System

Abstract

A system is provided.SOLUTION: The system includes a means for receiving a question input from a user terminal, a means for delivering the question content to a natural language processing engine and analyzing it, a means for acquiring related information from a database on the basis of an analysis result, and a means for generating an answer on the basis of the acquired information and transmitting it to the user terminal.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In tennis and other sports, junior players aiming to become professional players face difficulties in forming a concrete career image, and there are problems with not being able to obtain appropriate information due to the area of ​​residence and information asymmetry. Furthermore, talented junior players are at risk of not being able to find the optimal development course due to a lack of information, and the path to becoming a professional player is closed. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for receiving a question entered from a user terminal, a means for passing the question content to a natural language processing engine for analysis, a means for retrieving related information from a database based on the analysis results, and a means for generating an answer based on the retrieved information and transmitting it to the user terminal. The system also includes a means for retrieving information from a database that stores the experiences of top professionals, professionals who tried but failed, and agents in response to the question content. The system also includes a means for receiving user profile information and selecting an AI model to provide information most suited to the user's characteristics. This system makes it easier for junior players and their parents to obtain information to create specific and realistic career plans, regardless of location or information asymmetry.

[0006] "User terminal" refers to a device, typically a computer or smartphone, that a junior athlete or their guardian accesses to enter questions and receive responses.

[0007] "Questions" refer to text information entered in natural language by junior players and their parents regarding their careers as they aim to become professional players.

[0008] A "natural language processing engine" refers to a software module that analyzes input natural language text and extracts keywords and context.

[0009] "Analysis results" refers to the keywords, context, and related information extracted by the natural language processing engine.

[0010] "Database" refers to data storage that contains information such as top professionals, professionals who tried but failed to reach the top, and agent experiences.

[0011] A "generative AI model" refers to artificial intelligence that generates appropriate answers to user questions based on information obtained from a database.

[0012] "Answer" refers to the answer text generated by the generative AI model and sent to the user device.

[0013] "Profile information" refers to personal information registered by a user, such as their age, years of experience, and current rank.

[0014] "Top professional" refers to a professional athlete who is active and successful on a global scale.

[0015] "Professionals who tried but failed to reach the top" refers to professional athletes who aimed to reach the world level but did not reach the top professional level.

[0016] An "agent" is a professional who supports the activities of professional athletes and provides advice on career plans, contracts, etc. [Brief explanation of the drawings]

[0017] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0018] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0020] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0021] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0022] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0023] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0025] [First embodiment]

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

[0027] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0028] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0030] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0034] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0035] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0037] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0038] This invention relates to a system that uses a generative AI model to provide specific career counseling to junior athletes. The system's main components are a user terminal, a central server, and a database. Users can use this system to obtain specific career plans and realistic information for those aiming to become professional athletes.

[0039] System Overview

[0040] User terminal

[0041] The user terminal is a device used by junior athletes and their guardians to input questions and receive answers. Typically, a smartphone or computer is used. Questions input from the user terminal are sent to a central server via the Internet.

[0042] Central Server

[0043] The central server plays a central role in analyzing incoming questions and generating appropriate answers. The server is equipped with a natural language processing engine and generative AI models, which work together to create answers to users' questions.

[0044] Database

[0045] The database contains information such as the experiences of professional players, stories of players who tried but failed, advice from agents, etc. Appropriate information is searched from this database and used to generate answers for the generative AI model.

[0046] Program processing

[0047] Receiving questions

[0048] A question sent from a user terminal is received by a central server, which first passes the question to a natural language processing engine to begin analysis.

[0049] Natural Language Processing and Analysis

[0050] The server's natural language processing engine analyzes the incoming question and extracts important keywords and context, and the results of this analysis are passed to a generative AI model.

[0051] Searching the database

[0052] The generative AI model then generates queries based on the analysis results, which retrieve relevant information from the database (such as the experiences of professional players or advice from agents).

[0053] Generate answers

[0054] Based on the acquired information, the generative AI model generates an appropriate answer to the user's question, which is then sent back to the user's device.

[0055] Specific examples

[0056] For example, if a user enters the question, "What are the benefits of going to college after graduating from high school to become a professional tennis player?", the question is first sent to the server. The natural language processing engine on the server extracts the keywords "professional tennis player," "high school graduation," "going to college," and "benefits." Next, the generative AI model searches a database based on these keywords to obtain information on cases of players who have succeeded as professionals after going to college and the benefits of going to college. Finally, the generative AI model generates an answer such as, "There are several cases of players who have succeeded as professionals after going to college, and it is beneficial for some players because it allows them to balance their studies with a shared training environment," and sends this to the user's device.

[0057] In this way, the present invention enables junior athletes and their guardians to easily draw up specific and realistic career plans, independent of location and information asymmetry.

[0058] The processing flow will be explained below.

[0059] Step 1:

[0060] Enter a question from the user's device. The user launches the career consultation app and enters the question in the text box. Once the question is complete, the user clicks the send button.

[0061] Step 2:

[0062] The user terminal sends the question to the central server. Once the user has completed the input, the question is sent to the central server via the Internet.

[0063] Step 3:

[0064] The server receives the questions. The central server receives the questions sent from the user terminals and passes the data to the text analysis module.

[0065] Step 4:

[0066] The server passes the question to a natural language processing engine for analysis. The text analysis module sends the question to the natural language processing engine, which analyzes the question and extracts keywords and context.

[0067] Step 5:

[0068] The server passes the analysis results to the generative AI model, and the analysis results obtained from the natural language processing engine are fed back to the generative AI model.

[0069] Step 6:

[0070] The server generates and sends a query to the database. The generative AI model generates a query to obtain the necessary information based on the analysis results and sends it to the database.

[0071] Step 7:

[0072] The database returns relevant information. Based on the query, the database searches for relevant information (experiences of professional players, stories of professional challenges, advice from agents, etc.) and returns this to the central server.

[0073] Step 8:

[0074] The server generates an answer based on the information it obtains. The generative AI model analyzes the information received from the database and generates an appropriate answer to the user's question.

[0075] Step 9:

[0076] The server transmits the generated answer to the user terminal, and performs communication to transmit the generated answer to the user terminal.

[0077] Step 10:

[0078] The user terminal displays the answer. The user terminal displays the answer received from the central server so that the user can confirm it. The user can confirm the displayed answer and enter the question again if necessary.

[0079] Through this series of processes, the system can provide quick and appropriate answers to users' questions.

[0080] Example 1

[0081] 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."

[0082] Traditional career counseling systems make it difficult for junior athletes and their guardians to obtain the information they need to draw up specific and realistic career plans. In particular, there is a lack of concrete advice based on experience and a path to becoming a professional athlete, making it difficult to obtain sufficient information when formulating a specific career plan.

[0083] 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.

[0084] In this invention, the server includes means for receiving a question input from a user terminal, means for passing the question content to a natural language processing engine for analysis, means for retrieving related information from a database based on the analysis results, and means for generating an answer based on the retrieved information and transmitting it to the user terminal. This enables junior players and their parents to easily draw up specific and realistic career plans based on the experiences of professional players and agents.

[0085] A "user device" is an electronic device such as a computer or smartphone that junior athletes and their parents use to enter questions and check answers.

[0086] A "question" is a question that a user inputs to obtain specific information about their career plan or how to become a professional athlete.

[0087] A "server" is a central computer system that receives questions sent from user terminals, analyzes them, generates appropriate answers, and sends them to the user terminals.

[0088] A "natural language processing engine" is a software component that analyzes the content of questions from users and extracts keywords and context.

[0089] A "database" is a collection of information that stores relevant information such as the experiences of professional athletes and advice from agents.

[0090] A "generative AI model" is an algorithm that generates appropriate answers to user questions using information obtained from a database based on the results analyzed by a natural language processing engine.

[0091] A "query" is a specific search condition or instruction that a generative AI model generates to search a database based on the analysis results.

[0092] An "answer" is the specific information or advice that the generative AI model generates in response to a user's question and sends to the user's device.

[0093] "Profile information" is personal data that is useful for career counseling, such as the user's age, type of sport, and goals.

[0094] "Selection" refers to the act of choosing the most suitable generative AI model based on the user's profile information and questions.

[0095] This invention relates to a system that uses a generative AI model to provide specific career counseling for junior athletes. The system's main components are a user terminal, a central server, and a database.

[0096] User terminal

[0097] The user terminal is a device used by junior athletes and their parents to input questions and receive answers. Typically, a smartphone or computer is used. Questions input from the user terminal are sent to a central server via the Internet.

[0098] Central Server

[0099] The central server plays a central role in analyzing incoming questions and generating appropriate answers. The server is equipped with a natural language processing engine and generative AI models, which work together to create answers to users' questions.

[0100] Database

[0101] The database contains information such as the experiences of professional players, stories of players who tried but failed, advice from agents, etc. Appropriate information is searched from this database and used to generate answers for the generative AI model.

[0102] Program processing

[0103] A question sent from a user device is first received by a central server. The server then passes the question to a natural language processing engine to begin analysis. The natural language processing engine in the server analyzes the received question and extracts important keywords and context. The results of this analysis are then passed to a generative AI model.

[0104] The generative AI model generates a query to the database based on the analysis results. Based on this query, relevant information (for example, the experiences of professional athletes or advice from agents) is retrieved from the database. Based on the retrieved information, the generative AI model generates an appropriate answer to the user's question. The generated answer is then sent back to the user's device.

[0105] Usage example

[0106] For example, if a user enters the question, "What are the benefits of going to college after graduating from high school to become a professional tennis player?", the question is first sent to the server. The natural language processing engine on the server extracts the keywords "professional tennis player," "high school graduation," "going to college," and "benefits." Next, the generative AI model searches a database based on these keywords to obtain information on cases of players who have succeeded as professionals after going to college and the benefits of going to college. Finally, the generative AI model generates an answer such as, "There are several cases of players who have succeeded as professionals after going to college, and it is beneficial for some players because it allows them to share a training environment and balance their studies," and sends this to the user's device.

[0107] In this way, the present invention allows junior athletes and their guardians to easily create specific and realistic career plans, regardless of location or information asymmetry. It is also possible to select the optimal generative AI model based on the user's profile information to provide information that best suits the user's characteristics.

[0108] Prompt Sentence Examples

[0109] "What is the best career plan for becoming a professional basketball player?"

[0110] "Is it better to aim to become a professional immediately after graduating from high school or to go to college and then aim to do so?"

[0111] Please tell me how to choose an agent.

[0112] "What kind of training did successful professional athletes do?"

[0113] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0114] Step 1:

[0115] A user terminal inputs a question from the user.

[0116] Input: The user inputs characters and enters the question.

[0117] What happens: A user types the question "What are the benefits of going to college after high school to become a professional tennis player?" into a text input field on their smartphone or computer.

[0118] Step 2:

[0119] A user terminal sends a query to a central server.

[0120] Input: The question typed by the user.

[0121] Specific operation: The device sends the question to a central server via the Internet.

[0122] Output: The query is received by the central server.

[0123] Step 3:

[0124] The server passes the question to a natural language processing engine and begins analysis.

[0125] Input: The query received by the central server.

[0126] How it works: The server passes the question to a natural language processing engine, which extracts important keywords such as "professional tennis player," "high school graduation," "college enrollment," and "merits."

[0127] Output: Parsed keywords and context information.

[0128] Step 4:

[0129] The server generates a query based on the analysis results and searches the database.

[0130] Input: Analysis results (keywords and context information) from the natural language processing engine.

[0131] Specific operation: The generative AI model generates a specific search query for the database based on the analysis results. For example, it generates a query such as "professional tennis player, high school graduate, college admission, merits."

[0132] Output: Relevant information retrieved from the database (e.g., professional player experiences, agent advice, etc.).

[0133] Step 5:

[0134] The server generates a response based on the information it has obtained.

[0135] Input: Relevant information retrieved from the database.

[0136] Specific operation: Based on the information acquired by the generative AI model, it generates an appropriate answer to the user's question. For example, it generates an answer such as, "There are several examples of players who have successfully become professionals after attending university, and it is beneficial for some players because it allows them to balance their studies with a shared training environment."

[0137] Output: The generated answer.

[0138] Step 6:

[0139] The server generates a response and sends it to the user terminal.

[0140] Input: The generated answer text.

[0141] Specific operation: The server sends the response to the user terminal.

[0142] Output: The answer text displayed on the user's terminal.

[0143] Step 7:

[0144] The user reviews the answer and decides on the next action.

[0145] Input: The answer displayed on the user's terminal.

[0146] Specific operation: The user checks the answer displayed on the device. For example, they may decide, "Now that I understand the benefits of going to college, I'll consider that path."

[0147] Output: The user's new understanding or next action.

[0148] (Application example 1)

[0149] 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."

[0150] It is difficult for junior players and their guardians to obtain real-time information on specific career plans for those aiming to become professional players. Furthermore, there is no way to easily input questions in-store and receive appropriate answers on the spot, which reduces the efficiency of career counseling. This makes it difficult to obtain the necessary information at the right time, potentially resulting in delays in career development.

[0151] 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.

[0152] In this invention, the server includes means for receiving a question input from a user terminal, means for passing the content of the question to a natural language processing engine for analysis, means for retrieving related information from a database based on the analysis results, means for generating an answer based on the retrieved related information and transmitting it to the user terminal, and means for inputting a question using a smart terminal in the store and retrieving the answer in real time, thereby enabling junior athletes and their guardians to easily receive career counseling in the store and obtain prompt and appropriate information.

[0153] A "user terminal" is a device used by a user to input questions and receive answers, and refers to an electronic device such as a smartphone or computer.

[0154] The term "means for receiving a question" refers to a function for transmitting a question input from a user terminal to a server and receiving the question.

[0155] A "natural language processing engine" refers to technology that analyzes input questions and extracts important keywords and context.

[0156] "Means of analysis" refers to the process of passing the question content to a natural language processing engine for analysis.

[0157] "Relevant information" refers to information in the database that is necessary to generate an appropriate answer to a user's question.

[0158] "Database" refers to a collection of data containing information such as the experiences of professionals, challengers, and intermediaries.

[0159] "Means for obtaining" refers to the function for searching and obtaining related information from a database based on the analysis results.

[0160] "Means for generating an answer" refers to the process for creating an appropriate answer to a user's question based on the relevant information obtained.

[0161] "Means for obtaining information in real time" refers to a function for quickly generating and providing answers on the spot to questions entered by users in the store.

[0162] "In-store" refers to physical locations visited by junior athletes and their parents, such as sporting goods stores and sports clubs.

[0163] This invention relates to a system that allows junior athletes and their guardians to obtain specific career plans and information for becoming professional athletes in real time within sporting goods stores and sports clubs. The system's main components are a user terminal, a central server, and a database, and it operates as follows:

[0164] First, the user terminal is a device that junior players and their guardians use to input questions and receive answers. Common electronic devices such as smartphones, tablets, and laptops can be used as user terminals. This allows users to easily access the system within the store.

[0165] Next, when a question is entered from the user's device, it is sent via the Internet to a central server. The central server receives the question and first analyzes it using a natural language processing engine. For example, Python's openai library is used as the natural language processing engine. The content of the question is analyzed, and important keywords and context are extracted.

[0166] Based on the analysis results, the central server generates a query to a database to search for relevant information. The database contains the experiences and advice of professionals, challengers, and intermediaries, and appropriate information is retrieved from this database. Based on the retrieved information, a generative AI model generates an appropriate answer to the user's question. For example, the OpenAI API is used as the generative AI model.

[0167] The generated answer is then sent back to the user's device, allowing the user to receive the answer in real time. This series of processes allows users to easily receive career advice in-store and quickly obtain useful information.

[0168] As a specific example, if a user enters the question, "What are the benefits of going to college after graduating from high school to become a professional tennis player?", the question is sent to a central server, and the natural language processing engine extracts the keywords "professional tennis player," "high school graduation," "going to college," and "benefits." Next, the generative AI model searches a database based on these keywords to obtain information on cases of players who have succeeded as professionals after going to college and the benefits of going to college. Finally, the generative AI model generates an answer such as, "There are several cases of players who have succeeded as professionals after going to college, and it is beneficial for some players because it allows them to share a training environment and balance their studies," and sends this to the user's device.

[0169] In this way, the present invention allows junior athletes and their guardians to create specific and realistic career plans in real time within the store.

[0170] An example prompt is:

[0171] Question: What are the benefits of going to college after high school to become a professional tennis player?

[0172] Extract keywords: professional tennis player, high school graduation, college admission, benefits

[0173] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0174] Step 1:

[0175] The user's device inputs a question and sends it to a central server. The user inputs a question on a smartphone or tablet, and the input text data is sent to the server via an HTTP request or similar. The input is in text format, and the user's specific question is sent as text. The output is the question text.

[0176] Step 2:

[0177] The server passes the received question to a natural language processing engine for analysis. Specifically, the server uses the Python openai library to analyze the question and extract important keywords and context. The input is the question text submitted by the user, and the output is a list of extracted keywords.

[0178] Step 3:

[0179] The server generates queries to a database based on the extracted keywords to search and retrieve relevant information. The database stores the experiences and career-related information of professionals, challengers, and intermediaries. The input is a list of extracted keywords, and the output is a list of related information.

[0180] Step 4:

[0181] Based on the related information acquired by the server, a generative AI model is used to generate an appropriate answer to the user's question. For example, the OpenAI API is used as the generative AI model. The input is a list of related information acquired from a database, and the output is the generated answer text.

[0182] Step 5:

[0183] The server sends the generated answer to the user's device, and the user receives the answer in real time. Specifically, the answer is sent from the server to the user's device via an HTTP response or similar and is displayed on the user's device screen. The input is the generated answer text, and the output is the answer displayed on the user's device.

[0184] This series of processes allows users to obtain specific career plans and information in real time within the store, significantly improving the efficiency of career consultations.

[0185] 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.

[0186] This invention relates to a system that uses a generative AI model to provide specific career counseling to junior athletes. The system's main components are a user terminal, a central server, a database, and an emotion engine. Users can use this system to obtain specific career plans and realistic information for those aiming to become professional athletes. Furthermore, by using the emotion engine, appropriate answers can be provided based on the user's emotions and psychological state.

[0187] System Overview

[0188] User terminal

[0189] The user terminal is a device used by junior athletes and their guardians to input questions and receive answers. Typically, a smartphone or computer is used. Questions input from the user terminal are sent to a central server via the Internet.

[0190] Central Server

[0191] The central server plays a central role in analyzing incoming questions and generating appropriate answers. The server is equipped with a natural language processing engine, an emotion engine, and a generative AI model, which work together to create answers to users' questions.

[0192] Database

[0193] The database contains information such as the experiences of professional players, stories of players who tried but failed, advice from agents, etc. Appropriate information is searched from this database and used to generate answers for the generative AI model.

[0194] Emotion Engine

[0195] The emotion engine analyzes user emotions from their questions and profile information. This engine works in conjunction with the natural language processing engine to analyze the user's emotions and psychological state, and feeds the results back to the generative AI model.

[0196] Program processing

[0197] Question reception and sentiment analysis

[0198] A question sent from a user's device is received by a central server. The server first passes the question to a natural language processing engine for analysis. An emotion engine also runs simultaneously to recognize the user's emotion from the question, thereby extracting emotional nuances and intensity.

[0199] Natural Language Processing and Analysis

[0200] The natural language processing engine on the server analyzes the received question and extracts important keywords and context. The analysis results are passed to the generative AI model. The emotion analysis results from the emotion engine are also provided to the generative AI model.

[0201] Searching the database

[0202] The generative AI model uses the analyzed keywords, context, and sentiment information to generate queries against the database, which then retrieves relevant information from the database (such as professional player experiences or agent advice).

[0203] Generate answers

[0204] Based on the acquired information and the results of sentiment analysis, the generative AI model generates an appropriate response to the user's question. The generated response adjusts tone and expression to take emotions into account, making it more relatable to the user.

[0205] Submitting and viewing answers

[0206] The generated answer is sent back to the user terminal, where it is displayed for the user to review. The user can then review the displayed answer and re-enter the question if necessary.

[0207] Specific examples

[0208] For example, if a user inputs a question such as, "I've been losing games lately and I'm feeling depressed. What should I do?", the emotion engine will recognize the emotion "depressed." This emotional information, along with the analysis results, will be provided to the generative AI model. The generative AI model will then use the analysis results to retrieve relevant database information and generate an answer containing appropriate encouragement and advice for dealing with the "depressed" feeling. This answer will then be sent to the user's device and displayed.

[0209] In this way, by combining emotion engines, it becomes possible to respond in accordance with the user's psychological state, thereby providing better support.

[0210] The processing flow will be explained below.

[0211] Step 1:

[0212] The user enters a question from their device. The user launches the career consultation app and enters the question, "I've been losing games lately and I'm feeling depressed. What should I do?" into the text box. Once the question is entered, the user clicks the send button.

[0213] Step 2:

[0214] The user terminal sends the question to the central server. Once the user has completed the input, the question is sent to the central server via the Internet.

[0215] Step 3:

[0216] The server receives the questions. The central server receives the questions sent from the user terminal and passes the data to the text analysis module and emotion engine.

[0217] Step 4:

[0218] The server passes the question to a natural language processing engine for analysis. The text analysis module sends the question, "I've been losing games lately and I'm feeling down. What should I do?" to the natural language processing engine, which analyzes the question and extracts keywords and context such as "game," "keep losing," "feelings," "depressed," and "what should I do."

[0219] Step 5:

[0220] The server passes the question to the emotion engine, which analyzes the emotion. The emotion engine analyzes the question and recognizes the emotion "depressed." This emotional information is fed back to the generative AI model.

[0221] Step 6:

[0222] The server passes the analysis results and emotional information to the generative AI model. The analysis results and emotional information obtained from the natural language processing engine and emotion engine are fed back to the generative AI model.

[0223] Step 7:

[0224] The server generates and sends a query to the database. Based on the analysis results and emotional information, the generative AI model generates a query to obtain information related to "constant losses" and "depression" and sends it to the database.

[0225] Step 8:

[0226] The database returns relevant information. Based on the query, the database searches for information such as professional player experiences (e.g., words of encouragement and advice from players who have had similar experiences) or agent advice (e.g., mental coping strategies) and sends this back to the central server.

[0227] Step 9:

[0228] The server generates an answer based on the information it obtains. The generative AI model analyzes the information received from the database and emotional information, and generates an appropriate answer to the user's question, "I've been losing games lately and I'm feeling down. What should I do?" For example, it might say, "Many professional players have had similar experiences. The important thing is to reflect on your own growth without getting caught up in the results. Professional player A also experienced similar feelings at the same time, but by reviewing his training routine, he was able to achieve better results in his next game."

[0229] Step 10:

[0230] The server transmits the generated answer to the user terminal, and performs communication to transmit the generated answer to the user terminal.

[0231] Step 11:

[0232] The user terminal displays the answer. The user terminal displays the answer received from the central server so that the user can confirm it. The user can confirm the displayed answer and enter the question again if necessary.

[0233] Through this series of processes, the system not only provides quick and appropriate answers to users' questions, but also enables support that takes into account the user's emotions.

[0234] Example 2

[0235] 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."

[0236] Conventional career counseling systems have difficulty providing appropriate answers to user questions that take into account emotions and context. In particular, when junior athletes and others seek career counseling in an emotional state, answers that are sensitive to the user's emotions are required, but conventional systems have not been able to adequately meet this demand. Furthermore, they lack the functionality to provide specific answers based on the experiences and advice of experts.

[0237] 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.

[0238] In this invention, the server includes means for receiving a question input from a user terminal, means for passing the question content to a natural language processing engine for analysis, means for analyzing the user's emotions from the analysis results using an emotion engine, means for retrieving related information from a database based on the analysis results and emotion information, and means for generating an answer based on the retrieved information and emotion information, adjusting the tone and expression, and transmitting the answer to the user terminal. This makes it possible to provide a highly empathetic answer that takes emotion and context into consideration.

[0239] "User Device" refers to the device used by junior athletes and their parents to input questions and receive answers. Smartphones and computers are commonly used.

[0240] The "Central Server" is a system that plays a central role in receiving and analyzing user questions and generating appropriate answers. It is equipped with a natural language processing engine, an emotion engine, and a generative AI model.

[0241] A "natural language processing engine" is an engine that analyzes received questions and extracts important keywords and context.

[0242] The "emotion engine" is an engine that analyzes user emotions from their questions and profile information. It works in conjunction with the natural language processing engine.

[0243] A "generative AI model" is a model that generates answers to user questions based on analysis results and sentiment analysis results.

[0244] The "database" is a data store that stores information such as the experiences of professional players, stories of players who tried but failed, and advice from agents.

[0245] "Receiving a question" is the process by which the central server receives a question sent from a user terminal.

[0246] "Question analysis" is the process in which the natural language processing engine performs morphological analysis of the question to extract important keywords and context. The emotion engine also works simultaneously to recognize emotions.

[0247] "Related information retrieval" is the process of searching and retrieving related information from a database based on the generated query.

[0248] "Answer generation" is the process in which the generative AI model creates an appropriate answer to the user's question based on the acquired information and the results of sentiment analysis.

[0249] "Tone and expression adjustment" is the process of adjusting the generated response to make it more relatable to the user's emotions and psychological state.

[0250] "Sending an answer" is the process of sending the generated answer to the user terminal.

[0251] "Displaying the answer" is the process in which the user terminal displays the answer received from the central server on the screen so that the user can check it.

[0252] This invention relates to a system that uses a generative AI model to provide specific career counseling to junior athletes. The system's main components are a user terminal, a central server, a database, and an emotion engine. Users can use this system to obtain specific career plans and realistic information for those aiming to become professional athletes. Furthermore, by using the emotion engine, appropriate answers can be provided based on the user's emotions and psychological state.

[0253] User terminal

[0254] A user terminal is a device used by junior athletes and their guardians to input questions and receive answers. Typically, a smartphone or computer is used. Specifically, users can input and submit questions through a dedicated application or web browser on the terminal. Questions input from the user terminal are transmitted to a central server via the Internet.

[0255] Central Server

[0256] The central server plays a central role in analyzing received questions and generating appropriate answers. The server is equipped with a natural language processing engine, an emotion engine, and a generative AI model, which work together to create answers to users' questions. Specifically, the server first passes the question to the natural language processing engine, which performs morphological analysis. This analysis extracts important keywords and context. The emotion engine also works simultaneously to recognize the user's emotions from the content of the question.

[0257] Database

[0258] The database contains information such as the experiences of professional players, stories of players who tried but failed, and advice from agents. Appropriate information is searched for in this database and used to generate answers for the generative AI model. For example, in response to the question, "What kind of training is required to become a professional soccer player?", relevant training menus and success stories are retrieved from the database.

[0259] Emotion Engine

[0260] The emotion engine analyzes a user's emotions from their questions and profile information. This engine works in conjunction with the natural language processing engine to analyze the user's emotions and psychological state, and feeds the results back to the generative AI model. For example, in response to the question, "I've been losing games lately and I'm feeling depressed. What should I do?" emotions such as "depression" and "anxiety" are recognized.

[0261] Generate and submit answers

[0262] The central server uses the generative AI model to generate an appropriate answer to the user's question based on the analysis results of the natural language processing engine and emotion engine. The generated answer adjusts the tone and expression to take emotion into account, making it more relatable to the user. The generated answer is then sent back to the user's device, where it is displayed on the screen. The user can then check the displayed answer and enter a new question if necessary.

[0263] Specific examples

[0264] For example, if a user enters a question such as, "I've been losing games lately and I'm feeling down. What should I do?", the question is sent from the user's device to the central server. The server receives the question and analyzes it using a natural language processing engine and an emotion engine. As a result of the analysis, the emotion "down" is recognized. Next, the generative AI model retrieves relevant information from the database based on the analysis results and generates an answer such as, "Losing is part of the experience. Let's work hard together to achieve better results next time!" This answer is sent to the user's device and displayed. The user can review the answer and ask the question again if necessary.

[0265] Prompt Sentence Examples

[0266] "I've been losing a lot of games lately and I'm feeling down. What should I do?"

[0267] "I want to be a professional soccer player. What kind of training do I need?"

[0268] The present invention allows users to receive specific and empathetic answers that are tailored to their own situations and feelings, enabling better career counseling.

[0269] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0270] Step 1:

[0271] The user uses a terminal to input a question. For example, they might input something like, "I've been losing games lately and I'm feeling depressed. What should I do?" The input question is sent to a central server via the Internet. The input data is sent to the server in text format.

[0272] Step 2:

[0273] The central server receives questions sent from user devices. The server temporarily stores the received questions and passes them to a natural language processing engine. The input data is the user's question text, and the output is data for analysis.

[0274] Step 3:

[0275] The server's natural language processing engine analyzes the received question. Morphological analysis is performed to extract important keywords and context from the question. For example, keywords such as "game," "keep losing," "feelings," and "depressed" are extracted from the question. The input data is the user's question text, and the output is keywords and context information.

[0276] Step 4:

[0277] The server's emotion engine analyzes the user's emotions from the question. Based on the analysis results of the natural language processing engine, the emotional nuances contained in the question are analyzed. For example, the emotion "depressed" is recognized. The input data is the analyzed keywords and text, and the output is emotional information such as "depressed."

[0278] Step 5:

[0279] The server uses a generative AI model to generate queries to the database based on the analysis results of the natural language processing engine and emotion engine. For example, based on information such as "feeling depressed" or "continuously losing games," it creates a query to retrieve related database information. The input data is the analysis results and emotion information, and the output is a database query.

[0280] Step 6:

[0281] The server uses the generated query to search a database that contains information such as the experiences of professional athletes, advice from agents, and training menus. The search results include information on related training content and past success stories. The input data is the query, and the output is the search results.

[0282] Step 7:

[0283] The server uses the acquired information and the results of emotion analysis to generate an appropriate answer to the user's question using a generative AI model. For example, it generates a response such as, "Losing is part of the experience. Let's work hard together to achieve better results next time!" The input data are search results and emotion information, and the output is the generated answer.

[0284] Step 8:

[0285] The tone and expression of the answers generated by the generative AI model are adjusted within the server. For example, to make the answer more relatable to the user, the answer may be adjusted to include more kindness or encouragement. The input data is the generated answer, and the output is the adjusted answer.

[0286] Step 9:

[0287] The server sends the final answer to the user terminal using the HTTP / HTTPS protocol, and the answer data is encoded in JSON format. The input data is the adjusted answer, and the output is the transmitted data.

[0288] Step 10:

[0289] The user terminal displays the answer received from the server on the screen. The user can check the displayed answer and re-enter the question if necessary. The input data is the received data, and the output is the answer displayed to the user.

[0290] (Application example 2)

[0291] 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."

[0292] Conventional online counseling systems provide information without considering the user's emotions, making it difficult to provide appropriate advice suited to each user's psychological state. In particular, when dealing with security-related inquiries or psychological stress, emotion analysis and emotion-based response generation are necessary, but few systems have such functionality.

[0293] 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 a question input from a user terminal; means for passing the question content to a natural language processing engine for analysis; means for acquiring related information from a database based on the analysis results; means for generating an answer based on the acquired information and sending it to the user terminal; means for analyzing the user's emotions using an emotion engine and reflecting the results in answer generation; and means for the generative AI model for sending a query to an endpoint and generating an answer using a prompt sentence for generating appropriate advice. This makes it possible to provide appropriate counseling that takes into account the user's emotions and psychological state.

[0294] A "user terminal" is an electronic device that allows a user to input questions and receive answers, and includes a smartphone or computer.

[0295] A "natural language processing engine" is software that analyzes input natural language text and extracts keywords and context.

[0296] The "database" is an electronic information management system for storing information such as the experiences of professional athletes, stories of athletes who tried but failed, and advice from agents.

[0297] The "emotion engine" is software that analyzes a user's emotions from their questions and profile information, and feeds the results back to the generative AI model.

[0298] A "generative AI model" is an artificial intelligence system that generates appropriate answers and advice based on the analysis results provided by a natural language processing engine and an emotion engine.

[0299] A "prompt" is an instruction used by a generative AI model to generate an appropriate response, which may include contextual and emotional information.

[0300] System Overview

[0301] This invention is a system that allows junior athletes and security service users to receive specific career counseling and advice on psychological stress online. The system's main components are a user terminal, a central server, a database, an emotion engine, and a generative AI model.

[0302] User terminal

[0303] A user terminal is a device through which a user enters a question and receives a response. Specifically, this can be a smartphone or a computer. The user enters a question into the terminal using text or voice input, and the content is transmitted to a central server via the Internet.

[0304] Central Server

[0305] The central server plays a central role in analyzing incoming questions and generating appropriate answers. The server is equipped with a natural language processing engine, an emotion engine, and a generative AI model, which work together to create answers to users' questions.

[0306] Database

[0307] The database stores information such as the experiences of professional players, stories of players who tried but failed, and advice from agents, etc. Appropriate information is searched from this database and used to generate answers for the generative AI model.

[0308] Emotion Engine

[0309] The emotion engine analyzes user emotions from their questions and profile information. This engine works in conjunction with the natural language processing engine to analyze the user's emotions and psychological state, and feeds the results back to the generative AI model.

[0310] Program processing

[0311] Question reception and sentiment analysis

[0312] The server receives the question sent from the user's device. It then passes the question to a natural language processing engine to begin analysis. At the same time, an emotion engine runs to recognize the user's emotion from the question, thereby extracting emotional nuances and intensity.

[0313] Natural Language Processing and Analysis

[0314] The natural language processing engine on the server analyzes the received question and extracts important keywords and context. The analysis results are passed to the generative AI model. The emotion analysis results from the emotion engine are also provided to the generative AI model.

[0315] Searching the database

[0316] The generative AI model generates queries to the database based on the analyzed keywords, context, and sentiment information, and based on these queries, relevant information is retrieved from the database.

[0317] Generate answers

[0318] Based on the acquired information and the results of sentiment analysis, the generative AI model generates an appropriate response to the user's question. The generated response adjusts tone and expression to take emotions into account, making it more relatable to the user.

[0319] Submitting and viewing answers

[0320] The generated answer is sent back to the user terminal, where it is displayed for the user to review. The user can then review the displayed answer and re-enter the question if necessary.

[0321] Specific examples

[0322] For example, if a user inputs a question such as, "Work hasn't been going well recently and I'm feeling stressed. What should I do?", the emotion engine will recognize the emotion "stress." This emotion information, along with the analysis results, will be provided to the generative AI model. Based on the analysis results, the generative AI model will retrieve information from related databases and generate an answer that includes appropriate counseling and advice for dealing with "stress." This answer will then be sent to the user's device and displayed.

[0323] Example prompt sentence:

[0324] "A user asked the question, 'Work hasn't been going well lately and I'm feeling stressed. What should I do?' The emotion is 'stressed' and the tone is 'high.' Please provide appropriate counseling and advice."

[0325] In this way, by combining emotion engines, it becomes possible to respond in accordance with the user's psychological state, thereby providing better support.

[0326] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0327] Step 1: Receiving the question

[0328] The server receives a question input from the user terminal. The input includes the question text from the user terminal. For example, a question such as "Work hasn't been going well lately and I'm feeling stressed. What should I do?" is sent. This question text is passed to the next processing step as is.

[0329] Step 2: Sentiment Analysis

[0330] The emotion engine in the server analyzes the received question text. The question text received in step 1 is used as input. The emotion engine extracts emotions from the question content and assigns emotion labels such as "stress" or "depression." For example, the emotion "stress" is recognized from the question. This emotion information is output as a label and its intensity (score) and passed to the next step.

[0331] Step 3: Natural Language Processing

[0332] The natural language processing engine on the server analyzes the question text. As input, it uses the question text received in step 1 and the emotional information obtained in step 2. The natural language processing engine extracts keywords and context from the question. For example, keywords such as "work" and "stress" are extracted. The results of this analysis are output in text format and passed to the next step.

[0333] Step 4: Database Search

[0334] The server generates a query to the database based on the analysis results of natural language processing and emotional information. It uses the outputs of steps 2 and 3 as input. The database contains personal experiences of professional athletes and agents, as well as psychological advice information. Based on the query, the server searches the database for relevant information. For example, it retrieves "advice related to stress." The search results are output in text format and passed to the next step.

[0335] Step 5: Answer Generation

[0336] The generative AI model on the server generates an answer to the question based on information retrieved from the database. The search results obtained in step 4 and the analysis results from steps 2 and 3 are used as input. The generative AI model uses prompt text to generate an appropriate answer. For example, a prompt text such as "The user asked, 'Work hasn't been going well recently and I'm feeling stressed. What should I do?' The emotion is 'stressed' and the tone is 'high'. Please provide appropriate counseling and advice" is created and input into the AI ​​model. The generated answer is advice such as "First, take a deep breath and relax. Next, break down your work into small tasks and tackle them one by one," and is output in text format.

[0337] Step 6: Submit your response

[0338] The server sends the generated answer to the user's terminal. The answer text obtained in step 5 is used as input. The answer is sent to the user's terminal, and the user can check its contents. As output, the answer in text format is displayed on the user's terminal. The user can consider their next action based on the displayed answer.

[0339] This processing step allows the user to receive specific and effective advice that is in line with their own feelings and circumstances.

[0340] 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.

[0341] 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.

[0342] 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.

[0343] [Second embodiment]

[0344] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0345] 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.

[0346] 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).

[0347] 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.

[0348] 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.

[0349] 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).

[0350] 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.

[0351] 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.

[0352] 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.

[0353] 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.

[0354] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0355] 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."

[0356] This invention relates to a system that uses a generative AI model to provide specific career counseling to junior athletes. The system's main components are a user terminal, a central server, and a database. Users can use this system to obtain specific career plans and realistic information for those aiming to become professional athletes.

[0357] System Overview

[0358] User terminal

[0359] The user terminal is a device used by junior athletes and their guardians to input questions and receive answers. Typically, a smartphone or computer is used. Questions input from the user terminal are sent to a central server via the Internet.

[0360] Central Server

[0361] The central server plays a central role in analyzing incoming questions and generating appropriate answers. The server is equipped with a natural language processing engine and generative AI models, which work together to create answers to users' questions.

[0362] Database

[0363] The database contains information such as the experiences of professional players, stories of players who tried but failed, advice from agents, etc. Appropriate information is searched from this database and used to generate answers for the generative AI model.

[0364] Program processing

[0365] Receiving questions

[0366] A question sent from a user terminal is received by a central server, which first passes the question to a natural language processing engine to begin analysis.

[0367] Natural Language Processing and Analysis

[0368] The server's natural language processing engine analyzes the incoming question and extracts important keywords and context, and the results of this analysis are passed to a generative AI model.

[0369] Searching the database

[0370] The generative AI model then generates queries based on the analysis results, which retrieve relevant information from the database (such as the experiences of professional players or advice from agents).

[0371] Generate answers

[0372] Based on the acquired information, the generative AI model generates an appropriate answer to the user's question, which is then sent back to the user's device.

[0373] Specific examples

[0374] For example, if a user enters the question, "What are the benefits of going to college after graduating from high school to become a professional tennis player?", the question is first sent to the server. The natural language processing engine on the server extracts the keywords "professional tennis player," "high school graduation," "going to college," and "benefits." Next, the generative AI model searches a database based on these keywords to obtain information on cases of players who have succeeded as professionals after going to college and the benefits of going to college. Finally, the generative AI model generates an answer such as, "There are several cases of players who have succeeded as professionals after going to college, and it is beneficial for some players because it allows them to balance their studies with a shared training environment," and sends this to the user's device.

[0375] In this way, the present invention enables junior athletes and their guardians to easily draw up specific and realistic career plans, independent of location and information asymmetry.

[0376] The processing flow will be explained below.

[0377] Step 1:

[0378] Enter a question from the user's device. The user launches the career consultation app and enters the question in the text box. Once the question is complete, the user clicks the send button.

[0379] Step 2:

[0380] The user terminal sends the question to the central server. Once the user has completed the input, the question is sent to the central server via the Internet.

[0381] Step 3:

[0382] The server receives the questions. The central server receives the questions sent from the user terminals and passes the data to the text analysis module.

[0383] Step 4:

[0384] The server passes the question to a natural language processing engine for analysis. The text analysis module sends the question to the natural language processing engine, which analyzes the question and extracts keywords and context.

[0385] Step 5:

[0386] The server passes the analysis results to the generative AI model, and the analysis results obtained from the natural language processing engine are fed back to the generative AI model.

[0387] Step 6:

[0388] The server generates and sends a query to the database. The generative AI model generates a query to obtain the necessary information based on the analysis results and sends it to the database.

[0389] Step 7:

[0390] The database returns relevant information. Based on the query, the database searches for relevant information (experiences of professional players, stories of professional challenges, advice from agents, etc.) and returns this to the central server.

[0391] Step 8:

[0392] The server generates an answer based on the information it obtains. The generative AI model analyzes the information received from the database and generates an appropriate answer to the user's question.

[0393] Step 9:

[0394] The server transmits the generated answer to the user terminal, and performs communication to transmit the generated answer to the user terminal.

[0395] Step 10:

[0396] The user terminal displays the answer. The user terminal displays the answer received from the central server so that the user can confirm it. The user can confirm the displayed answer and enter the question again if necessary.

[0397] Through this series of processes, the system can provide quick and appropriate answers to users' questions.

[0398] Example 1

[0399] 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."

[0400] Traditional career counseling systems make it difficult for junior athletes and their guardians to obtain the information they need to draw up specific and realistic career plans. In particular, there is a lack of concrete advice based on experience and a path to becoming a professional athlete, making it difficult to obtain sufficient information when formulating a specific career plan.

[0401] 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.

[0402] In this invention, the server includes means for receiving a question input from a user terminal, means for passing the question content to a natural language processing engine for analysis, means for retrieving related information from a database based on the analysis results, and means for generating an answer based on the retrieved information and transmitting it to the user terminal. This enables junior players and their parents to easily draw up specific and realistic career plans based on the experiences of professional players and agents.

[0403] A "user device" is an electronic device such as a computer or smartphone that junior athletes and their parents use to enter questions and check answers.

[0404] A "question" is a question that a user inputs to obtain specific information about their career plan or how to become a professional athlete.

[0405] A "server" is a central computer system that receives questions sent from user terminals, analyzes them, generates appropriate answers, and sends them to the user terminals.

[0406] A "natural language processing engine" is a software component that analyzes the content of questions from users and extracts keywords and context.

[0407] A "database" is a collection of information that stores relevant information such as the experiences of professional athletes and advice from agents.

[0408] A "generative AI model" is an algorithm that generates appropriate answers to user questions using information obtained from a database based on the results analyzed by a natural language processing engine.

[0409] A "query" is a specific search condition or instruction that a generative AI model generates to search a database based on the analysis results.

[0410] An "answer" is the specific information or advice that the generative AI model generates in response to a user's question and sends to the user's device.

[0411] "Profile information" is personal data that is useful for career counseling, such as the user's age, type of sport, and goals.

[0412] "Selection" refers to the act of choosing the most suitable generative AI model based on the user's profile information and questions.

[0413] This invention relates to a system that uses a generative AI model to provide specific career counseling for junior athletes. The system's main components are a user terminal, a central server, and a database.

[0414] User terminal

[0415] The user terminal is a device used by junior athletes and their parents to input questions and receive answers. Typically, a smartphone or computer is used. Questions input from the user terminal are sent to a central server via the Internet.

[0416] Central Server

[0417] The central server plays a central role in analyzing incoming questions and generating appropriate answers. The server is equipped with a natural language processing engine and generative AI models, which work together to create answers to users' questions.

[0418] Database

[0419] The database contains information such as the experiences of professional players, stories of players who tried but failed, advice from agents, etc. Appropriate information is searched from this database and used to generate answers for the generative AI model.

[0420] Program processing

[0421] A question sent from a user device is first received by a central server. The server then passes the question to a natural language processing engine to begin analysis. The natural language processing engine in the server analyzes the received question and extracts important keywords and context. The results of this analysis are then passed to a generative AI model.

[0422] The generative AI model generates a query to the database based on the analysis results. Based on this query, relevant information (for example, the experiences of professional athletes or advice from agents) is retrieved from the database. Based on the retrieved information, the generative AI model generates an appropriate answer to the user's question. The generated answer is then sent back to the user's device.

[0423] Usage example

[0424] For example, if a user enters the question, "What are the benefits of going to college after graduating from high school to become a professional tennis player?", the question is first sent to the server. The natural language processing engine on the server extracts the keywords "professional tennis player," "high school graduation," "going to college," and "benefits." Next, the generative AI model searches a database based on these keywords to obtain information on cases of players who have succeeded as professionals after going to college and the benefits of going to college. Finally, the generative AI model generates an answer such as, "There are several cases of players who have succeeded as professionals after going to college, and it is beneficial for some players because it allows them to share a training environment and balance their studies," and sends this to the user's device.

[0425] In this way, the present invention allows junior athletes and their guardians to easily create specific and realistic career plans, regardless of location or information asymmetry. It is also possible to select the optimal generative AI model based on the user's profile information to provide information that best suits the user's characteristics.

[0426] Prompt Sentence Examples

[0427] "What is the best career plan for becoming a professional basketball player?"

[0428] "Is it better to aim to become a professional immediately after graduating from high school or to go to college and then aim to do so?"

[0429] Please tell me how to choose an agent.

[0430] "What kind of training did successful professional athletes do?"

[0431] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0432] Step 1:

[0433] A user terminal inputs a question from the user.

[0434] Input: The user inputs characters and enters the question.

[0435] What happens: A user types the question "What are the benefits of going to college after high school to become a professional tennis player?" into a text input field on their smartphone or computer.

[0436] Step 2:

[0437] A user terminal sends a query to a central server.

[0438] Input: The question typed by the user.

[0439] Specific operation: The device sends the question to a central server via the Internet.

[0440] Output: The query is received by the central server.

[0441] Step 3:

[0442] The server passes the question to a natural language processing engine and begins analysis.

[0443] Input: The query received by the central server.

[0444] How it works: The server passes the question to a natural language processing engine, which extracts important keywords such as "professional tennis player," "high school graduation," "college enrollment," and "merits."

[0445] Output: Parsed keywords and context information.

[0446] Step 4:

[0447] The server generates a query based on the analysis results and searches the database.

[0448] Input: Analysis results (keywords and context information) from the natural language processing engine.

[0449] Specific operation: The generative AI model generates a specific search query for the database based on the analysis results. For example, it generates a query such as "professional tennis player, high school graduate, college admission, merits."

[0450] Output: Relevant information retrieved from the database (e.g., professional player experiences, agent advice, etc.).

[0451] Step 5:

[0452] The server generates a response based on the information it has obtained.

[0453] Input: Relevant information retrieved from the database.

[0454] Specific operation: Based on the information acquired by the generative AI model, it generates an appropriate answer to the user's question. For example, it generates an answer such as, "There are several examples of players who have successfully become professionals after attending university, and it is beneficial for some players because it allows them to balance their studies with a shared training environment."

[0455] Output: The generated answer.

[0456] Step 6:

[0457] The server generates a response and sends it to the user terminal.

[0458] Input: The generated answer text.

[0459] Specific operation: The server sends the response to the user terminal.

[0460] Output: The answer text displayed on the user's terminal.

[0461] Step 7:

[0462] The user reviews the answer and decides on the next action.

[0463] Input: The answer displayed on the user's terminal.

[0464] Specific operation: The user checks the answer displayed on the device. For example, they may decide, "Now that I understand the benefits of going to college, I'll consider that path."

[0465] Output: The user's new understanding or next action.

[0466] (Application example 1)

[0467] 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."

[0468] It is difficult for junior players and their guardians to obtain real-time information on specific career plans for those aiming to become professional players. Furthermore, there is no way to easily input questions in-store and receive appropriate answers on the spot, which reduces the efficiency of career counseling. This makes it difficult to obtain the necessary information at the right time, potentially resulting in delays in career development.

[0469] 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.

[0470] In this invention, the server includes means for receiving a question input from a user terminal, means for passing the content of the question to a natural language processing engine for analysis, means for retrieving related information from a database based on the analysis results, means for generating an answer based on the retrieved related information and transmitting it to the user terminal, and means for inputting a question using a smart terminal in the store and retrieving the answer in real time, thereby enabling junior athletes and their guardians to easily receive career counseling in the store and obtain prompt and appropriate information.

[0471] A "user terminal" is a device used by a user to input questions and receive answers, and refers to an electronic device such as a smartphone or computer.

[0472] The term "means for receiving a question" refers to a function for transmitting a question input from a user terminal to a server and receiving the question.

[0473] A "natural language processing engine" refers to technology that analyzes input questions and extracts important keywords and context.

[0474] "Means of analysis" refers to the process of passing the question content to a natural language processing engine for analysis.

[0475] "Relevant information" refers to information in the database that is necessary to generate an appropriate answer to a user's question.

[0476] "Database" refers to a collection of data containing information such as the experiences of professionals, challengers, and intermediaries.

[0477] "Means for obtaining" refers to the function for searching and obtaining related information from a database based on the analysis results.

[0478] "Means for generating an answer" refers to the process for creating an appropriate answer to a user's question based on the relevant information obtained.

[0479] "Means for obtaining information in real time" refers to a function for quickly generating and providing answers on the spot to questions entered by users in the store.

[0480] "In-store" refers to physical locations visited by junior athletes and their parents, such as sporting goods stores and sports clubs.

[0481] This invention relates to a system that allows junior athletes and their guardians to obtain specific career plans and information for becoming professional athletes in real time within sporting goods stores and sports clubs. The system's main components are a user terminal, a central server, and a database, and it operates as follows:

[0482] First, the user terminal is a device that junior players and their guardians use to input questions and receive answers. Common electronic devices such as smartphones, tablets, and laptops can be used as user terminals. This allows users to easily access the system within the store.

[0483] Next, when a question is entered from the user's device, it is sent via the Internet to a central server. The central server receives the question and first analyzes it using a natural language processing engine. For example, Python's openai library is used as the natural language processing engine. The content of the question is analyzed, and important keywords and context are extracted.

[0484] Based on the analysis results, the central server generates a query to a database to search for relevant information. The database contains the experiences and advice of professionals, challengers, and intermediaries, and appropriate information is retrieved from this database. Based on the retrieved information, a generative AI model generates an appropriate answer to the user's question. For example, the OpenAI API is used as the generative AI model.

[0485] The generated answer is then sent back to the user's device, allowing the user to receive the answer in real time. This series of processes allows users to easily receive career advice in-store and quickly obtain useful information.

[0486] As a specific example, if a user enters the question, "What are the benefits of going to college after graduating from high school to become a professional tennis player?", the question is sent to a central server, and the natural language processing engine extracts the keywords "professional tennis player," "high school graduation," "going to college," and "benefits." Next, the generative AI model searches a database based on these keywords to obtain information on cases of players who have succeeded as professionals after going to college and the benefits of going to college. Finally, the generative AI model generates an answer such as, "There are several cases of players who have succeeded as professionals after going to college, and it is beneficial for some players because it allows them to share a training environment and balance their studies," and sends this to the user's device.

[0487] In this way, the present invention allows junior athletes and their guardians to create specific and realistic career plans in real time within the store.

[0488] An example prompt is:

[0489] Question: What are the benefits of going to college after high school to become a professional tennis player?

[0490] Extract keywords: professional tennis player, high school graduation, college admission, benefits

[0491] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0492] Step 1:

[0493] The user's device inputs a question and sends it to a central server. The user inputs a question on a smartphone or tablet, and the input text data is sent to the server via an HTTP request or similar. The input is in text format, and the user's specific question is sent as text. The output is the question text.

[0494] Step 2:

[0495] The server passes the received question to a natural language processing engine for analysis. Specifically, the server uses the Python openai library to analyze the question and extract important keywords and context. The input is the question text submitted by the user, and the output is a list of extracted keywords.

[0496] Step 3:

[0497] The server generates queries to a database based on the extracted keywords to search and retrieve relevant information. The database stores the experiences and career-related information of professionals, challengers, and intermediaries. The input is a list of extracted keywords, and the output is a list of related information.

[0498] Step 4:

[0499] Based on the related information acquired by the server, a generative AI model is used to generate an appropriate answer to the user's question. For example, the OpenAI API is used as the generative AI model. The input is a list of related information acquired from a database, and the output is the generated answer text.

[0500] Step 5:

[0501] The server sends the generated answer to the user's device, and the user receives the answer in real time. Specifically, the answer is sent from the server to the user's device via an HTTP response or similar and is displayed on the user's device screen. The input is the generated answer text, and the output is the answer displayed on the user's device.

[0502] This series of processes allows users to obtain specific career plans and information in real time within the store, significantly improving the efficiency of career consultations.

[0503] 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.

[0504] This invention relates to a system that uses a generative AI model to provide specific career counseling to junior athletes. The system's main components are a user terminal, a central server, a database, and an emotion engine. Users can use this system to obtain specific career plans and realistic information for those aiming to become professional athletes. Furthermore, by using the emotion engine, appropriate answers can be provided based on the user's emotions and psychological state.

[0505] System Overview

[0506] User terminal

[0507] The user terminal is a device used by junior athletes and their guardians to input questions and receive answers. Typically, a smartphone or computer is used. Questions input from the user terminal are sent to a central server via the Internet.

[0508] Central Server

[0509] The central server plays a central role in analyzing incoming questions and generating appropriate answers. The server is equipped with a natural language processing engine, an emotion engine, and a generative AI model, which work together to create answers to users' questions.

[0510] Database

[0511] The database contains information such as the experiences of professional players, stories of players who tried but failed, advice from agents, etc. Appropriate information is searched from this database and used to generate answers for the generative AI model.

[0512] Emotion Engine

[0513] The emotion engine analyzes user emotions from their questions and profile information. This engine works in conjunction with the natural language processing engine to analyze the user's emotions and psychological state, and feeds the results back to the generative AI model.

[0514] Program processing

[0515] Question reception and sentiment analysis

[0516] A question sent from a user's device is received by a central server. The server first passes the question to a natural language processing engine for analysis. An emotion engine also runs simultaneously to recognize the user's emotion from the question, thereby extracting emotional nuances and intensity.

[0517] Natural Language Processing and Analysis

[0518] The natural language processing engine on the server analyzes the received question and extracts important keywords and context. The analysis results are passed to the generative AI model. The emotion analysis results from the emotion engine are also provided to the generative AI model.

[0519] Searching the database

[0520] The generative AI model uses the analyzed keywords, context, and sentiment information to generate queries against the database, which then retrieves relevant information from the database (such as professional player experiences or agent advice).

[0521] Generate answers

[0522] Based on the acquired information and the results of sentiment analysis, the generative AI model generates an appropriate response to the user's question. The generated response adjusts tone and expression to take emotions into account, making it more relatable to the user.

[0523] Submitting and viewing answers

[0524] The generated answer is sent back to the user terminal, where it is displayed for the user to review. The user can then review the displayed answer and re-enter the question if necessary.

[0525] Specific examples

[0526] For example, if a user inputs a question such as, "I've been losing games lately and I'm feeling depressed. What should I do?", the emotion engine will recognize the emotion "depressed." This emotional information, along with the analysis results, will be provided to the generative AI model. The generative AI model will then use the analysis results to retrieve relevant database information and generate an answer containing appropriate encouragement and advice for dealing with the "depressed" feeling. This answer will then be sent to the user's device and displayed.

[0527] In this way, by combining emotion engines, it becomes possible to respond in accordance with the user's psychological state, thereby providing better support.

[0528] The processing flow will be explained below.

[0529] Step 1:

[0530] The user enters a question from their device. The user launches the career consultation app and enters the question, "I've been losing games lately and I'm feeling depressed. What should I do?" into the text box. Once the question is entered, the user clicks the send button.

[0531] Step 2:

[0532] The user terminal sends the question to the central server. Once the user has completed the input, the question is sent to the central server via the Internet.

[0533] Step 3:

[0534] The server receives the questions. The central server receives the questions sent from the user terminal and passes the data to the text analysis module and emotion engine.

[0535] Step 4:

[0536] The server passes the question to a natural language processing engine for analysis. The text analysis module sends the question, "I've been losing games lately and I'm feeling down. What should I do?" to the natural language processing engine, which analyzes the question and extracts keywords and context such as "game," "keep losing," "feelings," "depressed," and "what should I do."

[0537] Step 5:

[0538] The server passes the question to the emotion engine, which analyzes the emotion. The emotion engine analyzes the question and recognizes the emotion "depressed." This emotional information is fed back to the generative AI model.

[0539] Step 6:

[0540] The server passes the analysis results and emotional information to the generative AI model. The analysis results and emotional information obtained from the natural language processing engine and emotion engine are fed back to the generative AI model.

[0541] Step 7:

[0542] The server generates and sends a query to the database. Based on the analysis results and emotional information, the generative AI model generates a query to obtain information related to "constant losses" and "depression" and sends it to the database.

[0543] Step 8:

[0544] The database returns relevant information. Based on the query, the database searches for information such as professional player experiences (e.g., words of encouragement and advice from players who have had similar experiences) or agent advice (e.g., mental coping strategies) and sends this back to the central server.

[0545] Step 9:

[0546] The server generates an answer based on the information it obtains. The generative AI model analyzes the information received from the database and emotional information, and generates an appropriate answer to the user's question, "I've been losing games lately and I'm feeling down. What should I do?" For example, it might say, "Many professional players have had similar experiences. The important thing is to reflect on your own growth without getting caught up in the results. Professional player A also experienced similar feelings at the same time, but by reviewing his training routine, he was able to achieve better results in his next game."

[0547] Step 10:

[0548] The server transmits the generated answer to the user terminal, and performs communication to transmit the generated answer to the user terminal.

[0549] Step 11:

[0550] The user terminal displays the answer. The user terminal displays the answer received from the central server so that the user can confirm it. The user can confirm the displayed answer and enter the question again if necessary.

[0551] Through this series of processes, the system not only provides quick and appropriate answers to users' questions, but also enables support that takes into account the user's emotions.

[0552] Example 2

[0553] 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."

[0554] Conventional career counseling systems have difficulty providing appropriate answers to user questions that take into account emotions and context. In particular, when junior athletes and others seek career counseling in an emotional state, answers that are sensitive to the user's emotions are required, but conventional systems have not been able to adequately meet this demand. Furthermore, they lack the functionality to provide specific answers based on the experiences and advice of experts.

[0555] 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.

[0556] In this invention, the server includes means for receiving a question input from a user terminal, means for passing the question content to a natural language processing engine for analysis, means for analyzing the user's emotions from the analysis results using an emotion engine, means for retrieving related information from a database based on the analysis results and emotion information, and means for generating an answer based on the retrieved information and emotion information, adjusting the tone and expression, and transmitting the answer to the user terminal. This makes it possible to provide a highly empathetic answer that takes emotion and context into consideration.

[0557] "User Device" refers to the device used by junior athletes and their parents to input questions and receive answers. Smartphones and computers are commonly used.

[0558] The "Central Server" is a system that plays a central role in receiving and analyzing user questions and generating appropriate answers. It is equipped with a natural language processing engine, an emotion engine, and a generative AI model.

[0559] A "natural language processing engine" is an engine that analyzes received questions and extracts important keywords and context.

[0560] The "emotion engine" is an engine that analyzes user emotions from their questions and profile information. It works in conjunction with the natural language processing engine.

[0561] A "generative AI model" is a model that generates answers to user questions based on analysis results and sentiment analysis results.

[0562] The "database" is a data store that stores information such as the experiences of professional players, stories of players who tried but failed, and advice from agents.

[0563] "Receiving a question" is the process by which the central server receives a question sent from a user terminal.

[0564] "Question analysis" is the process in which the natural language processing engine performs morphological analysis of the question to extract important keywords and context. The emotion engine also works simultaneously to recognize emotions.

[0565] "Related information retrieval" is the process of searching and retrieving related information from a database based on the generated query.

[0566] "Answer generation" is the process in which the generative AI model creates an appropriate answer to the user's question based on the acquired information and the results of sentiment analysis.

[0567] "Tone and expression adjustment" is the process of adjusting the generated response to make it more relatable to the user's emotions and psychological state.

[0568] "Sending an answer" is the process of sending the generated answer to the user terminal.

[0569] "Displaying the answer" is the process in which the user terminal displays the answer received from the central server on the screen so that the user can check it.

[0570] This invention relates to a system that uses a generative AI model to provide specific career counseling to junior athletes. The system's main components are a user terminal, a central server, a database, and an emotion engine. Users can use this system to obtain specific career plans and realistic information for those aiming to become professional athletes. Furthermore, by using the emotion engine, appropriate answers can be provided based on the user's emotions and psychological state.

[0571] User terminal

[0572] A user terminal is a device used by junior athletes and their guardians to input questions and receive answers. Typically, a smartphone or computer is used. Specifically, users can input and submit questions through a dedicated application or web browser on the terminal. Questions input from the user terminal are transmitted to a central server via the Internet.

[0573] Central Server

[0574] The central server plays a central role in analyzing received questions and generating appropriate answers. The server is equipped with a natural language processing engine, an emotion engine, and a generative AI model, which work together to create answers to users' questions. Specifically, the server first passes the question to the natural language processing engine, which performs morphological analysis. This analysis extracts important keywords and context. The emotion engine also works simultaneously to recognize the user's emotions from the content of the question.

[0575] Database

[0576] The database contains information such as the experiences of professional players, stories of players who tried but failed, and advice from agents. Appropriate information is searched for in this database and used to generate answers for the generative AI model. For example, in response to the question, "What kind of training is required to become a professional soccer player?", relevant training menus and success stories are retrieved from the database.

[0577] Emotion Engine

[0578] The emotion engine analyzes a user's emotions from their questions and profile information. This engine works in conjunction with the natural language processing engine to analyze the user's emotions and psychological state, and feeds the results back to the generative AI model. For example, in response to the question, "I've been losing games lately and I'm feeling depressed. What should I do?" emotions such as "depression" and "anxiety" are recognized.

[0579] Generate and submit answers

[0580] The central server uses the generative AI model to generate an appropriate answer to the user's question based on the analysis results of the natural language processing engine and emotion engine. The generated answer adjusts the tone and expression to take emotion into account, making it more relatable to the user. The generated answer is then sent back to the user's device, where it is displayed on the screen. The user can then check the displayed answer and enter a new question if necessary.

[0581] Specific examples

[0582] For example, if a user enters a question such as, "I've been losing games lately and I'm feeling down. What should I do?", the question is sent from the user's device to the central server. The server receives the question and analyzes it using a natural language processing engine and an emotion engine. As a result of the analysis, the emotion "down" is recognized. Next, the generative AI model retrieves relevant information from the database based on the analysis results and generates an answer such as, "Losing is part of the experience. Let's work hard together to achieve better results next time!" This answer is sent to the user's device and displayed. The user can review the answer and ask the question again if necessary.

[0583] Prompt Sentence Examples

[0584] "I've been losing a lot of games lately and I'm feeling down. What should I do?"

[0585] "I want to be a professional soccer player. What kind of training do I need?"

[0586] The present invention allows users to receive specific and empathetic answers that are tailored to their own situations and feelings, enabling better career counseling.

[0587] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0588] Step 1:

[0589] The user uses a terminal to input a question. For example, they might input something like, "I've been losing games lately and I'm feeling depressed. What should I do?" The input question is sent to a central server via the Internet. The input data is sent to the server in text format.

[0590] Step 2:

[0591] The central server receives questions sent from user devices. The server temporarily stores the received questions and passes them to a natural language processing engine. The input data is the user's question text, and the output is data for analysis.

[0592] Step 3:

[0593] The server's natural language processing engine analyzes the received question. Morphological analysis is performed to extract important keywords and context from the question. For example, keywords such as "game," "keep losing," "feelings," and "depressed" are extracted from the question. The input data is the user's question text, and the output is keywords and context information.

[0594] Step 4:

[0595] The server's emotion engine analyzes the user's emotions from the question. Based on the analysis results of the natural language processing engine, the emotional nuances contained in the question are analyzed. For example, the emotion "depressed" is recognized. The input data is the analyzed keywords and text, and the output is emotional information such as "depressed."

[0596] Step 5:

[0597] The server uses a generative AI model to generate queries to the database based on the analysis results of the natural language processing engine and emotion engine. For example, based on information such as "feeling depressed" or "continuously losing games," it creates a query to retrieve related database information. The input data is the analysis results and emotion information, and the output is a database query.

[0598] Step 6:

[0599] The server uses the generated query to search a database that contains information such as the experiences of professional athletes, advice from agents, and training menus. The search results include information on related training content and past success stories. The input data is the query, and the output is the search results.

[0600] Step 7:

[0601] The server uses the acquired information and the results of emotion analysis to generate an appropriate answer to the user's question using a generative AI model. For example, it generates a response such as, "Losing is part of the experience. Let's work hard together to achieve better results next time!" The input data are search results and emotion information, and the output is the generated answer.

[0602] Step 8:

[0603] The tone and expression of the answers generated by the generative AI model are adjusted within the server. For example, to make the answer more relatable to the user, the answer may be adjusted to include more kindness or encouragement. The input data is the generated answer, and the output is the adjusted answer.

[0604] Step 9:

[0605] The server sends the final answer to the user terminal using the HTTP / HTTPS protocol, and the answer data is encoded in JSON format. The input data is the adjusted answer, and the output is the transmitted data.

[0606] Step 10:

[0607] The user terminal displays the answer received from the server on the screen. The user can check the displayed answer and re-enter the question if necessary. The input data is the received data, and the output is the answer displayed to the user.

[0608] (Application example 2)

[0609] 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."

[0610] Conventional online counseling systems provide information without considering the user's emotions, making it difficult to provide appropriate advice suited to each user's psychological state. In particular, when dealing with security-related inquiries or psychological stress, emotion analysis and emotion-based response generation are necessary, but few systems have such functionality.

[0611] 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 a question input from a user terminal; means for passing the question content to a natural language processing engine for analysis; means for acquiring related information from a database based on the analysis results; means for generating an answer based on the acquired information and sending it to the user terminal; means for analyzing the user's emotions using an emotion engine and reflecting the results in answer generation; and means for the generative AI model for sending a query to an endpoint and generating an answer using a prompt sentence for generating appropriate advice. This makes it possible to provide appropriate counseling that takes into account the user's emotions and psychological state.

[0612] A "user terminal" is an electronic device that allows a user to input questions and receive answers, and includes a smartphone or computer.

[0613] A "natural language processing engine" is software that analyzes input natural language text and extracts keywords and context.

[0614] The "database" is an electronic information management system for storing information such as the experiences of professional athletes, stories of athletes who tried but failed, and advice from agents.

[0615] The "emotion engine" is software that analyzes a user's emotions from their questions and profile information, and feeds the results back to the generative AI model.

[0616] A "generative AI model" is an artificial intelligence system that generates appropriate answers and advice based on the analysis results provided by a natural language processing engine and an emotion engine.

[0617] A "prompt" is an instruction used by a generative AI model to generate an appropriate response, which may include contextual and emotional information.

[0618] System Overview

[0619] This invention is a system that allows junior athletes and security service users to receive specific career counseling and advice on psychological stress online. The system's main components are a user terminal, a central server, a database, an emotion engine, and a generative AI model.

[0620] User terminal

[0621] A user terminal is a device through which a user enters a question and receives a response. Specifically, this can be a smartphone or a computer. The user enters a question into the terminal using text or voice input, and the content is transmitted to a central server via the Internet.

[0622] Central Server

[0623] The central server plays a central role in analyzing incoming questions and generating appropriate answers. The server is equipped with a natural language processing engine, an emotion engine, and a generative AI model, which work together to create answers to users' questions.

[0624] Database

[0625] The database stores information such as the experiences of professional players, stories of players who tried but failed, and advice from agents, etc. Appropriate information is searched from this database and used to generate answers for the generative AI model.

[0626] Emotion Engine

[0627] The emotion engine analyzes user emotions from their questions and profile information. This engine works in conjunction with the natural language processing engine to analyze the user's emotions and psychological state, and feeds the results back to the generative AI model.

[0628] Program processing

[0629] Question reception and sentiment analysis

[0630] The server receives the question sent from the user's device. It then passes the question to a natural language processing engine to begin analysis. At the same time, an emotion engine runs to recognize the user's emotion from the question, thereby extracting emotional nuances and intensity.

[0631] Natural Language Processing and Analysis

[0632] The natural language processing engine on the server analyzes the received question and extracts important keywords and context. The analysis results are passed to the generative AI model. The emotion analysis results from the emotion engine are also provided to the generative AI model.

[0633] Searching the database

[0634] The generative AI model generates queries to the database based on the analyzed keywords, context, and sentiment information, and based on these queries, relevant information is retrieved from the database.

[0635] Generate answers

[0636] Based on the acquired information and the results of sentiment analysis, the generative AI model generates an appropriate response to the user's question. The generated response adjusts tone and expression to take emotions into account, making it more relatable to the user.

[0637] Submitting and viewing answers

[0638] The generated answer is sent back to the user terminal, where it is displayed for the user to review. The user can then review the displayed answer and re-enter the question if necessary.

[0639] Specific examples

[0640] For example, if a user inputs a question such as, "Work hasn't been going well recently and I'm feeling stressed. What should I do?", the emotion engine will recognize the emotion "stress." This emotion information, along with the analysis results, will be provided to the generative AI model. Based on the analysis results, the generative AI model will retrieve information from related databases and generate an answer that includes appropriate counseling and advice for dealing with "stress." This answer will then be sent to the user's device and displayed.

[0641] Example prompt sentence:

[0642] "A user asked the question, 'Work hasn't been going well lately and I'm feeling stressed. What should I do?' The emotion is 'stressed' and the tone is 'high.' Please provide appropriate counseling and advice."

[0643] In this way, by combining emotion engines, it becomes possible to respond in accordance with the user's psychological state, thereby providing better support.

[0644] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0645] Step 1: Receiving the question

[0646] The server receives a question input from the user terminal. The input includes the question text from the user terminal. For example, a question such as "Work hasn't been going well lately and I'm feeling stressed. What should I do?" is sent. This question text is passed to the next processing step as is.

[0647] Step 2: Sentiment Analysis

[0648] The emotion engine in the server analyzes the received question text. The question text received in step 1 is used as input. The emotion engine extracts emotions from the question content and assigns emotion labels such as "stress" or "depression." For example, the emotion "stress" is recognized from the question. This emotion information is output as a label and its intensity (score) and passed to the next step.

[0649] Step 3: Natural Language Processing

[0650] The natural language processing engine on the server analyzes the question text. As input, it uses the question text received in step 1 and the emotional information obtained in step 2. The natural language processing engine extracts keywords and context from the question. For example, keywords such as "work" and "stress" are extracted. The results of this analysis are output in text format and passed to the next step.

[0651] Step 4: Database Search

[0652] The server generates a query to the database based on the analysis results of natural language processing and emotional information. It uses the outputs of steps 2 and 3 as input. The database contains personal experiences of professional athletes and agents, as well as psychological advice information. Based on the query, the server searches the database for relevant information. For example, it retrieves "advice related to stress." The search results are output in text format and passed to the next step.

[0653] Step 5: Answer Generation

[0654] The generative AI model on the server generates an answer to the question based on information retrieved from the database. The search results obtained in step 4 and the analysis results from steps 2 and 3 are used as input. The generative AI model uses prompt text to generate an appropriate answer. For example, a prompt text such as "The user asked, 'Work hasn't been going well recently and I'm feeling stressed. What should I do?' The emotion is 'stressed' and the tone is 'high'. Please provide appropriate counseling and advice" is created and input into the AI ​​model. The generated answer is advice such as "First, take a deep breath and relax. Next, break down your work into small tasks and tackle them one by one," and is output in text format.

[0655] Step 6: Submit your response

[0656] The server sends the generated answer to the user's terminal. The answer text obtained in step 5 is used as input. The answer is sent to the user's terminal, and the user can check its contents. As output, the answer in text format is displayed on the user's terminal. The user can consider their next action based on the displayed answer.

[0657] This processing step allows the user to receive specific and effective advice that is in line with their own feelings and circumstances.

[0658] 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.

[0659] 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.

[0660] 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.

[0661] [Third embodiment]

[0662] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0663] 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.

[0664] 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).

[0665] 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.

[0666] 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.

[0667] 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).

[0668] 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.

[0669] 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.

[0670] 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.

[0671] 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.

[0672] 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.

[0673] 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."

[0674] This invention relates to a system that uses a generative AI model to provide specific career counseling to junior athletes. The system's main components are a user terminal, a central server, and a database. Users can use this system to obtain specific career plans and realistic information for those aiming to become professional athletes.

[0675] System Overview

[0676] User terminal

[0677] The user terminal is a device used by junior athletes and their guardians to input questions and receive answers. Typically, a smartphone or computer is used. Questions input from the user terminal are sent to a central server via the Internet.

[0678] Central Server

[0679] The central server plays a central role in analyzing incoming questions and generating appropriate answers. The server is equipped with a natural language processing engine and generative AI models, which work together to create answers to users' questions.

[0680] Database

[0681] The database contains information such as the experiences of professional players, stories of players who tried but failed, advice from agents, etc. Appropriate information is searched from this database and used to generate answers for the generative AI model.

[0682] Program processing

[0683] Receiving questions

[0684] A question sent from a user terminal is received by a central server, which first passes the question to a natural language processing engine to begin analysis.

[0685] Natural Language Processing and Analysis

[0686] The server's natural language processing engine analyzes the incoming question and extracts important keywords and context, and the results of this analysis are passed to a generative AI model.

[0687] Searching the database

[0688] The generative AI model then generates queries based on the analysis results, which retrieve relevant information from the database (such as the experiences of professional players or advice from agents).

[0689] Generate answers

[0690] Based on the acquired information, the generative AI model generates an appropriate answer to the user's question, which is then sent back to the user's device.

[0691] Specific examples

[0692] For example, if a user enters the question, "What are the benefits of going to college after graduating from high school to become a professional tennis player?", the question is first sent to the server. The natural language processing engine on the server extracts the keywords "professional tennis player," "high school graduation," "going to college," and "benefits." Next, the generative AI model searches a database based on these keywords to obtain information on cases of players who have succeeded as professionals after going to college and the benefits of going to college. Finally, the generative AI model generates an answer such as, "There are several cases of players who have succeeded as professionals after going to college, and it is beneficial for some players because it allows them to balance their studies with a shared training environment," and sends this to the user's device.

[0693] In this way, the present invention enables junior athletes and their guardians to easily draw up specific and realistic career plans, independent of location and information asymmetry.

[0694] The processing flow will be explained below.

[0695] Step 1:

[0696] Enter a question from the user's device. The user launches the career consultation app and enters the question in the text box. Once the question is complete, the user clicks the send button.

[0697] Step 2:

[0698] The user terminal sends the question to the central server. Once the user has completed the input, the question is sent to the central server via the Internet.

[0699] Step 3:

[0700] The server receives the questions. The central server receives the questions sent from the user terminals and passes the data to the text analysis module.

[0701] Step 4:

[0702] The server passes the question to a natural language processing engine for analysis. The text analysis module sends the question to the natural language processing engine, which analyzes the question and extracts keywords and context.

[0703] Step 5:

[0704] The server passes the analysis results to the generative AI model, and the analysis results obtained from the natural language processing engine are fed back to the generative AI model.

[0705] Step 6:

[0706] The server generates and sends a query to the database. The generative AI model generates a query to obtain the necessary information based on the analysis results and sends it to the database.

[0707] Step 7:

[0708] The database returns relevant information. Based on the query, the database searches for relevant information (experiences of professional players, stories of professional challenges, advice from agents, etc.) and returns this to the central server.

[0709] Step 8:

[0710] The server generates an answer based on the information it obtains. The generative AI model analyzes the information received from the database and generates an appropriate answer to the user's question.

[0711] Step 9:

[0712] The server transmits the generated answer to the user terminal, and performs communication to transmit the generated answer to the user terminal.

[0713] Step 10:

[0714] The user terminal displays the answer. The user terminal displays the answer received from the central server so that the user can confirm it. The user can confirm the displayed answer and enter the question again if necessary.

[0715] Through this series of processes, the system can provide quick and appropriate answers to users' questions.

[0716] Example 1

[0717] 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."

[0718] Traditional career counseling systems make it difficult for junior athletes and their guardians to obtain the information they need to draw up specific and realistic career plans. In particular, there is a lack of concrete advice based on experience and a path to becoming a professional athlete, making it difficult to obtain sufficient information when formulating a specific career plan.

[0719] 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.

[0720] In this invention, the server includes means for receiving a question input from a user terminal, means for passing the question content to a natural language processing engine for analysis, means for retrieving related information from a database based on the analysis results, and means for generating an answer based on the retrieved information and transmitting it to the user terminal. This enables junior players and their parents to easily draw up specific and realistic career plans based on the experiences of professional players and agents.

[0721] A "user device" is an electronic device such as a computer or smartphone that junior athletes and their parents use to enter questions and check answers.

[0722] A "question" is a question that a user inputs to obtain specific information about their career plan or how to become a professional athlete.

[0723] A "server" is a central computer system that receives questions sent from user terminals, analyzes them, generates appropriate answers, and sends them to the user terminals.

[0724] A "natural language processing engine" is a software component that analyzes the content of questions from users and extracts keywords and context.

[0725] A "database" is a collection of information that stores relevant information such as the experiences of professional athletes and advice from agents.

[0726] A "generative AI model" is an algorithm that generates appropriate answers to user questions using information obtained from a database based on the results analyzed by a natural language processing engine.

[0727] A "query" is a specific search condition or instruction that a generative AI model generates to search a database based on the analysis results.

[0728] An "answer" is the specific information or advice that the generative AI model generates in response to a user's question and sends to the user's device.

[0729] "Profile information" is personal data that is useful for career counseling, such as the user's age, type of sport, and goals.

[0730] "Selection" refers to the act of choosing the most suitable generative AI model based on the user's profile information and questions.

[0731] This invention relates to a system that uses a generative AI model to provide specific career counseling for junior athletes. The system's main components are a user terminal, a central server, and a database.

[0732] User terminal

[0733] The user terminal is a device used by junior athletes and their parents to input questions and receive answers. Typically, a smartphone or computer is used. Questions input from the user terminal are sent to a central server via the Internet.

[0734] Central Server

[0735] The central server plays a central role in analyzing incoming questions and generating appropriate answers. The server is equipped with a natural language processing engine and generative AI models, which work together to create answers to users' questions.

[0736] Database

[0737] The database contains information such as the experiences of professional players, stories of players who tried but failed, advice from agents, etc. Appropriate information is searched from this database and used to generate answers for the generative AI model.

[0738] Program processing

[0739] A question sent from a user device is first received by a central server. The server then passes the question to a natural language processing engine to begin analysis. The natural language processing engine in the server analyzes the received question and extracts important keywords and context. The results of this analysis are then passed to a generative AI model.

[0740] The generative AI model generates a query to the database based on the analysis results. Based on this query, relevant information (for example, the experiences of professional athletes or advice from agents) is retrieved from the database. Based on the retrieved information, the generative AI model generates an appropriate answer to the user's question. The generated answer is then sent back to the user's device.

[0741] Usage example

[0742] For example, if a user enters the question, "What are the benefits of going to college after graduating from high school to become a professional tennis player?", the question is first sent to the server. The natural language processing engine on the server extracts the keywords "professional tennis player," "high school graduation," "going to college," and "benefits." Next, the generative AI model searches a database based on these keywords to obtain information on cases of players who have succeeded as professionals after going to college and the benefits of going to college. Finally, the generative AI model generates an answer such as, "There are several cases of players who have succeeded as professionals after going to college, and it is beneficial for some players because it allows them to share a training environment and balance their studies," and sends this to the user's device.

[0743] In this way, the present invention allows junior athletes and their guardians to easily create specific and realistic career plans, regardless of location or information asymmetry. It is also possible to select the optimal generative AI model based on the user's profile information to provide information that best suits the user's characteristics.

[0744] Prompt Sentence Examples

[0745] "What is the best career plan for becoming a professional basketball player?"

[0746] "Is it better to aim to become a professional immediately after graduating from high school or to go to college and then aim to do so?"

[0747] Please tell me how to choose an agent.

[0748] "What kind of training did successful professional athletes do?"

[0749] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0750] Step 1:

[0751] A user terminal inputs a question from the user.

[0752] Input: The user inputs characters and enters the question.

[0753] What happens: A user types the question "What are the benefits of going to college after high school to become a professional tennis player?" into a text input field on their smartphone or computer.

[0754] Step 2:

[0755] A user terminal sends a query to a central server.

[0756] Input: The question typed by the user.

[0757] Specific operation: The device sends the question to a central server via the Internet.

[0758] Output: The query is received by the central server.

[0759] Step 3:

[0760] The server passes the question to a natural language processing engine and begins analysis.

[0761] Input: The query received by the central server.

[0762] How it works: The server passes the question to a natural language processing engine, which extracts important keywords such as "professional tennis player," "high school graduation," "college enrollment," and "merits."

[0763] Output: Parsed keywords and context information.

[0764] Step 4:

[0765] The server generates a query based on the analysis results and searches the database.

[0766] Input: Analysis results (keywords and context information) from the natural language processing engine.

[0767] Specific operation: The generative AI model generates a specific search query for the database based on the analysis results. For example, it generates a query such as "professional tennis player, high school graduate, college admission, merits."

[0768] Output: Relevant information retrieved from the database (e.g., professional player experiences, agent advice, etc.).

[0769] Step 5:

[0770] The server generates a response based on the information it has obtained.

[0771] Input: Relevant information retrieved from the database.

[0772] Specific operation: Based on the information acquired by the generative AI model, it generates an appropriate answer to the user's question. For example, it generates an answer such as, "There are several examples of players who have successfully become professionals after attending university, and it is beneficial for some players because it allows them to balance their studies with a shared training environment."

[0773] Output: The generated answer.

[0774] Step 6:

[0775] The server generates a response and sends it to the user terminal.

[0776] Input: The generated answer text.

[0777] Specific operation: The server sends the response to the user terminal.

[0778] Output: The answer text displayed on the user's terminal.

[0779] Step 7:

[0780] The user reviews the answer and decides on the next action.

[0781] Input: The answer displayed on the user's terminal.

[0782] Specific operation: The user checks the answer displayed on the device. For example, they may decide, "Now that I understand the benefits of going to college, I'll consider that path."

[0783] Output: The user's new understanding or next action.

[0784] (Application example 1)

[0785] 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."

[0786] It is difficult for junior players and their guardians to obtain real-time information on specific career plans for those aiming to become professional players. Furthermore, there is no way to easily input questions in-store and receive appropriate answers on the spot, which reduces the efficiency of career counseling. This makes it difficult to obtain the necessary information at the right time, potentially resulting in delays in career development.

[0787] 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.

[0788] In this invention, the server includes means for receiving a question input from a user terminal, means for passing the content of the question to a natural language processing engine for analysis, means for retrieving related information from a database based on the analysis results, means for generating an answer based on the retrieved related information and transmitting it to the user terminal, and means for inputting a question using a smart terminal in the store and retrieving the answer in real time, thereby enabling junior athletes and their guardians to easily receive career counseling in the store and obtain prompt and appropriate information.

[0789] A "user terminal" is a device used by a user to input questions and receive answers, and refers to an electronic device such as a smartphone or computer.

[0790] The term "means for receiving a question" refers to a function for transmitting a question input from a user terminal to a server and receiving the question.

[0791] A "natural language processing engine" refers to technology that analyzes input questions and extracts important keywords and context.

[0792] "Means of analysis" refers to the process of passing the question content to a natural language processing engine for analysis.

[0793] "Relevant information" refers to information in the database that is necessary to generate an appropriate answer to a user's question.

[0794] "Database" refers to a collection of data containing information such as the experiences of professionals, challengers, and intermediaries.

[0795] "Means for obtaining" refers to the function for searching and obtaining related information from a database based on the analysis results.

[0796] "Means for generating an answer" refers to the process for creating an appropriate answer to a user's question based on the relevant information obtained.

[0797] "Means for obtaining information in real time" refers to a function for quickly generating and providing answers on the spot to questions entered by users in the store.

[0798] "In-store" refers to physical locations visited by junior athletes and their parents, such as sporting goods stores and sports clubs.

[0799] This invention relates to a system that allows junior athletes and their guardians to obtain specific career plans and information for becoming professional athletes in real time within sporting goods stores and sports clubs. The system's main components are a user terminal, a central server, and a database, and it operates as follows:

[0800] First, the user terminal is a device that junior players and their guardians use to input questions and receive answers. Common electronic devices such as smartphones, tablets, and laptops can be used as user terminals. This allows users to easily access the system within the store.

[0801] Next, when a question is entered from the user's device, it is sent via the Internet to a central server. The central server receives the question and first analyzes it using a natural language processing engine. For example, Python's openai library is used as the natural language processing engine. The content of the question is analyzed, and important keywords and context are extracted.

[0802] Based on the analysis results, the central server generates a query to a database to search for relevant information. The database contains the experiences and advice of professionals, challengers, and intermediaries, and appropriate information is retrieved from this database. Based on the retrieved information, a generative AI model generates an appropriate answer to the user's question. For example, the OpenAI API is used as the generative AI model.

[0803] The generated answer is then sent back to the user's device, allowing the user to receive the answer in real time. This series of processes allows users to easily receive career advice in-store and quickly obtain useful information.

[0804] As a specific example, if a user enters the question, "What are the benefits of going to college after graduating from high school to become a professional tennis player?", the question is sent to a central server, and the natural language processing engine extracts the keywords "professional tennis player," "high school graduation," "going to college," and "benefits." Next, the generative AI model searches a database based on these keywords to obtain information on cases of players who have succeeded as professionals after going to college and the benefits of going to college. Finally, the generative AI model generates an answer such as, "There are several cases of players who have succeeded as professionals after going to college, and it is beneficial for some players because it allows them to share a training environment and balance their studies," and sends this to the user's device.

[0805] In this way, the present invention allows junior athletes and their guardians to create specific and realistic career plans in real time within the store.

[0806] An example prompt is:

[0807] Question: What are the benefits of going to college after high school to become a professional tennis player?

[0808] Extract keywords: professional tennis player, high school graduation, college admission, benefits

[0809] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0810] Step 1:

[0811] The user's device inputs a question and sends it to a central server. The user inputs a question on a smartphone or tablet, and the input text data is sent to the server via an HTTP request or similar. The input is in text format, and the user's specific question is sent as text. The output is the question text.

[0812] Step 2:

[0813] The server passes the received question to a natural language processing engine for analysis. Specifically, the server uses the Python openai library to analyze the question and extract important keywords and context. The input is the question text submitted by the user, and the output is a list of extracted keywords.

[0814] Step 3:

[0815] The server generates queries to a database based on the extracted keywords to search and retrieve relevant information. The database stores the experiences and career-related information of professionals, challengers, and intermediaries. The input is a list of extracted keywords, and the output is a list of related information.

[0816] Step 4:

[0817] Based on the related information acquired by the server, a generative AI model is used to generate an appropriate answer to the user's question. For example, the OpenAI API is used as the generative AI model. The input is a list of related information acquired from a database, and the output is the generated answer text.

[0818] Step 5:

[0819] The server sends the generated answer to the user's device, and the user receives the answer in real time. Specifically, the answer is sent from the server to the user's device via an HTTP response or similar and is displayed on the user's device screen. The input is the generated answer text, and the output is the answer displayed on the user's device.

[0820] This series of processes allows users to obtain specific career plans and information in real time within the store, significantly improving the efficiency of career consultations.

[0821] 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.

[0822] This invention relates to a system that uses a generative AI model to provide specific career counseling to junior athletes. The system's main components are a user terminal, a central server, a database, and an emotion engine. Users can use this system to obtain specific career plans and realistic information for those aiming to become professional athletes. Furthermore, by using the emotion engine, appropriate answers can be provided based on the user's emotions and psychological state.

[0823] System Overview

[0824] User terminal

[0825] The user terminal is a device used by junior athletes and their guardians to input questions and receive answers. Typically, a smartphone or computer is used. Questions input from the user terminal are sent to a central server via the Internet.

[0826] Central Server

[0827] The central server plays a central role in analyzing incoming questions and generating appropriate answers. The server is equipped with a natural language processing engine, an emotion engine, and a generative AI model, which work together to create answers to users' questions.

[0828] Database

[0829] The database contains information such as the experiences of professional players, stories of players who tried but failed, advice from agents, etc. Appropriate information is searched from this database and used to generate answers for the generative AI model.

[0830] Emotion Engine

[0831] The emotion engine analyzes user emotions from their questions and profile information. This engine works in conjunction with the natural language processing engine to analyze the user's emotions and psychological state, and feeds the results back to the generative AI model.

[0832] Program processing

[0833] Question reception and sentiment analysis

[0834] A question sent from a user's device is received by a central server. The server first passes the question to a natural language processing engine for analysis. An emotion engine also runs simultaneously to recognize the user's emotion from the question, thereby extracting emotional nuances and intensity.

[0835] Natural Language Processing and Analysis

[0836] The natural language processing engine on the server analyzes the received question and extracts important keywords and context. The analysis results are passed to the generative AI model. The emotion analysis results from the emotion engine are also provided to the generative AI model.

[0837] Searching the database

[0838] The generative AI model uses the analyzed keywords, context, and sentiment information to generate queries against the database, which then retrieves relevant information from the database (such as professional player experiences or agent advice).

[0839] Generate answers

[0840] Based on the acquired information and the results of sentiment analysis, the generative AI model generates an appropriate response to the user's question. The generated response adjusts tone and expression to take emotions into account, making it more relatable to the user.

[0841] Submitting and viewing answers

[0842] The generated answer is sent back to the user terminal, where it is displayed for the user to review. The user can then review the displayed answer and re-enter the question if necessary.

[0843] Specific examples

[0844] For example, if a user inputs a question such as, "I've been losing games lately and I'm feeling depressed. What should I do?", the emotion engine will recognize the emotion "depressed." This emotional information, along with the analysis results, will be provided to the generative AI model. The generative AI model will then use the analysis results to retrieve relevant database information and generate an answer containing appropriate encouragement and advice for dealing with the "depressed" feeling. This answer will then be sent to the user's device and displayed.

[0845] In this way, by combining emotion engines, it becomes possible to respond in accordance with the user's psychological state, thereby providing better support.

[0846] The processing flow will be explained below.

[0847] Step 1:

[0848] The user enters a question from their device. The user launches the career consultation app and enters the question, "I've been losing games lately and I'm feeling depressed. What should I do?" into the text box. Once the question is entered, the user clicks the send button.

[0849] Step 2:

[0850] The user terminal sends the question to the central server. Once the user has completed the input, the question is sent to the central server via the Internet.

[0851] Step 3:

[0852] The server receives the questions. The central server receives the questions sent from the user terminal and passes the data to the text analysis module and emotion engine.

[0853] Step 4:

[0854] The server passes the question to a natural language processing engine for analysis. The text analysis module sends the question, "I've been losing games lately and I'm feeling down. What should I do?" to the natural language processing engine, which analyzes the question and extracts keywords and context such as "game," "keep losing," "feelings," "depressed," and "what should I do."

[0855] Step 5:

[0856] The server passes the question to the emotion engine, which analyzes the emotion. The emotion engine analyzes the question and recognizes the emotion "depressed." This emotional information is fed back to the generative AI model.

[0857] Step 6:

[0858] The server passes the analysis results and emotional information to the generative AI model. The analysis results and emotional information obtained from the natural language processing engine and emotion engine are fed back to the generative AI model.

[0859] Step 7:

[0860] The server generates and sends a query to the database. Based on the analysis results and emotional information, the generative AI model generates a query to obtain information related to "constant losses" and "depression" and sends it to the database.

[0861] Step 8:

[0862] The database returns relevant information. Based on the query, the database searches for information such as professional player experiences (e.g., words of encouragement and advice from players who have had similar experiences) or agent advice (e.g., mental coping strategies) and sends this back to the central server.

[0863] Step 9:

[0864] The server generates an answer based on the information it obtains. The generative AI model analyzes the information received from the database and emotional information, and generates an appropriate answer to the user's question, "I've been losing games lately and I'm feeling down. What should I do?" For example, it might say, "Many professional players have had similar experiences. The important thing is to reflect on your own growth without getting caught up in the results. Professional player A also experienced similar feelings at the same time, but by reviewing his training routine, he was able to achieve better results in his next game."

[0865] Step 10:

[0866] The server transmits the generated answer to the user terminal, and performs communication to transmit the generated answer to the user terminal.

[0867] Step 11:

[0868] The user terminal displays the answer. The user terminal displays the answer received from the central server so that the user can confirm it. The user can confirm the displayed answer and enter the question again if necessary.

[0869] Through this series of processes, the system not only provides quick and appropriate answers to users' questions, but also enables support that takes into account the user's emotions.

[0870] Example 2

[0871] 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."

[0872] Conventional career counseling systems have difficulty providing appropriate answers to user questions that take into account emotions and context. In particular, when junior athletes and others seek career counseling in an emotional state, answers that are sensitive to the user's emotions are required, but conventional systems have not been able to adequately meet this demand. Furthermore, they lack the functionality to provide specific answers based on the experiences and advice of experts.

[0873] 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.

[0874] In this invention, the server includes means for receiving a question input from a user terminal, means for passing the question content to a natural language processing engine for analysis, means for analyzing the user's emotions from the analysis results using an emotion engine, means for retrieving related information from a database based on the analysis results and emotion information, and means for generating an answer based on the retrieved information and emotion information, adjusting the tone and expression, and transmitting the answer to the user terminal. This makes it possible to provide a highly empathetic answer that takes emotion and context into consideration.

[0875] "User Device" refers to the device used by junior athletes and their parents to input questions and receive answers. Smartphones and computers are commonly used.

[0876] The "Central Server" is a system that plays a central role in receiving and analyzing user questions and generating appropriate answers. It is equipped with a natural language processing engine, an emotion engine, and a generative AI model.

[0877] A "natural language processing engine" is an engine that analyzes received questions and extracts important keywords and context.

[0878] The "emotion engine" is an engine that analyzes user emotions from their questions and profile information. It works in conjunction with the natural language processing engine.

[0879] A "generative AI model" is a model that generates answers to user questions based on analysis results and sentiment analysis results.

[0880] The "database" is a data store that stores information such as the experiences of professional players, stories of players who tried but failed, and advice from agents.

[0881] "Receiving a question" is the process by which the central server receives a question sent from a user terminal.

[0882] "Question analysis" is the process in which the natural language processing engine performs morphological analysis of the question to extract important keywords and context. The emotion engine also works simultaneously to recognize emotions.

[0883] "Related information retrieval" is the process of searching and retrieving related information from a database based on the generated query.

[0884] "Answer generation" is the process in which the generative AI model creates an appropriate answer to the user's question based on the acquired information and the results of sentiment analysis.

[0885] "Tone and expression adjustment" is the process of adjusting the generated response to make it more relatable to the user's emotions and psychological state.

[0886] "Sending an answer" is the process of sending the generated answer to the user terminal.

[0887] "Displaying the answer" is the process in which the user terminal displays the answer received from the central server on the screen so that the user can check it.

[0888] This invention relates to a system that uses a generative AI model to provide specific career counseling to junior athletes. The system's main components are a user terminal, a central server, a database, and an emotion engine. Users can use this system to obtain specific career plans and realistic information for those aiming to become professional athletes. Furthermore, by using the emotion engine, appropriate answers can be provided based on the user's emotions and psychological state.

[0889] User terminal

[0890] A user terminal is a device used by junior athletes and their guardians to input questions and receive answers. Typically, a smartphone or computer is used. Specifically, users can input and submit questions through a dedicated application or web browser on the terminal. Questions input from the user terminal are transmitted to a central server via the Internet.

[0891] Central Server

[0892] The central server plays a central role in analyzing received questions and generating appropriate answers. The server is equipped with a natural language processing engine, an emotion engine, and a generative AI model, which work together to create answers to users' questions. Specifically, the server first passes the question to the natural language processing engine, which performs morphological analysis. This analysis extracts important keywords and context. The emotion engine also works simultaneously to recognize the user's emotions from the content of the question.

[0893] Database

[0894] The database contains information such as the experiences of professional players, stories of players who tried but failed, and advice from agents. Appropriate information is searched for in this database and used to generate answers for the generative AI model. For example, in response to the question, "What kind of training is required to become a professional soccer player?", relevant training menus and success stories are retrieved from the database.

[0895] Emotion Engine

[0896] The emotion engine analyzes a user's emotions from their questions and profile information. This engine works in conjunction with the natural language processing engine to analyze the user's emotions and psychological state, and feeds the results back to the generative AI model. For example, in response to the question, "I've been losing games lately and I'm feeling depressed. What should I do?" emotions such as "depression" and "anxiety" are recognized.

[0897] Generate and submit answers

[0898] The central server uses the generative AI model to generate an appropriate answer to the user's question based on the analysis results of the natural language processing engine and emotion engine. The generated answer adjusts the tone and expression to take emotion into account, making it more relatable to the user. The generated answer is then sent back to the user's device, where it is displayed on the screen. The user can then check the displayed answer and enter a new question if necessary.

[0899] Specific examples

[0900] For example, if a user enters a question such as, "I've been losing games lately and I'm feeling down. What should I do?", the question is sent from the user's device to the central server. The server receives the question and analyzes it using a natural language processing engine and an emotion engine. As a result of the analysis, the emotion "down" is recognized. Next, the generative AI model retrieves relevant information from the database based on the analysis results and generates an answer such as, "Losing is part of the experience. Let's work hard together to achieve better results next time!" This answer is sent to the user's device and displayed. The user can review the answer and ask the question again if necessary.

[0901] Prompt Sentence Examples

[0902] "I've been losing a lot of games lately and I'm feeling down. What should I do?"

[0903] "I want to be a professional soccer player. What kind of training do I need?"

[0904] The present invention allows users to receive specific and empathetic answers that are tailored to their own situations and feelings, enabling better career counseling.

[0905] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0906] Step 1:

[0907] The user uses a terminal to input a question. For example, they might input something like, "I've been losing games lately and I'm feeling depressed. What should I do?" The input question is sent to a central server via the Internet. The input data is sent to the server in text format.

[0908] Step 2:

[0909] The central server receives questions sent from user devices. The server temporarily stores the received questions and passes them to a natural language processing engine. The input data is the user's question text, and the output is data for analysis.

[0910] Step 3:

[0911] The server's natural language processing engine analyzes the received question. Morphological analysis is performed to extract important keywords and context from the question. For example, keywords such as "game," "keep losing," "feelings," and "depressed" are extracted from the question. The input data is the user's question text, and the output is keywords and context information.

[0912] Step 4:

[0913] The server's emotion engine analyzes the user's emotions from the question. Based on the analysis results of the natural language processing engine, the emotional nuances contained in the question are analyzed. For example, the emotion "depressed" is recognized. The input data is the analyzed keywords and text, and the output is emotional information such as "depressed."

[0914] Step 5:

[0915] The server uses a generative AI model to generate queries to the database based on the analysis results of the natural language processing engine and emotion engine. For example, based on information such as "feeling depressed" or "continuously losing games," it creates a query to retrieve related database information. The input data is the analysis results and emotion information, and the output is a database query.

[0916] Step 6:

[0917] The server uses the generated query to search a database that contains information such as the experiences of professional athletes, advice from agents, and training menus. The search results include information on related training content and past success stories. The input data is the query, and the output is the search results.

[0918] Step 7:

[0919] The server uses the acquired information and the results of emotion analysis to generate an appropriate answer to the user's question using a generative AI model. For example, it generates a response such as, "Losing is part of the experience. Let's work hard together to achieve better results next time!" The input data are search results and emotion information, and the output is the generated answer.

[0920] Step 8:

[0921] The tone and expression of the answers generated by the generative AI model are adjusted within the server. For example, to make the answer more relatable to the user, the answer may be adjusted to include more kindness or encouragement. The input data is the generated answer, and the output is the adjusted answer.

[0922] Step 9:

[0923] The server sends the final answer to the user terminal using the HTTP / HTTPS protocol, and the answer data is encoded in JSON format. The input data is the adjusted answer, and the output is the transmitted data.

[0924] Step 10:

[0925] The user terminal displays the answer received from the server on the screen. The user can check the displayed answer and re-enter the question if necessary. The input data is the received data, and the output is the answer displayed to the user.

[0926] (Application example 2)

[0927] 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."

[0928] Conventional online counseling systems provide information without considering the user's emotions, making it difficult to provide appropriate advice suited to each user's psychological state. In particular, when dealing with security-related inquiries or psychological stress, emotion analysis and emotion-based response generation are necessary, but few systems have such functionality.

[0929] 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 a question input from a user terminal; means for passing the question content to a natural language processing engine for analysis; means for acquiring related information from a database based on the analysis results; means for generating an answer based on the acquired information and sending it to the user terminal; means for analyzing the user's emotions using an emotion engine and reflecting the results in answer generation; and means for the generative AI model for sending a query to an endpoint and generating an answer using a prompt sentence for generating appropriate advice. This makes it possible to provide appropriate counseling that takes into account the user's emotions and psychological state.

[0930] A "user terminal" is an electronic device that allows a user to input questions and receive answers, and includes a smartphone or computer.

[0931] A "natural language processing engine" is software that analyzes input natural language text and extracts keywords and context.

[0932] The "database" is an electronic information management system for storing information such as the experiences of professional athletes, stories of athletes who tried but failed, and advice from agents.

[0933] The "emotion engine" is software that analyzes a user's emotions from their questions and profile information, and feeds the results back to the generative AI model.

[0934] A "generative AI model" is an artificial intelligence system that generates appropriate answers and advice based on the analysis results provided by a natural language processing engine and an emotion engine.

[0935] A "prompt" is an instruction used by a generative AI model to generate an appropriate response, which may include contextual and emotional information.

[0936] System Overview

[0937] This invention is a system that allows junior athletes and security service users to receive specific career counseling and advice on psychological stress online. The system's main components are a user terminal, a central server, a database, an emotion engine, and a generative AI model.

[0938] User terminal

[0939] A user terminal is a device through which a user enters a question and receives a response. Specifically, this can be a smartphone or a computer. The user enters a question into the terminal using text or voice input, and the content is transmitted to a central server via the Internet.

[0940] Central Server

[0941] The central server plays a central role in analyzing incoming questions and generating appropriate answers. The server is equipped with a natural language processing engine, an emotion engine, and a generative AI model, which work together to create answers to users' questions.

[0942] Database

[0943] The database stores information such as the experiences of professional players, stories of players who tried but failed, and advice from agents, etc. Appropriate information is searched from this database and used to generate answers for the generative AI model.

[0944] Emotion Engine

[0945] The emotion engine analyzes user emotions from their questions and profile information. This engine works in conjunction with the natural language processing engine to analyze the user's emotions and psychological state, and feeds the results back to the generative AI model.

[0946] Program processing

[0947] Question reception and sentiment analysis

[0948] The server receives the question sent from the user's device. It then passes the question to a natural language processing engine to begin analysis. At the same time, an emotion engine runs to recognize the user's emotion from the question, thereby extracting emotional nuances and intensity.

[0949] Natural Language Processing and Analysis

[0950] The natural language processing engine on the server analyzes the received question and extracts important keywords and context. The analysis results are passed to the generative AI model. The emotion analysis results from the emotion engine are also provided to the generative AI model.

[0951] Searching the database

[0952] The generative AI model generates queries to the database based on the analyzed keywords, context, and sentiment information, and based on these queries, relevant information is retrieved from the database.

[0953] Generate answers

[0954] Based on the acquired information and the results of sentiment analysis, the generative AI model generates an appropriate response to the user's question. The generated response adjusts tone and expression to take emotions into account, making it more relatable to the user.

[0955] Submitting and viewing answers

[0956] The generated answer is sent back to the user terminal, where it is displayed for the user to review. The user can then review the displayed answer and re-enter the question if necessary.

[0957] Specific examples

[0958] For example, if a user inputs a question such as, "Work hasn't been going well recently and I'm feeling stressed. What should I do?", the emotion engine will recognize the emotion "stress." This emotion information, along with the analysis results, will be provided to the generative AI model. Based on the analysis results, the generative AI model will retrieve information from related databases and generate an answer that includes appropriate counseling and advice for dealing with "stress." This answer will then be sent to the user's device and displayed.

[0959] Example prompt sentence:

[0960] "A user asked the question, 'Work hasn't been going well lately and I'm feeling stressed. What should I do?' The emotion is 'stressed' and the tone is 'high.' Please provide appropriate counseling and advice."

[0961] In this way, by combining emotion engines, it becomes possible to respond in accordance with the user's psychological state, thereby providing better support.

[0962] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0963] Step 1: Receiving the question

[0964] The server receives a question input from the user terminal. The input includes the question text from the user terminal. For example, a question such as "Work hasn't been going well lately and I'm feeling stressed. What should I do?" is sent. This question text is passed to the next processing step as is.

[0965] Step 2: Sentiment Analysis

[0966] The emotion engine in the server analyzes the received question text. The question text received in step 1 is used as input. The emotion engine extracts emotions from the question content and assigns emotion labels such as "stress" or "depression." For example, the emotion "stress" is recognized from the question. This emotion information is output as a label and its intensity (score) and passed to the next step.

[0967] Step 3: Natural Language Processing

[0968] The natural language processing engine on the server analyzes the question text. As input, it uses the question text received in step 1 and the emotional information obtained in step 2. The natural language processing engine extracts keywords and context from the question. For example, keywords such as "work" and "stress" are extracted. The results of this analysis are output in text format and passed to the next step.

[0969] Step 4: Database Search

[0970] The server generates a query to the database based on the analysis results of natural language processing and emotional information. It uses the outputs of steps 2 and 3 as input. The database contains personal experiences of professional athletes and agents, as well as psychological advice information. Based on the query, the server searches the database for relevant information. For example, it retrieves "advice related to stress." The search results are output in text format and passed to the next step.

[0971] Step 5: Answer Generation

[0972] The generative AI model on the server generates an answer to the question based on information retrieved from the database. The search results obtained in step 4 and the analysis results from steps 2 and 3 are used as input. The generative AI model uses prompt text to generate an appropriate answer. For example, a prompt text such as "The user asked, 'Work hasn't been going well recently and I'm feeling stressed. What should I do?' The emotion is 'stressed' and the tone is 'high'. Please provide appropriate counseling and advice" is created and input into the AI ​​model. The generated answer is advice such as "First, take a deep breath and relax. Next, break down your work into small tasks and tackle them one by one," and is output in text format.

[0973] Step 6: Submit your response

[0974] The server sends the generated answer to the user's terminal. The answer text obtained in step 5 is used as input. The answer is sent to the user's terminal, and the user can check its contents. As output, the answer in text format is displayed on the user's terminal. The user can consider their next action based on the displayed answer.

[0975] This processing step allows the user to receive specific and effective advice that is in line with their own feelings and circumstances.

[0976] 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.

[0977] 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.

[0978] 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.

[0979] [Fourth embodiment]

[0980] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0981] 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.

[0982] 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).

[0983] 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.

[0984] 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.

[0985] 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).

[0986] 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.

[0987] 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.

[0988] 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.

[0989] 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.

[0990] 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.

[0991] 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.

[0992] 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."

[0993] This invention relates to a system that uses a generative AI model to provide specific career counseling to junior athletes. The system's main components are a user terminal, a central server, and a database. Users can use this system to obtain specific career plans and realistic information for those aiming to become professional athletes.

[0994] System Overview

[0995] User terminal

[0996] The user terminal is a device used by junior athletes and their guardians to input questions and receive answers. Typically, a smartphone or computer is used. Questions input from the user terminal are sent to a central server via the Internet.

[0997] Central Server

[0998] The central server plays a central role in analyzing incoming questions and generating appropriate answers. The server is equipped with a natural language processing engine and generative AI models, which work together to create answers to users' questions.

[0999] Database

[1000] The database contains information such as the experiences of professional players, stories of players who tried but failed, advice from agents, etc. Appropriate information is searched from this database and used to generate answers for the generative AI model.

[1001] Program processing

[1002] Receiving questions

[1003] A question sent from a user terminal is received by a central server, which first passes the question to a natural language processing engine to begin analysis.

[1004] Natural Language Processing and Analysis

[1005] The server's natural language processing engine analyzes the incoming question and extracts important keywords and context, and the results of this analysis are passed to a generative AI model.

[1006] Searching the database

[1007] The generative AI model then generates queries based on the analysis results, which retrieve relevant information from the database (such as the experiences of professional players or advice from agents).

[1008] Generate answers

[1009] Based on the acquired information, the generative AI model generates an appropriate answer to the user's question, which is then sent back to the user's device.

[1010] Specific examples

[1011] For example, if a user enters the question, "What are the benefits of going to college after graduating from high school to become a professional tennis player?", the question is first sent to the server. The natural language processing engine on the server extracts the keywords "professional tennis player," "high school graduation," "going to college," and "benefits." Next, the generative AI model searches a database based on these keywords to obtain information on cases of players who have succeeded as professionals after going to college and the benefits of going to college. Finally, the generative AI model generates an answer such as, "There are several cases of players who have succeeded as professionals after going to college, and it is beneficial for some players because it allows them to balance their studies with a shared training environment," and sends this to the user's device.

[1012] In this way, the present invention enables junior athletes and their guardians to easily draw up specific and realistic career plans, independent of location and information asymmetry.

[1013] The processing flow will be explained below.

[1014] Step 1:

[1015] Enter a question from the user's device. The user launches the career consultation app and enters the question in the text box. Once the question is complete, the user clicks the send button.

[1016] Step 2:

[1017] The user terminal sends the question to the central server. Once the user has completed the input, the question is sent to the central server via the Internet.

[1018] Step 3:

[1019] The server receives the questions. The central server receives the questions sent from the user terminals and passes the data to the text analysis module.

[1020] Step 4:

[1021] The server passes the question to a natural language processing engine for analysis. The text analysis module sends the question to the natural language processing engine, which analyzes the question and extracts keywords and context.

[1022] Step 5:

[1023] The server passes the analysis results to the generative AI model, and the analysis results obtained from the natural language processing engine are fed back to the generative AI model.

[1024] Step 6:

[1025] The server generates and sends a query to the database. The generative AI model generates a query to obtain the necessary information based on the analysis results and sends it to the database.

[1026] Step 7:

[1027] The database returns relevant information. Based on the query, the database searches for relevant information (experiences of professional players, stories of professional challenges, advice from agents, etc.) and returns this to the central server.

[1028] Step 8:

[1029] The server generates an answer based on the information it obtains. The generative AI model analyzes the information received from the database and generates an appropriate answer to the user's question.

[1030] Step 9:

[1031] The server transmits the generated answer to the user terminal, and performs communication to transmit the generated answer to the user terminal.

[1032] Step 10:

[1033] The user terminal displays the answer. The user terminal displays the answer received from the central server so that the user can confirm it. The user can confirm the displayed answer and enter the question again if necessary.

[1034] Through this series of processes, the system can provide quick and appropriate answers to users' questions.

[1035] Example 1

[1036] 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."

[1037] Traditional career counseling systems make it difficult for junior athletes and their guardians to obtain the information they need to draw up specific and realistic career plans. In particular, there is a lack of concrete advice based on experience and a path to becoming a professional athlete, making it difficult to obtain sufficient information when formulating a specific career plan.

[1038] 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.

[1039] In this invention, the server includes means for receiving a question input from a user terminal, means for passing the question content to a natural language processing engine for analysis, means for retrieving related information from a database based on the analysis results, and means for generating an answer based on the retrieved information and transmitting it to the user terminal. This enables junior players and their parents to easily draw up specific and realistic career plans based on the experiences of professional players and agents.

[1040] A "user device" is an electronic device such as a computer or smartphone that junior athletes and their parents use to enter questions and check answers.

[1041] A "question" is a question that a user inputs to obtain specific information about their career plan or how to become a professional athlete.

[1042] A "server" is a central computer system that receives questions sent from user terminals, analyzes them, generates appropriate answers, and sends them to the user terminals.

[1043] A "natural language processing engine" is a software component that analyzes the content of questions from users and extracts keywords and context.

[1044] A "database" is a collection of information that stores relevant information such as the experiences of professional athletes and advice from agents.

[1045] A "generative AI model" is an algorithm that generates appropriate answers to user questions using information obtained from a database based on the results analyzed by a natural language processing engine.

[1046] A "query" is a specific search condition or instruction that a generative AI model generates to search a database based on the analysis results.

[1047] An "answer" is the specific information or advice that the generative AI model generates in response to a user's question and sends to the user's device.

[1048] "Profile information" is personal data that is useful for career counseling, such as the user's age, type of sport, and goals.

[1049] "Selection" refers to the act of choosing the most suitable generative AI model based on the user's profile information and questions.

[1050] This invention relates to a system that uses a generative AI model to provide specific career counseling for junior athletes. The system's main components are a user terminal, a central server, and a database.

[1051] User terminal

[1052] The user terminal is a device used by junior athletes and their parents to input questions and receive answers. Typically, a smartphone or computer is used. Questions input from the user terminal are sent to a central server via the Internet.

[1053] Central Server

[1054] The central server plays a central role in analyzing incoming questions and generating appropriate answers. The server is equipped with a natural language processing engine and generative AI models, which work together to create answers to users' questions.

[1055] Database

[1056] The database contains information such as the experiences of professional players, stories of players who tried but failed, advice from agents, etc. Appropriate information is searched from this database and used to generate answers for the generative AI model.

[1057] Program processing

[1058] A question sent from a user device is first received by a central server. The server then passes the question to a natural language processing engine to begin analysis. The natural language processing engine in the server analyzes the received question and extracts important keywords and context. The results of this analysis are then passed to a generative AI model.

[1059] The generative AI model generates a query to the database based on the analysis results. Based on this query, relevant information (for example, the experiences of professional athletes or advice from agents) is retrieved from the database. Based on the retrieved information, the generative AI model generates an appropriate answer to the user's question. The generated answer is then sent back to the user's device.

[1060] Usage example

[1061] For example, if a user enters the question, "What are the benefits of going to college after graduating from high school to become a professional tennis player?", the question is first sent to the server. The natural language processing engine on the server extracts the keywords "professional tennis player," "high school graduation," "going to college," and "benefits." Next, the generative AI model searches a database based on these keywords to obtain information on cases of players who have succeeded as professionals after going to college and the benefits of going to college. Finally, the generative AI model generates an answer such as, "There are several cases of players who have succeeded as professionals after going to college, and it is beneficial for some players because it allows them to share a training environment and balance their studies," and sends this to the user's device.

[1062] In this way, the present invention allows junior athletes and their guardians to easily create specific and realistic career plans, regardless of location or information asymmetry. It is also possible to select the optimal generative AI model based on the user's profile information to provide information that best suits the user's characteristics.

[1063] Prompt Sentence Examples

[1064] "What is the best career plan for becoming a professional basketball player?"

[1065] "Is it better to aim to become a professional immediately after graduating from high school or to go to college and then aim to do so?"

[1066] Please tell me how to choose an agent.

[1067] "What kind of training did successful professional athletes do?"

[1068] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1069] Step 1:

[1070] A user terminal inputs a question from the user.

[1071] Input: The user inputs characters and enters the question.

[1072] What happens: A user types the question "What are the benefits of going to college after high school to become a professional tennis player?" into a text input field on their smartphone or computer.

[1073] Step 2:

[1074] A user terminal sends a query to a central server.

[1075] Input: The question typed by the user.

[1076] Specific operation: The device sends the question to a central server via the Internet.

[1077] Output: The query is received by the central server.

[1078] Step 3:

[1079] The server passes the question to a natural language processing engine and begins analysis.

[1080] Input: The query received by the central server.

[1081] How it works: The server passes the question to a natural language processing engine, which extracts important keywords such as "professional tennis player," "high school graduation," "college enrollment," and "merits."

[1082] Output: Parsed keywords and context information.

[1083] Step 4:

[1084] The server generates a query based on the analysis results and searches the database.

[1085] Input: Analysis results (keywords and context information) from the natural language processing engine.

[1086] Specific operation: The generative AI model generates a specific search query for the database based on the analysis results. For example, it generates a query such as "professional tennis player, high school graduate, college admission, merits."

[1087] Output: Relevant information retrieved from the database (e.g., professional player experiences, agent advice, etc.).

[1088] Step 5:

[1089] The server generates a response based on the information it has obtained.

[1090] Input: Relevant information retrieved from the database.

[1091] Specific operation: Based on the information acquired by the generative AI model, it generates an appropriate answer to the user's question. For example, it generates an answer such as, "There are several examples of players who have successfully become professionals after attending university, and it is beneficial for some players because it allows them to balance their studies with a shared training environment."

[1092] Output: The generated answer.

[1093] Step 6:

[1094] The server generates a response and sends it to the user terminal.

[1095] Input: The generated answer text.

[1096] Specific operation: The server sends the response to the user terminal.

[1097] Output: The answer text displayed on the user's terminal.

[1098] Step 7:

[1099] The user reviews the answer and decides on the next action.

[1100] Input: The answer displayed on the user's terminal.

[1101] Specific operation: The user checks the answer displayed on the device. For example, they may decide, "Now that I understand the benefits of going to college, I'll consider that path."

[1102] Output: The user's new understanding or next action.

[1103] (Application example 1)

[1104] 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."

[1105] It is difficult for junior players and their guardians to obtain real-time information on specific career plans for those aiming to become professional players. Furthermore, there is no way to easily input questions in-store and receive appropriate answers on the spot, which reduces the efficiency of career counseling. This makes it difficult to obtain the necessary information at the right time, potentially resulting in delays in career development.

[1106] 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.

[1107] In this invention, the server includes means for receiving a question input from a user terminal, means for passing the content of the question to a natural language processing engine for analysis, means for retrieving related information from a database based on the analysis results, means for generating an answer based on the retrieved related information and transmitting it to the user terminal, and means for inputting a question using a smart terminal in the store and retrieving the answer in real time, thereby enabling junior athletes and their guardians to easily receive career counseling in the store and obtain prompt and appropriate information.

[1108] A "user terminal" is a device used by a user to input questions and receive answers, and refers to an electronic device such as a smartphone or computer.

[1109] The term "means for receiving a question" refers to a function for transmitting a question input from a user terminal to a server and receiving the question.

[1110] A "natural language processing engine" refers to technology that analyzes input questions and extracts important keywords and context.

[1111] "Means of analysis" refers to the process of passing the question content to a natural language processing engine for analysis.

[1112] "Relevant information" refers to information in the database that is necessary to generate an appropriate answer to a user's question.

[1113] "Database" refers to a collection of data containing information such as the experiences of professionals, challengers, and intermediaries.

[1114] "Means for obtaining" refers to the function for searching and obtaining related information from a database based on the analysis results.

[1115] "Means for generating an answer" refers to the process for creating an appropriate answer to a user's question based on the relevant information obtained.

[1116] "Means for obtaining information in real time" refers to a function for quickly generating and providing answers on the spot to questions entered by users in the store.

[1117] "In-store" refers to physical locations visited by junior athletes and their parents, such as sporting goods stores and sports clubs.

[1118] This invention relates to a system that allows junior athletes and their guardians to obtain specific career plans and information for becoming professional athletes in real time within sporting goods stores and sports clubs. The system's main components are a user terminal, a central server, and a database, and it operates as follows:

[1119] First, the user terminal is a device that junior players and their guardians use to input questions and receive answers. Common electronic devices such as smartphones, tablets, and laptops can be used as user terminals. This allows users to easily access the system within the store.

[1120] Next, when a question is entered from the user's device, it is sent via the Internet to a central server. The central server receives the question and first analyzes it using a natural language processing engine. For example, Python's openai library is used as the natural language processing engine. The content of the question is analyzed, and important keywords and context are extracted.

[1121] Based on the analysis results, the central server generates a query to a database to search for relevant information. The database contains the experiences and advice of professionals, challengers, and intermediaries, and appropriate information is retrieved from this database. Based on the retrieved information, a generative AI model generates an appropriate answer to the user's question. For example, the OpenAI API is used as the generative AI model.

[1122] The generated answer is then sent back to the user's device, allowing the user to receive the answer in real time. This series of processes allows users to easily receive career advice in-store and quickly obtain useful information.

[1123] As a specific example, if a user enters the question, "What are the benefits of going to college after graduating from high school to become a professional tennis player?", the question is sent to a central server, and the natural language processing engine extracts the keywords "professional tennis player," "high school graduation," "going to college," and "benefits." Next, the generative AI model searches a database based on these keywords to obtain information on cases of players who have succeeded as professionals after going to college and the benefits of going to college. Finally, the generative AI model generates an answer such as, "There are several cases of players who have succeeded as professionals after going to college, and it is beneficial for some players because it allows them to share a training environment and balance their studies," and sends this to the user's device.

[1124] In this way, the present invention allows junior athletes and their guardians to create specific and realistic career plans in real time within the store.

[1125] An example prompt is:

[1126] Question: What are the benefits of going to college after high school to become a professional tennis player?

[1127] Extract keywords: professional tennis player, high school graduation, college admission, benefits

[1128] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1129] Step 1:

[1130] The user's device inputs a question and sends it to a central server. The user inputs a question on a smartphone or tablet, and the input text data is sent to the server via an HTTP request or similar. The input is in text format, and the user's specific question is sent as text. The output is the question text.

[1131] Step 2:

[1132] The server passes the received question to a natural language processing engine for analysis. Specifically, the server uses the Python openai library to analyze the question and extract important keywords and context. The input is the question text submitted by the user, and the output is a list of extracted keywords.

[1133] Step 3:

[1134] The server generates queries to a database based on the extracted keywords to search and retrieve relevant information. The database stores the experiences and career-related information of professionals, challengers, and intermediaries. The input is a list of extracted keywords, and the output is a list of related information.

[1135] Step 4:

[1136] Based on the related information acquired by the server, a generative AI model is used to generate an appropriate answer to the user's question. For example, the OpenAI API is used as the generative AI model. The input is a list of related information acquired from a database, and the output is the generated answer text.

[1137] Step 5:

[1138] The server sends the generated answer to the user's device, and the user receives the answer in real time. Specifically, the answer is sent from the server to the user's device via an HTTP response or similar and is displayed on the user's device screen. The input is the generated answer text, and the output is the answer displayed on the user's device.

[1139] This series of processes allows users to obtain specific career plans and information in real time within the store, significantly improving the efficiency of career consultations.

[1140] 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.

[1141] This invention relates to a system that uses a generative AI model to provide specific career counseling to junior athletes. The system's main components are a user terminal, a central server, a database, and an emotion engine. Users can use this system to obtain specific career plans and realistic information for those aiming to become professional athletes. Furthermore, by using the emotion engine, appropriate answers can be provided based on the user's emotions and psychological state.

[1142] System Overview

[1143] User terminal

[1144] The user terminal is a device used by junior athletes and their guardians to input questions and receive answers. Typically, a smartphone or computer is used. Questions input from the user terminal are sent to a central server via the Internet.

[1145] Central Server

[1146] The central server plays a central role in analyzing incoming questions and generating appropriate answers. The server is equipped with a natural language processing engine, an emotion engine, and a generative AI model, which work together to create answers to users' questions.

[1147] Database

[1148] The database contains information such as the experiences of professional players, stories of players who tried but failed, advice from agents, etc. Appropriate information is searched from this database and used to generate answers for the generative AI model.

[1149] Emotion Engine

[1150] The emotion engine analyzes user emotions from their questions and profile information. This engine works in conjunction with the natural language processing engine to analyze the user's emotions and psychological state, and feeds the results back to the generative AI model.

[1151] Program processing

[1152] Question reception and sentiment analysis

[1153] A question sent from a user's device is received by a central server. The server first passes the question to a natural language processing engine for analysis. An emotion engine also runs simultaneously to recognize the user's emotion from the question, thereby extracting emotional nuances and intensity.

[1154] Natural Language Processing and Analysis

[1155] The natural language processing engine on the server analyzes the received question and extracts important keywords and context. The analysis results are passed to the generative AI model. The emotion analysis results from the emotion engine are also provided to the generative AI model.

[1156] Searching the database

[1157] The generative AI model uses the analyzed keywords, context, and sentiment information to generate queries against the database, which then retrieves relevant information from the database (such as professional player experiences or agent advice).

[1158] Generate answers

[1159] Based on the acquired information and the results of sentiment analysis, the generative AI model generates an appropriate response to the user's question. The generated response adjusts tone and expression to take emotions into account, making it more relatable to the user.

[1160] Submitting and viewing answers

[1161] The generated answer is sent back to the user terminal, where it is displayed for the user to review. The user can then review the displayed answer and re-enter the question if necessary.

[1162] Specific examples

[1163] For example, if a user inputs a question such as, "I've been losing games lately and I'm feeling depressed. What should I do?", the emotion engine will recognize the emotion "depressed." This emotional information, along with the analysis results, will be provided to the generative AI model. The generative AI model will then use the analysis results to retrieve relevant database information and generate an answer containing appropriate encouragement and advice for dealing with the "depressed" feeling. This answer will then be sent to the user's device and displayed.

[1164] In this way, by combining emotion engines, it becomes possible to respond in accordance with the user's psychological state, thereby providing better support.

[1165] The processing flow will be explained below.

[1166] Step 1:

[1167] The user enters a question from their device. The user launches the career consultation app and enters the question, "I've been losing games lately and I'm feeling depressed. What should I do?" into the text box. Once the question is entered, the user clicks the send button.

[1168] Step 2:

[1169] The user terminal sends the question to the central server. Once the user has completed the input, the question is sent to the central server via the Internet.

[1170] Step 3:

[1171] The server receives the questions. The central server receives the questions sent from the user terminal and passes the data to the text analysis module and emotion engine.

[1172] Step 4:

[1173] The server passes the question to a natural language processing engine for analysis. The text analysis module sends the question, "I've been losing games lately and I'm feeling down. What should I do?" to the natural language processing engine, which analyzes the question and extracts keywords and context such as "game," "keep losing," "feelings," "depressed," and "what should I do."

[1174] Step 5:

[1175] The server passes the question to the emotion engine, which analyzes the emotion. The emotion engine analyzes the question and recognizes the emotion "depressed." This emotional information is fed back to the generative AI model.

[1176] Step 6:

[1177] The server passes the analysis results and emotional information to the generative AI model. The analysis results and emotional information obtained from the natural language processing engine and emotion engine are fed back to the generative AI model.

[1178] Step 7:

[1179] The server generates and sends a query to the database. Based on the analysis results and emotional information, the generative AI model generates a query to obtain information related to "constant losses" and "depression" and sends it to the database.

[1180] Step 8:

[1181] The database returns relevant information. Based on the query, the database searches for information such as professional player experiences (e.g., words of encouragement and advice from players who have had similar experiences) or agent advice (e.g., mental coping strategies) and sends this back to the central server.

[1182] Step 9:

[1183] The server generates an answer based on the information it obtains. The generative AI model analyzes the information received from the database and emotional information, and generates an appropriate answer to the user's question, "I've been losing games lately and I'm feeling down. What should I do?" For example, it might say, "Many professional players have had similar experiences. The important thing is to reflect on your own growth without getting caught up in the results. Professional player A also experienced similar feelings at the same time, but by reviewing his training routine, he was able to achieve better results in his next game."

[1184] Step 10:

[1185] The server transmits the generated answer to the user terminal, and performs communication to transmit the generated answer to the user terminal.

[1186] Step 11:

[1187] The user terminal displays the answer. The user terminal displays the answer received from the central server so that the user can confirm it. The user can confirm the displayed answer and enter the question again if necessary.

[1188] Through this series of processes, the system not only provides quick and appropriate answers to users' questions, but also enables support that takes into account the user's emotions.

[1189] Example 2

[1190] 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."

[1191] Conventional career counseling systems have difficulty providing appropriate answers to user questions that take into account emotions and context. In particular, when junior athletes and others seek career counseling in an emotional state, answers that are sensitive to the user's emotions are required, but conventional systems have not been able to adequately meet this demand. Furthermore, they lack the functionality to provide specific answers based on the experiences and advice of experts.

[1192] 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.

[1193] In this invention, the server includes means for receiving a question input from a user terminal, means for passing the question content to a natural language processing engine for analysis, means for analyzing the user's emotions from the analysis results using an emotion engine, means for retrieving related information from a database based on the analysis results and emotion information, and means for generating an answer based on the retrieved information and emotion information, adjusting the tone and expression, and transmitting the answer to the user terminal. This makes it possible to provide a highly empathetic answer that takes emotion and context into consideration.

[1194] "User Device" refers to the device used by junior athletes and their parents to input questions and receive answers. Smartphones and computers are commonly used.

[1195] The "Central Server" is a system that plays a central role in receiving and analyzing user questions and generating appropriate answers. It is equipped with a natural language processing engine, an emotion engine, and a generative AI model.

[1196] A "natural language processing engine" is an engine that analyzes received questions and extracts important keywords and context.

[1197] The "emotion engine" is an engine that analyzes user emotions from their questions and profile information. It works in conjunction with the natural language processing engine.

[1198] A "generative AI model" is a model that generates answers to user questions based on analysis results and sentiment analysis results.

[1199] The "database" is a data store that stores information such as the experiences of professional players, stories of players who tried but failed, and advice from agents.

[1200] "Receiving a question" is the process by which the central server receives a question sent from a user terminal.

[1201] "Question analysis" is the process in which the natural language processing engine performs morphological analysis of the question to extract important keywords and context. The emotion engine also works simultaneously to recognize emotions.

[1202] "Related information retrieval" is the process of searching and retrieving related information from a database based on the generated query.

[1203] "Answer generation" is the process in which the generative AI model creates an appropriate answer to the user's question based on the acquired information and the results of sentiment analysis.

[1204] "Tone and expression adjustment" is the process of adjusting the generated response to make it more relatable to the user's emotions and psychological state.

[1205] "Sending an answer" is the process of sending the generated answer to the user terminal.

[1206] "Displaying the answer" is the process in which the user terminal displays the answer received from the central server on the screen so that the user can check it.

[1207] This invention relates to a system that uses a generative AI model to provide specific career counseling to junior athletes. The system's main components are a user terminal, a central server, a database, and an emotion engine. Users can use this system to obtain specific career plans and realistic information for those aiming to become professional athletes. Furthermore, by using the emotion engine, appropriate answers can be provided based on the user's emotions and psychological state.

[1208] User terminal

[1209] A user terminal is a device used by junior athletes and their guardians to input questions and receive answers. Typically, a smartphone or computer is used. Specifically, users can input and submit questions through a dedicated application or web browser on the terminal. Questions input from the user terminal are transmitted to a central server via the Internet.

[1210] Central Server

[1211] The central server plays a central role in analyzing received questions and generating appropriate answers. The server is equipped with a natural language processing engine, an emotion engine, and a generative AI model, which work together to create answers to users' questions. Specifically, the server first passes the question to the natural language processing engine, which performs morphological analysis. This analysis extracts important keywords and context. The emotion engine also works simultaneously to recognize the user's emotions from the content of the question.

[1212] Database

[1213] The database contains information such as the experiences of professional players, stories of players who tried but failed, and advice from agents. Appropriate information is searched for in this database and used to generate answers for the generative AI model. For example, in response to the question, "What kind of training is required to become a professional soccer player?", relevant training menus and success stories are retrieved from the database.

[1214] Emotion Engine

[1215] The emotion engine analyzes a user's emotions from their questions and profile information. This engine works in conjunction with the natural language processing engine to analyze the user's emotions and psychological state, and feeds the results back to the generative AI model. For example, in response to the question, "I've been losing games lately and I'm feeling depressed. What should I do?" emotions such as "depression" and "anxiety" are recognized.

[1216] Generate and submit answers

[1217] The central server uses the generative AI model to generate an appropriate answer to the user's question based on the analysis results of the natural language processing engine and emotion engine. The generated answer adjusts the tone and expression to take emotion into account, making it more relatable to the user. The generated answer is then sent back to the user's device, where it is displayed on the screen. The user can then check the displayed answer and enter a new question if necessary.

[1218] Specific examples

[1219] For example, if a user enters a question such as, "I've been losing games lately and I'm feeling down. What should I do?", the question is sent from the user's device to the central server. The server receives the question and analyzes it using a natural language processing engine and an emotion engine. As a result of the analysis, the emotion "down" is recognized. Next, the generative AI model retrieves relevant information from the database based on the analysis results and generates an answer such as, "Losing is part of the experience. Let's work hard together to achieve better results next time!" This answer is sent to the user's device and displayed. The user can review the answer and ask the question again if necessary.

[1220] Prompt Sentence Examples

[1221] "I've been losing a lot of games lately and I'm feeling down. What should I do?"

[1222] "I want to be a professional soccer player. What kind of training do I need?"

[1223] The present invention allows users to receive specific and empathetic answers that are tailored to their own situations and feelings, enabling better career counseling.

[1224] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1225] Step 1:

[1226] The user uses a terminal to input a question. For example, they might input something like, "I've been losing games lately and I'm feeling depressed. What should I do?" The input question is sent to a central server via the Internet. The input data is sent to the server in text format.

[1227] Step 2:

[1228] The central server receives questions sent from user devices. The server temporarily stores the received questions and passes them to a natural language processing engine. The input data is the user's question text, and the output is data for analysis.

[1229] Step 3:

[1230] The server's natural language processing engine analyzes the received question. Morphological analysis is performed to extract important keywords and context from the question. For example, keywords such as "game," "keep losing," "feelings," and "depressed" are extracted from the question. The input data is the user's question text, and the output is keywords and context information.

[1231] Step 4:

[1232] The server's emotion engine analyzes the user's emotions from the question. Based on the analysis results of the natural language processing engine, the emotional nuances contained in the question are analyzed. For example, the emotion "depressed" is recognized. The input data is the analyzed keywords and text, and the output is emotional information such as "depressed."

[1233] Step 5:

[1234] The server uses a generative AI model to generate queries to the database based on the analysis results of the natural language processing engine and emotion engine. For example, based on information such as "feeling depressed" or "continuously losing games," it creates a query to retrieve related database information. The input data is the analysis results and emotion information, and the output is a database query.

[1235] Step 6:

[1236] The server uses the generated query to search a database that contains information such as the experiences of professional athletes, advice from agents, and training menus. The search results include information on related training content and past success stories. The input data is the query, and the output is the search results.

[1237] Step 7:

[1238] The server uses the acquired information and the results of emotion analysis to generate an appropriate answer to the user's question using a generative AI model. For example, it generates a response such as, "Losing is part of the experience. Let's work hard together to achieve better results next time!" The input data are search results and emotion information, and the output is the generated answer.

[1239] Step 8:

[1240] The tone and expression of the answers generated by the generative AI model are adjusted within the server. For example, to make the answer more relatable to the user, the answer may be adjusted to include more kindness or encouragement. The input data is the generated answer, and the output is the adjusted answer.

[1241] Step 9:

[1242] The server sends the final answer to the user terminal using the HTTP / HTTPS protocol, and the answer data is encoded in JSON format. The input data is the adjusted answer, and the output is the transmitted data.

[1243] Step 10:

[1244] The user terminal displays the answer received from the server on the screen. The user can check the displayed answer and re-enter the question if necessary. The input data is the received data, and the output is the answer displayed to the user.

[1245] (Application example 2)

[1246] 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."

[1247] Conventional online counseling systems provide information without considering the user's emotions, making it difficult to provide appropriate advice suited to each user's psychological state. In particular, when dealing with security-related inquiries or psychological stress, emotion analysis and emotion-based response generation are necessary, but few systems have such functionality.

[1248] 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 a question input from a user terminal; means for passing the question content to a natural language processing engine for analysis; means for acquiring related information from a database based on the analysis results; means for generating an answer based on the acquired information and sending it to the user terminal; means for analyzing the user's emotions using an emotion engine and reflecting the results in answer generation; and means for the generative AI model for sending a query to an endpoint and generating an answer using a prompt sentence for generating appropriate advice. This makes it possible to provide appropriate counseling that takes into account the user's emotions and psychological state.

[1249] A "user terminal" is an electronic device that allows a user to input questions and receive answers, and includes a smartphone or computer.

[1250] A "natural language processing engine" is software that analyzes input natural language text and extracts keywords and context.

[1251] The "database" is an electronic information management system for storing information such as the experiences of professional athletes, stories of athletes who tried but failed, and advice from agents.

[1252] The "emotion engine" is software that analyzes a user's emotions from their questions and profile information, and feeds the results back to the generative AI model.

[1253] A "generative AI model" is an artificial intelligence system that generates appropriate answers and advice based on the analysis results provided by a natural language processing engine and an emotion engine.

[1254] A "prompt" is an instruction used by a generative AI model to generate an appropriate response, which may include contextual and emotional information.

[1255] System Overview

[1256] This invention is a system that allows junior athletes and security service users to receive specific career counseling and advice on psychological stress online. The system's main components are a user terminal, a central server, a database, an emotion engine, and a generative AI model.

[1257] User terminal

[1258] A user terminal is a device through which a user enters a question and receives a response. Specifically, this can be a smartphone or a computer. The user enters a question into the terminal using text or voice input, and the content is transmitted to a central server via the Internet.

[1259] Central Server

[1260] The central server plays a central role in analyzing incoming questions and generating appropriate answers. The server is equipped with a natural language processing engine, an emotion engine, and a generative AI model, which work together to create answers to users' questions.

[1261] Database

[1262] The database stores information such as the experiences of professional players, stories of players who tried but failed, and advice from agents, etc. Appropriate information is searched from this database and used to generate answers for the generative AI model.

[1263] Emotion Engine

[1264] The emotion engine analyzes user emotions from their questions and profile information. This engine works in conjunction with the natural language processing engine to analyze the user's emotions and psychological state, and feeds the results back to the generative AI model.

[1265] Program processing

[1266] Question reception and sentiment analysis

[1267] The server receives the question sent from the user's device. It then passes the question to a natural language processing engine to begin analysis. At the same time, an emotion engine runs to recognize the user's emotion from the question, thereby extracting emotional nuances and intensity.

[1268] Natural Language Processing and Analysis

[1269] The natural language processing engine on the server analyzes the received question and extracts important keywords and context. The analysis results are passed to the generative AI model. The emotion analysis results from the emotion engine are also provided to the generative AI model.

[1270] Searching the database

[1271] The generative AI model generates queries to the database based on the analyzed keywords, context, and sentiment information, and based on these queries, relevant information is retrieved from the database.

[1272] Generate answers

[1273] Based on the acquired information and the results of sentiment analysis, the generative AI model generates an appropriate response to the user's question. The generated response adjusts tone and expression to take emotions into account, making it more relatable to the user.

[1274] Submitting and viewing answers

[1275] The generated answer is sent back to the user terminal, where it is displayed for the user to review. The user can then review the displayed answer and re-enter the question if necessary.

[1276] Specific examples

[1277] For example, if a user inputs a question such as, "Work hasn't been going well recently and I'm feeling stressed. What should I do?", the emotion engine will recognize the emotion "stress." This emotion information, along with the analysis results, will be provided to the generative AI model. Based on the analysis results, the generative AI model will retrieve information from related databases and generate an answer that includes appropriate counseling and advice for dealing with "stress." This answer will then be sent to the user's device and displayed.

[1278] Example prompt sentence:

[1279] "A user asked the question, 'Work hasn't been going well lately and I'm feeling stressed. What should I do?' The emotion is 'stressed' and the tone is 'high.' Please provide appropriate counseling and advice."

[1280] In this way, by combining emotion engines, it becomes possible to respond in accordance with the user's psychological state, thereby providing better support.

[1281] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1282] Step 1: Receiving the question

[1283] The server receives a question input from the user terminal. The input includes the question text from the user terminal. For example, a question such as "Work hasn't been going well lately and I'm feeling stressed. What should I do?" is sent. This question text is passed to the next processing step as is.

[1284] Step 2: Sentiment Analysis

[1285] The emotion engine in the server analyzes the received question text. The question text received in step 1 is used as input. The emotion engine extracts emotions from the question content and assigns emotion labels such as "stress" or "depression." For example, the emotion "stress" is recognized from the question. This emotion information is output as a label and its intensity (score) and passed to the next step.

[1286] Step 3: Natural Language Processing

[1287] The natural language processing engine on the server analyzes the question text. As input, it uses the question text received in step 1 and the emotional information obtained in step 2. The natural language processing engine extracts keywords and context from the question. For example, keywords such as "work" and "stress" are extracted. The results of this analysis are output in text format and passed to the next step.

[1288] Step 4: Database Search

[1289] The server generates a query to the database based on the analysis results of natural language processing and emotional information. It uses the outputs of steps 2 and 3 as input. The database contains personal experiences of professional athletes and agents, as well as psychological advice information. Based on the query, the server searches the database for relevant information. For example, it retrieves "advice related to stress." The search results are output in text format and passed to the next step.

[1290] Step 5: Answer Generation

[1291] The generative AI model on the server generates an answer to the question based on information retrieved from the database. The search results obtained in step 4 and the analysis results from steps 2 and 3 are used as input. The generative AI model uses prompt text to generate an appropriate answer. For example, a prompt text such as "The user asked, 'Work hasn't been going well recently and I'm feeling stressed. What should I do?' The emotion is 'stressed' and the tone is 'high'. Please provide appropriate counseling and advice" is created and input into the AI ​​model. The generated answer is advice such as "First, take a deep breath and relax. Next, break down your work into small tasks and tackle them one by one," and is output in text format.

[1292] Step 6: Submit your response

[1293] The server sends the generated answer to the user's terminal. The answer text obtained in step 5 is used as input. The answer is sent to the user's terminal, and the user can check its contents. As output, the answer in text format is displayed on the user's terminal. The user can consider their next action based on the displayed answer.

[1294] This processing step allows the user to receive specific and effective advice that is in line with their own feelings and circumstances.

[1295] 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.

[1296] 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.

[1297] 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.

[1298] 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.

[1299] 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.

[1300] 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.

[1301] 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).

[1302] 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.

[1303] 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."

[1304] 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.

[1305] 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).

[1306] 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.

[1307] 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.

[1308] 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.

[1309] 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.

[1310] 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.

[1311] 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.

[1312] 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.

[1313] 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.

[1314] 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.

[1315] 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.

[1316] The following is further disclosed regarding the above embodiment.

[1317] (Claim 1)

[1318] means for receiving a question input from a user terminal;

[1319] A means of passing the question content to a natural language processing engine for analysis,

[1320] means for retrieving related information from a database based on the analysis results;

[1321] A means for generating a response based on the acquired information and transmitting the response to the user terminal;

[1322] A system including:

[1323] (Claim 2)

[1324] The system according to claim 1, further comprising means for acquiring information from a database storing the experiences of top professionals, professionals who tried but failed, and agents in response to the content of the question.

[1325] (Claim 3)

[1326] 10. The system of claim 1, further comprising means for receiving user profile information and selecting an AI model to provide information that best suits the user's characteristics.

[1327] "Example 1"

[1328] (Claim 1)

[1329] means for receiving a question input from a user terminal;

[1330] A means of passing the question content to a natural language processing engine for analysis,

[1331] means for retrieving related information from a database based on the analysis results;

[1332] means for generating a response based on the acquired information and transmitting the response to the user terminal;

[1333] A system including:

[1334] (Claim 2)

[1335] The system according to claim 1, further comprising means for acquiring information from a database storing the experiences of top athletes, athletes who tried but failed, and intermediaries in response to the content of the question.

[1336] (Claim 3)

[1337] 10. The system of claim 1, further comprising means for receiving user profile information and selecting a generative AI model to provide information that best suits the user's characteristics.

[1338] "Application Example 1"

[1339] (Claim 1)

[1340] means for receiving a question input from a user terminal;

[1341] A means of passing the question content to a natural language processing engine for analysis,

[1342] means for retrieving related information from a database based on the analysis results;

[1343] means for generating a response based on the acquired related information and transmitting the response to the user terminal;

[1344] A means of inputting questions using a smart device in the store and receiving answers in real time;

[1345] A system including:

[1346] (Claim 2)

[1347] 2. The system according to claim 1, further comprising means for obtaining information from a database storing experiences of professionals, challengers, and intermediaries in response to the content of the question.

[1348] (Claim 3)

[1349] 10. The system of claim 1, further comprising means for receiving user profile information and selecting an AI model to provide information that best suits the user's characteristics.

[1350] "Example 2: Combining Emotion Engines"

[1351] (Claim 1)

[1352] means for receiving a question input from a user terminal;

[1353] A means of passing the question content to a natural language processing engine for analysis,

[1354] A means for analyzing the user's emotions from the analysis results using an emotion engine;

[1355] means for retrieving related information from a database based on the analysis result and the emotion information;

[1356] means for generating a response based on the acquired information and emotion information, adjusting the tone and expression, and transmitting the response to the user terminal;

[1357] A system including:

[1358] (Claim 2)

[1359] The system according to claim 1, further comprising means for acquiring information from a database storing the experiences of top professionals, professionals who tried but failed, and agents in response to the content of the question.

[1360] (Claim 3)

[1361] 10. The system of claim 1, further comprising means for receiving user profile information and selecting an AI model to provide information that best suits the user's characteristics.

[1362] "Application example 2 when combining emotion engines"

[1363] (Claim 1)

[1364] means for receiving a question input from a user terminal;

[1365] A means of passing the question content to a natural language processing engine for analysis,

[1366] means for retrieving related information from a database based on the analysis results;

[1367] means for generating a response based on the acquired information and transmitting the response to the user terminal;

[1368] A means for analyzing the user's emotions using an emotion engine and reflecting the results in generating answers;

[1369] A system including:

[1370] (Claim 2)

[1371] The system according to claim 1, further comprising means for acquiring information from a database storing the experiences of top professionals, professionals who tried but failed, and agents in response to the content of the question.

[1372] (Claim 3)

[1373] 10. The system of claim 1, further comprising means for receiving user profile information and selecting an AI model to provide information that best suits the user's characteristics.

[1374] (Claim 4)

[1375] 10. The system of claim 1, wherein the generative AI model comprises means for generating an answer by sending a query to the endpoint and utilizing a prompt sentence to generate appropriate advice. [Explanation of symbols]

[1376] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for receiving a question input from a user terminal; A means of passing the question content to a natural language processing engine for analysis, means for retrieving related information from a database based on the analysis results; A means for generating a response based on the acquired information and transmitting the response to the user terminal; A system including:

2. 2. The system according to claim 1, further comprising means for acquiring information from a database storing the experiences of top professionals, professionals who tried but failed, and agents in response to the content of the question.

3. 10. The system of claim 1, further comprising means for receiving user profile information and selecting an AI model to provide information that best suits the user's characteristics.

Images