System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving a consultation content from a user; means for analyzing the consultation content using a natural-language processing technique; means for generating an answer to the consultation content using a generation AI based on the analyzed content; means for returning the generated answer to the user; and means for receiving a feedback from the user and performing analysis and generation again.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional coaching systems have a problem in that responses to users' concerns and problems are standardized, and they are unable to fully meet individual needs. Furthermore, it is difficult for users to continue receiving coaching until they are satisfied, which results in the inability to effectively provide new insights or action plans. The present invention aims to solve these problems by providing highly accurate coaching using generative AI and a system that allows users to receive unlimited coaching until they are satisfied. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for receiving a user's consultation content and analyzing it using natural language processing technology, and a means for generating optimal solutions and advice using a generation AI based on the analysis results. It also provides a system that includes a means for returning the generated answers to the user and a means for receiving feedback from the user and re-analyzing and generating solutions. Furthermore, by recording past consultation content and periodically analyzing it, the system provides new insights and suggestions, thereby enabling more personalized coaching for users. Furthermore, by referencing multiple data sources and generating optimal solutions, the system can provide more specific and practical advice.

[0006] "User" refers to an individual who uses this system to receive coaching.

[0007] "Consultation content" refers to the specific content of the worries or issues that the user inputs and requests the system to solve.

[0008] "Natural language processing" is a general term for technical methods that allow computers to understand and analyze human language.

[0009] "Generative AI" refers to artificial intelligence that automatically generates data and provides new information and solutions based on the results.

[0010] "Analysis" refers to the technical operation of breaking down input data and understanding its content and elements.

[0011] "Answer" refers to the solution or advice that the generative AI provides to the user based on the analysis results.

[0012] "Feedback" refers to the evaluation or opinion a user gives on a provided answer.

[0013] "Recording" refers to the act of saving the user's consultation details and feedback information so that they can be reused in the future.

[0014] "Data source" refers to the source of information or underlying data that generative AI references when generating solutions or advice.

[0015] "Advice" refers to specific guidelines for action or recommended solutions provided based on the user's inquiry. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0024] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0037] The system of the present invention is designed to provide highly accurate coaching using generative AI. This system is mainly composed of a user terminal, a server, and a database.

[0038] Overall system flow

[0039] Input and transmission from the user terminal

[0040] 1. The user inputs the details of the coaching they wish to receive from their device and makes a request to send it. Typically, the user enters the details of the consultation into the application's input field and presses the send button.

[0041] Server receives and analyzes the request

[0042] 2. The server receives the request from the user and analyzes its contents. Specifically, it preprocesses the input text using natural language processing technology and extracts important keywords and context. For example, if a request is entered such as "I'm worried about my career path," the server identifies the keywords "career path" and "worry" from the request.

[0043] Starting the generative AI and generating answers

[0044] 3. The server then activates the generation AI based on the analysis results to generate the optimal answer for the consultation. The generation AI references multiple data sources and extracts appropriate solutions and advice from them. For example, specific options such as "joining a new project" or "training to improve skills" are generated as "optimal advice regarding career paths."

[0045] Return of coaching content

[0046] 4. The server constructs a response to return the generated coaching content to the user. This response is formatted in a format that is easy for the user to understand and sent to the user's device as an HTTP response. The user's device receives this response and displays it on the screen. Specifically, it displays the message, "Your career path has the following options."

[0047] Processing Feedback

[0048] 5. The user can enter additional questions or feedback about the coaching content provided and submit the request again. For example, the user can enter feedback such as, "I would like to know a more specific action plan."

[0049] 6. The server receives the feedback and uses the generation AI to generate detailed coaching content. For example, a specific action plan such as "The following skill set is required to participate in the project" is provided.

[0050] Providing new insights

[0051] 7. The server records the user's past consultations and periodically analyzes them to generate new insights and suggestions. For example, it can analyze past consultation history and provide the latest information on project management.

[0052] Specific examples

[0053] For example, if a user enters "I'm having trouble communicating with my subordinates":

[0054] 1. The server receives this request and analyzes keywords such as "subordinate" and "communication."

[0055] 2. The generative AI refers to data on "effective communication methods with subordinates" and generates specific advice, such as "putting active listening into practice."

[0056] 3. If the user further provides feedback that they would like to know examples of specific situations, the server will launch the generation AI again and provide "specific examples of how to ask subordinates about the progress of a project."

[0057] In this way, the system of the present invention can provide highly accurate coaching tailored to the individual needs of the user and provide continuous support, allowing the user to receive more specific and useful advice and gain new insights and action plans.

[0058] The processing flow will be explained below.

[0059] Step 1:

[0060] The user enters their concerns or questions into the input field on the device and presses the send button. For example, they enter, "I'm worried about my career path. Please tell me how I should proceed," and then presses the send button.

[0061] Step 2:

[0062] The terminal sends the consultation details entered by the user to the server as an HTTP request.

[0063] Step 3:

[0064] The server receives the HTTP request and analyzes the request content. Specifically, the text is passed to a natural language processing (NLP) module for preprocessing such as tokenization, stop word removal, and stemming.

[0065] Step 4:

[0066] The server extracts important keywords and context from the analyzed text data. For example, it identifies the keywords "career path" and "worries."

[0067] Step 5:

[0068] The server selects and launches an appropriate generative AI model based on the extracted keywords.

[0069] Step 6:

[0070] The server uses generation AI to generate the optimal answer for the user's inquiry. Specifically, it references multiple data sources and generates specific options such as "joining a new project," "training to improve skills," and "consulting with a supervisor."

[0071] Step 7:

[0072] The server then formats the generated answers into an easy-to-read format, such as "Your career path includes the following options: 1. Join a new project within your department, 2. Take training to improve your skills, or 3. Talk to your manager to clarify your specific role."

[0073] Step 8:

[0074] The server sends the formatted answer to the user terminal as an HTTP response.

[0075] Step 9:

[0076] The device receives the HTTP response and displays it on the screen. For example, it might say, "Your career path has the following options: 1. Join a new project within your department. 2. Take training to improve your skills. 3. Talk to your manager to clarify your specific role."

[0077] Step 10:

[0078] The user enters a follow-up question or feedback on the answer provided, for example, "I'd like to know a more specific action plan," and hits the submit button again.

[0079] Step 11:

[0080] The device sends the new input to the server as an HTTP request.

[0081] Step 12:

[0082] The server receives the request again and performs additional analysis, especially generating more detailed information using generative AI to respond to user feedback.

[0083] Step 13:

[0084] The server then uses the generative AI to generate specific action plans and detailed advice, such as, "To participate in Project A, you first need the following skill set. You can acquire these skills by participating in Training Program B."

[0085] Step 14:

[0086] The server reformats the generated details and constructs a response to send back to the user.

[0087] Step 15:

[0088] The device receives the new response and displays it on the screen, for example, "To participate in Project A, you first need the following skill set. You can acquire these skills by participating in Training Program B."

[0089] Step 16:

[0090] The server records the user's past requests and responses in a database, analyzes them periodically, and generates new insights and suggestions.

[0091] Step 17:

[0092] The server generates new insights and suggestions based on the results of periodic analysis and notifies the user.

[0093] Step 18:

[0094] The device receives notifications from the server and displays them on the screen. For example, a notification might say, "We have the latest information on the latest trends and techniques for project management, which we previously discussed."

[0095] Example 1

[0096] 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."

[0097] Conventional coaching systems have struggled to provide quick and specific solutions to users' concerns. Furthermore, few systems offer ongoing support based on feedback, making it difficult for users to receive effective advice. Furthermore, because they are unable to provide new suggestions or insights based on past consultations, it is difficult to continuously support users' growth.

[0098] 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.

[0099] In this invention, the server includes means for receiving the consultation content from the user, means for analyzing the consultation content using natural language processing technology, means for generating an answer to the consultation content using a generation AI based on the analyzed data, means for returning the generated answer to the user, means for receiving feedback from the user and re-analyzing and generating an answer, and means for proposing specific options and action plans related to the consultation content. This makes it possible to provide the user with a quick and specific solution, and to provide continuous support based on feedback and new proposals based on past consultation content.

[0100] A "user" is an entity that uses the coaching system to input the details of a consultation and receives the generated advice and suggestions.

[0101] "Consultation content" refers to the problem or question that the user inputs to the coaching system and seeks to resolve.

[0102] "Natural language processing technology" is a technology that enables computers to understand, analyze, and generate human language, and includes text analysis and keyword extraction.

[0103] "Generative AI" is a general term for artificial intelligence models that generate optimal sentences or responses based on input prompts.

[0104] An "answer" is a solution or proposal that the generative AI generates based on the content of the consultation.

[0105] "Feedback" refers to a user entering more specific information or a follow-up question in response to a provided answer.

[0106] "Specific options and action plans" refer to specific action plans and options proposed by the generative AI that are directly linked to solving the user's problem.

[0107] "Sources" are multiple external data sources and knowledge bases that the generative AI references to generate answers.

[0108] This invention is a system that analyzes the content of a user's consultation and provides highly accurate coaching using a generative AI model. This system is mainly composed of a user terminal, a server, and a database.

[0109] Hardware and Software Configuration

[0110] User terminal

[0111] The user terminal consists of a mobile device or computer. The user uses this to input the content of the consultation and subsequent feedback. A web application or mobile application is installed on the user terminal, and the user accesses the system through this.

[0112] server

[0113] The server is responsible for receiving requests, analyzing them, and launching the generative AI. The server typically runs on a high-performance computing device or cloud service. It processes HTTP requests using a Python web framework (e.g., Flask or Django). Libraries such as NLTK and SpaCy are used for natural language processing. Generative AI models such as OpenAI's GPT-4 are used.

[0114] Database

[0115] The database records users' past consultation details and feedback. By using a relational database such as MySQL or PostgreSQL, data can be efficiently stored and managed.

[0116] System Operation

[0117] The user enters the content of their consultation in the application's input field and presses the send button to send a request. For example, the user might enter a content such as "I'm worried about my career path."

[0118] The server receives this and analyzes the text using natural language processing techniques, such as NLTK and SpaCy, to extract important keywords and context. For example, it identifies keywords such as "career path" and "concerns."

[0119] The server then launches a generative AI to generate the optimal answer based on the analysis results. The generative AI uses OpenAI's GPT-4 and other technologies to generate solutions by referencing multiple sources of information. For example, it suggests specific options such as "joining a new project" or "training to improve skills."

[0120] The server creates the generated answer in JSON format and sends it to the user's device as an HTTP response. The user's device receives it and displays it on the screen. For example, it might say, "Your career path has the following options."

[0121] The user can enter additional questions or feedback about the coaching provided. For example, the user can enter, "I'd like to know a more specific action plan."

[0122] The server receives the feedback, analyzes it again, and generates a new AI. It then launches the AI ​​to propose a detailed action plan. For example, it generates specific advice such as, "The following skill set is required to participate in the project."

[0123] Example prompt sentences

[0124] "I'm struggling with my career path. Can you give me some concrete advice on how to get involved in new projects and improve my skills?"

[0125] "I'm having trouble communicating with my subordinates. Can you give me some specific examples for different situations?"

[0126] This invention allows users to obtain quick and specific solutions and receive continuous support based on feedback. Furthermore, by obtaining new suggestions and insights based on past consultations, it is possible to continuously support the user's growth.

[0127] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0128] Step 1:

[0129] The user enters the content of their consultation into the application's input field and presses the send button. The input content is constructed as text data. For example, the specific content of their consultation may be, "I'm worried about my career path." The output is the input text data.

[0130] Step 2:

[0131] The user terminal sends the entered text data to the server as an HTTP POST request. The input is the text data entered by the user, and the output is data in the form of an HTTP request. Specifically, in the case of a web application, the request is sent using the JavaScript fetch API.

[0132] Step 3:

[0133] The server receives an HTTP POST request sent from the user device. The input is the HTTP request from the user device, and the output is text data extracted from the request. Specifically, the request data is obtained using a web framework such as Flask or Django.

[0134] Step 4:

[0135] The server analyzes the received text data using natural language processing technology. The input is the text data extracted from the request, and the output is the analyzed keywords and context. Specifically, it uses Python's NLTK and SpaCy to tokenize the text and extract important keywords. For example, keywords such as "career path" and "concerns" are identified.

[0136] Step 5:

[0137] The server launches a generative AI model based on the analysis results. The input is the analyzed keywords and context, and the output is a prompt to be passed to the generative AI. Specifically, a Python script is used to call the generative AI (e.g., OpenAI's GPT-4 API) and construct the prompt. For example, a prompt is generated as "the best advice regarding your career path."

[0138] Step 6:

[0139] The generative AI generates the optimal answer based on the prompt text. The input is the prompt text sent from the server, and the output is the generated text answer. For example, it generates specific solutions such as "join a new project" or "training to improve skills."

[0140] Step 7:

[0141] The server constructs a response based on the generated text answer. The input is the text answer from the generation AI, and the output is the response data in JSON format. Specifically, the JSON response constructed using Flask or Django is sent as an HTTP response.

[0142] Step 8:

[0143] The user terminal receives the JSON response sent from the server and displays it on the screen. The input is the JSON-formatted response data from the server, and the output is text displayed on the user interface. For example, "Your career path has the following options."

[0144] Step 9:

[0145] The user inputs additional questions or feedback regarding the provided coaching content and makes another transmission request. The input is the user's feedback regarding the provided answer, and the output is the text data entered as feedback. For example, the user might input, "I would like to know a more specific action plan."

[0146] Step 10:

[0147] The user terminal transmits the text data input as feedback to the server again as an HTTP POST request. The input is the text data input as feedback, and the output is data in the HTTP request format.

[0148] Step 11:

[0149] The server receives the resent HTTP POST request and re-analyzes the text data. The input is the HTTP request from the user device, and the output is the re-analyzed keywords and context. Again, a natural language processing library is used to tokenize the text and extract important keywords.

[0150] Step 12:

[0151] The server then launches the generative AI model again based on the reanalyzed results. The input is the reanalyzed keywords and context, and the output is a new prompt to be passed to the generative AI. The generative AI is then called to construct a new prompt.

[0152] Step 13:

[0153] The generation AI generates a detailed answer based on the second prompt. The input is the second prompt sent from the server, and the output is a detailed answer in the generated text. For example, it generates specific advice such as, "The following skill set is required to participate in the project."

[0154] Step 14:

[0155] The server reconstructs a response based on the detailed answer. The input is the text answer from the generation AI, and the output is the response data in JSON format. The reconstructed JSON response is sent again as an HTTP response.

[0156] Step 15:

[0157] The user device again receives the JSON response sent from the server and displays it on the screen. The input is the JSON-formatted response data from the server, and the output is text displayed on the user interface. For example, it displays a specific message such as, "The following skill set is required to participate in the project."

[0158] (Application example 1)

[0159] 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."

[0160] Customer service in stores depends on the skills and experience of the staff, making it difficult to provide consistent quality service. New employees and staff who are unfamiliar with customer service often have trouble receiving appropriate advice quickly. This creates a need for improving the skills of individual staff and the service quality of the entire store.

[0161] 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.

[0162] In this invention, the server includes means for receiving the content of the consultation from the user, means for analyzing the content of the consultation using natural language processing technology, means for generating an answer to the consultation using a generation AI based on the analyzed data, means for returning the generated answer to the user, means for receiving feedback from the user and re-analyzing and generating, and means for using the analyzed and generated data to improve the skills of store staff, thereby enabling store staff to solve problems and improve their skills in real time.

[0163] The "means for receiving consultation contents from the user" is a function including an interface for transmitting consultation contents input by the user to the system.

[0164] "Means for analyzing consultation content using natural language processing technology" is a function for analyzing input consultation content using natural language processing technology and extracting important keywords and context.

[0165] "Means of using generation AI based on analyzed data to generate an answer to the inquiry content" is a function that uses generation AI to generate the optimal answer based on analyzed data.

[0166] "Means for returning the generated answer to the user" is a function that includes an interface for returning and displaying the answer generated by the generation AI to the user.

[0167] The "means for receiving feedback from the user and performing analysis and generation again" is a function for receiving feedback provided by the user and performing the analysis and generation process again based on that feedback.

[0168] "Means of using the analyzed and generated data to improve the skills of store staff" is a function that uses the data obtained through the analysis and generation process to improve the customer service skills of store staff and solve problems.

[0169] The present invention will be described in detail below with reference to an embodiment thereof. Specifically, a specific method for introducing a coaching system for improving customer service skills into a brick-and-mortar store will be described.

[0170] System Configuration

[0171] The coaching system of the present invention is comprised of the following main components:

[0172] 1. User device: A smartphone used by store staff.

[0173] 2. Server: A central computer system that receives and analyzes consultation content, runs the generative AI, and processes feedback.

[0174] 3. Generative AI model: An AI model that uses natural language processing technology to generate optimal advice based on the content of a consultation (e.g., Hugging Face's GPT-3).

[0175] Hardware and Software

[0176] 1. Hardware:

[0177] Smartphone: Used by store staff as a user device.

[0178] Server computer: Provides the computational resources for hosting the generative AI models and databases.

[0179] 2. Software:

[0180] Natural language processing (NLP) library: Used to analyze consultation content.

[0181] Generative AI model: Hugging Face's GPT-3 is used to generate specific advice for the consultation content.

[0182] Database management system: Records user consultations and feedback and analyzes them periodically.

[0183] Data processing and calculation

[0184] 1. User Device:

[0185] Store staff enter the details of the consultation via a smartphone app and send it to the server.

[0186] The app will have an intuitive interface and will be designed to allow staff to easily input their enquiries.

[0187] 2. Server:

[0188] Receiving: The server receives the input from the user terminal and decodes the text data.

[0189] Analysis: Natural language processing techniques are used to analyze text data and extract key keywords and context.

[0190] Generation: Based on the analysis results, a generative AI model is run to generate optimal advice for the consultation.

[0191] Return: The generated advice is returned to the user's device and displayed on the smartphone screen.

[0192] Examples and prompts

[0193] Examples:

[0194] 1. Store staff enter "How to respond when receiving a customer complaint" into a smartphone app.

[0195] 2. The server receives this request and extracts the keyword "complaint handling" through natural language processing.

[0196] 3. The generative AI model generates specific advice such as, "It's important to stay calm and resolve the problem quickly."

[0197] 4. This advice is sent back to the staff member's smartphone and displayed.

[0198] Example prompt sentence:

[0199] How do you handle customer complaints about products?

[0200] "Please suggest ways to improve communication with team members."

[0201] This system enables store staff to solve problems in real time and improve their skills, contributing to improving the service quality of the entire store.

[0202] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0203] Step 1:

[0204] The user inputs the content of the consultation through a smartphone app and presses the send button. This input includes a specific question, such as "Please tell me how to respond when a customer complains." The input text data is sent to the server in the latest format (e.g., JSON).

[0205] Step 2:

[0206] The server receives text data sent from the user terminal. To analyze the received data, it first formats the text data and checks its format. The input data is extracted as plain text and prepared for the next analysis step. The input for this step is the content of the user's inquiry, and the output is formatted text data.

[0207] Step 3:

[0208] The server analyzes the formatted text data using natural language processing techniques. Specifically, it uses an NLP library (e.g., spaCy or NLTK) to extract important keywords and context from the text data. The input to this analysis step is the formatted text data, and the output is the extracted keywords and context information.

[0209] Step 4:

[0210] The server launches a generative AI model (e.g., Hugging Face GPT-3) based on the analysis results to generate the optimal answer. The generation prompt includes extracted keywords and contextual information and is input to the generative AI. The generative AI model uses the input prompt to generate the optimal answer. The input to this step is the analysis results, and the output is the generated answer (advice).

[0211] Step 5:

[0212] The server constructs a response to send the generated answer back to the user. The response is sent in HTTP format to the user's smartphone, which receives the response and displays it on the screen. The input of this step is the generated answer, and the output is the response sent to the user's terminal.

[0213] Step 6:

[0214] If the user wishes to provide further feedback or ask a follow-up question based on the provided answer, such as a request like "Please provide a more specific action plan," the user's feedback is also sent to the server, where it is parsed and generated through a similar processing step. The input of this step is the user's feedback, and the output is a regenerated, detailed answer.

[0215] Step 7:

[0216] The server records the user's past consultation details and feedback in a database and periodically analyzes them. The database also stores time-series data, and generates "new insights and suggestions" based on the results of periodic analysis. The input for this step is the past consultation details and feedback, and the output is newly generated suggestions and insights.

[0217] Through these steps, store staff are continuously supported in improving their customer service skills and resolving problems.

[0218] 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.

[0219] The system of the present invention is designed to provide highly accurate coaching by combining generative AI and an emotion engine. This system is mainly composed of a user terminal, a server, a database, and an emotion engine.

[0220] Overall system flow

[0221] Input and transmission from the user terminal

[0222] 1. The user inputs the details of the coaching they would like to receive from their device and sends a request. For example, they might input, "I'm worried about my career path. Please tell me how I should proceed," and press the send button.

[0223] Server receives and analyzes the request

[0224] 2. The server receives the request from the user and analyzes its contents. Specifically, it passes the text to a natural language processing (NLP) module for preprocessing such as tokenization, stop word removal, and stemming.

[0225] 3. The server extracts important keywords and context from the analyzed text data. For example, it identifies the keywords "career path" and "concerns."

[0226] Activating the Emotion Engine

[0227] 4. The server passes the extracted text data to the emotion engine, which analyzes the user's emotions. The emotion engine identifies the emotions contained in the text and classifies them into emotion categories such as "anxiety," "excitement," and "anger."

[0228] Starting the generative AI and generating answers

[0229] 5. The server then activates the generative AI, taking into account the analysis results of the emotion engine, to generate the optimal answer for the user's inquiry. For example, as "career path advice," it generates specific options such as "joining a new project" or "training to improve skills."

[0230] 6. The server formats the generated answer and constructs a response to send back to the user. This response is constructed in a format that reflects the user's emotional state. For example, if the user is feeling "anxious," it uses wording that makes them feel more reassured.

[0231] Return of coaching content

[0232] 7. The server sends the formatted answer to the user terminal as an HTTP response.

[0233] 8. The user device receives the HTTP response and displays it on the screen. For example, it might say, "Your career path has the following options: 1. Join a new project within your department. 2. Take training to improve your skills. 3. Talk to your manager to clarify your specific role."

[0234] Processing Feedback

[0235] 9. The user enters additional questions or feedback about the provided answer and submits the request again. For example, they enter "I'd like to know a more specific action plan" and press the submit button again.

[0236] 10. The server receives the feedback and uses the generative AI and emotion engine to generate detailed coaching content. For example, it provides a specific action plan such as, "To participate in Project A, you first need the following skill set. You can acquire these skills by participating in Training Program B."

[0237] Providing new insights

[0238] 11. The server records the user's past requests and responses in a database and periodically analyzes them to generate new insights and suggestions. For example, it can analyze past consultation history and provide the latest information on project management.

[0239] 12. The server generates new insights and suggestions based on the results of periodic analysis and notifies the user.

[0240] 13. The user device receives the notification from the server and displays it on the screen. For example, a notification may appear saying, "We have the latest information on the latest trends and techniques for project management, which we previously discussed."

[0241] Specific examples

[0242] For example, if a user enters "I'm having trouble communicating with my subordinates":

[0243] 1. The server receives this request and analyzes keywords such as "subordinate" and "communication."

[0244] 2. The emotion engine identifies the emotion of "being troubled."

[0245] 3. The generative AI references data on "effective communication methods with subordinates" and generates specific solutions. For example, it generates advice such as "Make an effort to actively listen."

[0246] 4. The server then takes into account the user's emotional state and formats the response in a reassuring way, for example, by displaying a message such as, "To solve your problem, let's start by actively listening."

[0247] This allows the system of the present invention to provide personalized, highly accurate coaching that takes into account the user's emotions, and to provide continuous support until the user is satisfied.

[0248] The processing flow will be explained below.

[0249] Step 1:

[0250] The user enters their concerns or questions into the input field on the device and presses the send button. For example, they enter, "I'm worried about my career path. Please tell me how I should proceed," and then presses the send button.

[0251] Step 2:

[0252] The terminal sends the consultation details entered by the user to the server as an HTTP request.

[0253] Step 3:

[0254] The server receives the HTTP request and analyzes the request content. Specifically, the text is passed to a natural language processing (NLP) module for preprocessing such as tokenization, stop word removal, and stemming.

[0255] Step 4:

[0256] The server extracts important keywords and context from the analyzed text data. For example, it identifies the keywords "career path" and "worries."

[0257] Step 5:

[0258] The server passes the extracted keywords to an emotion engine to analyze the user's emotions, for example, detecting whether the text contains the word "anxiety."

[0259] Step 6:

[0260] The emotion engine analyzes the text and classifies the user's emotional state, for example into emotion categories such as "anxiety," "excitement," and "anger."

[0261] Step 7:

[0262] The server optimizes the AI's response based on the user's emotional state. For example, if the user is feeling anxious, it will select reassuring language.

[0263] Step 8:

[0264] The server activates the appropriate generative AI model and generates the optimal answer to the user's inquiry, taking into account the results of the emotion engine. For example, it generates "specific advice on career paths" such as "joining a new project" or "training to improve skills."

[0265] Step 9:

[0266] The server formats the generated answers and summarizes them in an easy-to-read format. Reassuring language is added to reflect the emotional state. For example, "Your career path includes the following options: 1. Join a new project within your department. 2. Take training to improve your skills. 3. Talk to your manager to clarify your specific role. Rest assured, you'll see results soon."

[0267] Step 10:

[0268] The server sends the formatted answer to the user terminal as an HTTP response.

[0269] Step 11:

[0270] The device receives the HTTP response and displays it on the screen. For example, it might say, "Your career path has the following options: 1. Join a new project within your department. 2. Take training to improve your skills. 3. Talk to your manager to clarify your specific role. Don't worry, you'll see positive results soon."

[0271] Step 12:

[0272] The user can enter additional questions or feedback about the answers provided and press the submit button again. For example, they can enter "I'd like to know a more specific action plan" and press the submit button again.

[0273] Step 13:

[0274] The device sends the new input to the server as an HTTP request.

[0275] Step 14:

[0276] The server receives the request again and analyzes the new input. Specifically, it again preprocesses it using natural language processing technology to extract additional important keywords.

[0277] Step 15:

[0278] The server again uses the emotion engine to confirm the user's emotional state, for example detecting an increase in the emotion of "anxiety" based on additional input information.

[0279] Step 16:

[0280] The server passes the results of the analysis and emotion engine to the generation AI, which then generates an appropriate solution. For example, it generates a specific action plan such as, "To participate in Project A, you first need the following skill set. You can acquire these skills by participating in Training Program B."

[0281] Step 17:

[0282] The server reformats the generated details and constructs a response to send back to the user.

[0283] Step 18:

[0284] The device receives the new response and displays it on the screen, for example, "To participate in Project A, you first need the following skill set. You can acquire these skills by participating in Training Program B."

[0285] Step 19:

[0286] The server records the user's past requests and responses in a database, analyzes them periodically, and generates new insights and suggestions.

[0287] Step 20:

[0288] The server generates new insights and suggestions based on the results of periodic analysis and notifies the user.

[0289] Step 21:

[0290] The device receives notifications from the server and displays them on the screen. For example, a notification might say, "We have the latest information on the latest trends and techniques for project management, which we previously discussed."

[0291] Example 2

[0292] 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."

[0293] Conventional coaching systems have had the problem of being unable to generate personalized answers that take the user's emotions into account, which means they are unable to sufficiently increase user satisfaction. It has also been difficult to effectively utilize user feedback and provide continuous, highly accurate coaching.

[0294] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0295] In this invention, the server includes means for receiving consultation content from a user, means for analyzing the consultation content using natural language processing technology, means for identifying and classifying emotions based on the analyzed data, means for generating an answer to the consultation content using a generative AI model taking into account the emotion analysis results, means for formatting the generated answer in accordance with the user's emotional state and returning it to the user, and means for receiving feedback from the user and re-analyzing and generating an answer. This makes it possible to provide the user with personalized answers according to their emotions and provide continuous, highly accurate coaching.

[0296] The "means for receiving consultation content" is an interface for electronically collecting input information from users and processing it within the system.

[0297] "Natural language processing technology" is a technology that allows computers to understand and analyze human language, and includes processes such as tokenization and removal of stop words.

[0298] "Means for identifying and classifying emotions" refers to technology for detecting user emotions (e.g., anxiety, excitement, anger, etc.) from text data and classifying them into categories.

[0299] A "generative AI model" is an artificial intelligence technique for generating appropriate responses in natural language based on input prompts.

[0300] "Formulating" refers to a technology that converts the answers output by the generative AI model into the optimal format based on the user's emotions and situation.

[0301] The "means for receiving feedback" is an interface for collecting information and opinions re-entered from the user and using them to analyze the next step and generate answers.

[0302] "Multiple data sources" is a general term for various databases and information sources that are referenced to respond to the user's inquiry.

[0303] "Means of providing new insights and suggestions" refers to technology that analyzes past data, generates new knowledge and action plans, and proposes them to users.

[0304] The system of the present invention is designed to combine a generative AI model and an emotion engine to provide highly accurate coaching. This system is mainly composed of a user terminal, a server, a database, and an emotion engine. Specifically, it includes the following functions and processes:

[0305] Input and transmission from the user terminal

[0306] The user inputs the details of the coaching they would like to receive from their device and sends a request. Specifically, the user interface includes a text box where they can type, "I'm having trouble deciding on my career path. Can you tell me how I should proceed?" and then press the send button. The user device can be a smartphone, tablet, or computer.

[0307] Server receives and analyzes the request

[0308] The server receives the request sent by the user as an HTTP request and analyzes its contents. The received text data is passed to a natural language processing (NLP) module. For example, the NLP module performs preprocessing such as tokenizing the text, removing stop words, and stemming. This makes it possible to extract important keywords and context. For example, the keywords "career path" and "worries" are identified.

[0309] Activating the Emotion Engine

[0310] The server passes the analyzed text data to an emotion engine, which analyzes the user's emotions. The emotion engine identifies emotions contained in the text and classifies them into emotion categories such as "anxiety," "excitement," and "anger." As a specific example, it identifies the emotion "anxiety" from the phrase "I'm worried."

[0311] Starting the generative AI and generating answers

[0312] The server activates the generative AI model, taking into account the analysis results of the emotion engine, to generate the optimal answer to the user's inquiry. As a specific example of a prompt sentence, "Please give me some advice on my career path," is entered, and the generative AI model generates specific options such as "join a new project" and "take training to improve my skills." An existing large-scale language model (LLM) is used as the generative AI model.

[0313] Formatting and returning answers

[0314] The server formats the generated answer and constructs a response to send back to the user. This response is formatted in a way that reflects the user's emotional state. For example, if the user is feeling "anxious," it uses language that makes them feel more reassured. A specific example of a formatted answer would be, "Your career path has the following options: 1. Join a new project within your department. 2. Take training to improve your skills. 3. Talk to your manager to clarify your specific role."

[0315] Display on user terminal

[0316] The user device receives the HTTP response and displays it on the screen. For example, it displays "Your career path has the following options..."

[0317] User Feedback and Resend

[0318] The user can enter additional questions or feedback about the answers provided and submit the request again. For example, the user can enter "I would like to know a more specific action plan" in the text box and press the submit button again.

[0319] Providing new insights

[0320] The server records the user's past requests and responses in a database and periodically analyzes them to generate new insights and suggestions. As a specific example, past data in the database is analyzed to extract the "latest information about project management." Based on the results of the periodic analysis, new insights and suggestions are generated and notified. The user's device receives notifications from the server and displays them on the screen. For example, a notification may appear saying, "We have the latest information on recent trends and methods for project management, which you previously consulted about."

[0321] The system allows users to receive truly personalized and highly accurate coaching, which significantly increases user satisfaction.

[0322] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0323] Step 1:

[0324] The user inputs the desired coaching information from the device and makes a request to send it. The input information is "I'm worried about my career path. Please tell me how I should proceed" and is entered into the text box on the device, and the user presses the send button. The input data is sent to the server in JSON format.

[0325] Step 2:

[0326] The server receives this request. The received data is processed as an HTTP request. The server first parses the input data and extracts text data. The extracted text data is then passed to a natural language processing (NLP) module. Specific operations include preprocessing such as tokenization, stop word removal, and even stemming. The input is raw text data from the user, and the output is preprocessed text data.

[0327] Step 3:

[0328] The server analyzes the preprocessed text data and extracts important keywords and contexts. For example, it identifies the keywords "career path" and "worries." The input is the preprocessed text data, and the output is a list of extracted keywords. This operation allows the server to understand the meaning of the input data and identify important related elements.

[0329] Step 4:

[0330] The server passes the extracted text data to an emotion engine, which analyzes the user's emotions. The emotion engine identifies emotions contained in the text and classifies them into emotion categories such as anxiety, excitement, and anger. For example, it identifies the emotion "anxiety" from the phrase "I'm worried." The input is a list of extracted keywords, and the output is a list of emotion categories.

[0331] Step 5:

[0332] The server takes into account the analysis results of the emotion engine and passes the input prompt to the generative AI model. The specific prompt sentence is "Please give me some advice on my career path." The generative AI model generates the optimal answer based on the prompt. For example, it outputs options such as "join a new project" or "take training to improve your skills." The input is the prompt sentence, and the output is the generated list of advice.

[0333] Step 6:

[0334] The server formats the generated answer, converting it into a reassuring expression that reflects the user's emotional state. For example, it might format it as, "Your career path has the following options: 1. Join a new project within your department. 2. Take training to improve your skills. 3. Talk to your manager to clarify your specific role." The input is a list of advice from the generative AI model, and the output is the formatted answer.

[0335] Step 7:

[0336] The server sends the formatted answer to the user's terminal as an HTTP response. The sent data is in JSON format and is constructed in a form suitable for the display format of the user's terminal. The input is the formatted answer, and the output is an HTTP response.

[0337] Step 8:

[0338] The user device receives the HTTP response and displays it on the screen. For example, it displays "Your career path has the following options..." The input is the HTTP response from the server, and the output is the screen display in a format that the user can view.

[0339] Step 9:

[0340] The user enters additional questions or feedback about the provided answers and makes a request again. For example, the user enters "I would like to know a more specific action plan" in the text box and presses the submit button again. The input data is again sent to the server in JSON format.

[0341] Step 10:

[0342] The server receives the new feedback and repeats the steps of preprocessing, analysis, sentiment analysis, use of the generative AI model, answer formatting, and sending. For example, it provides a specific action plan such as, "To participate in Project A, you first need the following skill set. You can acquire these skills by participating in Training Program B." The input is new feedback from the user, and the output is a regenerated specific action plan.

[0343] (Application example 2)

[0344] 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."

[0345] Conventional coaching systems struggle to provide appropriate advice and solutions to users' concerns. Furthermore, they fail to properly consider the user's emotional state, making it impossible to provide personalized support that satisfies the user. Furthermore, they often fail to provide relevant content, resulting in a lack of practical support for users in solving their problems.

[0346] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving the content of the consultation from the user, means for analyzing the content of the consultation using natural language processing technology, means for generating an answer to the consultation content using a generation AI based on the analyzed data, means for returning content related to the generated answer to the user, and means for receiving feedback from the user and performing further analysis and generation. This makes it possible to provide personalized and practical coaching advice and related content while taking the user's emotional state into consideration.

[0347] The "means for receiving consultation contents from the user" is an interface for transmitting consultation contents input by the user through the terminal to the server.

[0348] "Means of analysis using natural language processing technology" refers to technology that performs preprocessing such as tokenizing received text data, removing stop words, and stemming.

[0349] "Means of using generative AI to generate answers to inquiries" refers to technology that uses a generative AI model to generate optimal answers based on data analyzed using natural language processing technology.

[0350] The "means for returning content related to the generated answer to the user" is an interface for returning content such as videos, articles, exercises, etc. related to the generated answer to the user.

[0351] "Means for receiving feedback from users and re-analyzing and re-generating" refers to technology that re-analyzes the feedback provided by the user using natural language processing technology and a generative AI model, and re-generates the optimal answer.

[0352] "Means for recording the content of users' past consultations, periodically analyzing it, and providing new insights and suggestions" refers to a technology that stores users' past consultation history in a database, periodically analyzes it, and generates new suggestions.

[0353] "Means of referencing multiple data sources to generate optimal solutions and related content" refers to technology that refers to multiple information sources depending on the content of the consultation and generates optimal advice and related content.

[0354] This system receives inquiries from users, generates optimal answers using natural language processing and generative AI technologies, and provides them to users along with related content. This system is primarily composed of a user terminal, a server, a database, and an emotion engine.

[0355] First, we will explain input and transmission from the user terminal. The user inputs the content of their consultation through a smartphone app and sends it to the server. For example, they might input a question such as, "I've been feeling stressed lately and I don't know what to do." The input data is sent to the server as an HTTP request.

[0356] Next, we will explain the processing on the server. The server analyzes the received text data using natural language processing technology. This analysis includes preprocessing such as tokenization, stop word removal, and stemming. Natural language processing technologies used include spaCy and NLTK.

[0357] Important keywords are extracted from the analyzed data and passed to the emotion engine, which identifies the emotions contained in the text and classifies them into emotion categories such as "anxiety" or "stress." The emotion analysis engine used is IBM Watson Tone Analyzer.

[0358] Next, a generative AI model is used based on the analysis results to generate the optimal answer to the user's inquiry. OpenAI GPT-3 and other models are used as generative AI models. For example, if the user's inquiry is "Please tell me how to relieve stress," the generative AI model will generate an answer such as "Light exercise and meditation every day are effective for relieving stress."

[0359] The generated answer is then returned to the user along with related content (videos, articles, exercises, etc.) For example, the answer may include a link to a video or article that explains a specific relaxation technique, providing the user with the resources to take specific steps.

[0360] Furthermore, the system can receive user feedback and perform further analysis and generate answers. For example, if a user sends feedback such as "I would like to know a more specific action plan," the server will again use NLP and generative AI models to provide a more detailed action plan.

[0361] To illustrate, here are some example prompts:

[0362] "User Question: "I've been feeling stressed lately and I don't know what to do." Emotion: Anxiety, Stress Generate an answer."

[0363] This system can provide personalized and practical coaching advice and related content that takes into account the user's emotional state, thereby supporting users in solving their problems more efficiently.

[0364] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0365] Step 1:

[0366] User input: The user inputs and submits the content of their problem through the smartphone app. For example, they might type, "I've been feeling stressed lately and I don't know what to do." The input is formatted as an HTTP request and sent to the server.

[0367] Step 2:

[0368] Server reception: The server receives the HTTP request from the user and extracts the text data. The input at this stage is the text of the user's consultation, and the output is this text data itself.

[0369] Step 3:

[0370] Natural Language Processing (NLP): The server analyzes the received text data using natural language processing techniques. Specifically, preprocessing such as tokenization (dividing the text into words and phrases), stop word removal (removing meaningless common words), and stemming (converting words to their base forms) is performed. The input is raw text data, and the output is preprocessed text data.

[0371] Step 4:

[0372] Keyword extraction: The server extracts important keywords from the preprocessed text data. For example, it identifies the keywords "stress" and "relief methods." The input at this stage is the preprocessed text data, and the output is a list of important keywords.

[0373] Step 5:

[0374] Sentiment analysis: The server passes the extracted keywords to the emotion engine to analyze the user's emotions. The emotion engine identifies emotions contained in the text and classifies them into emotion categories such as "anxiety" or "stress." The input is a list of keywords, and the output is a list of emotion categories.

[0375] Step 6:

[0376] Answer generation: The server uses a generative AI model based on the results of sentiment analysis to generate the optimal answer to the user's inquiry. For example, it generates an answer such as "Daily light exercise and meditation are effective for relieving stress." The input is a list of keywords and a list of sentiment categories, and the output is the generated answer text.

[0377] Step 7:

[0378] Content recommendation: The server identifies content (videos, articles, exercises, etc.) related to the generated answer and constructs a response to serve to the user. The input is the answer text, and the output is a response containing the answer text and links to the related content.

[0379] Step 8:

[0380] Response transmission: The server transmits the constructed response to the user terminal as an HTTP response. The input is the response data, and the output is the transmission status to the user terminal.

[0381] Step 9:

[0382] User display: The user device analyzes the HTTP response received from the server and displays it on the screen. For example, it might say, "Light exercise and meditation every day are effective for relieving stress. Try practicing with this video as a reference." The input is the HTTP response data, and the output is the text displayed to the user and a link to related content.

[0383] 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.

[0384] 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.

[0385] 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.

[0386] [Second embodiment]

[0387] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0388] 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.

[0389] 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).

[0390] 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.

[0391] 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.

[0392] 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).

[0393] 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.

[0394] 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.

[0395] 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.

[0396] 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.

[0397] 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.

[0398] 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."

[0399] The system of the present invention is designed to provide highly accurate coaching using generative AI. This system is mainly composed of a user terminal, a server, and a database.

[0400] Overall system flow

[0401] Input and transmission from the user terminal

[0402] 1. The user inputs the details of the coaching they wish to receive from their device and makes a request to send it. Typically, the user enters the details of the consultation into the application's input field and presses the send button.

[0403] Server receives and analyzes the request

[0404] 2. The server receives the request from the user and analyzes its contents. Specifically, it preprocesses the input text using natural language processing technology and extracts important keywords and context. For example, if a request is entered such as "I'm worried about my career path," the server identifies the keywords "career path" and "worry" from the request.

[0405] Starting the generative AI and generating answers

[0406] 3. The server then activates the generation AI based on the analysis results to generate the optimal answer for the consultation. The generation AI references multiple data sources and extracts appropriate solutions and advice from them. For example, specific options such as "joining a new project" or "training to improve skills" are generated as "optimal advice regarding career paths."

[0407] Return of coaching content

[0408] 4. The server constructs a response to return the generated coaching content to the user. This response is formatted in a format that is easy for the user to understand and sent to the user's device as an HTTP response. The user's device receives this response and displays it on the screen. Specifically, it displays the message, "Your career path has the following options."

[0409] Processing Feedback

[0410] 5. The user can enter additional questions or feedback about the coaching content provided and submit the request again. For example, the user can enter feedback such as, "I would like to know a more specific action plan."

[0411] 6. The server receives the feedback and uses the generation AI to generate detailed coaching content. For example, a specific action plan such as "The following skill set is required to participate in the project" is provided.

[0412] Providing new insights

[0413] 7. The server records the user's past consultations and periodically analyzes them to generate new insights and suggestions. For example, it can analyze past consultation history and provide the latest information on project management.

[0414] Specific examples

[0415] For example, if a user enters "I'm having trouble communicating with my subordinates":

[0416] 1. The server receives this request and analyzes keywords such as "subordinate" and "communication."

[0417] 2. The generative AI refers to data on "effective communication methods with subordinates" and generates specific advice, such as "putting active listening into practice."

[0418] 3. If the user further provides feedback that they would like to know examples of specific situations, the server will launch the generation AI again and provide "specific examples of how to ask subordinates about the progress of a project."

[0419] In this way, the system of the present invention can provide highly accurate coaching tailored to the individual needs of the user and provide continuous support, allowing the user to receive more specific and useful advice and gain new insights and action plans.

[0420] The processing flow will be explained below.

[0421] Step 1:

[0422] The user enters their concerns or questions into the input field on the device and presses the send button. For example, they enter, "I'm worried about my career path. Please tell me how I should proceed," and then presses the send button.

[0423] Step 2:

[0424] The terminal sends the consultation details entered by the user to the server as an HTTP request.

[0425] Step 3:

[0426] The server receives the HTTP request and analyzes the request content. Specifically, the text is passed to a natural language processing (NLP) module for preprocessing such as tokenization, stop word removal, and stemming.

[0427] Step 4:

[0428] The server extracts important keywords and context from the analyzed text data. For example, it identifies the keywords "career path" and "worries."

[0429] Step 5:

[0430] The server selects and launches an appropriate generative AI model based on the extracted keywords.

[0431] Step 6:

[0432] The server uses generation AI to generate the optimal answer for the user's inquiry. Specifically, it references multiple data sources and generates specific options such as "joining a new project," "training to improve skills," and "consulting with a supervisor."

[0433] Step 7:

[0434] The server then formats the generated answers into an easy-to-read format, such as "Your career path includes the following options: 1. Join a new project within your department, 2. Take training to improve your skills, or 3. Talk to your manager to clarify your specific role."

[0435] Step 8:

[0436] The server sends the formatted answer to the user terminal as an HTTP response.

[0437] Step 9:

[0438] The device receives the HTTP response and displays it on the screen. For example, it might say, "Your career path has the following options: 1. Join a new project within your department. 2. Take training to improve your skills. 3. Talk to your manager to clarify your specific role."

[0439] Step 10:

[0440] The user enters a follow-up question or feedback on the answer provided, for example, "I'd like to know a more specific action plan," and hits the submit button again.

[0441] Step 11:

[0442] The device sends the new input to the server as an HTTP request.

[0443] Step 12:

[0444] The server receives the request again and performs additional analysis, especially generating more detailed information using generative AI to respond to user feedback.

[0445] Step 13:

[0446] The server then uses the generative AI to generate specific action plans and detailed advice, such as, "To participate in Project A, you first need the following skill set. You can acquire these skills by participating in Training Program B."

[0447] Step 14:

[0448] The server reformats the generated details and constructs a response to send back to the user.

[0449] Step 15:

[0450] The device receives the new response and displays it on the screen, for example, "To participate in Project A, you first need the following skill set. You can acquire these skills by participating in Training Program B."

[0451] Step 16:

[0452] The server records the user's past requests and responses in a database, analyzes them periodically, and generates new insights and suggestions.

[0453] Step 17:

[0454] The server generates new insights and suggestions based on the results of periodic analysis and notifies the user.

[0455] Step 18:

[0456] The device receives notifications from the server and displays them on the screen. For example, a notification might say, "We have the latest information on the latest trends and techniques for project management, which we previously discussed."

[0457] Example 1

[0458] 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."

[0459] Conventional coaching systems have struggled to provide quick and specific solutions to users' concerns. Furthermore, few systems offer ongoing support based on feedback, making it difficult for users to receive effective advice. Furthermore, because they are unable to provide new suggestions or insights based on past consultations, it is difficult to continuously support users' growth.

[0460] 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.

[0461] In this invention, the server includes means for receiving the consultation content from the user, means for analyzing the consultation content using natural language processing technology, means for generating an answer to the consultation content using a generation AI based on the analyzed data, means for returning the generated answer to the user, means for receiving feedback from the user and re-analyzing and generating an answer, and means for proposing specific options and action plans related to the consultation content. This makes it possible to provide the user with a quick and specific solution, and to provide continuous support based on feedback and new proposals based on past consultation content.

[0462] A "user" is an entity that uses the coaching system to input the details of a consultation and receives the generated advice and suggestions.

[0463] "Consultation content" refers to the problem or question that the user inputs to the coaching system and seeks to resolve.

[0464] "Natural language processing technology" is a technology that enables computers to understand, analyze, and generate human language, and includes text analysis and keyword extraction.

[0465] "Generative AI" is a general term for artificial intelligence models that generate optimal sentences or responses based on input prompts.

[0466] An "answer" is a solution or proposal that the generative AI generates based on the content of the consultation.

[0467] "Feedback" refers to a user entering more specific information or a follow-up question in response to a provided answer.

[0468] "Specific options and action plans" refer to specific action plans and options proposed by the generative AI that are directly linked to solving the user's problem.

[0469] "Sources" are multiple external data sources and knowledge bases that the generative AI references to generate answers.

[0470] This invention is a system that analyzes the content of a user's consultation and provides highly accurate coaching using a generative AI model. This system is mainly composed of a user terminal, a server, and a database.

[0471] Hardware and Software Configuration

[0472] User terminal

[0473] The user terminal consists of a mobile device or computer. The user uses this to input the content of the consultation and subsequent feedback. A web application or mobile application is installed on the user terminal, and the user accesses the system through this.

[0474] server

[0475] The server is responsible for receiving requests, analyzing them, and launching the generative AI. The server typically runs on a high-performance computing device or cloud service. It processes HTTP requests using a Python web framework (e.g., Flask or Django). Libraries such as NLTK and SpaCy are used for natural language processing. Generative AI models such as OpenAI's GPT-4 are used.

[0476] Database

[0477] The database records users' past consultation details and feedback. By using a relational database such as MySQL or PostgreSQL, data can be efficiently stored and managed.

[0478] System Operation

[0479] The user enters the content of their inquiry into the application's input field and presses the send button to send a request. For example, the user might enter a content such as "I'm worried about my career path."

[0480] The server receives this and analyzes the text using natural language processing techniques, such as NLTK and SpaCy, to extract important keywords and context. For example, it identifies keywords such as "career path" and "concerns."

[0481] The server then launches a generative AI to generate the optimal answer based on the analysis results. The generative AI uses OpenAI's GPT-4 and other technologies to generate solutions by referencing multiple sources of information. For example, it suggests specific options such as "joining a new project" or "training to improve skills."

[0482] The server creates the generated answer in JSON format and sends it to the user's device as an HTTP response. The user's device receives it and displays it on the screen. For example, it might say, "Your career path has the following options."

[0483] The user can enter additional questions or feedback about the coaching provided. For example, the user can enter, "I'd like to know a more specific action plan."

[0484] The server receives the feedback, analyzes it again, and generates a new AI. It then launches the AI ​​to propose a detailed action plan. For example, it generates specific advice such as, "The following skill set is required to participate in the project."

[0485] Example prompt sentences

[0486] "I'm struggling with my career path. Can you give me some concrete advice on how to get involved in new projects and improve my skills?"

[0487] "I'm having trouble communicating with my subordinates. Can you give me some specific examples for different situations?"

[0488] This invention allows users to obtain quick and specific solutions and receive continuous support based on feedback. Furthermore, by obtaining new suggestions and insights based on past consultations, it is possible to continuously support the user's growth.

[0489] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0490] Step 1:

[0491] The user enters the content of their consultation into the application's input field and presses the send button. The input content is constructed as text data. For example, the specific content of their consultation may be, "I'm worried about my career path." The output is the input text data.

[0492] Step 2:

[0493] The user terminal sends the entered text data to the server as an HTTP POST request. The input is the text data entered by the user, and the output is data in the form of an HTTP request. Specifically, in the case of a web application, the request is sent using the JavaScript fetch API.

[0494] Step 3:

[0495] The server receives an HTTP POST request sent from the user device. The input is the HTTP request from the user device, and the output is text data extracted from the request. Specifically, the request data is obtained using a web framework such as Flask or Django.

[0496] Step 4:

[0497] The server analyzes the received text data using natural language processing technology. The input is the text data extracted from the request, and the output is the analyzed keywords and context. Specifically, it uses Python's NLTK and SpaCy to tokenize the text and extract important keywords. For example, keywords such as "career path" and "concerns" are identified.

[0498] Step 5:

[0499] The server launches a generative AI model based on the analysis results. The input is the analyzed keywords and context, and the output is a prompt to be passed to the generative AI. Specifically, a Python script is used to call the generative AI (e.g., OpenAI's GPT-4 API) and construct the prompt. For example, a prompt is generated as "the best advice regarding your career path."

[0500] Step 6:

[0501] The generative AI generates the optimal answer based on the prompt text. The input is the prompt text sent from the server, and the output is the generated text answer. For example, it generates specific solutions such as "join a new project" or "training to improve skills."

[0502] Step 7:

[0503] The server constructs a response based on the generated text answer. The input is the text answer from the generation AI, and the output is the response data in JSON format. Specifically, the JSON response constructed using Flask or Django is sent as an HTTP response.

[0504] Step 8:

[0505] The user terminal receives the JSON response sent from the server and displays it on the screen. The input is the JSON-formatted response data from the server, and the output is text displayed on the user interface. For example, "Your career path has the following options."

[0506] Step 9:

[0507] The user inputs additional questions or feedback regarding the provided coaching content and makes another transmission request. The input is the user's feedback regarding the provided answer, and the output is the text data entered as feedback. For example, the user might input, "I would like to know a more specific action plan."

[0508] Step 10:

[0509] The user terminal transmits the text data input as feedback to the server again as an HTTP POST request. The input is the text data input as feedback, and the output is data in the HTTP request format.

[0510] Step 11:

[0511] The server receives the resent HTTP POST request and re-analyzes the text data. The input is the HTTP request from the user device, and the output is the re-analyzed keywords and context. Again, a natural language processing library is used to tokenize the text and extract important keywords.

[0512] Step 12:

[0513] The server then launches the generative AI model again based on the reanalyzed results. The input is the reanalyzed keywords and context, and the output is a new prompt to be passed to the generative AI. The generative AI is then called to construct a new prompt.

[0514] Step 13:

[0515] The generation AI generates a detailed answer based on the second prompt. The input is the second prompt sent from the server, and the output is a detailed answer in the generated text. For example, it generates specific advice such as, "The following skill set is required to participate in the project."

[0516] Step 14:

[0517] The server reconstructs a response based on the detailed answer. The input is the text answer from the generation AI, and the output is the response data in JSON format. The reconstructed JSON response is sent again as an HTTP response.

[0518] Step 15:

[0519] The user device again receives the JSON response sent from the server and displays it on the screen. The input is the JSON-formatted response data from the server, and the output is text displayed on the user interface. For example, it displays a specific message such as, "The following skill set is required to participate in the project."

[0520] (Application example 1)

[0521] 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."

[0522] Customer service in stores depends on the skills and experience of the staff, making it difficult to provide consistent quality service. New employees and staff who are unfamiliar with customer service often have trouble receiving appropriate advice quickly. This creates a need for improving the skills of individual staff and the service quality of the entire store.

[0523] 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.

[0524] In this invention, the server includes means for receiving the content of the consultation from the user, means for analyzing the content of the consultation using natural language processing technology, means for generating an answer to the consultation using a generation AI based on the analyzed data, means for returning the generated answer to the user, means for receiving feedback from the user and re-analyzing and generating, and means for using the analyzed and generated data to improve the skills of store staff, thereby enabling store staff to solve problems and improve their skills in real time.

[0525] The "means for receiving consultation contents from the user" is a function including an interface for transmitting consultation contents input by the user to the system.

[0526] "Means for analyzing consultation content using natural language processing technology" is a function for analyzing input consultation content using natural language processing technology and extracting important keywords and context.

[0527] "Means of using generation AI based on analyzed data to generate an answer to the inquiry content" is a function that uses generation AI to generate the optimal answer based on analyzed data.

[0528] "Means for returning the generated answer to the user" is a function that includes an interface for returning and displaying the answer generated by the generation AI to the user.

[0529] The "means for receiving feedback from the user and performing analysis and generation again" is a function for receiving feedback provided by the user and performing the analysis and generation process again based on that feedback.

[0530] "Means of using the analyzed and generated data to improve the skills of store staff" is a function that uses the data obtained through the analysis and generation process to improve the customer service skills of store staff and solve problems.

[0531] The following describes in detail an embodiment of the present invention, specifically, a specific method for introducing a coaching system for improving customer service skills into a brick-and-mortar store.

[0532] System Configuration

[0533] The coaching system of the present invention is comprised of the following main components:

[0534] 1. User device: A smartphone used by store staff.

[0535] 2. Server: A central computer system that receives and analyzes consultation content, runs the generative AI, and processes feedback.

[0536] 3. Generative AI model: An AI model that uses natural language processing technology to generate optimal advice based on the content of a consultation (e.g., Hugging Face's GPT-3).

[0537] Hardware and Software

[0538] 1. Hardware:

[0539] Smartphone: Used by store staff as a user device.

[0540] Server computer: Provides the computational resources for hosting the generative AI models and databases.

[0541] 2. Software:

[0542] Natural language processing (NLP) library: Used to analyze consultation content.

[0543] Generative AI model: Hugging Face's GPT-3 is used to generate specific advice for the consultation content.

[0544] Database management system: Records user consultations and feedback and analyzes them periodically.

[0545] Data processing and calculation

[0546] 1. User Device:

[0547] Store staff enter the details of the consultation via a smartphone app and send it to the server.

[0548] The app will have an intuitive interface and will be designed to allow staff to easily input their enquiries.

[0549] 2. Server:

[0550] Receiving: The server receives the input from the user terminal and decodes the text data.

[0551] Analysis: Natural language processing techniques are used to analyze text data and extract key keywords and context.

[0552] Generation: Based on the analysis results, a generative AI model is run to generate optimal advice for the consultation.

[0553] Return: The generated advice is returned to the user's device and displayed on the smartphone screen.

[0554] Examples and prompts

[0555] Examples:

[0556] 1. Store staff enter "How to respond when receiving a customer complaint" into a smartphone app.

[0557] 2. The server receives this request and extracts the keyword "complaint handling" through natural language processing.

[0558] 3. The generative AI model generates specific advice such as, "It's important to stay calm and resolve the problem quickly."

[0559] 4. This advice is sent back to the staff member's smartphone and displayed.

[0560] Example prompt sentence:

[0561] How do you handle customer complaints about products?

[0562] "Please suggest ways to improve communication with team members."

[0563] This system enables store staff to solve problems in real time and improve their skills, contributing to improving the service quality of the entire store.

[0564] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0565] Step 1:

[0566] The user inputs the content of the consultation through a smartphone app and presses the send button. This input includes a specific question, such as "Please tell me how to respond when a customer complains." The input text data is sent to the server in the latest format (e.g., JSON).

[0567] Step 2:

[0568] The server receives text data sent from the user terminal. To analyze the received data, it first formats the text data and checks its format. The input data is extracted as plain text and prepared for the next analysis step. The input for this step is the content of the user's inquiry, and the output is formatted text data.

[0569] Step 3:

[0570] The server analyzes the formatted text data using natural language processing techniques. Specifically, it uses an NLP library (e.g., spaCy or NLTK) to extract important keywords and context from the text data. The input to this analysis step is the formatted text data, and the output is the extracted keywords and context information.

[0571] Step 4:

[0572] The server launches a generative AI model (e.g., Hugging Face GPT-3) based on the analysis results to generate the optimal answer. The generation prompt includes extracted keywords and contextual information and is input to the generative AI. The generative AI model uses the input prompt to generate the optimal answer. The input to this step is the analysis results, and the output is the generated answer (advice).

[0573] Step 5:

[0574] The server constructs a response to send the generated answer back to the user. The response is sent in HTTP format to the user's smartphone, which receives the response and displays it on the screen. The input of this step is the generated answer, and the output is the response sent to the user's terminal.

[0575] Step 6:

[0576] If the user wishes to provide further feedback or ask a follow-up question based on the provided answer, such as a request like "Please provide a more specific action plan," the user's feedback is also sent to the server, where it is parsed and generated through a similar processing step. The input of this step is the user's feedback, and the output is a regenerated, detailed answer.

[0577] Step 7:

[0578] The server records the user's past consultation details and feedback in a database and periodically analyzes them. The database also stores time-series data, and generates "new insights and suggestions" based on the results of periodic analysis. The input for this step is the past consultation details and feedback, and the output is newly generated suggestions and insights.

[0579] Through these steps, store staff are continuously supported in improving their customer service skills and resolving problems.

[0580] 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.

[0581] The system of the present invention is designed to provide highly accurate coaching by combining generative AI and an emotion engine. This system is mainly composed of a user terminal, a server, a database, and an emotion engine.

[0582] Overall system flow

[0583] Input and transmission from the user terminal

[0584] 1. The user inputs the details of the coaching they would like to receive from their device and sends a request. For example, they might input, "I'm worried about my career path. Please tell me how I should proceed," and press the send button.

[0585] Server receives and analyzes the request

[0586] 2. The server receives the request from the user and analyzes its contents. Specifically, it passes the text to a natural language processing (NLP) module for preprocessing such as tokenization, stop word removal, and stemming.

[0587] 3. The server extracts important keywords and context from the analyzed text data. For example, it identifies the keywords "career path" and "concerns."

[0588] Activating the Emotion Engine

[0589] 4. The server passes the extracted text data to the emotion engine, which analyzes the user's emotions. The emotion engine identifies the emotions contained in the text and classifies them into emotion categories such as "anxiety," "excitement," and "anger."

[0590] Starting the generative AI and generating answers

[0591] 5. The server then activates the generative AI, taking into account the analysis results of the emotion engine, to generate the optimal answer for the user's inquiry. For example, as "career path advice," it generates specific options such as "joining a new project" or "training to improve skills."

[0592] 6. The server formats the generated answer and constructs a response to send back to the user. This response is constructed in a format that reflects the user's emotional state. For example, if the user is feeling "anxious," it uses expressions that make the user feel more reassured.

[0593] Return of coaching content

[0594] 7. The server sends the formatted answer to the user terminal as an HTTP response.

[0595] 8. The user device receives the HTTP response and displays it on the screen. For example, it might say, "Your career path has the following options: 1. Join a new project within your department. 2. Take training to improve your skills. 3. Talk to your manager to clarify your specific role."

[0596] Processing Feedback

[0597] 9. The user enters additional questions or feedback about the provided answer and submits the request again. For example, they enter "I'd like to know a more specific action plan" and press the submit button again.

[0598] 10. The server receives the feedback and uses the generative AI and emotion engine to generate detailed coaching content. For example, it provides a specific action plan such as, "To participate in Project A, you first need the following skill set. You can acquire these skills by participating in Training Program B."

[0599] Providing new insights

[0600] 11. The server records the user's past requests and responses in a database and periodically analyzes them to generate new insights and suggestions. For example, it can analyze past consultation history and provide the latest information on project management.

[0601] 12. The server generates new insights and suggestions based on the results of periodic analysis and notifies the user.

[0602] 13. The user device receives the notification from the server and displays it on the screen. For example, a notification may appear saying, "We have the latest information on the latest trends and techniques for project management, which we previously discussed."

[0603] Specific examples

[0604] For example, if a user enters "I'm having trouble communicating with my subordinates":

[0605] 1. The server receives this request and analyzes keywords such as "subordinate" and "communication."

[0606] 2. The emotion engine identifies the emotion of "being troubled."

[0607] 3. The generative AI references data on "effective communication methods with subordinates" and generates specific solutions. For example, it generates advice such as "Make an effort to actively listen."

[0608] 4. The server then takes into account the user's emotional state and formats the response in a reassuring way, for example, by displaying a message such as, "To solve your problem, let's start by actively listening."

[0609] This allows the system of the present invention to provide personalized, highly accurate coaching that takes into account the user's emotions, and to provide continuous support until the user is satisfied.

[0610] The processing flow will be explained below.

[0611] Step 1:

[0612] The user enters their concerns or questions into the input field on the device and presses the send button. For example, they enter, "I'm worried about my career path. Please tell me how I should proceed," and then presses the send button.

[0613] Step 2:

[0614] The terminal sends the consultation details entered by the user to the server as an HTTP request.

[0615] Step 3:

[0616] The server receives the HTTP request and analyzes the request content. Specifically, the text is passed to a natural language processing (NLP) module for preprocessing such as tokenization, stop word removal, and stemming.

[0617] Step 4:

[0618] The server extracts important keywords and context from the analyzed text data. For example, it identifies the keywords "career path" and "worries."

[0619] Step 5:

[0620] The server passes the extracted keywords to an emotion engine to analyze the user's emotions, for example, detecting whether the text contains the word "anxiety."

[0621] Step 6:

[0622] The emotion engine analyzes the text and classifies the user's emotional state, for example into emotion categories such as "anxiety," "excitement," and "anger."

[0623] Step 7:

[0624] The server optimizes the AI's response based on the user's emotional state. For example, if the user is feeling anxious, it will select reassuring language.

[0625] Step 8:

[0626] The server activates the appropriate generative AI model and generates the optimal answer to the user's inquiry, taking into account the results of the emotion engine. For example, it generates "specific advice on career paths" such as "joining a new project" or "training to improve skills."

[0627] Step 9:

[0628] The server formats the generated answers and summarizes them in an easy-to-read format. Reassuring language is added to reflect the emotional state. For example, "Your career path includes the following options: 1. Join a new project within your department. 2. Take training to improve your skills. 3. Talk to your manager to clarify your specific role. Rest assured, you'll see results soon."

[0629] Step 10:

[0630] The server sends the formatted answer to the user terminal as an HTTP response.

[0631] Step 11:

[0632] The device receives the HTTP response and displays it on the screen. For example, it might say, "Your career path has the following options: 1. Join a new project within your department. 2. Take training to improve your skills. 3. Talk to your manager to clarify your specific role. Don't worry, you'll see positive results soon."

[0633] Step 12:

[0634] The user can enter additional questions or feedback about the answers provided and press the submit button again. For example, they can enter "I'd like to know a more specific action plan" and press the submit button again.

[0635] Step 13:

[0636] The device sends the new input to the server as an HTTP request.

[0637] Step 14:

[0638] The server receives the request again and analyzes the new input. Specifically, it again preprocesses it using natural language processing technology to extract additional important keywords.

[0639] Step 15:

[0640] The server again uses the emotion engine to confirm the user's emotional state, for example detecting an increase in the emotion of "anxiety" based on additional input information.

[0641] Step 16:

[0642] The server passes the results of the analysis and emotion engine to the generation AI, which then generates an appropriate solution. For example, it generates a specific action plan such as, "To participate in Project A, you first need the following skill set. You can acquire these skills by participating in Training Program B."

[0643] Step 17:

[0644] The server reformats the generated details and constructs a response to send back to the user.

[0645] Step 18:

[0646] The device receives the new response and displays it on the screen, for example, "To participate in Project A, you first need the following skill set. You can acquire these skills by participating in Training Program B."

[0647] Step 19:

[0648] The server records the user's past requests and responses in a database, analyzes them periodically, and generates new insights and suggestions.

[0649] Step 20:

[0650] The server generates new insights and suggestions based on the results of periodic analysis and notifies the user.

[0651] Step 21:

[0652] The device receives notifications from the server and displays them on the screen. For example, a notification might say, "We have the latest information on the latest trends and techniques for project management, which we previously discussed."

[0653] Example 2

[0654] 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."

[0655] Conventional coaching systems have had the problem of being unable to generate personalized answers that take the user's emotions into account, which means they are unable to sufficiently increase user satisfaction. It has also been difficult to effectively utilize user feedback and provide continuous, highly accurate coaching.

[0656] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0657] In this invention, the server includes means for receiving consultation content from a user, means for analyzing the consultation content using natural language processing technology, means for identifying and classifying emotions based on the analyzed data, means for generating an answer to the consultation content using a generative AI model taking into account the emotion analysis results, means for formatting the generated answer in accordance with the user's emotional state and returning it to the user, and means for receiving feedback from the user and re-analyzing and generating an answer. This makes it possible to provide the user with personalized answers according to their emotions and provide continuous, highly accurate coaching.

[0658] The "means for receiving consultation content" is an interface for electronically collecting input information from users and processing it within the system.

[0659] "Natural language processing technology" is a technology that allows computers to understand and analyze human language, and includes processes such as tokenization and removal of stop words.

[0660] "Means for identifying and classifying emotions" refers to technology for detecting user emotions (e.g., anxiety, excitement, anger, etc.) from text data and classifying them into categories.

[0661] A "generative AI model" is an artificial intelligence technique for generating appropriate responses in natural language based on input prompts.

[0662] "Formulating" refers to a technology that converts the answers output by the generative AI model into the optimal format based on the user's emotions and situation.

[0663] The "means for receiving feedback" is an interface for collecting information and opinions re-entered from the user and using them to analyze the next step and generate answers.

[0664] "Multiple data sources" is a general term for various databases and information sources that are referenced to respond to the user's inquiry.

[0665] "Means of providing new insights and suggestions" refers to technology that analyzes past data, generates new knowledge and action plans, and proposes them to users.

[0666] The system of the present invention is designed to combine a generative AI model and an emotion engine to provide highly accurate coaching. This system is mainly composed of a user terminal, a server, a database, and an emotion engine. Specifically, it includes the following functions and processes:

[0667] Input and transmission from the user terminal

[0668] The user inputs the details of the coaching they would like to receive from their device and sends a request. Specifically, the user interface includes a text box where they can type, "I'm having trouble deciding on my career path. Can you tell me how I should proceed?" and then press the send button. The user device can be a smartphone, tablet, or computer.

[0669] Server receives and analyzes the request

[0670] The server receives the request sent by the user as an HTTP request and analyzes its contents. The received text data is passed to a natural language processing (NLP) module. For example, the NLP module performs preprocessing such as tokenizing the text, removing stop words, and stemming. This makes it possible to extract important keywords and context. For example, the keywords "career path" and "worries" are identified.

[0671] Activating the Emotion Engine

[0672] The server passes the analyzed text data to an emotion engine, which analyzes the user's emotions. The emotion engine identifies emotions contained in the text and classifies them into emotion categories such as "anxiety," "excitement," and "anger." As a specific example, it identifies the emotion "anxiety" from the phrase "I'm worried."

[0673] Starting the generative AI and generating answers

[0674] The server activates the generative AI model, taking into account the analysis results of the emotion engine, to generate the optimal answer to the user's inquiry. As a specific example of a prompt sentence, "Please give me some advice on my career path," is entered, and the generative AI model generates specific options such as "join a new project" and "take training to improve my skills." An existing large-scale language model (LLM) is used as the generative AI model.

[0675] Formatting and returning answers

[0676] The server formats the generated answer and constructs a response to send back to the user. This response is formatted in a way that reflects the user's emotional state. For example, if the user is feeling "anxious," it uses language that makes them feel more reassured. A specific example of a formatted answer would be, "Your career path has the following options: 1. Join a new project within your department. 2. Take training to improve your skills. 3. Talk to your manager to clarify your specific role."

[0677] Display on user terminal

[0678] The user device receives the HTTP response and displays it on the screen. For example, it displays "Your career path has the following options..."

[0679] User Feedback and Resend

[0680] The user can enter additional questions or feedback about the answers provided and submit the request again. For example, the user can enter "I would like to know a more specific action plan" in the text box and press the submit button again.

[0681] Providing new insights

[0682] The server records the user's past requests and responses in a database and periodically analyzes them to generate new insights and suggestions. As a specific example, past data in the database is analyzed to extract the "latest information about project management." Based on the results of the periodic analysis, new insights and suggestions are generated and notified. The user's device receives notifications from the server and displays them on the screen. For example, a notification may appear saying, "We have the latest information on recent trends and methods for project management, which you previously consulted about."

[0683] The system allows users to receive truly personalized and highly accurate coaching, which significantly increases user satisfaction.

[0684] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0685] Step 1:

[0686] The user inputs the desired coaching information from the device and makes a request to send it. The input information is "I'm worried about my career path. Please tell me how I should proceed" and is entered into the text box on the device, and the user presses the send button. The input data is sent to the server in JSON format.

[0687] Step 2:

[0688] The server receives this request. The received data is processed as an HTTP request. The server first parses the input data and extracts text data. The extracted text data is then passed to a natural language processing (NLP) module. Specific operations include preprocessing such as tokenization, stop word removal, and even stemming. The input is raw text data from the user, and the output is preprocessed text data.

[0689] Step 3:

[0690] The server analyzes the preprocessed text data and extracts important keywords and contexts. For example, it identifies the keywords "career path" and "worries." The input is the preprocessed text data, and the output is a list of extracted keywords. This operation allows the server to understand the meaning of the input data and identify important related elements.

[0691] Step 4:

[0692] The server passes the extracted text data to an emotion engine, which analyzes the user's emotions. The emotion engine identifies emotions contained in the text and classifies them into emotion categories such as anxiety, excitement, and anger. For example, it identifies the emotion "anxiety" from the phrase "I'm worried." The input is a list of extracted keywords, and the output is a list of emotion categories.

[0693] Step 5:

[0694] The server takes into account the analysis results of the emotion engine and passes the input prompt to the generative AI model. The specific prompt sentence is "Please give me some advice on my career path." The generative AI model generates the optimal answer based on the prompt. For example, it outputs options such as "join a new project" or "take training to improve your skills." The input is the prompt sentence, and the output is the generated list of advice.

[0695] Step 6:

[0696] The server formats the generated answer, converting it into a reassuring expression that reflects the user's emotional state. For example, it might format it as, "Your career path has the following options: 1. Join a new project within your department. 2. Take training to improve your skills. 3. Talk to your manager to clarify your specific role." The input is a list of advice from the generative AI model, and the output is the formatted answer.

[0697] Step 7:

[0698] The server sends the formatted answer to the user's terminal as an HTTP response. The sent data is in JSON format and is constructed in a form suitable for the display format of the user's terminal. The input is the formatted answer, and the output is an HTTP response.

[0699] Step 8:

[0700] The user device receives the HTTP response and displays it on the screen. For example, it displays "Your career path has the following options..." The input is the HTTP response from the server, and the output is the screen display in a format that the user can view.

[0701] Step 9:

[0702] The user enters additional questions or feedback about the provided answers and makes a request again. For example, the user enters "I would like to know a more specific action plan" in the text box and presses the submit button again. The input data is again sent to the server in JSON format.

[0703] Step 10:

[0704] The server receives the new feedback and repeats the steps of preprocessing, analysis, sentiment analysis, use of the generative AI model, answer formatting, and sending. For example, it provides a specific action plan such as, "To participate in Project A, you first need the following skill set. You can acquire these skills by participating in Training Program B." The input is new feedback from the user, and the output is a regenerated specific action plan.

[0705] (Application example 2)

[0706] 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."

[0707] Conventional coaching systems struggle to provide appropriate advice and solutions to users' concerns. Furthermore, they fail to properly consider the user's emotional state, making it impossible to provide personalized support that satisfies the user. Furthermore, they often fail to provide relevant content, resulting in a lack of practical support for users in solving their problems.

[0708] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving the content of the consultation from the user, means for analyzing the content of the consultation using natural language processing technology, means for generating an answer to the consultation content using a generation AI based on the analyzed data, means for returning content related to the generated answer to the user, and means for receiving feedback from the user and performing further analysis and generation. This makes it possible to provide personalized and practical coaching advice and related content while taking the user's emotional state into consideration.

[0709] The "means for receiving consultation contents from the user" is an interface for transmitting consultation contents input by the user through the terminal to the server.

[0710] "Means of analysis using natural language processing technology" refers to technology that performs preprocessing such as tokenizing received text data, removing stop words, and stemming.

[0711] "Means of using generative AI to generate answers to inquiries" refers to technology that uses a generative AI model to generate optimal answers based on data analyzed using natural language processing technology.

[0712] The "means for returning content related to the generated answer to the user" is an interface for returning content such as videos, articles, exercises, etc. related to the generated answer to the user.

[0713] "Means for receiving feedback from users and re-analyzing and re-generating" refers to technology that re-analyzes the feedback provided by the user using natural language processing technology and a generative AI model, and re-generates the optimal answer.

[0714] "Means for recording the content of users' past consultations, periodically analyzing it, and providing new insights and suggestions" refers to a technology that stores users' past consultation history in a database, periodically analyzes it, and generates new suggestions.

[0715] "Means of referencing multiple data sources to generate optimal solutions and related content" refers to technology that refers to multiple information sources depending on the content of the consultation and generates optimal advice and related content.

[0716] This system receives inquiries from users, generates optimal answers using natural language processing and generative AI technologies, and provides them to users along with related content. This system is primarily composed of a user terminal, a server, a database, and an emotion engine.

[0717] First, we will explain input and transmission from the user terminal. The user inputs the content of their consultation through a smartphone app and sends it to the server. For example, they might input a question such as, "I've been feeling stressed lately and I don't know what to do." The input data is sent to the server as an HTTP request.

[0718] Next, we will explain the processing on the server. The server analyzes the received text data using natural language processing technology. This analysis includes preprocessing such as tokenization, stop word removal, and stemming. Natural language processing technologies used include spaCy and NLTK.

[0719] Important keywords are extracted from the analyzed data and passed to the emotion engine, which identifies the emotions contained in the text and classifies them into emotion categories such as "anxiety" or "stress." The emotion analysis engine used is IBM Watson Tone Analyzer.

[0720] Next, a generative AI model is used based on the analysis results to generate the optimal answer to the user's inquiry. OpenAI GPT-3 and other models are used as generative AI models. For example, if the user's inquiry is "Please tell me how to relieve stress," the generative AI model will generate an answer such as "Light exercise and meditation every day are effective for relieving stress."

[0721] The generated answer is then returned to the user along with related content (videos, articles, exercises, etc.) For example, the answer may include a link to a video or article that explains a specific relaxation technique, providing the user with the resources to take specific steps.

[0722] Furthermore, the system can receive user feedback and perform further analysis and generate answers. For example, if a user sends feedback such as "I would like to know a more specific action plan," the server will again use NLP and generative AI models to provide a more detailed action plan.

[0723] To illustrate, here are some example prompts:

[0724] "User Question: "I've been feeling stressed lately and I don't know what to do." Emotion: Anxiety, Stress Generate an answer."

[0725] This system can provide personalized and practical coaching advice and related content that takes into account the user's emotional state, thereby supporting users in solving their problems more efficiently.

[0726] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0727] Step 1:

[0728] User input: The user inputs and submits the content of their problem through the smartphone app. For example, they might type, "I've been feeling stressed lately and I don't know what to do." The input is formatted as an HTTP request and sent to the server.

[0729] Step 2:

[0730] Server reception: The server receives the HTTP request from the user and extracts the text data. The input at this stage is the text of the user's consultation, and the output is this text data itself.

[0731] Step 3:

[0732] Natural Language Processing (NLP): The server analyzes the received text data using natural language processing techniques. Specifically, preprocessing such as tokenization (dividing the text into words and phrases), stop word removal (removing meaningless common words), and stemming (converting words to their base forms) is performed. The input is raw text data, and the output is preprocessed text data.

[0733] Step 4:

[0734] Keyword extraction: The server extracts important keywords from the preprocessed text data. For example, it identifies the keywords "stress" and "relief methods." The input at this stage is the preprocessed text data, and the output is a list of important keywords.

[0735] Step 5:

[0736] Sentiment analysis: The server passes the extracted keywords to the emotion engine to analyze the user's emotions. The emotion engine identifies emotions contained in the text and classifies them into emotion categories such as "anxiety" or "stress." The input is a list of keywords, and the output is a list of emotion categories.

[0737] Step 6:

[0738] Answer generation: The server uses a generative AI model based on the results of sentiment analysis to generate the optimal answer to the user's inquiry. For example, it generates an answer such as "Daily light exercise and meditation are effective for relieving stress." The input is a list of keywords and a list of sentiment categories, and the output is the generated answer text.

[0739] Step 7:

[0740] Content recommendation: The server identifies content (videos, articles, exercises, etc.) related to the generated answer and constructs a response to serve to the user. The input is the answer text, and the output is a response containing the answer text and links to the related content.

[0741] Step 8:

[0742] Response transmission: The server transmits the constructed response to the user terminal as an HTTP response. The input is the response data, and the output is the transmission status to the user terminal.

[0743] Step 9:

[0744] User display: The user device analyzes the HTTP response received from the server and displays it on the screen. For example, it might say, "Light exercise and meditation every day are effective for relieving stress. Try practicing with this video as a reference." The input is the HTTP response data, and the output is the text displayed to the user and a link to related content.

[0745] 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.

[0746] 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.

[0747] 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.

[0748] [Third embodiment]

[0749] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0750] 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.

[0751] 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).

[0752] 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.

[0753] 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.

[0754] 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).

[0755] 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.

[0756] 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.

[0757] 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.

[0758] 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.

[0759] 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.

[0760] 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."

[0761] The system of the present invention is designed to provide highly accurate coaching using generative AI. This system is mainly composed of a user terminal, a server, and a database.

[0762] Overall system flow

[0763] Input and transmission from the user terminal

[0764] 1. The user inputs the details of the coaching they wish to receive from their device and makes a request to send it. Typically, the user enters the details of the consultation into the application's input field and presses the send button.

[0765] Server receives and analyzes the request

[0766] 2. The server receives the request from the user and analyzes its contents. Specifically, it preprocesses the input text using natural language processing technology and extracts important keywords and context. For example, if a request is entered such as "I'm worried about my career path," the server identifies the keywords "career path" and "worry" from the request.

[0767] Starting the generative AI and generating answers

[0768] 3. The server then activates the generation AI based on the analysis results to generate the optimal answer for the consultation. The generation AI references multiple data sources and extracts appropriate solutions and advice from them. For example, specific options such as "joining a new project" or "training to improve skills" are generated as "optimal advice regarding career paths."

[0769] Return of coaching content

[0770] 4. The server constructs a response to return the generated coaching content to the user. This response is formatted in a format that is easy for the user to understand and sent to the user's device as an HTTP response. The user's device receives this response and displays it on the screen. Specifically, it displays the message, "Your career path has the following options."

[0771] Processing Feedback

[0772] 5. The user can enter additional questions or feedback about the coaching content provided and submit the request again. For example, the user can enter feedback such as, "I would like to know a more specific action plan."

[0773] 6. The server receives the feedback and uses the generation AI to generate detailed coaching content. For example, a specific action plan such as "The following skill set is required to participate in the project" is provided.

[0774] Providing new insights

[0775] 7. The server records the user's past consultations and periodically analyzes them to generate new insights and suggestions. For example, it can analyze past consultation history and provide the latest information on project management.

[0776] Specific examples

[0777] For example, if a user enters "I'm having trouble communicating with my subordinates":

[0778] 1. The server receives this request and analyzes keywords such as "subordinate" and "communication."

[0779] 2. The generative AI refers to data on "effective communication methods with subordinates" and generates specific advice, such as "putting active listening into practice."

[0780] 3. If the user further provides feedback that they would like to know examples of specific situations, the server will launch the generation AI again and provide "specific examples of how to ask subordinates about the progress of a project."

[0781] In this way, the system of the present invention can provide highly accurate coaching tailored to the individual needs of the user and provide continuous support, allowing the user to receive more specific and useful advice and gain new insights and action plans.

[0782] The processing flow will be explained below.

[0783] Step 1:

[0784] The user enters their concerns or questions into the input field on the device and presses the send button. For example, they enter, "I'm worried about my career path. Please tell me how I should proceed," and then presses the send button.

[0785] Step 2:

[0786] The terminal sends the consultation details entered by the user to the server as an HTTP request.

[0787] Step 3:

[0788] The server receives the HTTP request and analyzes the request content. Specifically, the text is passed to a natural language processing (NLP) module for preprocessing such as tokenization, stop word removal, and stemming.

[0789] Step 4:

[0790] The server extracts important keywords and context from the analyzed text data. For example, it identifies the keywords "career path" and "worries."

[0791] Step 5:

[0792] The server selects and launches an appropriate generative AI model based on the extracted keywords.

[0793] Step 6:

[0794] The server uses generation AI to generate the optimal answer for the user's inquiry. Specifically, it references multiple data sources and generates specific options such as "joining a new project," "training to improve skills," and "consulting with a supervisor."

[0795] Step 7:

[0796] The server then formats the generated answers into an easy-to-read format, such as "Your career path includes the following options: 1. Join a new project within your department, 2. Take training to improve your skills, or 3. Talk to your manager to clarify your specific role."

[0797] Step 8:

[0798] The server sends the formatted answer to the user terminal as an HTTP response.

[0799] Step 9:

[0800] The device receives the HTTP response and displays it on the screen. For example, it might say, "Your career path has the following options: 1. Join a new project within your department. 2. Take training to improve your skills. 3. Talk to your manager to clarify your specific role."

[0801] Step 10:

[0802] The user enters a follow-up question or feedback on the answer provided, for example, "I'd like to know a more specific action plan," and hits the submit button again.

[0803] Step 11:

[0804] The device sends the new input to the server as an HTTP request.

[0805] Step 12:

[0806] The server receives the request again and performs additional analysis, especially generating more detailed information using generative AI to respond to user feedback.

[0807] Step 13:

[0808] The server then uses the generative AI to generate specific action plans and detailed advice, such as, "To participate in Project A, you first need the following skill set. You can acquire these skills by participating in Training Program B."

[0809] Step 14:

[0810] The server reformats the generated details and constructs a response to send back to the user.

[0811] Step 15:

[0812] The device receives the new response and displays it on the screen, for example, "To participate in Project A, you first need the following skill set. You can acquire these skills by participating in Training Program B."

[0813] Step 16:

[0814] The server records the user's past requests and responses in a database, analyzes them periodically, and generates new insights and suggestions.

[0815] Step 17:

[0816] The server generates new insights and suggestions based on the results of periodic analysis and notifies the user.

[0817] Step 18:

[0818] The device receives notifications from the server and displays them on the screen. For example, a notification might say, "We have the latest information on the latest trends and techniques for project management, which we previously discussed."

[0819] Example 1

[0820] 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."

[0821] Conventional coaching systems have struggled to provide quick and specific solutions to users' concerns. Furthermore, few systems offer ongoing support based on feedback, making it difficult for users to receive effective advice. Furthermore, because they are unable to provide new suggestions or insights based on past consultations, it is difficult to continuously support users' growth.

[0822] 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.

[0823] In this invention, the server includes means for receiving the consultation content from the user, means for analyzing the consultation content using natural language processing technology, means for generating an answer to the consultation content using a generation AI based on the analyzed data, means for returning the generated answer to the user, means for receiving feedback from the user and re-analyzing and generating an answer, and means for proposing specific options and action plans related to the consultation content. This makes it possible to provide the user with a quick and specific solution, and to provide continuous support based on feedback and new proposals based on past consultation content.

[0824] A "user" is an entity that uses the coaching system to input the details of a consultation and receives the generated advice and suggestions.

[0825] "Consultation content" refers to the problem or question that the user inputs to the coaching system and seeks to resolve.

[0826] "Natural language processing technology" is a technology that enables computers to understand, analyze, and generate human language, and includes text analysis and keyword extraction.

[0827] "Generative AI" is a general term for artificial intelligence models that generate optimal sentences or responses based on input prompts.

[0828] An "answer" is a solution or proposal that the generative AI generates based on the content of the consultation.

[0829] "Feedback" refers to a user entering more specific information or a follow-up question in response to a provided answer.

[0830] "Specific options and action plans" refer to specific action plans and options proposed by the generative AI that are directly linked to solving the user's problem.

[0831] "Sources" are multiple external data sources and knowledge bases that the generative AI references to generate answers.

[0832] This invention is a system that analyzes the content of a user's consultation and provides highly accurate coaching using a generative AI model. This system is mainly composed of a user terminal, a server, and a database.

[0833] Hardware and Software Configuration

[0834] User terminal

[0835] The user terminal consists of a mobile device or computer. The user uses this to input the content of the consultation and subsequent feedback. A web application or mobile application is installed on the user terminal, and the user accesses the system through this.

[0836] server

[0837] The server is responsible for receiving requests, analyzing them, and launching the generative AI. The server typically runs on a high-performance computing device or cloud service. It processes HTTP requests using a Python web framework (e.g., Flask or Django). Libraries such as NLTK and SpaCy are used for natural language processing. Generative AI models such as OpenAI's GPT-4 are used.

[0838] Database

[0839] The database records users' past consultation details and feedback. By using a relational database such as MySQL or PostgreSQL, data can be efficiently stored and managed.

[0840] System Operation

[0841] The user enters the content of their inquiry into the application's input field and presses the send button to send a request. For example, the user might enter a content such as "I'm worried about my career path."

[0842] The server receives this and analyzes the text using natural language processing techniques, such as NLTK and SpaCy, to extract important keywords and context. For example, it identifies keywords such as "career path" and "concerns."

[0843] The server then launches a generative AI to generate the optimal answer based on the analysis results. The generative AI uses OpenAI's GPT-4 and other technologies to generate solutions by referencing multiple sources of information. For example, it suggests specific options such as "joining a new project" or "training to improve skills."

[0844] The server creates the generated answer in JSON format and sends it to the user's device as an HTTP response. The user's device receives it and displays it on the screen. For example, it might say, "Your career path has the following options."

[0845] The user can enter additional questions or feedback about the coaching provided. For example, the user can enter, "I'd like to know a more specific action plan."

[0846] The server receives the feedback, analyzes it again, and generates a new AI. It then launches the AI ​​to propose a detailed action plan. For example, it generates specific advice such as, "The following skill set is required to participate in the project."

[0847] Example prompt sentences

[0848] "I'm struggling with my career path. Can you give me some concrete advice on how to get involved in new projects and improve my skills?"

[0849] "I'm having trouble communicating with my subordinates. Can you give me some specific examples for different situations?"

[0850] This invention allows users to obtain quick and specific solutions and receive continuous support based on feedback. Furthermore, by obtaining new suggestions and insights based on past consultations, it is possible to continuously support the user's growth.

[0851] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0852] Step 1:

[0853] The user enters the content of their consultation into the application's input field and presses the send button. The input content is constructed as text data. For example, the specific content of their consultation may be, "I'm worried about my career path." The output is the input text data.

[0854] Step 2:

[0855] The user terminal sends the entered text data to the server as an HTTP POST request. The input is the text data entered by the user, and the output is data in the form of an HTTP request. Specifically, in the case of a web application, the request is sent using the JavaScript fetch API.

[0856] Step 3:

[0857] The server receives an HTTP POST request sent from the user device. The input is the HTTP request from the user device, and the output is text data extracted from the request. Specifically, the request data is obtained using a web framework such as Flask or Django.

[0858] Step 4:

[0859] The server analyzes the received text data using natural language processing technology. The input is the text data extracted from the request, and the output is the analyzed keywords and context. Specifically, it uses Python's NLTK and SpaCy to tokenize the text and extract important keywords. For example, keywords such as "career path" and "concerns" are identified.

[0860] Step 5:

[0861] The server launches a generative AI model based on the analysis results. The input is the analyzed keywords and context, and the output is a prompt to be passed to the generative AI. Specifically, a Python script is used to call the generative AI (e.g., OpenAI's GPT-4 API) and construct the prompt. For example, a prompt is generated as "the best advice regarding your career path."

[0862] Step 6:

[0863] The generative AI generates the optimal answer based on the prompt text. The input is the prompt text sent from the server, and the output is the generated text answer. For example, it generates specific solutions such as "join a new project" or "training to improve skills."

[0864] Step 7:

[0865] The server constructs a response based on the generated text answer. The input is the text answer from the generation AI, and the output is the response data in JSON format. Specifically, the JSON response constructed using Flask or Django is sent as an HTTP response.

[0866] Step 8:

[0867] The user terminal receives the JSON response sent from the server and displays it on the screen. The input is the JSON-formatted response data from the server, and the output is text displayed on the user interface. For example, "Your career path has the following options."

[0868] Step 9:

[0869] The user inputs additional questions or feedback regarding the provided coaching content and makes another transmission request. The input is the user's feedback regarding the provided answer, and the output is the text data entered as feedback. For example, the user might input, "I would like to know a more specific action plan."

[0870] Step 10:

[0871] The user terminal transmits the text data input as feedback to the server again as an HTTP POST request. The input is the text data input as feedback, and the output is data in the HTTP request format.

[0872] Step 11:

[0873] The server receives the resent HTTP POST request and re-analyzes the text data. The input is the HTTP request from the user device, and the output is the re-analyzed keywords and context. Again, a natural language processing library is used to tokenize the text and extract important keywords.

[0874] Step 12:

[0875] The server then launches the generative AI model again based on the reanalyzed results. The input is the reanalyzed keywords and context, and the output is a new prompt to be passed to the generative AI. The generative AI is then called to construct a new prompt.

[0876] Step 13:

[0877] The generation AI generates a detailed answer based on the second prompt. The input is the second prompt sent from the server, and the output is a detailed answer in the generated text. For example, it generates specific advice such as, "The following skill set is required to participate in the project."

[0878] Step 14:

[0879] The server reconstructs a response based on the detailed answer. The input is the text answer from the generation AI, and the output is the response data in JSON format. The reconstructed JSON response is sent again as an HTTP response.

[0880] Step 15:

[0881] The user device again receives the JSON response sent from the server and displays it on the screen. The input is the JSON-formatted response data from the server, and the output is text displayed on the user interface. For example, it displays a specific message such as, "The following skill set is required to participate in the project."

[0882] (Application example 1)

[0883] 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."

[0884] Customer service in stores depends on the skills and experience of the staff, making it difficult to provide consistent quality service. New employees and staff who are unfamiliar with customer service often have trouble receiving appropriate advice quickly. This creates a need for improving the skills of individual staff and the service quality of the entire store.

[0885] 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.

[0886] In this invention, the server includes means for receiving the content of the consultation from the user, means for analyzing the content of the consultation using natural language processing technology, means for generating an answer to the consultation using a generation AI based on the analyzed data, means for returning the generated answer to the user, means for receiving feedback from the user and re-analyzing and generating, and means for using the analyzed and generated data to improve the skills of store staff, thereby enabling store staff to solve problems and improve their skills in real time.

[0887] The "means for receiving consultation contents from the user" is a function including an interface for transmitting consultation contents input by the user to the system.

[0888] "Means for analyzing consultation content using natural language processing technology" is a function for analyzing input consultation content using natural language processing technology and extracting important keywords and context.

[0889] "Means of using generation AI based on analyzed data to generate an answer to the inquiry content" is a function that uses generation AI to generate the optimal answer based on analyzed data.

[0890] "Means for returning the generated answer to the user" is a function that includes an interface for returning and displaying the answer generated by the generation AI to the user.

[0891] The "means for receiving feedback from the user and performing analysis and generation again" is a function for receiving feedback provided by the user and performing the analysis and generation process again based on that feedback.

[0892] "Means of using the analyzed and generated data to improve the skills of store staff" is a function that uses the data obtained through the analysis and generation process to improve the customer service skills of store staff and solve problems.

[0893] The following describes in detail an embodiment of the present invention, specifically, a specific method for introducing a coaching system for improving customer service skills into a brick-and-mortar store.

[0894] System Configuration

[0895] The coaching system of the present invention is comprised of the following main components:

[0896] 1. User device: A smartphone used by store staff.

[0897] 2. Server: A central computer system that receives and analyzes consultation content, runs the generative AI, and processes feedback.

[0898] 3. Generative AI model: An AI model that uses natural language processing technology to generate optimal advice based on the content of a consultation (e.g., Hugging Face's GPT-3).

[0899] Hardware and Software

[0900] 1. Hardware:

[0901] Smartphone: Used by store staff as a user device.

[0902] Server computer: Provides the computational resources for hosting the generative AI models and databases.

[0903] 2. Software:

[0904] Natural language processing (NLP) library: Used to analyze consultation content.

[0905] Generative AI model: Hugging Face's GPT-3 is used to generate specific advice for the consultation content.

[0906] Database management system: Records user consultations and feedback and analyzes them periodically.

[0907] Data processing and calculation

[0908] 1. User Device:

[0909] Store staff enter the details of the consultation via a smartphone app and send it to the server.

[0910] The app will have an intuitive interface and will be designed to allow staff to easily input their enquiries.

[0911] 2. Server:

[0912] Receiving: The server receives the input from the user terminal and decodes the text data.

[0913] Analysis: Natural language processing techniques are used to analyze text data and extract key keywords and context.

[0914] Generation: Based on the analysis results, a generative AI model is run to generate optimal advice for the consultation.

[0915] Return: The generated advice is returned to the user's device and displayed on the smartphone screen.

[0916] Examples and prompts

[0917] Examples:

[0918] 1. Store staff enter "How to respond when receiving a customer complaint" into a smartphone app.

[0919] 2. The server receives this request and extracts the keyword "complaint handling" through natural language processing.

[0920] 3. The generative AI model generates specific advice such as, "It's important to stay calm and resolve the problem quickly."

[0921] 4. This advice is sent back to the staff member's smartphone and displayed.

[0922] Example prompt sentence:

[0923] How do you handle customer complaints about products?

[0924] "Please suggest ways to improve communication with team members."

[0925] This system enables store staff to solve problems in real time and improve their skills, contributing to improving the service quality of the entire store.

[0926] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0927] Step 1:

[0928] The user inputs the content of the consultation through a smartphone app and presses the send button. This input includes a specific question, such as "Please tell me how to respond when a customer complains." The input text data is sent to the server in the latest format (e.g., JSON).

[0929] Step 2:

[0930] The server receives text data sent from the user terminal. To analyze the received data, it first formats the text data and checks its format. The input data is extracted as plain text and prepared for the next analysis step. The input for this step is the content of the user's inquiry, and the output is formatted text data.

[0931] Step 3:

[0932] The server analyzes the formatted text data using natural language processing techniques. Specifically, it uses an NLP library (e.g., spaCy or NLTK) to extract important keywords and context from the text data. The input to this analysis step is the formatted text data, and the output is the extracted keywords and context information.

[0933] Step 4:

[0934] The server launches a generative AI model (e.g., Hugging Face GPT-3) based on the analysis results to generate the optimal answer. The generation prompt includes extracted keywords and contextual information and is input to the generative AI. The generative AI model uses the input prompt to generate the optimal answer. The input to this step is the analysis results, and the output is the generated answer (advice).

[0935] Step 5:

[0936] The server constructs a response to send the generated answer back to the user. The response is sent in HTTP format to the user's smartphone, which receives the response and displays it on the screen. The input of this step is the generated answer, and the output is the response sent to the user's terminal.

[0937] Step 6:

[0938] If the user wishes to provide further feedback or ask a follow-up question based on the provided answer, such as a request like "Please provide a more specific action plan," the user's feedback is also sent to the server, where it is parsed and generated through a similar processing step. The input of this step is the user's feedback, and the output is a regenerated, detailed answer.

[0939] Step 7:

[0940] The server records the user's past consultation details and feedback in a database and periodically analyzes them. The database also stores time-series data, and generates "new insights and suggestions" based on the results of periodic analysis. The input for this step is the past consultation details and feedback, and the output is newly generated suggestions and insights.

[0941] Through these steps, store staff are continuously supported in improving their customer service skills and resolving problems.

[0942] 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.

[0943] The system of the present invention is designed to provide highly accurate coaching by combining generative AI and an emotion engine. This system is mainly composed of a user terminal, a server, a database, and an emotion engine.

[0944] Overall system flow

[0945] Input and transmission from the user terminal

[0946] 1. The user inputs the details of the coaching they would like to receive from their device and sends a request. For example, they might input, "I'm worried about my career path. Please tell me how I should proceed," and press the send button.

[0947] Server receives and analyzes the request

[0948] 2. The server receives the request from the user and analyzes its contents. Specifically, it passes the text to a natural language processing (NLP) module for preprocessing such as tokenization, stop word removal, and stemming.

[0949] 3. The server extracts important keywords and context from the analyzed text data. For example, it identifies the keywords "career path" and "concerns."

[0950] Activating the Emotion Engine

[0951] 4. The server passes the extracted text data to the emotion engine, which analyzes the user's emotions. The emotion engine identifies the emotions contained in the text and classifies them into emotion categories such as "anxiety," "excitement," and "anger."

[0952] Starting the generative AI and generating answers

[0953] 5. The server then activates the generative AI, taking into account the analysis results of the emotion engine, to generate the optimal answer for the user's inquiry. For example, as "career path advice," it generates specific options such as "joining a new project" or "training to improve skills."

[0954] 6. The server formats the generated answer and constructs a response to send back to the user. This response is constructed in a format that reflects the user's emotional state. For example, if the user is feeling "anxious," it uses expressions that make the user feel more reassured.

[0955] Return of coaching content

[0956] 7. The server sends the formatted answer to the user terminal as an HTTP response.

[0957] 8. The user device receives the HTTP response and displays it on the screen. For example, it might say, "Your career path has the following options: 1. Join a new project within your department. 2. Take training to improve your skills. 3. Talk to your manager to clarify your specific role."

[0958] Processing Feedback

[0959] 9. The user enters additional questions or feedback about the provided answer and submits the request again. For example, they enter "I'd like to know a more specific action plan" and press the submit button again.

[0960] 10. The server receives the feedback and uses the generative AI and emotion engine to generate detailed coaching content. For example, it provides a specific action plan such as, "To participate in Project A, you first need the following skill set. You can acquire these skills by participating in Training Program B."

[0961] Providing new insights

[0962] 11. The server records the user's past requests and responses in a database and periodically analyzes them to generate new insights and suggestions. For example, it can analyze past consultation history and provide the latest information on project management.

[0963] 12. The server generates new insights and suggestions based on the results of periodic analysis and notifies the user.

[0964] 13. The user device receives the notification from the server and displays it on the screen. For example, a notification may appear saying, "We have the latest information on the latest trends and techniques for project management, which we previously discussed."

[0965] Specific examples

[0966] For example, if a user enters "I'm having trouble communicating with my subordinates":

[0967] 1. The server receives this request and analyzes keywords such as "subordinate" and "communication."

[0968] 2. The emotion engine identifies the emotion of "being troubled."

[0969] 3. The generative AI references data on "effective communication methods with subordinates" and generates specific solutions. For example, it generates advice such as "Make an effort to actively listen."

[0970] 4. The server then takes into account the user's emotional state and formats the response in a reassuring way, for example, by displaying a message such as, "To solve your problem, let's start by actively listening."

[0971] This allows the system of the present invention to provide personalized, highly accurate coaching that takes into account the user's emotions, and to provide continuous support until the user is satisfied.

[0972] The processing flow will be explained below.

[0973] Step 1:

[0974] The user enters their concerns or questions into the input field on the device and presses the send button. For example, they enter, "I'm worried about my career path. Please tell me how I should proceed," and then presses the send button.

[0975] Step 2:

[0976] The terminal sends the consultation details entered by the user to the server as an HTTP request.

[0977] Step 3:

[0978] The server receives the HTTP request and analyzes the request content. Specifically, the text is passed to a natural language processing (NLP) module for preprocessing such as tokenization, stop word removal, and stemming.

[0979] Step 4:

[0980] The server extracts important keywords and context from the analyzed text data. For example, it identifies the keywords "career path" and "worries."

[0981] Step 5:

[0982] The server passes the extracted keywords to an emotion engine to analyze the user's emotions, for example, detecting whether the text contains the word "anxiety."

[0983] Step 6:

[0984] The emotion engine analyzes the text and classifies the user's emotional state, for example into emotion categories such as "anxiety," "excitement," and "anger."

[0985] Step 7:

[0986] The server optimizes the AI's response based on the user's emotional state. For example, if the user is feeling anxious, it will select reassuring language.

[0987] Step 8:

[0988] The server activates the appropriate generative AI model and generates the optimal answer to the user's inquiry, taking into account the results of the emotion engine. For example, it generates "specific advice on career paths" such as "joining a new project" or "training to improve skills."

[0989] Step 9:

[0990] The server formats the generated answers and summarizes them in an easy-to-read format. Reassuring language is added to reflect the emotional state. For example, "Your career path includes the following options: 1. Join a new project within your department. 2. Take training to improve your skills. 3. Talk to your manager to clarify your specific role. Rest assured, you'll see results soon."

[0991] Step 10:

[0992] The server sends the formatted answer to the user terminal as an HTTP response.

[0993] Step 11:

[0994] The device receives the HTTP response and displays it on the screen. For example, it might say, "Your career path has the following options: 1. Join a new project within your department. 2. Take training to improve your skills. 3. Talk to your manager to clarify your specific role. Don't worry, you'll see positive results soon."

[0995] Step 12:

[0996] The user can enter additional questions or feedback about the answers provided and press the submit button again. For example, they can enter "I'd like to know a more specific action plan" and press the submit button again.

[0997] Step 13:

[0998] The device sends the new input to the server as an HTTP request.

[0999] Step 14:

[1000] The server receives the request again and analyzes the new input. Specifically, it again preprocesses it using natural language processing technology to extract additional important keywords.

[1001] Step 15:

[1002] The server again uses the emotion engine to confirm the user's emotional state, for example detecting an increase in the emotion of "anxiety" based on additional input information.

[1003] Step 16:

[1004] The server passes the results of the analysis and emotion engine to the generation AI, which then generates an appropriate solution. For example, it generates a specific action plan such as, "To participate in Project A, you first need the following skill set. You can acquire these skills by participating in Training Program B."

[1005] Step 17:

[1006] The server reformats the generated details and constructs a response to send back to the user.

[1007] Step 18:

[1008] The device receives the new response and displays it on the screen. For example, it might say, "To participate in Project A, you first need the following skill set. You can acquire these skills by participating in Training Program B."

[1009] Step 19:

[1010] The server records the user's past requests and responses in a database, analyzes them periodically, and generates new insights and suggestions.

[1011] Step 20:

[1012] The server generates new insights and suggestions based on the results of periodic analysis and notifies the user.

[1013] Step 21:

[1014] The device receives notifications from the server and displays them on the screen. For example, a notification might say, "We have the latest information on the latest trends and techniques for project management, which we previously discussed."

[1015] Example 2

[1016] 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."

[1017] Conventional coaching systems have had the problem of being unable to generate personalized answers that take the user's emotions into account, which means they are unable to sufficiently increase user satisfaction. It has also been difficult to effectively utilize user feedback and provide continuous, highly accurate coaching.

[1018] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1019] In this invention, the server includes means for receiving consultation content from a user, means for analyzing the consultation content using natural language processing technology, means for identifying and classifying emotions based on the analyzed data, means for generating an answer to the consultation content using a generative AI model taking into account the emotion analysis results, means for formatting the generated answer in accordance with the user's emotional state and returning it to the user, and means for receiving feedback from the user and re-analyzing and generating an answer. This makes it possible to provide the user with personalized answers according to their emotions and provide continuous, highly accurate coaching.

[1020] The "means for receiving consultation content" is an interface for electronically collecting input information from users and processing it within the system.

[1021] "Natural language processing technology" is a technology that allows computers to understand and analyze human language, and includes processes such as tokenization and removal of stop words.

[1022] "Means for identifying and classifying emotions" refers to technology for detecting user emotions (e.g., anxiety, excitement, anger, etc.) from text data and classifying them into categories.

[1023] A "generative AI model" is an artificial intelligence technique for generating appropriate responses in natural language based on input prompts.

[1024] "Formulating" refers to a technology that converts the answers output by the generative AI model into the optimal format based on the user's emotions and situation.

[1025] The "means for receiving feedback" is an interface for collecting information and opinions re-entered from the user and using them to analyze the next step and generate answers.

[1026] "Multiple data sources" is a general term for various databases and information sources that are referenced to respond to the user's inquiry.

[1027] "Means of providing new insights and suggestions" refers to technology that analyzes past data, generates new knowledge and action plans, and proposes them to users.

[1028] The system of the present invention is designed to combine a generative AI model and an emotion engine to provide highly accurate coaching. This system is mainly composed of a user terminal, a server, a database, and an emotion engine. Specifically, it includes the following functions and processes:

[1029] Input and transmission from the user terminal

[1030] The user inputs the details of the coaching they would like to receive from their device and sends a request. Specifically, the user interface includes a text box where they can type, "I'm having trouble deciding on my career path. Can you tell me how I should proceed?" and then press the send button. The user device can be a smartphone, tablet, or computer.

[1031] Server receives and analyzes the request

[1032] The server receives the request sent by the user as an HTTP request and analyzes its contents. The received text data is passed to a natural language processing (NLP) module. For example, the NLP module performs preprocessing such as tokenizing the text, removing stop words, and stemming. This makes it possible to extract important keywords and context. For example, the keywords "career path" and "worries" are identified.

[1033] Activating the Emotion Engine

[1034] The server passes the analyzed text data to an emotion engine, which analyzes the user's emotions. The emotion engine identifies emotions contained in the text and classifies them into emotion categories such as "anxiety," "excitement," and "anger." As a specific example, it identifies the emotion "anxiety" from the phrase "I'm worried."

[1035] Starting the generative AI and generating answers

[1036] The server activates the generative AI model, taking into account the analysis results of the emotion engine, to generate the optimal answer to the user's inquiry. As a specific example of a prompt sentence, "Please give me some advice on my career path," is entered, and the generative AI model generates specific options such as "join a new project" and "take training to improve my skills." An existing large-scale language model (LLM) is used as the generative AI model.

[1037] Formatting and returning answers

[1038] The server formats the generated answer and constructs a response to send back to the user. This response is formatted in a way that reflects the user's emotional state. For example, if the user is feeling "anxious," it uses language that makes them feel more reassured. A specific example of a formatted answer would be, "Your career path has the following options: 1. Join a new project within your department. 2. Take training to improve your skills. 3. Talk to your manager to clarify your specific role."

[1039] Display on user terminal

[1040] The user device receives the HTTP response and displays it on the screen. For example, it displays "Your career path has the following options..."

[1041] User Feedback and Resend

[1042] The user can enter additional questions or feedback about the answers provided and submit the request again. For example, the user can enter "I would like to know a more specific action plan" in the text box and press the submit button again.

[1043] Providing new insights

[1044] The server records the user's past requests and responses in a database and periodically analyzes them to generate new insights and suggestions. As a specific example, past data in the database is analyzed to extract the "latest information about project management." Based on the results of the periodic analysis, new insights and suggestions are generated and notified. The user's device receives notifications from the server and displays them on the screen. For example, a notification may appear saying, "We have the latest information on recent trends and methods for project management, which you previously consulted about."

[1045] The system allows users to receive truly personalized and highly accurate coaching, which significantly increases user satisfaction.

[1046] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1047] Step 1:

[1048] The user inputs the desired coaching information from the device and makes a request to send it. The input information is "I'm worried about my career path. Please tell me how I should proceed" and is entered into the text box on the device, and the user presses the send button. The input data is sent to the server in JSON format.

[1049] Step 2:

[1050] The server receives this request. The received data is processed as an HTTP request. The server first parses the input data and extracts text data. The extracted text data is then passed to a natural language processing (NLP) module. Specific operations include preprocessing such as tokenization, stop word removal, and even stemming. The input is raw text data from the user, and the output is preprocessed text data.

[1051] Step 3:

[1052] The server analyzes the preprocessed text data and extracts important keywords and contexts. For example, it identifies the keywords "career path" and "worries." The input is the preprocessed text data, and the output is a list of extracted keywords. This operation allows the server to understand the meaning of the input data and identify important related elements.

[1053] Step 4:

[1054] The server passes the extracted text data to an emotion engine, which analyzes the user's emotions. The emotion engine identifies emotions contained in the text and classifies them into emotion categories such as anxiety, excitement, and anger. For example, it identifies the emotion "anxiety" from the phrase "I'm worried." The input is a list of extracted keywords, and the output is a list of emotion categories.

[1055] Step 5:

[1056] The server takes into account the analysis results of the emotion engine and passes the input prompt to the generative AI model. The specific prompt sentence is "Please give me some advice on my career path." The generative AI model generates the optimal answer based on the prompt. For example, it outputs options such as "join a new project" or "take training to improve your skills." The input is the prompt sentence, and the output is the generated list of advice.

[1057] Step 6:

[1058] The server formats the generated answer, converting it into a reassuring expression that reflects the user's emotional state. For example, it might format it as, "Your career path has the following options: 1. Join a new project within your department. 2. Take training to improve your skills. 3. Talk to your manager to clarify your specific role." The input is a list of advice from the generative AI model, and the output is the formatted answer.

[1059] Step 7:

[1060] The server sends the formatted answer to the user's terminal as an HTTP response. The sent data is in JSON format and is constructed in a form suitable for the display format of the user's terminal. The input is the formatted answer, and the output is an HTTP response.

[1061] Step 8:

[1062] The user device receives the HTTP response and displays it on the screen. For example, it displays "Your career path has the following options..." The input is the HTTP response from the server, and the output is the screen display in a format that the user can view.

[1063] Step 9:

[1064] The user enters additional questions or feedback about the provided answers and makes a request again. For example, the user enters "I would like to know a more specific action plan" in the text box and presses the submit button again. The input data is again sent to the server in JSON format.

[1065] Step 10:

[1066] The server receives the new feedback and repeats the steps of preprocessing, analysis, sentiment analysis, use of the generative AI model, answer formatting, and sending. For example, it provides a specific action plan such as, "To participate in Project A, you first need the following skill set. You can acquire these skills by participating in Training Program B." The input is new feedback from the user, and the output is a regenerated specific action plan.

[1067] (Application example 2)

[1068] 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."

[1069] Conventional coaching systems struggle to provide appropriate advice and solutions to users' concerns. Furthermore, they fail to properly consider the user's emotional state, making it impossible to provide personalized support that satisfies the user. Furthermore, they often fail to provide relevant content, resulting in a lack of practical support for users in solving their problems.

[1070] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving the content of the consultation from the user, means for analyzing the content of the consultation using natural language processing technology, means for generating an answer to the consultation content using a generation AI based on the analyzed data, means for returning content related to the generated answer to the user, and means for receiving feedback from the user and performing further analysis and generation. This makes it possible to provide personalized and practical coaching advice and related content while taking the user's emotional state into consideration.

[1071] The "means for receiving consultation contents from the user" is an interface for transmitting consultation contents input by the user through the terminal to the server.

[1072] "Means of analysis using natural language processing technology" refers to technology that performs preprocessing such as tokenizing received text data, removing stop words, and stemming.

[1073] "Means of using generative AI to generate answers to inquiries" refers to technology that uses a generative AI model to generate optimal answers based on data analyzed using natural language processing technology.

[1074] The "means for returning content related to the generated answer to the user" is an interface for returning content such as videos, articles, exercises, etc. related to the generated answer to the user.

[1075] "Means for receiving feedback from users and re-analyzing and re-generating" refers to technology that re-analyzes the feedback provided by the user using natural language processing technology and a generative AI model, and re-generates the optimal answer.

[1076] "Means for recording the content of users' past consultations, periodically analyzing it, and providing new insights and suggestions" refers to a technology that stores users' past consultation history in a database, periodically analyzes it, and generates new suggestions.

[1077] "Means of referencing multiple data sources to generate optimal solutions and related content" refers to technology that refers to multiple information sources depending on the content of the consultation and generates optimal advice and related content.

[1078] This system receives inquiries from users, generates optimal answers using natural language processing and generative AI technologies, and provides them to users along with related content. This system is primarily composed of a user terminal, a server, a database, and an emotion engine.

[1079] First, we will explain input and transmission from the user terminal. The user inputs the content of their consultation through a smartphone app and sends it to the server. For example, they might input a question such as, "I've been feeling stressed lately and I don't know what to do." The input data is sent to the server as an HTTP request.

[1080] Next, we will explain the processing on the server. The server analyzes the received text data using natural language processing technology. This analysis includes preprocessing such as tokenization, stop word removal, and stemming. Natural language processing technologies used include spaCy and NLTK.

[1081] Important keywords are extracted from the analyzed data and passed to the emotion engine, which identifies the emotions contained in the text and classifies them into emotion categories such as "anxiety" or "stress." The emotion analysis engine used is IBM Watson Tone Analyzer.

[1082] Next, a generative AI model is used based on the analysis results to generate the optimal answer to the user's inquiry. OpenAI GPT-3 and other models are used as generative AI models. For example, if the user's inquiry is "Please tell me how to relieve stress," the generative AI model will generate an answer such as "Light exercise and meditation every day are effective for relieving stress."

[1083] The generated answer is then returned to the user along with related content (videos, articles, exercises, etc.) For example, the answer may include a link to a video or article that explains a specific relaxation technique, providing the user with the resources to take specific steps.

[1084] Furthermore, the system can receive user feedback and perform further analysis and generate answers. For example, if a user sends feedback such as "I would like to know a more specific action plan," the server will again use NLP and generative AI models to provide a more detailed action plan.

[1085] To illustrate, here are some example prompts:

[1086] "User Question: "I've been feeling stressed lately and I don't know what to do." Emotion: Anxiety, Stress Generate an answer."

[1087] This system can provide personalized and practical coaching advice and related content that takes into account the user's emotional state, thereby supporting users in solving their problems more efficiently.

[1088] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1089] Step 1:

[1090] User input: The user inputs and submits the content of their problem through the smartphone app. For example, they might type, "I've been feeling stressed lately and I don't know what to do." The input is formatted as an HTTP request and sent to the server.

[1091] Step 2:

[1092] Server reception: The server receives the HTTP request from the user and extracts the text data. The input at this stage is the text of the user's consultation, and the output is this text data itself.

[1093] Step 3:

[1094] Natural Language Processing (NLP): The server analyzes the received text data using natural language processing techniques. Specifically, preprocessing such as tokenization (dividing the text into words and phrases), stop word removal (removing meaningless common words), and stemming (converting words to their base forms) is performed. The input is raw text data, and the output is preprocessed text data.

[1095] Step 4:

[1096] Keyword extraction: The server extracts important keywords from the preprocessed text data. For example, it identifies the keywords "stress" and "relief methods." The input at this stage is the preprocessed text data, and the output is a list of important keywords.

[1097] Step 5:

[1098] Sentiment analysis: The server passes the extracted keywords to the emotion engine to analyze the user's emotions. The emotion engine identifies emotions contained in the text and classifies them into emotion categories such as "anxiety" or "stress." The input is a list of keywords, and the output is a list of emotion categories.

[1099] Step 6:

[1100] Answer generation: The server uses a generative AI model based on the results of sentiment analysis to generate the optimal answer to the user's inquiry. For example, it generates an answer such as "Daily light exercise and meditation are effective for relieving stress." The input is a list of keywords and a list of sentiment categories, and the output is the generated answer text.

[1101] Step 7:

[1102] Content recommendation: The server identifies content (videos, articles, exercises, etc.) related to the generated answer and constructs a response to serve to the user. The input is the answer text, and the output is a response containing the answer text and links to the related content.

[1103] Step 8:

[1104] Response transmission: The server transmits the constructed response to the user terminal as an HTTP response. The input is the response data, and the output is the transmission status to the user terminal.

[1105] Step 9:

[1106] User display: The user device analyzes the HTTP response received from the server and displays it on the screen. For example, it might say, "Light exercise and meditation every day are effective for relieving stress. Try practicing with this video as a reference." The input is the HTTP response data, and the output is the text displayed to the user and a link to related content.

[1107] 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.

[1108] 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.

[1109] 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.

[1110] [Fourth embodiment]

[1111] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1112] 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.

[1113] 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).

[1114] 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.

[1115] 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.

[1116] 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).

[1117] 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.

[1118] 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.

[1119] 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.

[1120] 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.

[1121] 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.

[1122] 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.

[1123] 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."

[1124] The system of the present invention is designed to provide highly accurate coaching using generative AI. This system is mainly composed of a user terminal, a server, and a database.

[1125] Overall system flow

[1126] Input and transmission from the user terminal

[1127] 1. The user inputs the details of the coaching they wish to receive from their device and makes a request to send it. Typically, the user enters the details of the consultation into the application's input field and presses the send button.

[1128] Server receives and analyzes the request

[1129] 2. The server receives the request from the user and analyzes its contents. Specifically, it preprocesses the input text using natural language processing technology and extracts important keywords and context. For example, if a request is entered such as "I'm worried about my career path," the server identifies the keywords "career path" and "worry" from the request.

[1130] Starting the generative AI and generating answers

[1131] 3. The server then activates the generation AI based on the analysis results to generate the optimal answer for the consultation. The generation AI references multiple data sources and extracts appropriate solutions and advice from them. For example, specific options such as "joining a new project" or "training to improve skills" are generated as "optimal advice regarding career paths."

[1132] Return of coaching content

[1133] 4. The server constructs a response to return the generated coaching content to the user. This response is formatted in a format that is easy for the user to understand and sent to the user's device as an HTTP response. The user's device receives this response and displays it on the screen. Specifically, it displays the message, "Your career path has the following options."

[1134] Processing Feedback

[1135] 5. The user can enter additional questions or feedback about the coaching content provided and submit the request again. For example, the user can enter feedback such as, "I would like to know a more specific action plan."

[1136] 6. The server receives the feedback and uses the generation AI to generate detailed coaching content. For example, a specific action plan such as "The following skill set is required to participate in the project" is provided.

[1137] Providing new insights

[1138] 7. The server records the user's past consultations and periodically analyzes them to generate new insights and suggestions. For example, it can analyze past consultation history and provide the latest information on project management.

[1139] Specific examples

[1140] For example, if a user enters "I'm having trouble communicating with my subordinates":

[1141] 1. The server receives this request and analyzes keywords such as "subordinate" and "communication."

[1142] 2. The generative AI refers to data on "effective communication methods with subordinates" and generates specific advice, such as "putting active listening into practice."

[1143] 3. If the user further provides feedback that they would like to know examples of specific situations, the server will launch the generation AI again and provide "specific examples of how to ask subordinates about the progress of a project."

[1144] In this way, the system of the present invention can provide highly accurate coaching tailored to the individual needs of the user and provide continuous support, allowing the user to receive more specific and useful advice and gain new insights and action plans.

[1145] The processing flow will be explained below.

[1146] Step 1:

[1147] The user enters their concerns or questions into the input field on the device and presses the send button. For example, they enter, "I'm worried about my career path. Please tell me how I should proceed," and then presses the send button.

[1148] Step 2:

[1149] The terminal sends the consultation details entered by the user to the server as an HTTP request.

[1150] Step 3:

[1151] The server receives the HTTP request and analyzes the request content. Specifically, the text is passed to a natural language processing (NLP) module for preprocessing such as tokenization, stop word removal, and stemming.

[1152] Step 4:

[1153] The server extracts important keywords and context from the analyzed text data. For example, it identifies the keywords "career path" and "worries."

[1154] Step 5:

[1155] The server selects and launches an appropriate generative AI model based on the extracted keywords.

[1156] Step 6:

[1157] The server uses generation AI to generate the optimal answer for the user's inquiry. Specifically, it references multiple data sources and generates specific options such as "joining a new project," "training to improve skills," and "consulting with a supervisor."

[1158] Step 7:

[1159] The server then formats the generated answers into an easy-to-read format, such as "Your career path includes the following options: 1. Join a new project within your department, 2. Take training to improve your skills, or 3. Talk to your manager to clarify your specific role."

[1160] Step 8:

[1161] The server sends the formatted answer to the user terminal as an HTTP response.

[1162] Step 9:

[1163] The device receives the HTTP response and displays it on the screen. For example, it might say, "Your career path has the following options: 1. Join a new project within your department. 2. Take training to improve your skills. 3. Talk to your manager to clarify your specific role."

[1164] Step 10:

[1165] The user enters a follow-up question or feedback on the answer provided, for example, "I'd like to know a more specific action plan," and hits the submit button again.

[1166] Step 11:

[1167] The device sends the new input to the server as an HTTP request.

[1168] Step 12:

[1169] The server receives the request again and performs additional analysis, especially generating more detailed information using generative AI to respond to user feedback.

[1170] Step 13:

[1171] The server then uses the generative AI to generate specific action plans and detailed advice, such as, "To participate in Project A, you first need the following skill set. You can acquire these skills by participating in Training Program B."

[1172] Step 14:

[1173] The server reformats the generated details and constructs a response to send back to the user.

[1174] Step 15:

[1175] The device receives the new response and displays it on the screen, for example, "To participate in Project A, you first need the following skill set. You can acquire these skills by participating in Training Program B."

[1176] Step 16:

[1177] The server records the user's past requests and responses in a database, analyzes them periodically, and generates new insights and suggestions.

[1178] Step 17:

[1179] The server generates new insights and suggestions based on the results of periodic analysis and notifies the user.

[1180] Step 18:

[1181] The device receives notifications from the server and displays them on the screen. For example, a notification might say, "We have the latest information on the latest trends and techniques for project management, which we previously discussed."

[1182] Example 1

[1183] 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."

[1184] Conventional coaching systems have struggled to provide quick and specific solutions to users' concerns. Furthermore, few systems offer ongoing support based on feedback, making it difficult for users to receive effective advice. Furthermore, because they are unable to provide new suggestions or insights based on past consultations, it is difficult to continuously support users' growth.

[1185] 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.

[1186] In this invention, the server includes means for receiving the consultation content from the user, means for analyzing the consultation content using natural language processing technology, means for generating an answer to the consultation content using a generation AI based on the analyzed data, means for returning the generated answer to the user, means for receiving feedback from the user and re-analyzing and generating an answer, and means for proposing specific options and action plans related to the consultation content. This makes it possible to provide the user with a quick and specific solution, and to provide continuous support based on feedback and new proposals based on past consultation content.

[1187] A "user" is an entity that uses the coaching system to input the details of a consultation and receives the generated advice and suggestions.

[1188] "Consultation content" refers to the problem or question that the user inputs to the coaching system and seeks to resolve.

[1189] "Natural language processing technology" is a technology that enables computers to understand, analyze, and generate human language, and includes text analysis and keyword extraction.

[1190] "Generative AI" is a general term for artificial intelligence models that generate optimal sentences or responses based on input prompts.

[1191] An "answer" is a solution or proposal that the generative AI generates based on the content of the consultation.

[1192] "Feedback" refers to a user entering more specific information or a follow-up question in response to a provided answer.

[1193] "Specific options and action plans" refer to specific action plans and options proposed by the generative AI that are directly linked to solving the user's problem.

[1194] "Sources" are multiple external data sources and knowledge bases that the generative AI references to generate answers.

[1195] This invention is a system that analyzes the content of a user's consultation and provides highly accurate coaching using a generative AI model. This system is mainly composed of a user terminal, a server, and a database.

[1196] Hardware and Software Configuration

[1197] User terminal

[1198] The user terminal consists of a mobile device or computer. The user uses this to input the content of the consultation and subsequent feedback. A web application or mobile application is installed on the user terminal, and the user accesses the system through this.

[1199] server

[1200] The server is responsible for receiving requests, analyzing them, and launching the generative AI. The server typically runs on a high-performance computing device or cloud service. It processes HTTP requests using a Python web framework (e.g., Flask or Django). Libraries such as NLTK and SpaCy are used for natural language processing. Generative AI models such as OpenAI's GPT-4 are used.

[1201] Database

[1202] The database records users' past consultation details and feedback. By using a relational database such as MySQL or PostgreSQL, data can be efficiently stored and managed.

[1203] System Operation

[1204] The user enters the content of their inquiry into the application's input field and presses the send button to send a request. For example, the user might enter a content such as "I'm worried about my career path."

[1205] The server receives this and analyzes the text using natural language processing techniques, such as NLTK and SpaCy, to extract important keywords and context. For example, it identifies keywords such as "career path" and "concerns."

[1206] The server then launches a generative AI to generate the optimal answer based on the analysis results. The generative AI uses OpenAI's GPT-4 and other technologies to generate solutions by referencing multiple sources of information. For example, it suggests specific options such as "joining a new project" or "training to improve skills."

[1207] The server creates the generated answer in JSON format and sends it to the user's device as an HTTP response. The user's device receives it and displays it on the screen. For example, it might say, "Your career path has the following options."

[1208] The user can enter additional questions or feedback about the coaching provided. For example, the user can enter, "I'd like to know a more specific action plan."

[1209] The server receives the feedback, analyzes it again, and generates a new AI. It then launches the AI ​​to propose a detailed action plan. For example, it generates specific advice such as, "The following skill set is required to participate in the project."

[1210] Example prompt sentences

[1211] "I'm struggling with my career path. Can you give me some concrete advice on how to get involved in new projects and improve my skills?"

[1212] "I'm having trouble communicating with my subordinates. Can you give me some specific examples for different situations?"

[1213] This invention allows users to obtain quick and specific solutions and receive continuous support based on feedback. Furthermore, by obtaining new suggestions and insights based on past consultations, it is possible to continuously support the user's growth.

[1214] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1215] Step 1:

[1216] The user enters the content of their consultation into the application's input field and presses the send button. The input content is constructed as text data. For example, the specific content of their consultation may be, "I'm worried about my career path." The output is the input text data.

[1217] Step 2:

[1218] The user terminal sends the entered text data to the server as an HTTP POST request. The input is the text data entered by the user, and the output is data in the form of an HTTP request. Specifically, in the case of a web application, the request is sent using the JavaScript fetch API.

[1219] Step 3:

[1220] The server receives an HTTP POST request sent from the user device. The input is the HTTP request from the user device, and the output is text data extracted from the request. Specifically, the request data is obtained using a web framework such as Flask or Django.

[1221] Step 4:

[1222] The server analyzes the received text data using natural language processing technology. The input is the text data extracted from the request, and the output is the analyzed keywords and context. Specifically, it uses Python's NLTK and SpaCy to tokenize the text and extract important keywords. For example, keywords such as "career path" and "concerns" are identified.

[1223] Step 5:

[1224] The server launches a generative AI model based on the analysis results. The input is the analyzed keywords and context, and the output is a prompt to be passed to the generative AI. Specifically, a Python script is used to call the generative AI (e.g., OpenAI's GPT-4 API) and construct the prompt. For example, a prompt is generated as "the best advice regarding your career path."

[1225] Step 6:

[1226] The generative AI generates the optimal answer based on the prompt text. The input is the prompt text sent from the server, and the output is the generated text answer. For example, it generates specific solutions such as "join a new project" or "training to improve skills."

[1227] Step 7:

[1228] The server constructs a response based on the generated text answer. The input is the text answer from the generation AI, and the output is the response data in JSON format. Specifically, the JSON response constructed using Flask or Django is sent as an HTTP response.

[1229] Step 8:

[1230] The user terminal receives the JSON response sent from the server and displays it on the screen. The input is the JSON-formatted response data from the server, and the output is text displayed on the user interface. For example, "Your career path has the following options."

[1231] Step 9:

[1232] The user inputs additional questions or feedback regarding the provided coaching content and makes another transmission request. The input is the user's feedback regarding the provided answer, and the output is the text data entered as feedback. For example, the user might input, "I would like to know a more specific action plan."

[1233] Step 10:

[1234] The user terminal transmits the text data input as feedback to the server again as an HTTP POST request. The input is the text data input as feedback, and the output is data in the HTTP request format.

[1235] Step 11:

[1236] The server receives the resent HTTP POST request and re-analyzes the text data. The input is the HTTP request from the user device, and the output is the re-analyzed keywords and context. Again, a natural language processing library is used to tokenize the text and extract important keywords.

[1237] Step 12:

[1238] The server then launches the generative AI model again based on the reanalyzed results. The input is the reanalyzed keywords and context, and the output is a new prompt to be passed to the generative AI. The generative AI is then called to construct a new prompt.

[1239] Step 13:

[1240] The generation AI generates a detailed answer based on the second prompt. The input is the second prompt sent from the server, and the output is a detailed answer in the generated text. For example, it generates specific advice such as, "The following skill set is required to participate in the project."

[1241] Step 14:

[1242] The server reconstructs a response based on the detailed answer. The input is the text answer from the generation AI, and the output is the response data in JSON format. The reconstructed JSON response is sent again as an HTTP response.

[1243] Step 15:

[1244] The user device again receives the JSON response sent from the server and displays it on the screen. The input is the JSON-formatted response data from the server, and the output is text displayed on the user interface. For example, it displays a specific message such as, "The following skill set is required to participate in the project."

[1245] (Application example 1)

[1246] 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."

[1247] Customer service in stores depends on the skills and experience of the staff, making it difficult to provide consistent quality service. New employees and staff who are unfamiliar with customer service often have trouble receiving appropriate advice quickly. This creates a need for improving the skills of individual staff and the service quality of the entire store.

[1248] 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.

[1249] In this invention, the server includes means for receiving the content of the consultation from the user, means for analyzing the content of the consultation using natural language processing technology, means for generating an answer to the consultation using a generation AI based on the analyzed data, means for returning the generated answer to the user, means for receiving feedback from the user and re-analyzing and generating, and means for using the analyzed and generated data to improve the skills of store staff, thereby enabling store staff to solve problems and improve their skills in real time.

[1250] The "means for receiving consultation contents from the user" is a function including an interface for transmitting consultation contents input by the user to the system.

[1251] "Means for analyzing consultation content using natural language processing technology" is a function for analyzing input consultation content using natural language processing technology and extracting important keywords and context.

[1252] "Means of using generation AI based on analyzed data to generate an answer to the inquiry content" is a function that uses generation AI to generate the optimal answer based on analyzed data.

[1253] "Means for returning the generated answer to the user" is a function that includes an interface for returning and displaying the answer generated by the generation AI to the user.

[1254] The "means for receiving feedback from the user and performing analysis and generation again" is a function for receiving feedback provided by the user and performing the analysis and generation process again based on that feedback.

[1255] "Means of using the analyzed and generated data to improve the skills of store staff" is a function that uses the data obtained through the analysis and generation process to improve the customer service skills of store staff and solve problems.

[1256] The following describes in detail an embodiment of the present invention, specifically, a specific method for introducing a coaching system for improving customer service skills into a brick-and-mortar store.

[1257] System Configuration

[1258] The coaching system of the present invention is comprised of the following main components:

[1259] 1. User device: A smartphone used by store staff.

[1260] 2. Server: A central computer system that receives and analyzes consultation content, runs the generative AI, and processes feedback.

[1261] 3. Generative AI model: An AI model that uses natural language processing technology to generate optimal advice based on the content of a consultation (e.g., Hugging Face's GPT-3).

[1262] Hardware and Software

[1263] 1. Hardware:

[1264] Smartphone: Used by store staff as a user device.

[1265] Server computer: Provides the computational resources for hosting the generative AI models and databases.

[1266] 2. Software:

[1267] Natural language processing (NLP) library: Used to analyze consultation content.

[1268] Generative AI model: Hugging Face's GPT-3 is used to generate specific advice for the consultation content.

[1269] Database management system: Records user consultations and feedback and analyzes them periodically.

[1270] Data processing and calculation

[1271] 1. User Device:

[1272] Store staff enter the details of the consultation via a smartphone app and send it to the server.

[1273] The app will have an intuitive interface and will be designed to allow staff to easily input their enquiries.

[1274] 2. Server:

[1275] Receiving: The server receives the input from the user terminal and decodes the text data.

[1276] Analysis: Natural language processing techniques are used to analyze text data and extract key keywords and context.

[1277] Generation: Based on the analysis results, a generative AI model is run to generate optimal advice for the consultation.

[1278] Return: The generated advice is returned to the user's device and displayed on the smartphone screen.

[1279] Examples and prompts

[1280] Examples:

[1281] 1. Store staff enter "How to respond when receiving a customer complaint" into a smartphone app.

[1282] 2. The server receives this request and extracts the keyword "complaint handling" through natural language processing.

[1283] 3. The generative AI model generates specific advice such as, "It's important to stay calm and resolve the problem quickly."

[1284] 4. This advice is sent back to the staff member's smartphone and displayed.

[1285] Example prompt sentence:

[1286] How do you handle customer complaints about products?

[1287] "Please suggest ways to improve communication with team members."

[1288] This system enables store staff to solve problems in real time and improve their skills, contributing to improving the service quality of the entire store.

[1289] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1290] Step 1:

[1291] The user inputs the content of the consultation through a smartphone app and presses the send button. This input includes a specific question, such as "Please tell me how to respond when a customer complains." The input text data is sent to the server in the latest format (e.g., JSON).

[1292] Step 2:

[1293] The server receives text data sent from the user terminal. To analyze the received data, it first formats the text data and checks its format. The input data is extracted as plain text and prepared for the next analysis step. The input for this step is the content of the user's inquiry, and the output is formatted text data.

[1294] Step 3:

[1295] The server analyzes the formatted text data using natural language processing techniques. Specifically, it uses an NLP library (e.g., spaCy or NLTK) to extract important keywords and context from the text data. The input to this analysis step is the formatted text data, and the output is the extracted keywords and context information.

[1296] Step 4:

[1297] The server launches a generative AI model (e.g., Hugging Face GPT-3) based on the analysis results to generate the optimal answer. The generation prompt includes extracted keywords and contextual information and is input to the generative AI. The generative AI model uses the input prompt to generate the optimal answer. The input to this step is the analysis results, and the output is the generated answer (advice).

[1298] Step 5:

[1299] The server constructs a response to send the generated answer back to the user. The response is sent in HTTP format to the user's smartphone, which receives the response and displays it on the screen. The input of this step is the generated answer, and the output is the response sent to the user's terminal.

[1300] Step 6:

[1301] If the user wishes to provide further feedback or ask a follow-up question based on the provided answer, such as a request like "Please provide a more specific action plan," the user's feedback is also sent to the server, where it is parsed and generated through a similar processing step. The input of this step is the user's feedback, and the output is a regenerated, detailed answer.

[1302] Step 7:

[1303] The server records the user's past consultation details and feedback in a database and periodically analyzes them. The database also stores time-series data, and generates "new insights and suggestions" based on the results of periodic analysis. The input for this step is the past consultation details and feedback, and the output is newly generated suggestions and insights.

[1304] Through these steps, store staff are continuously supported in improving their customer service skills and resolving problems.

[1305] 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.

[1306] The system of the present invention is designed to provide highly accurate coaching by combining generative AI and an emotion engine. This system is mainly composed of a user terminal, a server, a database, and an emotion engine.

[1307] Overall system flow

[1308] Input and transmission from the user terminal

[1309] 1. The user inputs the details of the coaching they would like to receive from their device and sends a request. For example, they might input, "I'm worried about my career path. Please tell me how I should proceed," and press the send button.

[1310] Server receives and analyzes the request

[1311] 2. The server receives the request from the user and analyzes its contents. Specifically, it passes the text to a natural language processing (NLP) module for preprocessing such as tokenization, stop word removal, and stemming.

[1312] 3. The server extracts important keywords and context from the analyzed text data. For example, it identifies the keywords "career path" and "concerns."

[1313] Activating the Emotion Engine

[1314] 4. The server passes the extracted text data to the emotion engine, which analyzes the user's emotions. The emotion engine identifies the emotions contained in the text and classifies them into emotion categories such as "anxiety," "excitement," and "anger."

[1315] Starting the generative AI and generating answers

[1316] 5. The server then activates the generative AI, taking into account the analysis results of the emotion engine, to generate the optimal answer for the user's inquiry. For example, as "career path advice," it generates specific options such as "joining a new project" or "training to improve skills."

[1317] 6. The server formats the generated answer and constructs a response to send back to the user. This response is constructed in a format that reflects the user's emotional state. For example, if the user is feeling "anxious," it uses expressions that make the user feel more reassured.

[1318] Return of coaching content

[1319] 7. The server sends the formatted answer to the user terminal as an HTTP response.

[1320] 8. The user device receives the HTTP response and displays it on the screen. For example, it might say, "Your career path has the following options: 1. Join a new project within your department. 2. Take training to improve your skills. 3. Talk to your manager to clarify your specific role."

[1321] Processing Feedback

[1322] 9. The user enters additional questions or feedback about the provided answer and submits the request again. For example, they enter "I'd like to know a more specific action plan" and press the submit button again.

[1323] 10. The server receives the feedback and uses the generative AI and emotion engine to generate detailed coaching content. For example, it provides a specific action plan such as, "To participate in Project A, you first need the following skill set. You can acquire these skills by participating in Training Program B."

[1324] Providing new insights

[1325] 11. The server records the user's past requests and responses in a database and periodically analyzes them to generate new insights and suggestions. For example, it can analyze past consultation history and provide the latest information on project management.

[1326] 12. The server generates new insights and suggestions based on the results of periodic analysis and notifies the user.

[1327] 13. The user device receives the notification from the server and displays it on the screen. For example, a notification may appear saying, "We have the latest information on the latest trends and techniques for project management, which we previously discussed."

[1328] Specific examples

[1329] For example, if a user enters "I'm having trouble communicating with my subordinates":

[1330] 1. The server receives this request and analyzes keywords such as "subordinate" and "communication."

[1331] 2. The emotion engine identifies the emotion of "being troubled."

[1332] 3. The generative AI references data on "effective communication methods with subordinates" and generates specific solutions. For example, it generates advice such as "Make an effort to actively listen."

[1333] 4. The server then takes into account the user's emotional state and formats the response in a reassuring way, for example, by displaying a message such as, "To solve your problem, let's start by actively listening."

[1334] This allows the system of the present invention to provide personalized, highly accurate coaching that takes into account the user's emotions, and to provide continuous support until the user is satisfied.

[1335] The processing flow will be explained below.

[1336] Step 1:

[1337] The user enters their concerns or questions into the input field on the device and presses the send button. For example, they enter, "I'm worried about my career path. Please tell me how I should proceed," and then presses the send button.

[1338] Step 2:

[1339] The terminal sends the consultation details entered by the user to the server as an HTTP request.

[1340] Step 3:

[1341] The server receives the HTTP request and analyzes the request content. Specifically, the text is passed to a natural language processing (NLP) module for preprocessing such as tokenization, stop word removal, and stemming.

[1342] Step 4:

[1343] The server extracts important keywords and context from the analyzed text data. For example, it identifies the keywords "career path" and "worries."

[1344] Step 5:

[1345] The server passes the extracted keywords to an emotion engine to analyze the user's emotions, for example, detecting whether the text contains the word "anxiety."

[1346] Step 6:

[1347] The emotion engine analyzes the text and classifies the user's emotional state, for example into emotion categories such as "anxiety," "excitement," and "anger."

[1348] Step 7:

[1349] The server optimizes the AI's response based on the user's emotional state. For example, if the user is feeling anxious, it will select reassuring language.

[1350] Step 8:

[1351] The server activates the appropriate generative AI model and generates the optimal answer to the user's inquiry, taking into account the results of the emotion engine. For example, it generates "specific advice on career paths" such as "joining a new project" or "training to improve skills."

[1352] Step 9:

[1353] The server formats the generated answers and summarizes them in an easy-to-read format. Reassuring language is added to reflect the emotional state. For example, "Your career path includes the following options: 1. Join a new project within your department. 2. Take training to improve your skills. 3. Talk to your manager to clarify your specific role. Rest assured, you'll see results soon."

[1354] Step 10:

[1355] The server sends the formatted answer to the user terminal as an HTTP response.

[1356] Step 11:

[1357] The device receives the HTTP response and displays it on the screen. For example, it might say, "Your career path has the following options: 1. Join a new project within your department. 2. Take training to improve your skills. 3. Talk to your manager to clarify your specific role. Don't worry, you'll see positive results soon."

[1358] Step 12:

[1359] The user can enter additional questions or feedback about the answers provided and press the submit button again. For example, they can enter "I'd like to know a more specific action plan" and press the submit button again.

[1360] Step 13:

[1361] The device sends the new input to the server as an HTTP request.

[1362] Step 14:

[1363] The server receives the request again and analyzes the new input. Specifically, it again preprocesses it using natural language processing technology to extract additional important keywords.

[1364] Step 15:

[1365] The server again uses the emotion engine to confirm the user's emotional state, for example detecting an increase in the emotion of "anxiety" based on additional input information.

[1366] Step 16:

[1367] The server passes the results of the analysis and emotion engine to the generation AI, which then generates an appropriate solution. For example, it generates a specific action plan such as, "To participate in Project A, you first need the following skill set. You can acquire these skills by participating in Training Program B."

[1368] Step 17:

[1369] The server reformats the generated details and constructs a response to send back to the user.

[1370] Step 18:

[1371] The device receives the new response and displays it on the screen. For example, it might say, "To participate in Project A, you first need the following skill set. You can acquire these skills by participating in Training Program B."

[1372] Step 19:

[1373] The server records the user's past requests and responses in a database, analyzes them periodically, and generates new insights and suggestions.

[1374] Step 20:

[1375] The server generates new insights and suggestions based on the results of periodic analysis and notifies the user.

[1376] Step 21:

[1377] The device receives notifications from the server and displays them on the screen. For example, a notification might say, "We have the latest information on the latest trends and techniques for project management, which we previously discussed."

[1378] Example 2

[1379] 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."

[1380] Conventional coaching systems have had the problem of being unable to generate personalized answers that take the user's emotions into account, which means they are unable to sufficiently increase user satisfaction. It has also been difficult to effectively utilize user feedback and provide continuous, highly accurate coaching.

[1381] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1382] In this invention, the server includes means for receiving consultation content from a user, means for analyzing the consultation content using natural language processing technology, means for identifying and classifying emotions based on the analyzed data, means for generating an answer to the consultation content using a generative AI model taking into account the emotion analysis results, means for formatting the generated answer in accordance with the user's emotional state and returning it to the user, and means for receiving feedback from the user and re-analyzing and generating an answer. This makes it possible to provide the user with personalized answers according to their emotions and provide continuous, highly accurate coaching.

[1383] The "means for receiving consultation content" is an interface for electronically collecting input information from users and processing it within the system.

[1384] "Natural language processing technology" is a technology that allows computers to understand and analyze human language, and includes processes such as tokenization and removal of stop words.

[1385] "Means for identifying and classifying emotions" refers to technology for detecting user emotions (e.g., anxiety, excitement, anger, etc.) from text data and classifying them into categories.

[1386] A "generative AI model" is an artificial intelligence technique for generating appropriate responses in natural language based on input prompts.

[1387] "Formulating" refers to a technology that converts the answers output by the generative AI model into the optimal format based on the user's emotions and situation.

[1388] The "means for receiving feedback" is an interface for collecting information and opinions re-entered from the user and using them to analyze the next step and generate answers.

[1389] "Multiple data sources" is a general term for various databases and information sources that are referenced to respond to the user's inquiry.

[1390] "Means of providing new insights and suggestions" refers to technology that analyzes past data, generates new knowledge and action plans, and proposes them to users.

[1391] The system of the present invention is designed to combine a generative AI model and an emotion engine to provide highly accurate coaching. This system is mainly composed of a user terminal, a server, a database, and an emotion engine. Specifically, it includes the following functions and processes:

[1392] Input and transmission from the user terminal

[1393] The user inputs the details of the coaching they would like to receive from their device and sends a request. Specifically, the user interface includes a text box where they can type, "I'm having trouble deciding on my career path. Can you tell me how I should proceed?" and then press the send button. The user device can be a smartphone, tablet, or computer.

[1394] Server receives and analyzes the request

[1395] The server receives the request sent by the user as an HTTP request and analyzes its contents. The received text data is passed to a natural language processing (NLP) module. For example, the NLP module performs preprocessing such as tokenizing the text, removing stop words, and stemming. This makes it possible to extract important keywords and context. For example, the keywords "career path" and "worries" are identified.

[1396] Activating the Emotion Engine

[1397] The server passes the analyzed text data to an emotion engine, which analyzes the user's emotions. The emotion engine identifies emotions contained in the text and classifies them into emotion categories such as "anxiety," "excitement," and "anger." As a specific example, it identifies the emotion "anxiety" from the phrase "I'm worried."

[1398] Starting the generative AI and generating answers

[1399] The server activates the generative AI model, taking into account the analysis results of the emotion engine, to generate the optimal answer to the user's inquiry. As a specific example of a prompt sentence, "Please give me some advice on my career path," is entered, and the generative AI model generates specific options such as "join a new project" and "take training to improve my skills." An existing large-scale language model (LLM) is used as the generative AI model.

[1400] Formatting and returning answers

[1401] The server formats the generated answer and constructs a response to send back to the user. This response is formatted in a way that reflects the user's emotional state. For example, if the user is feeling "anxious," it uses language that makes them feel more reassured. A specific example of a formatted answer would be, "Your career path has the following options: 1. Join a new project within your department. 2. Take training to improve your skills. 3. Talk to your manager to clarify your specific role."

[1402] Display on user terminal

[1403] The user device receives the HTTP response and displays it on the screen. For example, it displays "Your career path has the following options..."

[1404] User Feedback and Resend

[1405] The user can enter additional questions or feedback about the answers provided and submit the request again. For example, the user can enter "I would like to know a more specific action plan" in the text box and press the submit button again.

[1406] Providing new insights

[1407] The server records the user's past requests and responses in a database and periodically analyzes them to generate new insights and suggestions. As a specific example, past data in the database is analyzed to extract the "latest information about project management." Based on the results of the periodic analysis, new insights and suggestions are generated and notified. The user's device receives notifications from the server and displays them on the screen. For example, a notification may appear saying, "We have the latest information on recent trends and methods for project management, which you previously consulted about."

[1408] The system allows users to receive truly personalized and highly accurate coaching, which significantly increases user satisfaction.

[1409] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1410] Step 1:

[1411] The user inputs the desired coaching information from the device and makes a request to send it. The input information is "I'm worried about my career path. Please tell me how I should proceed" and is entered into the text box on the device, and the user presses the send button. The input data is sent to the server in JSON format.

[1412] Step 2:

[1413] The server receives this request. The received data is processed as an HTTP request. The server first parses the input data and extracts text data. The extracted text data is then passed to a natural language processing (NLP) module. Specific operations include preprocessing such as tokenization, stop word removal, and even stemming. The input is raw text data from the user, and the output is preprocessed text data.

[1414] Step 3:

[1415] The server analyzes the preprocessed text data and extracts important keywords and contexts. For example, it identifies the keywords "career path" and "worries." The input is the preprocessed text data, and the output is a list of extracted keywords. This operation allows the server to understand the meaning of the input data and identify important related elements.

[1416] Step 4:

[1417] The server passes the extracted text data to an emotion engine, which analyzes the user's emotions. The emotion engine identifies emotions contained in the text and classifies them into emotion categories such as anxiety, excitement, and anger. For example, it identifies the emotion "anxiety" from the phrase "I'm worried." The input is a list of extracted keywords, and the output is a list of emotion categories.

[1418] Step 5:

[1419] The server takes into account the analysis results of the emotion engine and passes the input prompt to the generative AI model. The specific prompt sentence is "Please give me some advice on my career path." The generative AI model generates the optimal answer based on the prompt. For example, it outputs options such as "join a new project" or "take training to improve your skills." The input is the prompt sentence, and the output is the generated list of advice.

[1420] Step 6:

[1421] The server formats the generated answer, converting it into a reassuring expression that reflects the user's emotional state. For example, it might format it as, "Your career path has the following options: 1. Join a new project within your department. 2. Take training to improve your skills. 3. Talk to your manager to clarify your specific role." The input is a list of advice from the generative AI model, and the output is the formatted answer.

[1422] Step 7:

[1423] The server sends the formatted answer to the user's terminal as an HTTP response. The sent data is in JSON format and is constructed in a form suitable for the display format of the user's terminal. The input is the formatted answer, and the output is an HTTP response.

[1424] Step 8:

[1425] The user device receives the HTTP response and displays it on the screen. For example, it displays "Your career path has the following options..." The input is the HTTP response from the server, and the output is the screen display in a format that the user can view.

[1426] Step 9:

[1427] The user enters additional questions or feedback about the provided answers and makes a request again. For example, the user enters "I would like to know a more specific action plan" in the text box and presses the submit button again. The input data is again sent to the server in JSON format.

[1428] Step 10:

[1429] The server receives the new feedback and repeats the steps of preprocessing, analysis, sentiment analysis, use of the generative AI model, answer formatting, and sending. For example, it provides a specific action plan such as, "To participate in Project A, you first need the following skill set. You can acquire these skills by participating in Training Program B." The input is new feedback from the user, and the output is a regenerated specific action plan.

[1430] (Application example 2)

[1431] 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."

[1432] Conventional coaching systems struggle to provide appropriate advice and solutions to users' concerns. Furthermore, they fail to properly consider the user's emotional state, making it impossible to provide personalized support that satisfies the user. Furthermore, they often fail to provide relevant content, resulting in a lack of practical support for users in solving their problems.

[1433] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving the content of the consultation from the user, means for analyzing the content of the consultation using natural language processing technology, means for generating an answer to the consultation content using a generation AI based on the analyzed data, means for returning content related to the generated answer to the user, and means for receiving feedback from the user and performing further analysis and generation. This makes it possible to provide personalized and practical coaching advice and related content while taking the user's emotional state into consideration.

[1434] The "means for receiving consultation contents from the user" is an interface for transmitting consultation contents input by the user through the terminal to the server.

[1435] "Means of analysis using natural language processing technology" refers to technology that performs preprocessing such as tokenizing received text data, removing stop words, and stemming.

[1436] "Means of using generative AI to generate answers to inquiries" refers to technology that uses a generative AI model to generate optimal answers based on data analyzed using natural language processing technology.

[1437] The "means for returning content related to the generated answer to the user" is an interface for returning content such as videos, articles, exercises, etc. related to the generated answer to the user.

[1438] "Means for receiving feedback from users and re-analyzing and re-generating" refers to technology that re-analyzes the feedback provided by the user using natural language processing technology and a generative AI model, and re-generates the optimal answer.

[1439] "Means for recording the content of users' past consultations, periodically analyzing it, and providing new insights and suggestions" refers to a technology that stores users' past consultation history in a database, periodically analyzes it, and generates new suggestions.

[1440] "Means of referencing multiple data sources to generate optimal solutions and related content" refers to technology that refers to multiple information sources depending on the content of the consultation and generates optimal advice and related content.

[1441] This system receives inquiries from users, generates optimal answers using natural language processing and generative AI technologies, and provides them to users along with related content. This system is primarily composed of a user terminal, a server, a database, and an emotion engine.

[1442] First, we will explain input and transmission from the user terminal. The user inputs the content of their consultation through a smartphone app and sends it to the server. For example, they might input a question such as, "I've been feeling stressed lately and I don't know what to do." The input data is sent to the server as an HTTP request.

[1443] Next, we will explain the processing on the server. The server analyzes the received text data using natural language processing technology. This analysis includes preprocessing such as tokenization, stop word removal, and stemming. Natural language processing technologies used include spaCy and NLTK.

[1444] Important keywords are extracted from the analyzed data and passed to the emotion engine, which identifies the emotions contained in the text and classifies them into emotion categories such as "anxiety" or "stress." The emotion analysis engine used is IBM Watson Tone Analyzer.

[1445] Next, a generative AI model is used based on the analysis results to generate the optimal answer to the user's inquiry. OpenAI GPT-3 and other models are used as generative AI models. For example, if the user's inquiry is "Please tell me how to relieve stress," the generative AI model will generate an answer such as "Light exercise and meditation every day are effective for relieving stress."

[1446] The generated answer is then returned to the user along with related content (videos, articles, exercises, etc.) For example, the answer may include a link to a video or article that explains a specific relaxation technique, providing the user with the resources to take specific steps.

[1447] Furthermore, the system can receive user feedback and perform further analysis and generate answers. For example, if a user sends feedback such as "I would like to know a more specific action plan," the server will again use NLP and generative AI models to provide a more detailed action plan.

[1448] To illustrate, here are some example prompts:

[1449] "User Question: "I've been feeling stressed lately and I don't know what to do." Emotion: Anxiety, Stress Generate an answer."

[1450] This system can provide personalized and practical coaching advice and related content that takes into account the user's emotional state, thereby supporting users in solving their problems more efficiently.

[1451] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1452] Step 1:

[1453] User input: The user inputs and submits the content of their problem through the smartphone app. For example, they might type, "I've been feeling stressed lately and I don't know what to do." The input is formatted as an HTTP request and sent to the server.

[1454] Step 2:

[1455] Server reception: The server receives the HTTP request from the user and extracts the text data. The input at this stage is the text of the user's consultation, and the output is this text data itself.

[1456] Step 3:

[1457] Natural Language Processing (NLP): The server analyzes the received text data using natural language processing techniques. Specifically, preprocessing such as tokenization (dividing the text into words and phrases), stop word removal (removing meaningless common words), and stemming (converting words to their base forms) is performed. The input is raw text data, and the output is preprocessed text data.

[1458] Step 4:

[1459] Keyword extraction: The server extracts important keywords from the preprocessed text data. For example, it identifies the keywords "stress" and "relief methods." The input at this stage is the preprocessed text data, and the output is a list of important keywords.

[1460] Step 5:

[1461] Sentiment analysis: The server passes the extracted keywords to the emotion engine to analyze the user's emotions. The emotion engine identifies emotions contained in the text and classifies them into emotion categories such as "anxiety" or "stress." The input is a list of keywords, and the output is a list of emotion categories.

[1462] Step 6:

[1463] Answer generation: The server uses a generative AI model based on the results of sentiment analysis to generate the optimal answer to the user's inquiry. For example, it generates an answer such as "Daily light exercise and meditation are effective for relieving stress." The input is a list of keywords and a list of sentiment categories, and the output is the generated answer text.

[1464] Step 7:

[1465] Content recommendation: The server identifies content (videos, articles, exercises, etc.) related to the generated answer and constructs a response to serve to the user. The input is the answer text, and the output is a response containing the answer text and links to the related content.

[1466] Step 8:

[1467] Response transmission: The server transmits the constructed response to the user terminal as an HTTP response. The input is the response data, and the output is the transmission status to the user terminal.

[1468] Step 9:

[1469] User display: The user device analyzes the HTTP response received from the server and displays it on the screen. For example, it might say, "Light exercise and meditation every day are effective for relieving stress. Try practicing with this video as a reference." The input is the HTTP response data, and the output is the text displayed to the user and a link to related content.

[1470] 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.

[1471] 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.

[1472] 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.

[1473] 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.

[1474] 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.

[1475] 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.

[1476] 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).

[1477] 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.

[1478] 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."

[1479] 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.

[1480] 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).

[1481] 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.

[1482] 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.

[1483] 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.

[1484] 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.

[1485] 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.

[1486] 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.

[1487] 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.

[1488] 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.

[1489] 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.

[1490] 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.

[1491] The following is further disclosed regarding the above embodiment.

[1492] (Claim 1)

[1493] A means for receiving consultation content from a user;

[1494] A means for analyzing the content of the consultation using natural language processing technology;

[1495] A means for generating answers to inquiries using a generation AI based on the analyzed data; and

[1496] means for returning the generated answer to the user;

[1497] A means for receiving feedback from users and re-analyzing and generating;

[1498] A system including:

[1499] (Claim 2)

[1500] 2. The system according to claim 1, further comprising means for recording the content of a user's past consultations, periodically analyzing the content, and providing new insights and suggestions.

[1501] (Claim 3)

[1502] 2. The system according to claim 1, further comprising means for referencing a plurality of data sources corresponding to the consultation content and generating an optimal solution.

[1503] "Example 1"

[1504] (Claim 1)

[1505] A means for receiving consultation content from a user;

[1506] A means for analyzing the content of the consultation using natural language processing technology;

[1507] A means for generating answers to inquiries using a generation AI based on the analyzed data; and

[1508] means for returning the generated answer to the user;

[1509] A means for receiving feedback from users and re-analyzing and generating;

[1510] A means to propose specific options and action plans regarding the consultation content, and

[1511] A system including:

[1512] (Claim 2)

[1513] 2. The system according to claim 1, further comprising means for recording the content of a user's past consultations, periodically analyzing the content, and providing new insights and suggestions.

[1514] (Claim 3)

[1515] 2. The system according to claim 1, further comprising means for referencing a plurality of information sources corresponding to the consultation content and generating an optimal solution.

[1516] "Application Example 1"

[1517] (Claim 1)

[1518] A means for receiving consultation content from a user;

[1519] A means for analyzing the content of the consultation using natural language processing technology;

[1520] A means for generating answers to inquiries using a generation AI based on the analyzed data; and

[1521] means for returning the generated answer to the user;

[1522] A means for receiving feedback from users and re-analyzing and generating;

[1523] A means for using the analyzed and generated data to improve the skills of store staff;

[1524] A system including:

[1525] (Claim 2)

[1526] 2. The system according to claim 1, further comprising means for recording the content of a user's past consultations, periodically analyzing the content, and providing new insights and suggestions.

[1527] (Claim 3)

[1528] 2. The system according to claim 1, further comprising means for referencing a plurality of data sources corresponding to the consultation content and generating an optimal solution.

[1529] "Example 2: Combining Emotion Engines"

[1530] (Claim 1)

[1531] A means for receiving consultation content from a user;

[1532] A means for analyzing the content of the consultation using natural language processing technology;

[1533] means for identifying and classifying emotions based on the analyzed data; and

[1534] A means for generating an answer to the consultation content using a generative AI model taking into account the results of the sentiment analysis;

[1535] means for adapting the generated answer to the user's emotional state and returning the answer to the user;

[1536] A means for receiving feedback from users and re-analyzing and generating;

[1537] A system including:

[1538] (Claim 2)

[1539] 2. The system according to claim 1, further comprising means for recording the content of a user's past consultations, periodically analyzing the content, and providing new insights and suggestions.

[1540] (Claim 3)

[1541] 2. The system according to claim 1, further comprising means for referencing a plurality of data sources corresponding to the consultation content and generating an optimal solution.

[1542] "Application example 2 when combining emotion engines"

[1543] (Claim 1)

[1544] A means for receiving consultation content from a user;

[1545] A means for analyzing the content of the consultation using natural language processing technology;

[1546] A means for generating answers to inquiries using a generation AI based on the analyzed data; and

[1547] means for returning generated answers and associated content to the user;

[1548] A means for receiving feedback from users and re-analyzing and generating;

[1549] A system including:

[1550] (Claim 2)

[1551] 2. The system according to claim 1, further comprising means for recording the content of a user's past consultations, periodically analyzing the content, and providing new insights and suggestions.

[1552] (Claim 3)

[1553] The system according to claim 1, further comprising means for referencing multiple data sources corresponding to the consultation content and generating optimal solutions and related content. [Explanation of symbols]

[1554] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for receiving consultation content from a user; A means for analyzing the content of the consultation using natural language processing technology; A means for generating answers to inquiries using a generation AI based on the analyzed data; and means for returning the generated answer to the user; A means for receiving feedback from users and re-analyzing and generating; A system including:

2. 2. The system according to claim 1, further comprising means for recording the contents of past consultations of the user, periodically analyzing the contents, and providing new insights and suggestions.

3. The system according to claim 1 , further comprising means for referencing a plurality of data sources corresponding to the consultation content and generating an optimal solution.

Images