom instructions and sends them to the device via an API.

[1151] Input: Custom instructions.

[1152] Output: Encrypted custom instructions are sent to the terminal.

[1153] Step 8:

[1154] The device applies the custom instructions it receives to the generative AI, either stored in an instruction configuration file or via an API call.

[1155] Input: Encrypted custom instructions.

[1156] Output: Applied to the generative AI via an instruction configuration file or API calls.

[1157] Step 9:

[1158] The user inputs a question into the generative AI, for example, "Tell me about the latest trends in educational technology."

[1159] Input: The user's question.

[1160] Output: The question is sent to the generative AI.

[1161] Step 10:

[1162] Generative AI generates optimal answers based on custom instructions. For example, it can provide specific answers such as, "The latest trends in educational technology include personalized learning using AI, virtual classrooms using VR, and the use of gamification."

[1163] Input: User questions and custom instructions.

[1164] Output: The best answer generated.

[1165] Step 11:

[1166] The device visually displays the generated answers to the user in the form of text, graphs, charts, etc., within a web browser or application.

[1167] Input: The generated answer.

[1168] Output: The visual information that is displayed to the user.

[1169] Step 12:

[1170] The user inputs feedback for the provided answer and sends it to the server. The user's feedback includes specific comments such as "This information was helpful" or "I would like more information."

[1171] Input: User feedback.

[1172] Output: The feedback data is sent to the server.

[1173] Step 13:

[1174] The server analyzes the received feedback and uses it to optimize the generative AI's custom instructions. Text mining technology is used to analyze the feedback, extracting information to generate more accurate instructions.

[1175] Input: User feedback data.

[1176] Output: Optimized custom instructions.

[1177] (Application example 1)

[1178] 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."

[1179] Existing factory robot systems are difficult to customize based on the skill level and background information of operators, making it difficult to provide efficient instructions or troubleshoot. This problem is particularly pronounced between new employees and experienced operators, and if appropriate information is not provided to both parties, it can have a negative impact on the efficiency and quality of the production process.

[1180] 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.

[1181] In this invention, the server includes an input means for a user to input their own knowledge and background information, a transmission means for transmitting data acquired from the input means, an analysis means for analyzing the data received by the server and identifying the user's background information and areas of interest, an instruction generation means for generating custom instructions for the generative AI based on the information identified by the analysis means, a transmission means for transmitting the custom instructions to a user terminal, an application means for applying the custom instructions to the generative AI, a means installed in a factory robot that manages an industrial process and provides individually customized operating instructions and troubleshooting guides based on the operator's background information, and a feedback processing means for the factory robot to collect and analyze operator feedback and optimize the custom instructions for the generative AI. This enables efficient instruction provision and troubleshooting that corresponds to the individual skill level and background information of the operator.

[1182] The "input means for the user to input his / her own knowledge and background information" is an interface device for the operator to input his / her own skill level, experience, and area of ​​interest.

[1183] The "transmission means for transmitting data acquired from the input means to a server" is a system for transmitting information collected from the input means to a server using a secure communication protocol.

[1184] The "analysis means for analyzing data received by the server and identifying the user's background information and areas of interest" is a system that analyzes data received within the server and identifies the operator's skill level, experience, and areas of interest using natural language processing technology.

[1185] "Instruction generation means for generating custom instructions for the generative AI based on the information identified by the analysis means" refers to a system that creates individual instructions and troubleshooting guides that the generative AI provides to the operator based on the analyzed information.

[1186] The "transmission means for transmitting the custom instructions to the user terminal" is a system that transfers the generated custom instructions to the operator's terminal.

[1187] The "means for applying the custom instructions to the generative AI" is a system that reflects the custom instructions in the settings and commands of the generative AI.

[1188] "A means for installing on a factory robot that manages an industrial process and providing individually customized operating instructions and troubleshooting guides based on the operator's background information" is a system that is installed on a factory robot and provides instructions and guides according to the operator's skills and experience.

[1189] The "feedback processing means for the factory robot to collect and analyze operator feedback to optimize the generative AI's custom instructions" is a system that collects feedback from operators and optimizes the generative AI's instructions based on the results of the analysis.

[1190] This invention is a system that provides factory robots with custom instructions based on background information and generates optimal guides according to the skills and experience of operators. This system aims to improve production efficiency by automatically customizing instructions based on information input by operators.

[1191] System Configuration

[1192] 1. Input Method

[1193] Operators use devices such as tablets and smartphones to input their own operating experience and areas of interest. For example, they input information such as, "I'm a beginner at robot operation. Please teach me the basic operations." through a dedicated user interface.

[1194] 2. Transmission Method

[1195] The entered information is encrypted in JSON format and sent securely to the cloud server using the HTTPS protocol, ensuring the safety of the data.

[1196] 3. Data Analysis

[1197] The server decodes the received data and uses a natural language processing (NLP) engine (e.g., NLTK, SpaCy) to analyze the operator's background information and areas of interest, and then generates an operator profile based on the results. Specifically, it uses keyword extraction and classification techniques to identify the operator's skill level and experience.

[1198] 4. Instruction Generation

[1199] The server generates custom instructions for the generative AI (e.g., GPT-3.5) from the analyzed data. For example, it generates a "step-by-step guide for basic operations" for newcomers with little experience, and a "troubleshooting optimization method" for veterans.

[1200] 5. Sending instructions

[1201] The generated custom instructions are then re-encrypted via an API and sent to the operator's terminal, which provides a user interface to display the received instructions and collect operator feedback.

[1202] 6. Feedback Processing

[1203] Feedback from operators is sent to a cloud server where it is analyzed and used to optimize instructions by the generative AI. For example, specific comments such as "This information was helpful" or "I would like more information" are analyzed.

[1204] Hardware and software used

[1205] Hardware:

[1206] Tablets, smartphones: Devices used by operators to input data about operations and provide feedback.

[1207] Cloud server: Infrastructure for receiving data, analyzing it, and generating instructions.

[1208] software:

[1209] Natural language processing engines: NLTK, SpaCy

[1210] Generative AI models: GPT-3.5, etc.

[1211] Data transmission protocol: HTTPS, JSON format

[1212] Specific examples

[1213] The operator uses a tablet to input and send the message, "I'm a beginner at robot operation. Please teach me the basic operations." The server analyzes the received information and generates custom instructions such as "Step-by-step guide for basic operations: 1. Turn on the power 2. Basic movement operations 3. How to use the sensors," and sends them to the terminal. The operator operates the robot according to the custom instructions and then provides feedback.

[1214] Prompt Sentence Examples

[1215] "Basic Robot Operation Guide: 1. Turning on the power 2. Basic movement operations 3. How to use the sensors"

[1216] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1217] Step 1:

[1218] The user uses a tablet or smartphone to input their own operating experience and areas of interest. At this time, the user enters information such as "I am a beginner at robot operation. Please tell me the basic operations." through a dedicated user interface. The input information is parsed into JSON format.

[1219] input:

[1220] Text data about user experience and areas of interest entered into a tablet or smartphone by the user.

[1221] output:

[1222] Parsed data in JSON format.

[1223] Step 2:

[1224] The terminal transmits the data acquired from the input means to the cloud server in encrypted JSON format using the HTTPS protocol, thereby ensuring the security of the data.

[1225] input:

[1226] Parsed JSON format data.

[1227] output:

[1228] The encrypted data is sent to the cloud server using the HTTPS protocol.

[1229] Step 3:

[1230] The server decodes the received data and uses a natural language processing (NLP) engine to analyze the operator's background information and areas of interest, specifically using NLP tools such as NLTK and SpaCy to perform keyword extraction and classification to identify the operator's skill level and experience.

[1231] input:

[1232] Encrypted JSON formatted data.

[1233] output:

[1234] Operator profile information (skill level, experience, etc.).

[1235] Step 4:

[1236] The server generates custom instructions for the generative AI (e.g., GPT-3.5) from the analyzed data, generating a "step-by-step guide to basic operations" for newcomers with little experience, and a "troubleshooting optimization method" for veterans.

[1237] input:

[1238] Operator profile information.

[1239] output:

[1240] Custom instructions (e.g., "Step-by-step guide to basic operations").

[1241] Step 5:

[1242] The server re-encrypts the generated custom instructions via API and sends them to the operator's device, where the operator displays the received instructions and performs operations based on their content.

[1243] input:

[1244] Custom instructions.

[1245] output:

[1246] Encrypted custom instructions are sent to the operator's terminal.

[1247] Step 6:

[1248] The user operates the robot by following custom instructions displayed, for example, a "step-by-step guide to basic operations."

[1249] input:

[1250] Custom instructions.

[1251] output:

[1252] User control of the robot.

[1253] Step 7:

[1254] After completing the operation, the user inputs feedback into the device. For example, they input comments such as "This information was helpful" or "I would like more detailed information." The device then sends this feedback to the server in JSON format using the transmission method.

[1255] input:

[1256] Text data of user feedback.

[1257] output:

[1258] The feedback data is parsed in JSON format and sent to the server.

[1259] Step 8:

[1260] The server decodes and analyzes the feedback data and uses it to optimize the generative AI's custom instructions, resulting in more accurate instructions for future iterations.

[1261] input:

[1262] Feedback data.

[1263] output:

[1264] Optimized custom instructions.

[1265] 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.

[1266] This invention is a system that generates custom instructions for generative AI based on the user's background information and emotional state, thereby providing the optimal answer the user desires. In particular, this invention achieves more personalized responses by combining an emotion engine that recognizes the user's emotions.

[1267] System Overview

[1268] 1. Input Method

[1269] User: Accesses the system and enters their knowledge and background information through a dedicated input interface, which may include text boxes and voice input options. For example, they might enter, "I'm an engineer with over 10 years of experience. I'm looking for detailed technical information."

[1270] 2. Transmission Method

[1271] Terminal: User-entered information is packaged in JSON format and sent to the server using a secure protocol.

[1272] 3. Data Reception and Analysis

[1273] Server: Decodes the received data, stores it in a specialized database, and analyzes it. Natural language processing (NLP) algorithms are used to identify the user's background information and areas of interest. For example, information such as "Occupation: Engineer," "Years of experience: 10 years," and "Area of ​​interest: Technical details" can be extracted.

[1274] 4. Emotion recognition

[1275] Device: Operates an emotion engine to recognize emotions from the voice and text data input by the user. It uses voice analysis, facial recognition, or text analysis to identify the user's emotional state. For example, it obtains information such as "The user is excited" or "The user is feeling stressed."

[1276] 5. Instruction Generation

[1277] Server: Automatically generates custom instructions for the generative AI based on the background information acquired by the analytical means and the emotional state recognized by the emotion engine. For example, if the user is feeling stressed, the server adds an instruction such as "answer with kindness."

[1278] 6. Sending generation instructions

[1279] Server: Packages the generated custom instructions in JSON format, encrypts them, and sends them to the device.

[1280] 7. Applying Custom Instructions

[1281] Terminal: Decodes the received custom instructions and applies them to the generative AI, either by updating the configuration file or through API calls.

[1282] 8. User Questions

[1283] User: Asks a question to the generative AI with custom instructions applied, for example, "Tell me about the latest trends in AI technology."

[1284] 9. Generative AI Responses

[1285] Generative AI: Generates optimal answers to user questions based on custom instructions. Provides detailed answers based on the user's technical background and emotional state. For example, it generates specific answers such as, "The latest AI technology trends include deep learning, reinforcement learning, and natural language processing. These technologies are..."

[1286] 10. Results display

[1287] Terminal: Generated answers are displayed on the user's screen, often in the form of text, graphs, charts, or other visual aids.

[1288] 11. Feedback Processing

[1289] User: Enter feedback on the answer provided. For example, "This information was very helpful" or "I'd like to see more specific examples."

[1290] Server: Analyzes user feedback and uses it to improve the custom instructions for the generative AI. Based on the feedback, the instruction generation algorithm is adjusted to improve the accuracy of answers in future.

[1291] Through this system, users can efficiently obtain responses optimized for their technical background and emotional state.

[1292] The processing flow will be explained below.

[1293] Step 1:

[1294] User: Accesses the system's website or application and enters their knowledge and background information through a dedicated input interface, for example, "I am a software engineer with over 10 years of experience. I would like to learn more about the latest AI technologies."

[1295] Step 2:

[1296] Terminal: The information entered by the user is packaged in JSON format, encrypted using HTTPS, and sent to the server.

[1297] Step 3:

[1298] Server: Receives the data, decodes it from JSON format, and stores it in a database, which stores the user's background information, occupation, years of experience, areas of interest, etc.

[1299] Step 4:

[1300] Server: Analyzes the stored data using natural language processing (NLP) algorithms, for example, to determine that the user is a software engineer, has more than 10 years of experience, and is interested in AI technology.

[1301] Step 5:

[1302] On the device: Run an emotion engine to recognize emotions from the user's voice and text data. Use voice analysis, facial recognition, or text analysis techniques to identify the user's emotional state. For example, determine whether the user is excited or stressed.

[1303] Step 6:

[1304] Server: Generates custom instructions based on the analyzed background information and emotional state. For example, if the user is excited, the instructions are set to respond in a detailed and positive tone.

[1305] Step 7:

[1306] Server: Repackage the generated custom instructions in JSON format, re-encrypt them, and send them to the device.

[1307] Step 8:

[1308] Terminal: Decodes the received custom instructions and applies them to the generative AI by updating the AI's configuration file or by using an API call to reflect the instructions.

[1309] Step 9:

[1310] User: Asks a question to the generative AI with custom instructions applied, for example, "Tell me about the latest trends in AI technology."

[1311] Step 10:

[1312] Generative AI: Generates optimal answers to user questions based on custom instructions. For example, it provides specific and detailed answers such as, "The latest AI technology trends include deep learning, reinforcement learning, and natural language processing. Each technology is..."

[1313] Step 11:

[1314] Terminal: Generated answers are displayed on the user's screen, and can be visually interpreted in the form of text, graphs, charts, etc.

[1315] Step 12:

[1316] User: Enter feedback on the answer provided. For example, "This information was very helpful. I'd like to see more specific examples."

[1317] Step 13:

[1318] Server: Re-analyzes the feedback sent by the user and uses it to improve the custom instructions for the generative AI. Based on the feedback, the instruction generation algorithm is adjusted to improve the accuracy of answers in the future.

[1319] This allows users to efficiently receive responses that are optimized for their own technical background and emotional state.

[1320] Example 2

[1321] 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."

[1322] Conventional generative AI systems generate answers by taking into account only the user's background information, which means they are unable to provide personalized responses that reflect the user's emotional state. This reduces user satisfaction and makes it difficult to use the system effectively.

[1323] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an input means through which a user inputs their own knowledge and background information, a transmission means for transmitting data acquired from the input means to the server, an analysis means for analyzing the data received by the server and identifying the user's background information and areas of interest, an instruction generation means for generating custom instructions for the generative AI based on information acquired by the analysis means and the emotion recognition means, a transmission means for transmitting the custom instructions to the user terminal, and an application means for applying the custom instructions to the generative AI. This makes it possible to provide an optimal response according to the user's technical background and emotional state.

[1324] "User" refers to an individual or organization that uses the system.

[1325] "Knowledge" is a general term for specialized fields and general information that a user possesses.

[1326] "Background information" refers to personal information such as the user's occupation, years of experience, and areas of interest.

[1327] "Input means" refers to an interface that allows a user to input information through text, voice, or the like.

[1328] The "transmission means" refers to a means for sending data acquired through the input means to the server.

[1329] "Server" refers to a computer system that receives data via the Internet, analyzes it, and performs the necessary processing.

[1330] "Analysis means" refers to the methods and algorithms used by the server to interpret the data received and identify the user's background information and areas of interest.

[1331] "Emotion recognition means" refers to an engine or algorithm for identifying a user's emotional state from their voice or text data.

[1332] "Instruction generation means" refers to a means for automatically generating custom instructions for the generative AI based on information obtained by the analysis means and emotion recognition means.

[1333] "Custom instructions" refers to special instructions or settings that a generative AI needs to generate the best answer to a user's question.

[1334] "Means of application" refers to the means for applying custom instructions to generative AI.

[1335] "Generative AI" refers to models and systems that use artificial intelligence techniques to generate responses in natural language.

[1336] "Natural language processing algorithms" refer to computational methods for understanding and analyzing text data.

[1337] This invention is a system that generates custom instructions for a generative AI based on the user's background information and emotional state, and provides the optimal answer the user desires. This system is specifically designed to achieve more personalized responses by combining an emotion engine that recognizes the user's emotions.

[1338] First, a user logs into the system and enters their knowledge and background information through a dedicated input interface. This interface includes text boxes and voice input options. For example, a user might enter, "I'm an engineer with over 10 years of experience. I'm looking for detailed technical information." This information is packaged in JSON format and sent to the server using a secure protocol (e.g., HTTPS).

[1339] The server decodes the received data, stores it in a specialized database (e.g., MySQL, NoSQL), and then uses natural language processing (NLP) algorithms (e.g., SpaCy, NLTK) to identify the user's background information and areas of interest. The extracted information might be "Occupation: Engineer," "Years of experience: 10 years," or "Area of ​​interest: Technical details."

[1340] Next, the device recognizes emotions from the user's input data. It uses an emotion engine (e.g., IBM Watson Tone Analyzer, Microsoft Azure Emotion API) to identify the user's emotional state using voice analysis, facial recognition, or text analysis. For example, if a user inputs, "I'm very tired from my recent project, but I'd like to learn more about new technologies," the device can obtain an emotional state such as, "The user is feeling tired."

[1341] The server automatically generates custom instructions for the generative AI (e.g., GPT series) based on the background information acquired by the analysis means and the emotional state recognized by the emotion engine. This can include instructions such as "focus on technical details and provide helpful answers." The generated custom instructions are again packaged in JSON format, encrypted, and sent to the device.

[1342] The device that receives the custom instructions decodes them and applies them to the generative AI through configuration file updates or API calls. When a user inputs a question such as, "Please tell me about the latest trends in AI technology," the generative AI generates the optimal answer based on the custom instructions. For example, a specific answer such as, "The latest trends in AI technology include deep learning, reinforcement learning, and natural language processing. These technologies are..." can be obtained.

[1343] Finally, the device displays the generated answer on the user's screen. The display format can be text, graphs, charts, etc. For example, if the user provides feedback on the provided answer, such as "This information was very helpful" or "I'd like to know more specific examples," the server analyzes that feedback and uses it to improve the generative AI's instruction generation algorithm. This allows for improved answer accuracy in future answers.

[1344] This allows users to efficiently obtain responses that are optimized for their technical background and emotional state.

[1345] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1346] Step 1:

[1347] The user enters their knowledge and background information through an input interface. This input can be done using text boxes or voice input options. For example, they might enter information like, "I'm an engineer with over 10 years of experience. I'm looking for detailed technical information." The input data is packaged in JSON format.

[1348] Input: User text / voice input of knowledge and background information

[1349] Output: JSON formatted data package

[1350] Step 2:

[1351] The terminal sends the information entered by the user to the server using a secure protocol (such as HTTPS). Specifically, it is sent as an HTTP POST request. The communication at this time is encrypted, so the safety of the input data is maintained.

[1352] Input: JSON format data package

[1353] Output: HTTP POST request to the server

[1354] Step 3:

[1355] The server decodes the received data and stores it in a specialized database (e.g., MySQL or NoSQL). Next, it uses natural language processing (NLP) algorithms (e.g., SpaCy or NLTK) to identify the user's background information and areas of interest. For example, information such as "Occupation: Engineer," "Years of experience: 10 years," and "Area of ​​interest: Technical details" can be extracted.

[1356] Input: JSON formatted data received as an HTTP POST request to the server

[1357] Output: Decoded user background information and regions of interest

[1358] Step 4:

[1359] The device runs an emotion engine to recognize the user's emotional state from input data. This is done using emotion recognition tools such as IBM Watson Tone Analyzer and Microsoft Azure Emotion API. Through voice analysis, facial recognition, or text analysis, the device identifies the user's emotional state, such as excitement or fatigue.

[1360] Input: JSON formatted text / audio data

[1361] Output: User's emotional state (e.g., excited, tired)

[1362] Step 5:

[1363] The server automatically generates custom instructions for the generative AI based on the analyzed background information and the identified emotional state. For example, if the user is feeling stressed, the server adds an instruction such as "Respond with kindness." The instructions are packaged in JSON format.

[1364] Input: User background information and emotional state

[1365] Output: Custom instructions (JSON format)

[1366] Step 6:

[1367] The server then packages the generated custom instructions in JSON format, encrypts them, and sends them to the device using a secure protocol (such as SSL / TLS).

[1368] Input: Custom instructions (JSON format)

[1369] Output: Encrypted custom instructions (sent to the terminal)

[1370] Step 7:

[1371] The device decodes the received custom instructions and applies them to the generative AI, either through configuration file updates or API calls, allowing the generative AI to generate optimal responses based on the user's information.

[1372] Input: Received custom instructions (JSON format)

[1373] Output: Applied instructions to the generative AI

[1374] Step 8:

[1375] Users can then ask questions to the generative AI with custom instructions applied, for example, by typing, "Tell me about the latest trends in AI technology."

[1376] Input: User question (text input)

[1377] Output: Question data (JSON format)

[1378] Step 9:

[1379] Generative AI generates the best answer to a user's question based on custom instructions. For example, it can provide a specific answer such as, "The latest trends in AI technology include deep learning, reinforcement learning, and natural language processing. These technologies are..."

[1380] Input: User question data (JSON format)

[1381] Output: Best answer (text format)

[1382] Step 10:

[1383] The terminal displays the generated answers on the user screen. The display format can be text, graphs, charts, etc. For example, if you need a graph to visually explain the latest technology trends, you can display it using an appropriate library (e.g., D3.js or Chart.js).

[1384] Input: Generated answer (text format)

[1385] Output: Answer displayed to the user

[1386] Step 11:

[1387] The user can input feedback for the provided answer, such as "This information was very helpful" or "I would like to know more specific examples."

[1388] Input: User feedback (text input)

[1389] Output: Feedback data (JSON format)

[1390] The server analyzes user feedback and uses it to improve the custom instructions of the generative AI. The feedback data is fed back to a new custom instruction generation algorithm to improve the accuracy of answers from the next time onwards.

[1391] Input: Feedback data (JSON format)

[1392] Output: Improved custom instruction generation algorithm

[1393] (Application example 2)

[1394] 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."

[1395] When a user searches for or purchases products in a virtual store, there is a need for a system that automatically provides optimal product suggestions and information based on the user's emotional state and background information. However, while conventional systems can generate responses based on the user's background information, they cannot generate responses that take the user's emotional state into account. As a result, optimal suggestions are not made based on the user's emotions when searching for products, which can lead to a decrease in satisfaction and a decrease in purchasing motivation.

[1396] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes an input means through which a user inputs their own knowledge and background information, a transmission means for transmitting data acquired from the input means to the server, an analysis means for analyzing the data received by the server and identifying the user's background information and areas of interest, an instruction generation means for generating custom instructions for the generative AI based on the information identified by the analysis means, a transmission means for transmitting the custom instructions to the user terminal, an application means for applying the custom instructions to the generative AI, an emotion recognition means for recognizing the user's emotional state from the user's input, and a suggestion means for suggesting optimal products and providing information in a virtual store based on the user's background information and emotional state. This enables suggestions and answers optimized for the user's technical background and emotional state.

[1397] A "user" is an entity that accesses the system and inputs their knowledge and background information.

[1398] "Background information" is personal information such as the user's occupation, years of experience, areas of interest, etc.

[1399] "Input means" refers to an interface through which a user inputs their own knowledge and background information.

[1400] The "transmission means" is a means for transmitting data acquired from the input means to the server.

[1401] The "server" is the central processing unit of the system that analyzes the received data and generates optimal instructions for the user.

[1402] The "analysis means" is a means for analyzing the data received by the server and identifying the user's background information and areas of interest.

[1403] The "instruction generation means" is a means for generating custom instructions for the generative AI based on the information identified by the analysis means.

[1404] "Custom instructions" are specific instructions to a generative AI that are generated based on the user's background information and emotional state.

[1405] The "application means" is a means for applying the generated custom instructions to the generative AI.

[1406] "Emotion recognition means" is a means for recognizing an emotional state from a user's input.

[1407] The "suggestion means" is a means for suggesting optimal products and providing information within the virtual store based on the user's background information and emotional state.

[1408] "Generative AI" is artificial intelligence that generates optimal responses and suggestions based on the user's background information and emotional state.

[1409] A "virtual store" is a virtual store set up on the Internet to offer products and services.

[1410] The system of the present invention is a solution for virtual stores that provides optimal product suggestions and information to users based on their background information and emotional state. This system provides support for users to efficiently search for and purchase products in stores.

[1411] System Overview

[1412] The system consists of the following components:

[1413] 1. User Device

[1414] The user device provides an interface for users to input their background information and emotional state. Specifically, a smartphone or a head-mounted display (HMD) is used.

[1415] 2. Server

[1416] The server receives and analyzes data sent from the user's device. It is equipped with a natural language processing engine (NLPProcessor) and an emotion recognition engine (EmotionRecognition).

[1417] 3. Generative AI

[1418] Generative AI (Custom AI) provides optimal product suggestions and information to users based on custom instructions received from the server.

[1419] User terminal processing

[1420] The user terminal is equipped with a text box and / or voice input options for the user to enter information, such as "I am a designer with over 5 years of experience." This information is then sent to the server via a security protocol.

[1421] Server Processing

[1422] The server analyzes the received data using a natural language processing engine (NLPProcessor) to identify the user's background information and emotional state. For example, information such as "Occupation: Designer," "Years of Experience: 5 years," and "Emotion: Excited" may be analyzed. The custom instructions constructed based on this information include instructions for the generative AI on how to respond.

[1423] emotion recognition

[1424] The EmotionRecognition engine recognizes the emotional state of a user from their input data. It uses techniques from speech analysis, facial recognition, and text analysis. For example, if a user's input includes "I'm super excited about the new design tool," the EmotionRecognition engine will identify the emotional state as "excited."

[1425] Custom Instruction Generation

[1426] The server generates custom instructions based on the analysis results, such as "Since the user is a designer and is excited, kindly provide detailed information about the latest design tools." This custom instruction is sent to the AI ​​generator, which then provides optimal product suggestions and information.

[1427] Generative AI response

[1428] The generative AI responds to the user according to the custom instructions it receives. For example, in response to a user question, "Tell me about new design tools," it generates a specific answer such as, "CAD software X is a cutting-edge design tool. Using this..."

[1429] Feedback Processing

[1430] Users can enter feedback on the answers provided, which is sent to the server to help improve the generated AI's custom instructions.

[1431] Specific examples

[1432] For example, if a user enters, "I'm a designer and I'm looking for the latest design tools," and then asks, "Tell me about new design tools," the system will suggest the latest design software and examples of its use based on the user's background information and emotional state.

[1433] Prompt Sentence Examples

[1434] "I'm a designer with over 5 years of experience."

[1435] "Tell me about the latest design tools."

[1436] In this way, users can receive personalized suggestions and answers that are optimized for their background information and emotional state, making their shopping experience in the virtual store more efficient and satisfying.

[1437] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1438] Step 1:

[1439] Enter the user's background information. The user enters their background information and areas of interest through a text box or voice input interface. For example, they might enter information such as, "I'm a designer with over 5 years of experience." This becomes the initial input data for the system.

[1440] Step 2:

[1441] The device sends the entered data to the server. The obtained user background information is packaged in JSON format and sent to the server using a security protocol (e.g., HTTPS). At this time, the data is formatted and validated to prevent unauthorized data entry.

[1442] input:

[1443] User-supplied background information (e.g., "I'm a designer with over 5 years of experience.")

[1444] output:

[1445] JSON format data (e.g., "{"Occupation": "Designer", "Experience": "5+ years"}")

[1446] Step 3:

[1447] The server analyzes the received data. The server decodes the received JSON format data and analyzes it using a natural language processing engine (NLPProcessor). For example, information such as "Occupation: Designer" and "Years of experience: 5 years" is extracted and stored in a database.

[1448] input:

[1449] User data in JSON format

[1450] output:

[1451] Analyzed background information (e.g., "Occupation: Designer" and "Years of experience: 5 years")

[1452] Step 4:

[1453] Emotional states are identified using emotion recognition means. The emotion engine (EmotionRecognition) recognizes emotional states based on the voice and text data entered by the user. Using voice analysis and text analysis techniques, emotional states such as "the user is excited" are identified.

[1454] input:

[1455] User-entered text and voice data

[1456] output:

[1457] Perceived emotional state (e.g., "I'm excited")

[1458] Step 5:

[1459] The server generates custom instructions. Based on the background information and emotional state identified by the analysis means, the instruction generation means generates custom instructions containing specific instructions for the generative AI, such as "provide a friendly description of the latest tools for designers."

[1460] input:

[1461] Background information and emotional state

[1462] output:

[1463] Custom instructions (e.g., "Helpful instructions on the latest tools for designers")

[1464] Step 6:

[1465] The custom instructions are sent to the user device. The server packages the generated custom instructions in JSON format and sends them to the user device using a security protocol. The user device decodes the received custom instructions.

[1466] input:

[1467] Generated Custom Instructions

[1468] output:

[1469] Custom instructions in JSON format sent to the user device

[1470] Step 7:

[1471] Apply custom instructions to the generative AI. Custom instructions received on the user's device are applied to the generative AI (CustomAI). This is done by updating the configuration file or by calling the API.

[1472] input:

[1473] Decoded Custom Instructions

[1474] output:

[1475] New instructions set for generative AI

[1476] Step 8:

[1477] A user asks a generative AI a question, for example, "Tell me about a new design tool." The generative AI generates the best answer based on custom instructions.

[1478] input:

[1479] User questions (e.g., "Tell me about the new design tool.")

[1480] output:

[1481] Generative AI answers (e.g., "The latest design tool is CAD software X. Using this...")

[1482] Step 9:

[1483] The terminal displays the generated answer to the user, and the generated answer is displayed on the user's screen in a visually easy-to-understand format such as text or a graph.

[1484] input:

[1485] Generative AI answers

[1486] output:

[1487] The answer displayed on the user's device (e.g., "CAD software X is a cutting-edge design tool. Using this...")

[1488] Step 10:

[1489] Feedback processing is performed. The user enters feedback on the provided answers. For example, they enter their impressions, such as "This information was very helpful." This feedback is sent to the server and used to improve the generative AI.

[1490] input:

[1491] User feedback (e.g., "This information was very helpful")

[1492] output:

[1493] Generative AI improvement data

[1494] In this way, a personalized purchasing experience based on the user's technological background and emotional state is achieved.

[1495] 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.

[1496] 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.

[1497] 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.

[1498] [Fourth embodiment]

[1499] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1500] 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.

[1501] 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).

[1502] 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.

[1503] 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.

[1504] 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).

[1505] 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.

[1506] 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.

[1507] 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.

[1508] 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.

[1509] 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.

[1510] 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.

[1511] 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."

[1512] The present invention is a system that generates custom instructions for a generative AI based on the user's background information, thereby providing the optimal answer the user desires. Specifically, this system uses the following means.

[1513] System Overview

[1514] 1. Input Method

[1515] User: Accesses the system and enters their knowledge and background information through a dedicated input interface. This interface can be a web form, an application UI, etc. For example, a user who is an educator might enter, "I have over 10 years of teaching experience and would like to learn more about the latest educational technologies."

[1516] 2. Transmission Method

[1517] Terminal: User-entered information is encrypted as JSON data and sent to the server using a secure communication protocol (e.g., HTTPS). This transmission method is built into the client-side application code.

[1518] 3. Data Reception and Analysis

[1519] Server: The received data is decoded and stored in a database. The stored data is then analyzed using natural language processing (NLP) algorithms. Specifically, text mining techniques are used to extract information such as the user's occupation, years of experience, and areas of interest, and a user profile is generated based on the analysis results.

[1520] 4. Instruction Generation

[1521] Server: Automatically generates custom instructions for the generative AI based on user information identified through analytical methods. For example, for a user with extensive teaching experience, the server might generate instructions such as "provide a detailed explanation of the latest educational technologies and examples of their practical applications."

[1522] 5. Sending generation instructions

[1523] Server: The generated custom instructions are re-encrypted and sent to the device via the API.

[1524] 6. Applying Custom Instructions

[1525] Device: The user device applies the received custom instructions to the generative AI and saves them in an instruction configuration file or applies them immediately via an API call.

[1526] 7. User Response

[1527] Generative AI: Generates optimal answers to user questions based on custom instructions. For example, if a user asks, "What are the latest trends in educational technology?", the AI ​​can provide a specific answer such as, "The latest trends in educational technology include personalized learning using AI, virtual classrooms using VR, and the use of gamification."

[1528] 8. Results display

[1529] Terminal: The generated answers are presented visually to the user, either in a web browser or in an application, in the form of text, graphs, charts, etc.

[1530] 9. Feedback Processing

[1531] User: Enters feedback on the provided answer and submits it to the server again. The feedback includes specific comments such as "This information was helpful" or "I would like more information."

[1532] Server: Analyzes the received feedback and helps optimize the custom instructions for the generative AI.

[1533] Through this system, users will be able to effectively obtain information tailored to their own expertise and interests, greatly increasing the utility of generative AI.

[1534] The processing flow will be explained below.

[1535] Step 1:

[1536] User: Accesses the system's website or application and enters their knowledge and background information through a dedicated input interface, for example, "I am a doctor and have been working for five years. I would like to learn more about the latest treatments."

[1537] Step 2:

[1538] Terminal: User-entered information is packaged in JSON format, encrypted as an HTTP POST request, and sent to the server using a security protocol (e.g., HTTPS).

[1539] Step 3:

[1540] Server: Receives the transmitted data, decodes it, and stores it in a database. For security reasons, the data is encrypted before storage. It also operates a monitoring system to detect unauthorized access.

[1541] Step 4:

[1542] Server: Analyzes the user's information stored in the database using a natural language processing (NLP) algorithm. This analysis identifies the user's occupation, years of experience, and specific areas of interest. For example, the following data is extracted: "Occupation: Doctor," "Years of experience: 5 years," and "Area of ​​interest: Latest treatments."

[1543] Step 5:

[1544] Server: Automatically generates custom instructions for the generative AI based on the analysis results. Instructions can be set in the form of, for example, "Provide answers that include detailed explanations and the latest research findings in the medical field."

[1545] Step 6:

[1546] Server: The generated custom instructions are packaged again in JSON format, encrypted, and sent to the device. This process also uses a secure communication protocol.

[1547] Step 7:

[1548] Terminal: Decodes the received custom instructions and applies them to the generative AI, either by updating the configuration file or through API calls.

[1549] Step 8:

[1550] User: Asks a question to the generative AI with custom instructions applied, such as "Please tell me more about the latest anti-cancer drug treatments."

[1551] Step 9:

[1552] Generative AI: Generates optimal answers to user questions based on custom instructions. For example, it generates answers that include expert explanations such as, "New anti-cancer drug treatments include molecular targeted therapy and immunotherapy. Details of each are as follows..."

[1553] Step 10:

[1554] Terminal: The generated answers are displayed on the user's screen, not only in text format but also visually using graphs and charts as needed.

[1555] Step 11:

[1556] Users: Enter feedback on the answers provided. Feedback can be specific, such as "This answer was very helpful" or "I need more information."

[1557] Step 12:

[1558] Server: Re-analyzes the feedback sent by the user and uses it to improve the custom instructions for the generative AI. Based on the feedback, the instruction generation algorithm is adjusted to improve the accuracy of answers in the future.

[1559] This series of processes enables users to efficiently obtain information optimized according to their expertise and interests.

[1560] Example 1

[1561] 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."

[1562] Currently, systems that use generative AI to provide answers to users have difficulty generating customized answers based on the user's background information and areas of interest. Additionally, they lack the ability to optimize system performance based on user feedback, making it difficult to provide information that satisfies users.

[1563] 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.

[1564] In this invention, the server includes input means for a user to input their own knowledge and background information, transmission means for transmitting data acquired from the input means to the server, analysis means for analyzing the data received by the server and identifying the user's background information and areas of interest, instruction generation means for generating custom instructions for the generative AI based on the information identified by the analysis means, transmission means for transmitting the custom instructions to a user terminal, application means for applying the custom instructions to the generative AI, response means for a user to input a question for the generative AI and generate an optimal answer based on the question, display means for visually displaying the generated answer to the user, feedback transmission means for acquiring user feedback and transmitting the feedback to the server, and feedback analysis means for analyzing the feedback and optimizing the custom instructions for the generative AI. This enables users to accurately acquire information based on their own expertise and areas of interest, improving the recognition accuracy and utility value of the entire system.

[1565] A "user" is an individual or entity that accesses the system and inputs their knowledge and background information.

[1566] "Input means" refers to an interface through which a user inputs their own knowledge and background information, such as a web form or an application UI.

[1567] The "transmission means" is a means for transmitting the data entered by the user to the server, and uses data encryption and a secure communication protocol such as HTTP.

[1568] A "server" is a computer system that receives data sent by a user, analyzes it, and performs the necessary processing.

[1569] "Analysis means" refers to algorithms or techniques that analyze the data received by the server and identify the user's background information and areas of interest.

[1570] "Database" means a relational database or other data storage system used by the server to store data received by the server.

[1571] A "natural language processing (NLP) algorithm" is a technology that uses text mining technology and other techniques to analyze user input data and understand its meaning and intent.

[1572] The "instruction generation means" is a function that automatically generates custom instructions for the generative AI based on the user information identified by the analysis means.

[1573] "Generative AI" is an artificial intelligence model that generates optimal answers to user questions based on custom instructions.

[1574] A "response means" is a means by which a generative AI generates the optimal answer to a user's question.

[1575] The "display means" is a means for visually displaying the generated answers to the user, and may be displayed in the form of text, graphs, charts, or the like.

[1576] The "feedback sending means" is a means by which a user inputs feedback on a provided answer and sends it to the server.

[1577] "Feedback analysis means" is a technology that analyzes the feedback received by the server and optimizes the custom instructions of the generative AI.

[1578] A "secure communication protocol" is a protocol for ensuring security when sending and receiving data, and an example of this is HTTPS.

[1579] "Custom instructions" are specialized instructions for generative AI that are automatically generated based on the user's background information.

[1580] The present invention provides a system that generates custom instructions for a generative AI based on a user's background information and provides optimal answers. A specific embodiment of this system will be described in detail below.

[1581] System Overview

[1582] Enter user information

[1583] Users enter their knowledge and background information through a dedicated input interface (web form or application UI). This interface is built using HTML and CSS, and the front-end uses JavaScript to process user input. For example, an educator might enter, "I have over 10 years of teaching experience and would like to learn more about the latest educational technologies."

[1584] Sending data

[1585] The terminal encrypts the information entered by the user as JSON format data, uses a standard encryption library, and sends the encrypted data to the server using a secure communication protocol such as HTTPS. This process is implemented using JavaScript or Python coding.

[1586] Receiving and storing data

[1587] The server receives the data sent from the device, decodes it, and stores it in a database. Specifically, it uses a relational database such as MySQL or PostgreSQL to efficiently manage the received data.

[1588] Data analysis

[1589] The server analyzes the stored data using natural language processing (NLP) algorithms, using Python libraries such as nltk and spaCy, and employs text mining techniques to extract information such as the user's occupation, years of experience, and areas of interest, and then generates a user profile.

[1590] Custom Instruction Generation

[1591] The server automatically generates custom instructions for the generative AI based on the analyzed user information. For example, for a user with extensive teaching experience, the server might generate instructions such as "Provide a detailed explanation of the latest educational technologies and examples of their practical applications." This generation is performed using a generative AI model (e.g., GPT-3).

[1592] Sending instructions

[1593] The server then re-encrypts the generated custom instructions and sends them to the device. This process is performed through an API, which uses a standard REST API and can be implemented using a web framework such as Flask or Django.

[1594] Applying the Instructions

[1595] The device applies the received custom instructions to the generative AI. The instructions are stored in a configuration file or applied immediately via API calls, which can include updating a JSON file or making requests to an API endpoint.

[1596] Responding to user questions

[1597] Generative AI generates optimal answers to user questions based on custom instructions. For example, if a user asks, "What are the latest trends in educational technology?", generative AI can provide a specific answer such as, "The latest trends in educational technology include personalized learning using AI, virtual classrooms using VR, and the use of gamification."

[1598] Displaying the results

[1599] The device visually displays the generated answers to the user in the form of text, graphs, charts, etc., delivered in a web browser or application using HTML, CSS, and JavaScript.

[1600] Obtaining and analyzing feedback

[1601] The user inputs feedback on the provided answers and sends it to the server. The feedback sending means is a function for collecting user comments and ratings. The server analyzes the received feedback and uses the feedback analysis means to optimize the custom instructions of the generative AI.

[1602] Examples and prompts

[1603] Specific examples

[1604] User types, "I have over 10 years of teaching experience and would like to learn more about the latest educational technologies."

[1605] The device encrypts the information and sends it to the server via HTTPS.

[1606] The server analyzes the information and identifies the following: "Teaching experience: 10+ years, Area of ​​interest: Educational technology."

[1607] The server generates custom instructions such as "Detailed explanation of the latest educational technologies and their practical applications."

[1608] The server sends these instructions to the terminal, which then applies them to the generative AI.

[1609] When a user asks, "Tell me about the latest trends in education technology," generative AI provides a specific answer.

[1610] Prompt Sentence Examples

[1611] For Educators

[1612] "Write detailed instruction for users with 10+ years of teaching experience about the latest educational technologies and their practical applications."

[1613] For general users

[1614] "Create instructions that take a user's expert background information and generate the best answer based on that information."

[1615] The above is an embodiment of the present invention, which allows a user to accurately obtain information based on their own specialized knowledge or areas of interest.

[1616] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1617] Step 1:

[1618] Users input their knowledge and background information through a dedicated input interface. The input is in text format, for example, "I have more than 10 years of teaching experience. I would like to learn more about the latest educational technologies."

[1619] Input: Text data entered by a user into an input interface.

[1620] Output: The input text data is sent to the next processing step.

[1621] Step 2:

[1622] The device converts the information entered by the user into JSON format data and encrypts it using a standard encryption library to keep the data secure.

[1623] Input: Text data entered by the user.

[1624] Output: Encrypted data in JSON format.

[1625] Step 3:

[1626] The device sends the encrypted data to the server using a secure communication protocol such as HTTPS. The sending process is implemented by program code on the device.

[1627] Input: Encrypted JSON formatted data.

[1628] Output: The encrypted data sent to the server.

[1629] Step 4:

[1630] The server receives the encrypted data and decodes it. The decoded data is then stored in a database, typically a relational database such as MySQL or PostgreSQL.

[1631] Input: Encrypted data.

[1632] Output: The decoded data is stored in the database.

[1633] Step 5:

[1634] The server analyzes the received data using natural language processing (NLP) algorithms. Specifically, it uses Python libraries (nltk, spaCy) to extract the user's occupation, years of experience, and areas of interest.

[1635] Input: Decoded user text data.

[1636] Output: User profile information (occupation, years of experience, areas of interest).

[1637] Step 6:

[1638] The server automatically generates custom instructions for the generative AI based on the analyzed user information. This generation uses a generative AI model (e.g., GPT-3).

[1639] Input: User profile information.

[1640] Output: Custom instructions (e.g., "Describe the latest educational technologies and their practical applications").

[1641] Step 7:

[1642] The server re-encrypts the generated custom instructions and sends them to the device via an API.

[1643] Input: Custom instructions.

[1644] Output: Encrypted custom instructions are sent to the terminal.

[1645] Step 8:

[1646] The device applies the custom instructions it receives to the generative AI, either stored in an instruction configuration file or via an API call.

[1647] Input: Encrypted custom instructions.

[1648] Output: Applied to the generative AI via an instruction configuration file or API calls.

[1649] Step 9:

[1650] The user inputs a question into the generative AI, for example, "Tell me about the latest trends in educational technology."

[1651] Input: The user's question.

[1652] Output: The question is sent to the generative AI.

[1653] Step 10:

[1654] Generative AI generates optimal answers based on custom instructions. For example, it can provide specific answers such as, "The latest trends in educational technology include personalized learning using AI, virtual classrooms using VR, and the use of gamification."

[1655] Input: User questions and custom instructions.

[1656] Output: The best answer generated.

[1657] Step 11:

[1658] The device visually displays the generated answers to the user in the form of text, graphs, charts, etc., within a web browser or application.

[1659] Input: The generated answer.

[1660] Output: The visual information that is displayed to the user.

[1661] Step 12:

[1662] The user inputs feedback for the provided answer and sends it to the server. The user's feedback includes specific comments such as "This information was helpful" or "I would like more information."

[1663] Input: User feedback.

[1664] Output: The feedback data is sent to the server.

[1665] Step 13:

[1666] The server analyzes the received feedback and uses it to optimize the generative AI's custom instructions. Text mining technology is used to analyze the feedback, extracting information to generate more accurate instructions.

[1667] Input: User feedback data.

[1668] Output: Optimized custom instructions.

[1669] (Application example 1)

[1670] 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."

[1671] Existing factory robot systems are difficult to customize based on the skill level and background information of operators, making it difficult to provide efficient instructions or troubleshoot. This problem is particularly pronounced between new employees and experienced operators, and if appropriate information is not provided to both parties, it can have a negative impact on the efficiency and quality of the production process.

[1672] 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.

[1673] In this invention, the server includes an input means for a user to input their own knowledge and background information, a transmission means for transmitting data acquired from the input means, an analysis means for analyzing the data received by the server and identifying the user's background information and areas of interest, an instruction generation means for generating custom instructions for the generative AI based on the information identified by the analysis means, a transmission means for transmitting the custom instructions to a user terminal, an application means for applying the custom instructions to the generative AI, a means installed in a factory robot that manages an industrial process and provides individually customized operating instructions and troubleshooting guides based on the operator's background information, and a feedback processing means for the factory robot to collect and analyze operator feedback and optimize the custom instructions for the generative AI. This enables efficient instruction provision and troubleshooting that corresponds to the individual skill level and background information of the operator.

[1674] The "input means for the user to input his / her own knowledge and background information" is an interface device for the operator to input his / her own skill level, experience, and area of ​​interest.

[1675] The "transmission means for transmitting data acquired from the input means to a server" is a system for transmitting information collected from the input means to a server using a secure communication protocol.

[1676] The "analysis means for analyzing data received by the server and identifying the user's background information and areas of interest" is a system that analyzes data received within the server and identifies the operator's skill level, experience, and areas of interest using natural language processing technology.

[1677] "Instruction generation means for generating custom instructions for the generative AI based on the information identified by the analysis means" refers to a system that creates individual instructions and troubleshooting guides that the generative AI provides to the operator based on the analyzed information.

[1678] The "transmission means for transmitting the custom instructions to the user terminal" is a system that transfers the generated custom instructions to the operator's terminal.

[1679] The "means for applying the custom instructions to the generative AI" is a system that reflects the custom instructions in the settings and commands of the generative AI.

[1680] "A means for installing on a factory robot that manages an industrial process and providing individually customized operating instructions and troubleshooting guides based on the operator's background information" is a system that is installed on a factory robot and provides instructions and guides according to the operator's skills and experience.

[1681] The "feedback processing means for the factory robot to collect and analyze operator feedback to optimize the generative AI's custom instructions" is a system that collects feedback from operators and optimizes the generative AI's instructions based on the results of the analysis.

[1682] This invention is a system that provides factory robots with custom instructions based on background information and generates optimal guides according to the skills and experience of operators. This system aims to improve production efficiency by automatically customizing instructions based on information input by operators.

[1683] System Configuration

[1684] 1. Input Method

[1685] Operators use devices such as tablets and smartphones to input their own operating experience and areas of interest. For example, they input information such as, "I'm a beginner at robot operation. Please teach me the basic operations." through a dedicated user interface.

[1686] 2. Transmission Method

[1687] The entered information is encrypted in JSON format and sent securely to the cloud server using the HTTPS protocol, ensuring the safety of the data.

[1688] 3. Data Analysis

[1689] The server decodes the received data and uses a natural language processing (NLP) engine (e.g., NLTK, SpaCy) to analyze the operator's background information and areas of interest, and then generates an operator profile based on the results. Specifically, it uses keyword extraction and classification techniques to identify the operator's skill level and experience.

[1690] 4. Instruction Generation

[1691] The server generates custom instructions for the generative AI (e.g., GPT-3.5) from the analyzed data. For example, it generates a "step-by-step guide for basic operations" for newcomers with little experience, and a "troubleshooting optimization method" for veterans.

[1692] 5. Sending instructions

[1693] The generated custom instructions are then re-encrypted via an API and sent to the operator's terminal, which provides a user interface to display the received instructions and collect operator feedback.

[1694] 6. Feedback Processing

[1695] Feedback from operators is sent to a cloud server where it is analyzed and used to optimize instructions by the generative AI. For example, specific comments such as "This information was helpful" or "I would like more information" are analyzed.

[1696] Hardware and software used

[1697] Hardware:

[1698] Tablets, smartphones: Devices used by operators to input data about operations and provide feedback.

[1699] Cloud server: Infrastructure for receiving data, analyzing it, and generating instructions.

[1700] software:

[1701] Natural language processing engines: NLTK, SpaCy

[1702] Generative AI models: GPT-3.5, etc.

[1703] Data transmission protocol: HTTPS, JSON format

[1704] Specific examples

[1705] The operator uses a tablet to input and send the message, "I'm a beginner at robot operation. Please teach me the basic operations." The server analyzes the received information and generates custom instructions such as "Step-by-step guide for basic operations: 1. Turn on the power 2. Basic movement operations 3. How to use the sensors," and sends them to the terminal. The operator operates the robot according to the custom instructions and then provides feedback.

[1706] Prompt Sentence Examples

[1707] "Basic Robot Operation Guide: 1. Turning on the power 2. Basic movement operations 3. How to use the sensors"

[1708] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1709] Step 1:

[1710] The user uses a tablet or smartphone to input their own operating experience and areas of interest. At this time, the user enters information such as "I am a beginner at robot operation. Please tell me the basic operations." through a dedicated user interface. The input information is parsed into JSON format.

[1711] input:

[1712] Text data about user experience and areas of interest entered into a tablet or smartphone by the user.

[1713] output:

[1714] Parsed data in JSON format.

[1715] Step 2:

[1716] The terminal transmits the data acquired from the input means to the cloud server in encrypted JSON format using the HTTPS protocol, thereby ensuring the security of the data.

[1717] input:

[1718] Parsed JSON format data.

[1719] output:

[1720] The encrypted data is sent to the cloud server using the HTTPS protocol.

[1721] Step 3:

[1722] The server decodes the received data and uses a natural language processing (NLP) engine to analyze the operator's background information and areas of interest, specifically using NLP tools such as NLTK and SpaCy to perform keyword extraction and classification to identify the operator's skill level and experience.

[1723] input:

[1724] Encrypted JSON formatted data.

[1725] output:

[1726] Operator profile information (skill level, experience, etc.).

[1727] Step 4:

[1728] The server generates custom instructions for the generative AI (e.g., GPT-3.5) from the analyzed data, generating a "step-by-step guide to basic operations" for newcomers with little experience, and a "troubleshooting optimization method" for veterans.

[1729] input:

[1730] Operator profile information.

[1731] output:

[1732] Custom instructions (e.g., "Step-by-step guide to basic operations").

[1733] Step 5:

[1734] The server re-encrypts the generated custom instructions via API and sends them to the operator's device, where the operator displays the received instructions and performs operations based on their content.

[1735] input:

[1736] Custom instructions.

[1737] output:

[1738] Encrypted custom instructions are sent to the operator's terminal.

[1739] Step 6:

[1740] The user operates the robot by following custom instructions displayed, for example, a "step-by-step guide to basic operations."

[1741] input:

[1742] Custom instructions.

[1743] output:

[1744] User control of the robot.

[1745] Step 7:

[1746] After completing the operation, the user inputs feedback into the device. For example, they input comments such as "This information was helpful" or "I would like more detailed information." The device then sends this feedback to the server in JSON format using the transmission method.

[1747] input:

[1748] Text data of user feedback.

[1749] output:

[1750] The feedback data is parsed in JSON format and sent to the server.

[1751] Step 8:

[1752] The server decodes and analyzes the feedback data and uses it to optimize the generative AI's custom instructions, resulting in more accurate instructions for future iterations.

[1753] input:

[1754] Feedback data.

[1755] output:

[1756] Optimized custom instructions.

[1757] 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.

[1758] This invention is a system that generates custom instructions for generative AI based on the user's background information and emotional state, thereby providing the optimal answer the user desires. In particular, this invention achieves more personalized responses by combining an emotion engine that recognizes the user's emotions.

[1759] System Overview

[1760] 1. Input Method

[1761] User: Accesses the system and enters their knowledge and background information through a dedicated input interface, which may include text boxes and voice input options. For example, they might enter, "I'm an engineer with over 10 years of experience. I'm looking for detailed technical information."

[1762] 2. Transmission Method

[1763] Terminal: User-entered information is packaged in JSON format and sent to the server using a secure protocol.

[1764] 3. Data Reception and Analysis

[1765] Server: Decodes the received data, stores it in a specialized database, and analyzes it. Natural language processing (NLP) algorithms are used to identify the user's background information and areas of interest. For example, information such as "Occupation: Engineer," "Years of experience: 10 years," and "Area of ​​interest: Technical details" can be extracted.

[1766] 4. Emotion recognition

[1767] Device: Operates an emotion engine to recognize emotions from the voice and text data input by the user. It uses voice analysis, facial recognition, or text analysis to identify the user's emotional state. For example, it obtains information such as "The user is excited" or "The user is feeling stressed."

[1768] 5. Instruction Generation

[1769] Server: Automatically generates custom instructions for the generative AI based on the background information acquired by the analytical means and the emotional state recognized by the emotion engine. For example, if the user is feeling stressed, the server adds an instruction such as "answer with kindness."

[1770] 6. Sending generation instructions

[1771] Server: Packages the generated custom instructions in JSON format, encrypts them, and sends them to the device.

[1772] 7. Applying Custom Instructions

[1773] Terminal: Decodes the received custom instructions and applies them to the generative AI, either by updating the configuration file or through API calls.

[1774] 8. User Questions

[1775] User: Asks a question to the generative AI with custom instructions applied, for example, "Tell me about the latest trends in AI technology."

[1776] 9. Generative AI Responses

[1777] Generative AI: Generates optimal answers to user questions based on custom instructions. Provides detailed answers based on the user's technical background and emotional state. For example, it generates specific answers such as, "The latest AI technology trends include deep learning, reinforcement learning, and natural language processing. These technologies are..."

[1778] 10. Results display

[1779] Terminal: Generated answers are displayed on the user's screen, often in the form of text, graphs, charts, or other visual aids.

[1780] 11. Feedback Processing

[1781] User: Enter feedback on the answer provided. For example, "This information was very helpful" or "I'd like to see more specific examples."

[1782] Server: Analyzes user feedback and uses it to improve the custom instructions for the generative AI. Based on the feedback, the instruction generation algorithm is adjusted to improve the accuracy of answers in future.

[1783] Through this system, users can efficiently obtain responses optimized for their technical background and emotional state.

[1784] The processing flow will be explained below.

[1785] Step 1:

[1786] User: Accesses the system's website or application and enters their knowledge and background information through a dedicated input interface, for example, "I am a software engineer with over 10 years of experience. I would like to learn more about the latest AI technologies."

[1787] Step 2:

[1788] Terminal: The information entered by the user is packaged in JSON format, encrypted using HTTPS, and sent to the server.

[1789] Step 3:

[1790] Server: Receives the data, decodes it from JSON format, and stores it in a database, which stores the user's background information, occupation, years of experience, areas of interest, etc.

[1791] Step 4:

[1792] Server: Analyzes the stored data using natural language processing (NLP) algorithms, for example, to determine that the user is a software engineer, has more than 10 years of experience, and is interested in AI technology.

[1793] Step 5:

[1794] On the device: Run an emotion engine to recognize emotions from the user's voice and text data. Use voice analysis, facial recognition, or text analysis techniques to identify the user's emotional state. For example, determine whether the user is excited or stressed.

[1795] Step 6:

[1796] Server: Generates custom instructions based on the analyzed background information and emotional state. For example, if the user is excited, the instructions are set to respond in a detailed and positive tone.

[1797] Step 7:

[1798] Server: Repackage the generated custom instructions in JSON format, re-encrypt them, and send them to the device.

[1799] Step 8:

[1800] Terminal: Decodes the received custom instructions and applies them to the generative AI by updating the AI's configuration file or by using an API call to reflect the instructions.

[1801] Step 9:

[1802] User: Asks a question to the generative AI with custom instructions applied, for example, "Tell me about the latest trends in AI technology."

[1803] Step 10:

[1804] Generative AI: Generates optimal answers to user questions based on custom instructions. For example, it provides specific and detailed answers such as, "The latest AI technology trends include deep learning, reinforcement learning, and natural language processing. Each technology is..."

[1805] Step 11:

[1806] Terminal: Generated answers are displayed on the user's screen, and can be visually interpreted in the form of text, graphs, charts, etc.

[1807] Step 12:

[1808] User: Enter feedback on the answer provided. For example, "This information was very helpful. I'd like to see more specific examples."

[1809] Step 13:

[1810] Server: Re-analyzes the feedback sent by the user and uses it to improve the custom instructions for the generative AI. Based on the feedback, the instruction generation algorithm is adjusted to improve the accuracy of answers in the future.

[1811] This allows users to efficiently receive responses that are optimized for their own technical background and emotional state.

[1812] Example 2

[1813] 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."

[1814] Conventional generative AI systems generate answers by taking into account only the user's background information, which means they are unable to provide personalized responses that reflect the user's emotional state. This reduces user satisfaction and makes it difficult to use the system effectively.

[1815] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an input means through which a user inputs their own knowledge and background information, a transmission means for transmitting data acquired from the input means to the server, an analysis means for analyzing the data received by the server and identifying the user's background information and areas of interest, an instruction generation means for generating custom instructions for the generative AI based on information acquired by the analysis means and the emotion recognition means, a transmission means for transmitting the custom instructions to the user terminal, and an application means for applying the custom instructions to the generative AI. This makes it possible to provide an optimal response according to the user's technical background and emotional state.

[1816] "User" refers to an individual or organization that uses the system.

[1817] "Knowledge" is a general term for specialized fields and general information that a user possesses.

[1818] "Background information" refers to personal information such as the user's occupation, years of experience, and areas of interest.

[1819] "Input means" refers to an interface that allows a user to input information through text, voice, or the like.

[1820] The "transmission means" refers to a means for sending data acquired through the input means to the server.

[1821] "Server" refers to a computer system that receives data via the Internet, analyzes it, and performs the necessary processing.

[1822] "Analysis means" refers to the methods and algorithms used by the server to interpret the data received and identify the user's background information and areas of interest.

[1823] "Emotion recognition means" refers to an engine or algorithm for identifying a user's emotional state from their voice or text data.

[1824] "Instruction generation means" refers to a means for automatically generating custom instructions for the generative AI based on information obtained by the analysis means and emotion recognition means.

[1825] "Custom instructions" refers to special instructions or settings that a generative AI needs to generate the best answer to a user's question.

[1826] "Means of application" refers to the means for applying custom instructions to generative AI.

[1827] "Generative AI" refers to models and systems that use artificial intelligence techniques to generate responses in natural language.

[1828] "Natural language processing algorithms" refer to computational methods for understanding and analyzing text data.

[1829] This invention is a system that generates custom instructions for a generative AI based on the user's background information and emotional state, and provides the optimal answer the user desires. This system is specifically designed to achieve more personalized responses by combining an emotion engine that recognizes the user's emotions.

[1830] First, a user logs into the system and enters their knowledge and background information through a dedicated input interface. This interface includes text boxes and voice input options. For example, a user might enter, "I'm an engineer with over 10 years of experience. I'm looking for detailed technical information." This information is packaged in JSON format and sent to the server using a secure protocol (e.g., HTTPS).

[1831] The server decodes the received data, stores it in a specialized database (e.g., MySQL, NoSQL), and then uses natural language processing (NLP) algorithms (e.g., SpaCy, NLTK) to identify the user's background information and areas of interest. The extracted information might be "Occupation: Engineer," "Years of experience: 10 years," or "Area of ​​interest: Technical details."

[1832] Next, the device recognizes emotions from the user's input data. It uses an emotion engine (e.g., IBM Watson Tone Analyzer, Microsoft Azure Emotion API) to identify the user's emotional state using voice analysis, facial recognition, or text analysis. For example, if a user inputs, "I'm very tired from my recent project, but I'd like to learn more about new technologies," the device can obtain an emotional state such as, "The user is feeling tired."

[1833] The server automatically generates custom instructions for the generative AI (e.g., GPT series) based on the background information acquired by the analysis means and the emotional state recognized by the emotion engine. This can include instructions such as "focus on technical details and provide helpful answers." The generated custom instructions are again packaged in JSON format, encrypted, and sent to the device.

[1834] The device that receives the custom instructions decodes them and applies them to the generative AI through configuration file updates or API calls. When a user inputs a question such as, "Please tell me about the latest trends in AI technology," the generative AI generates the optimal answer based on the custom instructions. For example, a specific answer such as, "The latest trends in AI technology include deep learning, reinforcement learning, and natural language processing. These technologies are..." can be obtained.

[1835] Finally, the device displays the generated answer on the user's screen. The display format can be text, graphs, charts, etc. For example, if the user provides feedback on the provided answer, such as "This information was very helpful" or "I'd like to know more specific examples," the server analyzes that feedback and uses it to improve the generative AI's instruction generation algorithm. This allows for improved answer accuracy in future answers.

[1836] This allows users to efficiently obtain responses that are optimized for their technical background and emotional state.

[1837] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1838] Step 1:

[1839] The user enters their knowledge and background information through an input interface. This input can be done using text boxes or voice input options. For example, they might enter information like, "I'm an engineer with over 10 years of experience. I'm looking for detailed technical information." The input data is packaged in JSON format.

[1840] Input: User text / voice input of knowledge and background information

[1841] Output: JSON formatted data package

[1842] Step 2:

[1843] The terminal sends the information entered by the user to the server using a secure protocol (such as HTTPS). Specifically, it is sent as an HTTP POST request. The communication at this time is encrypted, so the safety of the input data is maintained.

[1844] Input: JSON format data package

[1845] Output: HTTP POST request to the server

[1846] Step 3:

[1847] The server decodes the received data and stores it in a specialized database (e.g., MySQL or NoSQL). Next, it uses natural language processing (NLP) algorithms (e.g., SpaCy or NLTK) to identify the user's background information and areas of interest. For example, information such as "Occupation: Engineer," "Years of experience: 10 years," and "Area of ​​interest: Technical details" can be extracted.

[1848] Input: JSON formatted data received as an HTTP POST request to the server

[1849] Output: Decoded user background information and regions of interest

[1850] Step 4:

[1851] The device runs an emotion engine to recognize the user's emotional state from input data. This is done using emotion recognition tools such as IBM Watson Tone Analyzer and Microsoft Azure Emotion API. Through voice analysis, facial recognition, or text analysis, the device identifies the user's emotional state, such as excitement or fatigue.

[1852] Input: JSON formatted text / audio data

[1853] Output: User's emotional state (e.g., excited, tired)

[1854] Step 5:

[1855] The server automatically generates custom instructions for the generative AI based on the analyzed background information and the identified emotional state. For example, if the user is feeling stressed, the server adds an instruction such as "Respond with kindness." The instructions are packaged in JSON format.

[1856] Input: User background information and emotional state

[1857] Output: Custom instructions (JSON format)

[1858] Step 6:

[1859] The server then packages the generated custom instructions in JSON format, encrypts them, and sends them to the device using a secure protocol (such as SSL / TLS).

[1860] Input: Custom instructions (JSON format)

[1861] Output: Encrypted custom instructions (sent to the terminal)

[1862] Step 7:

[1863] The device decodes the received custom instructions and applies them to the generative AI, either through configuration file updates or API calls, allowing the generative AI to generate optimal responses based on the user's information.

[1864] Input: Received custom instructions (JSON format)

[1865] Output: Applied instructions to the generative AI

[1866] Step 8:

[1867] Users can then ask questions to the generative AI with custom instructions applied, for example, by typing, "Tell me about the latest trends in AI technology."

[1868] Input: User question (text input)

[1869] Output: Question data (JSON format)

[1870] Step 9:

[1871] Generative AI generates the best answer to a user's question based on custom instructions. For example, it can provide a specific answer such as, "The latest trends in AI technology include deep learning, reinforcement learning, and natural language processing. These technologies are..."

[1872] Input: User question data (JSON format)

[1873] Output: Best answer (text format)

[1874] Step 10:

[1875] The terminal displays the generated answers on the user screen. The display format can be text, graphs, charts, etc. For example, if you need a graph to visually explain the latest technology trends, you can display it using an appropriate library (e.g., D3.js or Chart.js).

[1876] Input: Generated answer (text format)

[1877] Output: Answer displayed to the user

[1878] Step 11:

[1879] The user can input feedback for the provided answer, such as "This information was very helpful" or "I would like to know more specific examples."

[1880] Input: User feedback (text input)

[1881] Output: Feedback data (JSON format)

[1882] The server analyzes user feedback and uses it to improve the custom instructions of the generative AI. The feedback data is fed back to a new custom instruction generation algorithm to improve the accuracy of answers from the next time onwards.

[1883] Input: Feedback data (JSON format)

[1884] Output: Improved custom instruction generation algorithm

[1885] (Application example 2)

[1886] 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."

[1887] When a user searches for or purchases products in a virtual store, there is a need for a system that automatically provides optimal product suggestions and information based on the user's emotional state and background information. However, while conventional systems can generate responses based on the user's background information, they cannot generate responses that take the user's emotional state into account. As a result, optimal suggestions are not made based on the user's emotions when searching for products, which can lead to a decrease in satisfaction and a decrease in purchasing motivation.

[1888] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes an input means through which a user inputs their own knowledge and background information, a transmission means for transmitting data acquired from the input means to the server, an analysis means for analyzing the data received by the server and identifying the user's background information and areas of interest, an instruction generation means for generating custom instructions for the generative AI based on the information identified by the analysis means, a transmission means for transmitting the custom instructions to the user terminal, an application means for applying the custom instructions to the generative AI, an emotion recognition means for recognizing the user's emotional state from the user's input, and a suggestion means for suggesting optimal products and providing information in a virtual store based on the user's background information and emotional state. This enables suggestions and answers optimized for the user's technical background and emotional state.

[1889] A "user" is an entity that accesses the system and inputs their knowledge and background information.

[1890] "Background information" is personal information such as the user's occupation, years of experience, areas of interest, etc.

[1891] "Input means" refers to an interface through which a user inputs their own knowledge and background information.

[1892] The "transmission means" is a means for transmitting data acquired from the input means to the server.

[1893] The "server" is the central processing unit of the system that analyzes the received data and generates optimal instructions for the user.

[1894] The "analysis means" is a means for analyzing the data received by the server and identifying the user's background information and areas of interest.

[1895] The "instruction generation means" is a means for generating custom instructions for the generative AI based on the information identified by the analysis means.

[1896] "Custom instructions" are specific instructions to a generative AI that are generated based on the user's background information and emotional state.

[1897] The "application means" is a means for applying the generated custom instructions to the generative AI.

[1898] "Emotion recognition means" is a means for recognizing an emotional state from a user's input.

[1899] The "suggestion means" is a means for suggesting optimal products and providing information within the virtual store based on the user's background information and emotional state.

[1900] "Generative AI" is artificial intelligence that generates optimal responses and suggestions based on the user's background information and emotional state.

[1901] A "virtual store" is a virtual store set up on the Internet to offer products and services.

[1902] The system of the present invention is a solution for virtual stores that provides optimal product suggestions and information to users based on their background information and emotional state. This system provides support for users to efficiently search for and purchase products in stores.

[1903] System Overview

[1904] The system consists of the following components:

[1905] 1. User Device

[1906] The user device provides an interface for users to input their background information and emotional state. Specifically, a smartphone or a head-mounted display (HMD) is used.

[1907] 2. Server

[1908] The server receives and analyzes data sent from the user's device. It is equipped with a natural language processing engine (NLPProcessor) and an emotion recognition engine (EmotionRecognition).

[1909] 3. Generative AI

[1910] Generative AI (Custom AI) provides optimal product suggestions and information to users based on custom instructions received from the server.

[1911] User terminal processing

[1912] The user terminal is equipped with a text box and / or voice input options for the user to enter information, such as "I am a designer with over 5 years of experience." This information is then sent to the server via a security protocol.

[1913] Server Processing

[1914] The server analyzes the received data using a natural language processing engine (NLPProcessor) to identify the user's background information and emotional state. For example, information such as "Occupation: Designer," "Years of Experience: 5 years," and "Emotion: Excited" may be analyzed. The custom instructions constructed based on this information include instructions for the generative AI on how to respond.

[1915] emotion recognition

[1916] The EmotionRecognition engine recognizes the emotional state of a user from their input data. It uses techniques from speech analysis, facial recognition, and text analysis. For example, if a user's input includes "I'm super excited about the new design tool," the EmotionRecognition engine will identify the emotional state as "excited."

[1917] Custom Instruction Generation

[1918] The server generates custom instructions based on the analysis results, such as "Since the user is a designer and is excited, kindly provide detailed information about the latest design tools." This custom instruction is sent to the AI ​​generator, which then provides optimal product suggestions and information.

[1919] Generative AI response

[1920] The generative AI responds to the user according to the custom instructions it receives. For example, in response to a user question, "Tell me about new design tools," it generates a specific answer such as, "CAD software X is a cutting-edge design tool. Using this..."

[1921] Feedback Processing

[1922] Users can enter feedback on the answers provided, which is sent to the server to help improve the generated AI's custom instructions.

[1923] Specific examples

[1924] For example, if a user enters, "I'm a designer and I'm looking for the latest design tools," and then asks, "Tell me about new design tools," the system will suggest the latest design software and examples of its use based on the user's background information and emotional state.

[1925] Prompt Sentence Examples

[1926] "I'm a designer with over 5 years of experience."

[1927] "Tell me about the latest design tools."

[1928] In this way, users can receive personalized suggestions and answers that are optimized for their background information and emotional state, making their shopping experience in the virtual store more efficient and satisfying.

[1929] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1930] Step 1:

[1931] Enter the user's background information. The user enters their background information and areas of interest through a text box or voice input interface. For example, they might enter information such as, "I'm a designer with over 5 years of experience." This becomes the initial input data for the system.

[1932] Step 2:

[1933] The device sends the entered data to the server. The obtained user background information is packaged in JSON format and sent to the server using a security protocol (e.g., HTTPS). At this time, the data is formatted and validated to prevent unauthorized data entry.

[1934] input:

[1935] User-supplied background information (e.g., "I'm a designer with over 5 years of experience.")

[1936] output:

[1937] JSON format data (e.g., "{"Occupation": "Designer", "Experience": "5+ years"}")

[1938] Step 3:

[1939] The server analyzes the received data. The server decodes the received JSON format data and analyzes it using a natural language processing engine (NLPProcessor). For example, information such as "Occupation: Designer" and "Years of experience: 5 years" is extracted and stored in a database.

[1940] input:

[1941] User data in JSON format

[1942] output:

[1943] Analyzed background information (e.g., "Occupation: Designer" and "Years of experience: 5 years")

[1944] Step 4:

[1945] Emotional states are identified using emotion recognition means. The emotion engine (EmotionRecognition) recognizes emotional states based on the voice and text data entered by the user. Using voice analysis and text analysis techniques, emotional states such as "the user is excited" are identified.

[1946] input:

[1947] User-entered text and voice data

[1948] output:

[1949] Perceived emotional state (e.g., "I'm excited")

[1950] Step 5:

[1951] The server generates custom instructions. Based on the background information and emotional state identified by the analysis means, the instruction generation means generates custom instructions containing specific instructions for the generative AI, such as "provide a friendly description of the latest tools for designers."

[1952] input:

[1953] Background information and emotional state

[1954] output:

[1955] Custom instructions (e.g., "Helpful instructions on the latest tools for designers")

[1956] Step 6:

[1957] The custom instructions are sent to the user device. The server packages the generated custom instructions in JSON format and sends them to the user device using a security protocol. The user device decodes the received custom instructions.

[1958] input:

[1959] Generated Custom Instructions

[1960] output:

[1961] Custom instructions in JSON format sent to the user device

[1962] Step 7:

[1963] Apply custom instructions to the generative AI. Custom instructions received on the user's device are applied to the generative AI (CustomAI). This is done by updating the configuration file or by calling the API.

[1964] input:

[1965] Decoded Custom Instructions

[1966] output:

[1967] New instructions set for generative AI

[1968] Step 8:

[1969] A user asks a generative AI a question, for example, "Tell me about a new design tool." The generative AI generates the best answer based on custom instructions.

[1970] input:

[1971] User questions (e.g., "Tell me about the new design tool.")

[1972] output:

[1973] Generative AI answers (e.g., "The latest design tool is CAD software X. Using this...")

[1974] Step 9:

[1975] The terminal displays the generated answer to the user, and the generated answer is displayed on the user's screen in a visually easy-to-understand format such as text or a graph.

[1976] input:

[1977] Generative AI answers

[1978] output:

[1979] The answer displayed on the user's device (e.g., "CAD software X is a cutting-edge design tool. Using this...")

[1980] Step 10:

[1981] Feedback processing is performed. The user enters feedback on the provided answers. For example, they enter their impressions, such as "This information was very helpful." This feedback is sent to the server and used to improve the generative AI.

[1982] input:

[1983] User feedback (e.g., "This information was very helpful")

[1984] output:

[1985] Generative AI improvement data

[1986] In this way, a personalized purchasing experience based on the user's technological background and emotional state is achieved.

[1987] 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.

[1988] 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.

[1989] 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.

[1990] 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.

[1991] 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.

[1992] 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.

[1993] 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).

[1994] 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.

[1995] 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."

[1996] 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.

[1997] 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).

[1998] 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.

[1999] 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.

[2000] 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.

[2001] 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.

[2002] 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.

[2003] 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.

[2004] 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.

[2005] 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.

[2006] 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.

[2007] 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.

[2008] The following is further disclosed regarding the above embodiment.

[2009] (Claim 1)

[2010] an input means for a user to input his / her knowledge and background information;

[2011] a transmitting means for transmitting the data acquired from the input means to a server;

[2012] an analysis means for analyzing the data received by the server and identifying background information and areas of interest of the user;

[2013] instruction generation means for generating custom instructions for the generative AI based on the information identified by the analysis means;

[2014] a transmitting means for transmitting the custom instruction to a user terminal;

[2015] an application means for applying the custom instruction to a generative AI;

[2016] A system including:

[2017] (Claim 2)

[2018] 2. The system of claim 1, wherein the analyzing means uses a natural language processing algorithm to identify the user's background information and areas of interest.

[2019] (Claim 3)

[2020] 2. The system of claim 1, wherein the instruction generation means configures the generative AI to provide answers that include technical details and the latest research results based on the user's background information.

[2021] "Example 1"

[2022] (Claim 1)

[2023] an input means for a user to input his / her knowledge and background information;

[2024] a transmitting means for transmitting the data acquired from the input means to a server;

[2025] an analysis means for analyzing the data received by the server and identifying background information and areas of interest of the user;

[2026] instruction generation means for generating custom instructions for the generative AI based on the information identified by the analysis means;

[2027] a transmitting means for transmitting the custom instruction to a user terminal;

[2028] an application means for applying the custom instruction to a generative AI;

[2029] A response means for allowing a user to input a question to the generative AI and generate an optimal answer based on the question;

[2030] a display means for visually displaying the generated answer to the user;

[2031] feedback sending means for obtaining user feedback and sending the feedback to a server;

[2032] A feedback analysis means for analyzing the feedback and optimizing custom instructions for the generative AI;

[2033] A system including:

[2034] (Claim 2)

[2035] 2. The system of claim 1, wherein the analyzing means uses a natural language processing algori...

Claims

1. an input means for a user to input his / her knowledge and background information; a transmitting means for transmitting the data acquired from the input means to a server; an analysis means for analyzing the data received by the server and identifying background information and areas of interest of the user; instruction generation means for generating custom instructions for the generative AI based on the information identified by the analysis means; a transmitting means for transmitting the custom instruction to a user terminal; an application means for applying the custom instruction to a generative AI; A system including:

2. 2. The system of claim 1, wherein the analyzing means uses natural language processing algorithms to identify the user's background information and areas of interest.

3. 2. The system according to claim 1, wherein the instruction generation means configures the generative AI to provide answers that include technical details and the latest research results based on the user's background information.

Images