system

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving a question or problem entered by a user; means for analyzing the question or problem using natural language processing to identify an intent; means for retrieving relevant information from a database based on the result of the analysis; means for executing an algorithm that mimics the CEO's decision-making process; means for generating an answer based on the result of the algorithm; and means for providing the generated answer to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In modern corporate management, the will, thinking, and judgment of leaders have a major impact on the company's development. However, it is not realistic for leaders to always provide accurate advice to all employees. Large companies, in particular, face the challenge of inefficient decision-making due to a lack of guidelines and support for employees to make their own decisions. Another problem is that employees have limited means of quickly finding appropriate solutions to their work-related problems and concerns. [Means for solving the problem]

[0005] The present invention provides the following means to solve the above problems.

[0006] The system includes a means for receiving questions or tasks entered by a user, a means for analyzing the questions or tasks using natural language processing to identify the intent, a means for searching a database for related information based on the analysis results, a means for executing an algorithm that mimics the CEO's decision-making process, a means for generating answers based on the results of the algorithm, and a means for providing the generated answers to the user. This system automatically analyzes questions or tasks entered by users, searches and integrates related information, and generates and provides answers using the mimicking algorithm, thereby providing an environment in which employees can make decisions quickly.

[0007] A "user" is an end user who inputs questions or issues into the system and receives the information or answers provided.

[0008] The "means for receiving questions and assignments" refers to a device or software module that receives questions and assignments in the form of text data entered by the user and incorporates them into the system.

[0009] "Natural language processing" is a string processing technology that analyzes input text data and understands its meaning and intent. Specifically, it includes technologies such as topic modeling and keyword extraction.

[0010] The "means for identifying intent" refers to an algorithm or software module that identifies the user's intent from the analyzed question or task content and executes the next processing step based on that information.

[0011] A "database" is a digital storage system for organizing and centralizing related information and data, including past statements, books, interviews, and business strategies.

[0012] An "algorithm that mimics the CEO's decision-making process" is a mathematical model or rule-based system that analyzes and simulates the decision-making process of a specific leader.

[0013] The "answer generation means" is a software module or algorithm that generates specific answers or suggestions to the user's questions based on the results obtained by the mimicry algorithm.

[0014] The "means for providing to the user" refers to a device or software module for displaying the generated answer to the user in an easy-to-understand manner. [Brief explanation of the drawings]

[0015] [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

[0016] 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.

[0017] First, the terms used in the following description will be explained.

[0018] 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).

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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."

[0036] This invention provides a system that mimics the decision-making process of corporate leaders. Specifically, it analyzes questions and issues entered by users, generates optimal answers based on related information, and provides them to the users. We generate a program for this system and explain its processing in natural language.

[0037] Program Overview

[0038] The system analyzes questions and issues entered by users and generates answers based on the leader's past statements and business strategies. The server handles the main processing, while the terminal provides the interface with the user.

[0039] Processing flow (overview)

[0040] 1. Accepting user questions

[0041] Users input questions and tasks in text format through the terminal.

[0042] 2. Question analysis and information extraction

[0043] The server receives the question sent from the terminal and analyzes the intent of the question using natural language processing.

[0044] Based on the analysis results, the server searches the database for relevant information.

[0045] 3. Imitating the decision-making process

[0046] The server runs an algorithm that mimics the CEO's decision-making process and generates the optimal answer.

[0047] 4. Answer generation and provision

[0048] The server sends the generated answer to the terminal, which displays the answer to the user.

[0049] Specific examples

[0050] Example 1: New market entry question

[0051] The user types into the terminal, "I'm wondering whether to enter a new market. What should I do?" The terminal sends this question to the server.

[0052] The server receives the question and uses natural language processing to extract the keyword "enter new markets." It then searches a database for relevant past statements and strategies and runs an algorithm that mimics a CEO's decision-making process. The resulting advice is specific: "Research market demand, evaluate risks and rewards, and consider partnerships." The server then sends the answer to the device, which displays it to the user.

[0053] Example 2: Project Delay Question

[0054] The user types into the terminal, "What would you do if the project was delayed?" The terminal sends this question to the server.

[0055] The server receives the question and uses natural language processing to extract the keyword "project delay." It then searches a database for relevant past statements and strategies and runs an algorithm that mimics the CEO's decision-making process. The result is specific advice: "Quickly identify the cause of the delay, reallocate resources, review priorities, and strengthen communication." The server sends this answer to the device, which displays it to the user.

[0056] The system is designed to help employees improve their decision-making skills and contribute to the company's growth. It provides quick answers to users' questions and issues, and shares the CEO's decision-making process, ensuring consistency of knowledge across the company.

[0057] The processing flow will be explained below.

[0058] Step 1:

[0059] The user enters a question or problem in text format into the terminal. For example, they enter a question like, "I'm wondering whether to enter a new market. What should I do?"

[0060] Step 2:

[0061] The terminal checks the user's question data and sends it to the server in text format.

[0062] Step 3:

[0063] The server receives the question data sent from the terminal and converts the received text data into a format for internal processing.

[0064] Step 4:

[0065] The server uses a natural language processing (NLP) module to analyze the question text, including topic modeling and keyword extraction.

[0066] Step 5:

[0067] The server identifies the user's intent based on the analysis of the question text. For example, if the keyword "entering a new market" is extracted, the server identifies the intent as "decision-making regarding market expansion."

[0068] Step 6:

[0069] Based on the specified intent, the server searches a database for relevant information, including information on the CEO's past statements, books, interviews, and business strategies.

[0070] Step 7:

[0071] The server retrieves the relevant information and runs an algorithm that mimics the CEO's decision-making process, taking into account past successes and failures to arrive at the optimal answer.

[0072] Step 8:

[0073] The server formats the generated answer and converts it into an output format for presentation to the user.

[0074] Step 9:

[0075] The server sends the formatted response to the terminal. The response data is formatted to be easy for the user to understand.

[0076] Step 10:

[0077] The device will then display the response data received from the server to the user, and provide specific advice such as, "When entering a new market, it is important to thoroughly research the target market's demand and evaluate the risks and rewards. It would also be a good idea to consider collaborating with partner companies."

[0078] Example 1

[0079] 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."

[0080] In modern business, employees need to have strong leadership skills and a wealth of knowledge to make appropriate and prompt decisions. However, not all employees have the decision-making ability of a leader, which can result in poor judgment and a decline in overall corporate performance. If there were a system that could mimic a leader's decision-making process and provide appropriate advice, it would be possible to improve employees' decision-making skills and increase the efficiency of the entire company. Against this background, the present invention aims to provide a system that mimics a leader's decision-making process and quickly provides optimal answers to users.

[0081] 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.

[0082] In this invention, the server includes: means for receiving a question or task entered by a user; means for analyzing the question or task using natural language processing to identify the intent; means for searching a database for related information based on the analysis results; means for executing an algorithm that mimics the decision-making process; means for generating an answer based on the result of the algorithm; means for providing the generated answer to the user; means including a terminal and a web browser or dedicated application for the user to view the answer; means for using a BERT model or GPT model in natural language processing; and means for using a database to search past statements and business strategies based on analyzed keywords. This enables users to quickly obtain specific advice based on a sophisticated decision-making process like that of a leader.

[0083] "User" refers to a user who can input questions or issues into the system and receive answers.

[0084] "Terminal" refers to a hardware device, such as a PC, smartphone, or tablet, through which a user enters questions or tasks and receives answers.

[0085] "Server" refers to a central system that receives questions or challenges sent by users, performs natural language processing, searches a database for relevant information, generates answers, and provides them to users.

[0086] "Natural language processing" refers to the technology that enables computers to understand and process human language, including analyzing text and identifying intent.

[0087] The "BERT model" is a type of natural language processing algorithm based on transformer technology, and is particularly good at analyzing text taking context into account.

[0088] The "GPT model" is a type of natural language processing algorithm that uses generative techniques, and is a technology that generates language based on large amounts of text data.

[0089] "Database" means a collection of information used by a system to store, search, and retrieve information, including but not limited to SQL Server and NoSQL databases.

[0090] "Questions and issues" refer to specific problems or doubts that users input into the system and seek to resolve.

[0091] "Identifying intent" refers to the process of using natural language processing technology to clarify the user's requirements and goals behind the entered question or task.

[0092] "Algorithms that mimic decision-making processes" refers to computational methods that derive optimal answers based on the past decision-making criteria and methods of leaders and CEOs.

[0093] "Generating an answer" refers to the process of creating appropriate advice or solutions to a user's questions or challenges based on analyzed information and decision-making processes.

[0094] A "web browser" refers to software that enables users to interact with servers over the Internet, and includes browsers such as Chrome and Firefox.

[0095] "Purpose-built application" refers to software developed for a specific purpose, to facilitate user access to a system.

[0096] MODE FOR CARRYING OUT THE INVENTION

[0097] This invention provides a system that mimics the decision-making process of corporate leaders. This system analyzes questions and issues entered by users, generates optimal answers based on related information, and provides them to the users. In this system, the server handles the main processing, and the terminal provides the interface with the user.

[0098] First, the user uses their own device to input a question or problem. Specifically, they enter the question into a text input field in a web browser or a dedicated application. This question is specific and based on the user's concerns or problems. For example, "I'm wondering whether to enter a new market. What should I do?" Once the input is complete, the user clicks the send button, and the content is sent to the server.

[0099] Next, the server receives the submitted question data. The server analyzes the intent of the question using natural language processing techniques such as Google's BERT model or OpenAI's GPT model. This analysis first involves normalizing and tokenizing the sentence (dividing it into words), and then extracting keywords and related information. For example, keywords such as "entering new markets" and "project delays" are extracted.

[0100] The server then runs an algorithm that mimics the decision-making process of a company leader based on the extracted keywords and contextual information. The algorithm includes logic to derive the optimal answer by referencing a database containing past statements and business strategies. Specifically, the database contains information such as books, interviews, and business strategy information, and is managed using SQL Server or a NoSQL database.

[0101] After the algorithm is executed, the server generates a specific answer to the question, such as advice such as "research market demand, evaluate risk and return, and consider partnerships." Finally, the server sends the answer to the user's device, which displays it to the user, either by refreshing the web page or by displaying a dedicated application pop-up.

[0102] ---

[0103] Examples:

[0104] The user types into the device, "I'm wondering whether to enter a new market. What should I do?" The device sends this question to the server. The server receives the question and uses natural language processing to extract the keyword "enter a new market." It then searches a database for related past statements and strategies and runs an algorithm that mimics the decision-making process of a corporate leader. As a result, specific advice is generated: "Research market demand, evaluate risks and returns, and consider partnerships." The server sends this answer to the device, which displays it to the user.

[0105] ---

[0106] Examples of prompts:

[0107] 1. "What is the best way to go to market?"

[0108] 2. "What is the best way to address a delayed project?"

[0109] As described above, this system is able to provide prompt and appropriate advice in response to user questions and issues, allowing users to obtain specific advice based on a high-level decision-making process similar to that of a leader, thereby improving the efficiency of the entire company.

[0110] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0111] Step 1: Accepting user questions

[0112] A user uses a terminal to input a question or problem. Specifically, the user enters the question in a text input field in a web browser or a dedicated application and clicks the send button. This sends the question data in text format to the server. The input might be, for example, "I'm wondering whether to enter a new market. What should I do?" and the output is the text data to be sent.

[0113] Step 2: Question analysis and information extraction

[0114] The server receives the question data sent by the user. The server analyzes the text using a natural language processing model (BERT model or GPT model). Specific analysis operations include normalizing the text (removing unnecessary spaces and symbols), tokenizing (dividing it into words), and stemming (reducing words to their original form). The text data received in step 1 is given as input, and the extracted keywords and contextual information (e.g., entering a new market) are obtained as output.

[0115] Step 3: Mimic the decision-making process

[0116] The server runs an algorithm that mimics the decision-making process based on the keywords and contextual information obtained in step 2. This algorithm references a database that stores past statements and business strategies to retrieve relevant information. Specifically, it searches the database for the required information using SQL or NoSQL queries. The input is the extracted keywords (e.g., "enter a new market"), and the output is relevant information for decision-making (e.g., past market analysis data, risk assessment, etc.).

[0117] Step 4: Answer Generation

[0118] The server generates the optimal answer to the user's question based on the related information obtained in step 3. For generation, a natural language generation model (such as a GPT model) is again used. Specifically, the related information is provided as input data, and the generation model uses it to generate a natural, contextual answer. The input is the related information and the prompt sentence of the generation AI model, and the output is the generated specific answer text.

[0119] Step 5: Provide your answers

[0120] The server sends the answer generated in step 4 to the user's device. The device analyzes the received answer and displays it to the user. Specifically, the answer is displayed by updating the web page or by displaying a popup in a dedicated application. The input is the generated answer text, and the output is the answer content displayed on the user's screen.

[0121] The above is a specific description of each processing step of this system, including input, data processing, output, and specific operations at each step.

[0122] (Application example 1)

[0123] 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."

[0124] Providing specific, practical advice to help store managers and administrators make quick and accurate decisions in the daily tasks they face is not easy. Optimal advice based on experience and past data is particularly required for a wide range of tasks, such as inventory management, staff shift management, and new product introductions, but there is no established method for providing this advice.

[0125] 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.

[0126] In this invention, the server includes means for receiving a question or task input by a user, means for analyzing the question or task using natural language processing to identify the intent, means for searching a database for related information based on the analysis result, means for executing an algorithm that mimics the decision-making process of the leader, means for generating an answer based on the result of the algorithm, means for providing the generated answer to the user, means for using information context to provide advice on various tasks, and means for generating optimal advice using a generative AI model. This makes it possible to provide quick and specific advice for the daily tasks faced by managers and store managers of brick-and-mortar stores.

[0127] The "means for receiving questions and assignments entered by the user" refers to an interface and interactive communication function for receiving questions and assignments in text format entered by the user through a terminal.

[0128] "Means of analyzing and identifying intent using natural language processing" refers to an analytical technology that recognizes questions or tasks entered in text form by users and understands their meaning and purpose.

[0129] "Means for searching for relevant information from a database" refers to a technology that identifies the necessary data based on the intent of the analyzed question or task, and retrieves the appropriate information from the database that stores that data.

[0130] "Means for implementing algorithms that mimic the decision-making process of leaders" refers to technology that uses similar algorithms to make optimal decisions based on the decision-making processes used by corporate leaders in the past.

[0131] "Answer generation means" refers to techniques for creating specific answers to user questions or challenges based on acquired information and simulated decision-making processes.

[0132] The "means for providing the generated answer to the user" refers to an interface and communication technology for transmitting the generated answer to the user terminal and displaying the result to the user.

[0133] "Means using information context to provide advice on various operations" refers to means for providing advice using specific and detailed information on various operations related to managing a physical store (e.g., inventory management, staff management, new product introduction, etc.).

[0134] "Means for generating optimal advice using generative AI models" refers to technology that utilizes artificial intelligence technology to generate the most appropriate advice or answer to a user's question or issue.

[0135] This invention provides a support tool for store managers and administrators to instantly make optimal decisions in their daily work. Specifically, it is implemented as a smartphone application that provides quick and accurate answers based on user input.

[0136] The system consists of a user terminal (a smartphone in this case) and a server. The system includes the following main functional blocks:

[0137] User device functions

[0138] An interface is implemented on the user terminal for users to input questions and tasks. The user inputs a question in text format and sends it to the server.

[0139] Server Features

[0140] The server is responsible for the main data processing and response generation. It performs the following tasks:

[0141] 1. Question analysis:

[0142] The server analyzes the user-submitted question using natural language processing techniques (e.g., the transformers library), which perform topic modeling and keyword extraction to identify the intent of the question.

[0143] 2. Information Search:

[0144] Based on the intent of the question, relevant information (past statements, business strategies, operational know-how, etc.) is searched from a database.

[0145] 3. Answer generation:

[0146] It uses algorithms that mimic the decision-making process of leaders and generative AI models (e.g., transformers' question-answering pipeline) to generate optimal answers, leveraging diverse business context in the process.

[0147] 4. Provide answers:

[0148] The generated answer is sent to the user terminal and finally displayed to the user.

[0149] Specific use cases

[0150] For example, if a store manager were to enter a question through the app such as, "Which products would you recommend for this weekend's sale?", the following process would take place:

[0151] 1. The user terminal receives the query and sends it to the server.

[0152] 2. The server analyzes the question and extracts keywords such as "sale" and "recommended products."

[0153] 3. Search the database for relevant past sales data and competitive information on the product.

[0154] 4. Using a generative AI model, mimicking the leader's decision-making process, generate the answer "Provide a list of products with high sales performance."

[0155] 5. The server sends this response to the user's terminal and displays it to the user.

[0156] Prompt Sentence Examples

[0157] "Please give me some advice on inventory management."

[0158] "What items would you recommend in this weekend's sale?"

[0159] This system will enable store managers and supervisors to receive prompt and specific advice on a wide range of tasks.

[0160] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0161] Step 1:

[0162] The user inputs a question or task. Specifically, the question is entered in text format through a dedicated smartphone application, and is sent to the server by pressing the send button. An example of input in this case would be "Which products do you recommend for this weekend's sale?" The output is text data from the user.

[0163] Step 2:

[0164] The terminal sends the question entered by the user to the server, where the text data entered by the user is converted into packets and sent to the server via Internet communication. The input is the text data from the user, and the output is the transmitted packets.

[0165] Step 3:

[0166] The server analyzes the received question. Specifically, it uses natural language processing technology to analyze the question and performs topic modeling and keyword extraction. Here, keywords such as "sale" and "recommended products" are extracted, for example. The input is the user's text data, and the output is the extracted keywords and intent.

[0167] Step 4:

[0168] The server searches the database based on the analysis results. Specifically, it searches the database for relevant past data (e.g., past statements, business strategies, operational know-how, etc.) based on the extracted keywords and intent. The input is the extracted keywords and intent, and the output is a list of related information.

[0169] Step 5:

[0170] The server runs an algorithm that mimics the leader's decision-making process. Specifically, it uses relevant information to run the decision-making algorithm and generate an appropriate answer. The input is a list of relevant information, and the output is the generated answer.

[0171] Step 6:

[0172] The server generates optimal advice using a generative AI model (e.g., a question-answering pipeline in transformers) to generate specific advice. The input is the result of the decision-making algorithm, and the output is the final generated advice.

[0173] Step 7:

[0174] The server sends the generated answer to the user terminal. Specifically, it converts the generated advice in text format into packets and sends them to the user terminal via Internet communication. The input is the generated advice, and the output is the transmitted packets.

[0175] Step 8:

[0176] The terminal receives advice from the server and displays it to the user. Specifically, it converts the received packets into text data and displays it through a user interface. The input is the received packets, and the output is the display on the user interface.

[0177] 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.

[0178] This invention combines a system that mimics the decision-making process of corporate leaders with an emotion engine that recognizes user emotions. The program processing of this system is explained in natural language below. The program is executed through interaction between the server, terminals, and users.

[0179] Program Overview

[0180] This system analyzes questions and issues entered by users, generates optimal answers based on relevant information and emotional data, and provides them to the users. The server handles the main processing, while the terminal provides the interface with the user.

[0181] Processing flow (overview)

[0182] 1. Accepting user questions

[0183] Users input questions and tasks in text format through the terminal.

[0184] 2. Question analysis and information extraction

[0185] The server receives the question sent from the terminal and analyzes the intent of the question using natural language processing.

[0186] Based on the analysis results, the server searches the database for relevant information.

[0187] 3. Emotion recognition

[0188] The server uses an emotion engine to extract emotion data from the user's input text, for example, to determine whether the user is feeling anxious or excited.

[0189] 4. Imitating the decision-making process

[0190] The server runs an algorithm that mimics the CEO's decision-making process, including the extracted emotional data, to generate the optimal answer.

[0191] 5. Answer Generation and Delivery

[0192] The server formats the generated responses, adjusting the tone and content based on the emotional data, and provides them to the user.

[0193] Specific examples

[0194] Example 1: New market entry question

[0195] The user types into the terminal, "I'm wondering whether to enter a new market. What should I do?" The terminal sends this question to the server.

[0196] The server receives the question and uses natural language processing to extract the keyword "entering new markets." It then searches a database for related past statements and strategies. It then uses an emotion engine to recognize the emotion "worried" from the user's text. The server then takes this emotion data into account and runs an algorithm that mimics a CEO's decision-making process. As a result, it generates specific advice: "Research market demand, evaluate risks and rewards, and consider partnerships." The answer includes emotionally sensitive language: "We understand your concerns. To alleviate them, it's important to conduct thorough market research and risk assessment." The server then sends this answer to the device, which displays it to the user.

[0197] Example 2: Project Delay Question

[0198] The user types into the terminal, "What would you do if the project was delayed?" The terminal sends this question to the server.

[0199] The server receives the question and uses natural language processing to extract the keyword "project delay." It then searches a database for related past statements and strategies. It then uses an emotion engine to recognize the emotion of "impatience" from the user's text. The server then takes this emotion data into account and runs an algorithm that mimics a CEO's decision-making process. As a result, it generates specific advice: "Quickly identify the cause of the delay, reallocate resources, review priorities, and strengthen communication." The response includes a tone that takes emotion into consideration: "We understand your current impatience. To respond calmly, please prioritize identifying the cause of the delay." The server then sends this response to the device, which displays it to the user.

[0200] This system is designed to help employees improve their decision-making skills and contribute to the development of the company. It provides quick answers to users' questions and issues, and by combining the CEO's decision-making process with emotion recognition, it ensures consistency of knowledge across the company and mental health care for employees.

[0201] The processing flow will be explained below.

[0202] Step 1:

[0203] A user types a question or challenge into the device in text format, for example, "I'm wondering whether to expand into a new market. What should I do?"

[0204] Step 2:

[0205] The terminal receives the user's input and sends the data to the server in text format.

[0206] Step 3:

[0207] The server checks the query data received from the terminal and adjusts the format appropriately for internal processing.

[0208] Step 4:

[0209] The server applies natural language processing (NLP) modules to analyze the question text, including topic modeling and keyword extraction.

[0210] Step 5:

[0211] The server uses the analysis results to identify the subject and intent of the question, for example extracting the main theme of "entering new markets."

[0212] Step 6:

[0213] Based on the specified intent, the server searches a database of relevant information, including information on past statements, books, interviews, and business strategies.

[0214] Step 7:

[0215] The server uses an emotion engine to extract emotion data from the user's input text, for example, to recognize whether the user is feeling "anxious."

[0216] Step 8:

[0217] The server runs an algorithm to mimic the leader's decision-making process, integrating the identified intent with the extracted emotional data to generate the optimal answer.

[0218] Step 9:

[0219] The server then formats the generated responses, adjusting the tone and content based on the user's emotions. For example, if a user is feeling anxious, reassuring language will be added.

[0220] Step 10:

[0221] The server then sends the formatted answer data to the terminal in a format that is easy for the user to understand.

[0222] Step 11:

[0223] The device displays the answer received from the server to the user. For example, it might say, "When entering a new market, it is important to thoroughly research the target market's demand and evaluate the risks and rewards. It would also be a good idea to consider collaborating with partner companies. We understand your concerns. To alleviate them, it is important to conduct thorough market research and risk assessment."

[0224] Example 2

[0225] 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."

[0226] In modern companies, quick and accurate decision-making is required, but few systems provide responses that appropriately consider the user's emotions during the decision-making process. In particular, there is a need for a system that can generate answers that reflect the user's emotions while mimicking the decision-making process of a leader.

[0227] 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.

[0228] In this invention, the server includes means for receiving a question or task input by a user, means for analyzing the question or task using natural language processing to identify the intent, means for searching a database for related information based on the analysis results, means for extracting emotional data from the user's input, means for executing an algorithm that mimics a CEO's decision-making process based on the analysis results including the emotional data, means for generating an answer that takes the emotional data into consideration based on the results of the algorithm, and means for providing the generated answer to the user. This makes it possible to provide an appropriate answer that takes the user's emotions into consideration while mimicking a leader's decision-making process.

[0229] "User" refers to a person who uses the system to enter questions or issues and receive answers.

[0230] "Terminal" refers to a device that provides an interface for users to access the system and input questions or tasks. Examples include personal computers and smartphones.

[0231] "Question or Problem" refers to a textual inquiry that a user enters into the system seeking a solution.

[0232] "Natural language processing" refers to the technology for analyzing user-entered text and understanding its intent and sentiment. Specifically, it includes topic modeling and keyword extraction.

[0233] "Database" refers to a collection of information that the system references, including past statements, books, interviews, and business strategies.

[0234] "Emotion engine" refers to technology for extracting emotional data from user input, such as a sentiment analysis API.

[0235] "Emotion data" refers to emotional state information extracted from text entered by a user, including, for example, feelings of anxiety or impatience.

[0236] An "algorithm" is a set of computational steps to solve a specific problem or perform a computation, in this case to mimic the decision-making process of a CEO.

[0237] "Answer" refers to a response from the system to a user's question or problem, containing appropriate information and taking into account the user's feelings.

[0238] "Means for providing" refers to the technical means by which the server displays the answer to the user, specifically including sending the answer to the terminal.

[0239] This invention is a system that mimics the decision-making process of corporate leaders and recognizes user emotions. The main processing is handled by the server, and the user and terminal provide the interface.

[0240] Program processing overview

[0241] This system analyzes questions and issues entered by users, generates optimal answers based on relevant information and emotional data, and provides them to users. The main technologies and the hardware and software used are described below.

[0242] 1. Accepting user questions

[0243] The user enters a question in text format using a device, such as a PC or smartphone.

[0244] Example: User types, "I'm wondering whether to expand into a new market. What should I do?"

[0245] 2. Question analysis and information extraction

[0246] The server receives the question sent from the terminal and analyzes the intent of the question using natural language processing.

[0247] In this case, natural language processing libraries such as SpaCy and NLTK are used.

[0248] The server searches for relevant information from a database (for example, MySQL (registered trademark) or PostgreSQL) based on the analyzed keywords.

[0249] 3. Emotion recognition

[0250] The server uses an emotion engine to extract emotion data from the user's input text.

[0251] Specifically, we will use the sentiment analysis API of Microsoft (registered trademark) Azure (registered trademark) Cognitive Services.

[0252] The server recognizes emotions such as "worried" and adds them to the analysis results.

[0253] 4. Imitating the decision-making process

[0254] The server then runs an algorithm that mimics the CEO's decision-making process, including the extracted emotional data.

[0255] For example, machine learning models such as TENSORFLOW (registered trademark) and Scikit-learn are used.

[0256] 5. Answer Generation and Delivery

[0257] The server formats the responses it generates, adjusting the tone and content based on emotional data.

[0258] The server converts the final response into JSON format and sends it to the terminal.

[0259] The terminal parses the received JSON data and displays it to the user.

[0260] Specific examples

[0261] Example 1: New market entry question

[0262] A user types into their terminal, "I'm wondering whether to expand into a new market. What should I do?"

[0263] The terminal sends this question to the server.

[0264] The server receives the question and uses natural language processing to extract the keyword "entering new markets."

[0265] Next, the database is searched for relevant past statements and strategies.

[0266] An emotion engine is used to recognize the emotion of "worried" from the user's text.

[0267] The server then takes this emotional data into account and runs an algorithm that mimics the CEO's decision-making process.

[0268] The result is specific advice on "market demand research, risk and return assessment, and partnership considerations."

[0269] The response includes sensitive language such as, "We understand your concerns. To alleviate them, it is important to conduct thorough market research and risk assessment."

[0270] The server sends this response to the terminal, which displays it to the user.

[0271] This system is designed to improve users' decision-making ability and contribute to the development of the company. It provides quick answers to users' questions and issues, and by combining the CEO's decision-making process with emotion recognition, it can ensure consistency of knowledge across the company and mental health care for employees.

[0272] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0273] Step 1: Accepting user questions

[0274] Specific actions

[0275] The user enters a question in text format using a terminal.

[0276] For example, a user might type, "I'm wondering whether to expand into a new market. What should I do?"

[0277] The terminal interface has an input field and a "Submit" button, which the user presses to send the question to the server.

[0278] input

[0279] Text data entered by the user into the terminal.

[0280] output

[0281] The text data sent to the server.

[0282] Step 2: Question analysis and information extraction

[0283] Specific actions

[0284] The server receives the question sent from the terminal and analyzes the text data.

[0285] The intent of the question is analyzed using natural language processing technology, for example using libraries such as SpaCy and NLTK.

[0286] The server extracts keywords such as "entering new markets" from the analysis results.

[0287] Based on the extracted keywords, the server retrieves relevant information from a database (e.g., MySQL or PostgreSQL) and temporarily stores it.

[0288] input

[0289] The text data received by the server.

[0290] output

[0291] Data and related information extracted as keywords.

[0292] Step 3: Emotion Recognition

[0293] Specific actions

[0294] The server uses an emotion engine to extract emotion data from the user's input text.

[0295] Specifically, it calls the sentiment analysis API of Microsoft Azure's Cognitive Services and sends text data.

[0296] Based on the received emotion data, emotions such as "worried" or "anxious" are recognized from the user's text.

[0297] The server adds this emotion data to the previously extracted keywords and related information.

[0298] input

[0299] Text data and already extracted keywords.

[0300] output

[0301] Analysis results with added emotion data.

[0302] Step 4: Imitate the decision-making process

[0303] Specific actions

[0304] The server runs an algorithm that mimics the CEO's decision-making process based on the analysis results, including the extracted emotional data.

[0305] For example, use machine learning models such as TensorFlow or Scikit-learn and load pre-trained algorithms.

[0306] The server inputs the analysis results and emotional data into an algorithm to generate the optimal answer.

[0307] The answers generated include specific advice such as "research market demand, assess risks, and consider partnerships."

[0308] input

[0309] Analysis results with added emotion data.

[0310] output

[0311] Algorithmically generated answers.

[0312] Step 5: Generate and provide answers

[0313] Specific actions

[0314] The server formats the generated responses, adjusting the tone and content based on the emotional data.

[0315] Specifically, the generated answers will be enhanced with emotionally sensitive language such as, "We understand your concerns. To alleviate them, it is important to conduct thorough market research and risk assessments."

[0316] The final answer is converted to JSON format and sent to the terminal.

[0317] The terminal parses the received JSON data and displays it to the user.

[0318] input

[0319] Algorithmically generated answers.

[0320] output

[0321] The final answer provided to the user.

[0322] (Application example 2)

[0323] 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."

[0324] Conventionally, security services have lacked systems that can quickly and accurately respond when users feel anxious or worried. As a result, it is difficult for users to find an appropriate solution, which can lead to a decline in the quality of security services. Furthermore, the inability to respond appropriately to users' emotions can further increase anxiety and impatience. The present invention aims to solve these problems.

[0325] 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 or task entered by a user, means for analyzing the question or task using natural language processing and identifying the intent, means for recognizing emotions from the entered text, means for searching a database for related information based on the analysis results and emotions, means for executing an algorithm that mimics the decision-making process, means for generating an answer that takes emotions into consideration based on the results of the algorithm, and means for providing the generated answer to the user. This enables a quick and accurate response when a user of a security service feels anxious or concerned. Furthermore, generating an answer that takes the user's emotions into consideration can improve the user's sense of security.

[0326] A "question" is text entered by a user regarding a particular problem or question.

[0327] A "problem" refers to a particular problem situation or challenge that a user wishes to solve.

[0328] "Natural language processing" is a general term for technology that allows computers to understand, analyze, and generate human language.

[0329] "Emotion" refers to a psychological state extracted from the text entered by the user, such as anxiety or impatience.

[0330] A "database" is a collection of related information organized for efficient searching and retrieval.

[0331] An "algorithm that mimics the decision-making process" is a computational procedure that replicates the decision-making process of corporate leaders.

[0332] An "answer" is a response generated by the server in response to a user's question or task.

[0333] "Relevant information" refers to data or documents that are directly related to the question or issue.

[0334] "Emotion recognition" refers to the technology of identifying a user's psychological state from their input text.

[0335] "Means for providing to the user" refers to the interface or method for showing the generated answer to the user.

[0336] This system analyzes questions and issues entered by users, generates and provides optimal answers based on related emotional data, and is implemented through interactions between the server, terminals, and users.

[0337] The server is the main processing unit and includes the following elements:

[0338] A way to receive questions and assignments

[0339] A means of analyzing questions and issues using natural language processing

[0340] A method for recognizing emotions from input text

[0341] A means of searching for relevant information from a database based on analysis results and sentiment

[0342] A means of implementing algorithms that mimic decision-making processes

[0343] A means of generating answers based on the results of an algorithm

[0344] A means of providing the generated answer to the user

[0345] Hardware and Software Configuration

[0346] Hardware:

[0347] Smartphone (user device)

[0348] Server (main processing and database management)

[0349] software:

[0350] Amazon Web Services (AWS (registered trademark)) Lambda (serverless computing)

[0351] Google Cloud Natural Language API (Natural Language Processing)

[0352] IBM Watson(R) Emotion Analysis

[0353] Python (programming language)

[0354] Data processing and calculation

[0355] 1. Receiving questions and assignments:

[0356] A user uses a smartphone to input a question or problem, for example, "My home security system has detected an abnormality. I'm worried. What should I do?"

[0357] 2. Analysis of questions and issues:

[0358] The server uses the Google Cloud Natural Language API to analyze the user's question or issue and extract key keywords (e.g., "security system," "anomaly").

[0359] 3. Emotion recognition:

[0360] The server uses IBM Watson Emotion Analysis to identify emotions from the user's input text (e.g., "anxiety").

[0361] 4. Information Search:

[0362] The server searches the database for relevant information based on the analyzed keywords and emotional data.

[0363] 5. Imitating the decision-making process:

[0364] The server runs an algorithm that mimics the decision-making process of a company leader, combining relevant information and emotional data to generate the best answer.

[0365] 6. Generate and provide answers:

[0366] The server adjusts the generated answer taking into account the user's emotions and displays it on the smartphone (e.g., "If an abnormality is detected, first remain calm and call your emergency contact or the nearest police station.").

[0367] Prompt Sentence Examples

[0368] User Question: "My home security system is detecting something abnormal. I'm worried. What should I do?"

[0369] Analyzed keywords: "security system", "abnormality"

[0370] Recognized emotion: "Anxiety"

[0371] Generated advice: "If an abnormality is detected, first remain calm and call your emergency contact or the nearest police station. Also, check the system logs and gather as much information as possible."

[0372] This system can provide users with optimal means to quickly and accurately resolve security-related issues and concerns. In particular, by taking emotional data into consideration, it can provide solutions that are suited to the psychological state of each individual user.

[0373] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0374] Step 1:

[0375] A user inputs a question or problem into their smartphone. For example, they input text like, "My home security system has detected an abnormality. I'm worried. What should I do?" This text is then sent from the device to the server. The input data is the user text, and the output data is the raw text sent to the server.

[0376] Step 2:

[0377] The server sends the received text to the Google Cloud Natural Language API and analyzes it using natural language processing. Specifically, the server extracts key keywords from the text. For example, the keywords "security system" and "abnormal" are extracted. The input data is the raw text, and the output data is the analyzed keywords.

[0378] Step 3:

[0379] The server uses IBM Watson Emotion Analysis to recognize emotions from the user's text based on the extracted keywords. Specifically, the raw text is sent to the emotion recognition engine, and the emotion "anxiety" is extracted as a result. The input data is the raw text and keywords, and the output data is the recognized emotion.

[0380] Step 4:

[0381] The server searches a database for relevant information based on the analyzed keywords and emotions. For example, past documents and advice on how to respond to security system anomalies are searched for. The input data is keyword and emotion data, and the output data is a set of related information.

[0382] Step 5:

[0383] The server runs an algorithm that mimics the decision-making process based on relevant information and emotional data. Specifically, it mimics past decisions made by company leaders and generates appropriate advice. The input data is relevant information and emotional data, and the output data is the generated advice.

[0384] Step 6:

[0385] The server adjusts the content and tone of the generated advice to provide it to the user based on the emotional data. For example, it uses language that alleviates anxiety. The input data are the generated advice and emotional data, and the output data is the optimized advice.

[0386] Step 7:

[0387] The device displays the optimized advice to the user, allowing the user to act based on the advice. Specifically, the advice is displayed on the smartphone screen. The input data is the optimized advice, and the output data is displayed to the user.

[0388] 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.

[0389] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0390] 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.

[0391] [Second embodiment]

[0392] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0393] 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.

[0394] 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).

[0395] 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.

[0396] 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.

[0397] 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).

[0398] 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.

[0399] 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.

[0400] 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.

[0401] 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.

[0402] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0403] 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."

[0404] This invention provides a system that mimics the decision-making process of corporate leaders. Specifically, it analyzes questions and issues entered by users, generates optimal answers based on related information, and provides them to the users. We generate a program for this system and explain its processing in natural language.

[0405] Program Overview

[0406] The system analyzes questions and issues entered by users and generates answers based on the leader's past statements and business strategies. The server handles the main processing, while the terminal provides the interface with the user.

[0407] Processing flow (overview)

[0408] 1. Accepting user questions

[0409] Users input questions and tasks in text format through the terminal.

[0410] 2. Question analysis and information extraction

[0411] The server receives the question sent from the terminal and analyzes the intent of the question using natural language processing.

[0412] Based on the analysis results, the server searches the database for relevant information.

[0413] 3. Imitating the decision-making process

[0414] The server runs an algorithm that mimics the CEO's decision-making process and generates the optimal answer.

[0415] 4. Answer generation and provision

[0416] The server sends the generated answer to the terminal, which displays the answer to the user.

[0417] Specific examples

[0418] Example 1: New market entry question

[0419] The user types into the terminal, "I'm wondering whether to enter a new market. What should I do?" The terminal sends this question to the server.

[0420] The server receives the question and uses natural language processing to extract the keyword "enter new markets." It then searches a database for relevant past statements and strategies and runs an algorithm that mimics a CEO's decision-making process. The resulting advice is specific: "Research market demand, evaluate risks and rewards, and consider partnerships." The server then sends the answer to the device, which displays it to the user.

[0421] Example 2: Project Delay Question

[0422] The user types into the terminal, "What would you do if the project was delayed?" The terminal sends this question to the server.

[0423] The server receives the question and uses natural language processing to extract the keyword "project delay." It then searches a database for relevant past statements and strategies and runs an algorithm that mimics the CEO's decision-making process. The result is specific advice: "Quickly identify the cause of the delay, reallocate resources, review priorities, and strengthen communication." The server sends this answer to the device, which displays it to the user.

[0424] The system is designed to help employees improve their decision-making skills and contribute to the company's growth. It provides quick answers to users' questions and issues, and shares the CEO's decision-making process, ensuring consistency of knowledge across the company.

[0425] The processing flow will be explained below.

[0426] Step 1:

[0427] The user enters a question or problem in text format into the terminal. For example, they enter a question like, "I'm wondering whether to enter a new market. What should I do?"

[0428] Step 2:

[0429] The terminal checks the user's question data and sends it to the server in text format.

[0430] Step 3:

[0431] The server receives the question data sent from the terminal and converts the received text data into a format for internal processing.

[0432] Step 4:

[0433] The server uses a natural language processing (NLP) module to analyze the question text, including topic modeling and keyword extraction.

[0434] Step 5:

[0435] The server identifies the user's intent based on the analysis of the question text. For example, if the keyword "entering a new market" is extracted, the server identifies the intent as "decision-making regarding market expansion."

[0436] Step 6:

[0437] Based on the specified intent, the server searches a database for relevant information, including information on the CEO's past statements, books, interviews, and business strategies.

[0438] Step 7:

[0439] The server retrieves the relevant information and runs an algorithm that mimics the CEO's decision-making process, taking into account past successes and failures to arrive at the optimal answer.

[0440] Step 8:

[0441] The server formats the generated answer and converts it into an output format for presentation to the user.

[0442] Step 9:

[0443] The server sends the formatted response to the terminal. The response data is formatted to be easy for the user to understand.

[0444] Step 10:

[0445] The device will then display the response data received from the server to the user, and provide specific advice such as, "When entering a new market, it is important to thoroughly research the target market's demand and evaluate the risks and rewards. It would also be a good idea to consider collaborating with partner companies."

[0446] Example 1

[0447] 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."

[0448] In modern business, employees need to have strong leadership skills and a wealth of knowledge to make appropriate and prompt decisions. However, not all employees have the decision-making ability of a leader, which can result in poor judgment and a decline in overall corporate performance. If there were a system that could mimic a leader's decision-making process and provide appropriate advice, it would be possible to improve employees' decision-making skills and increase the efficiency of the entire company. Against this background, the present invention aims to provide a system that mimics a leader's decision-making process and quickly provides optimal answers to users.

[0449] 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.

[0450] In this invention, the server includes: means for receiving a question or task entered by a user; means for analyzing the question or task using natural language processing to identify the intent; means for searching a database for related information based on the analysis results; means for executing an algorithm that mimics the decision-making process; means for generating an answer based on the result of the algorithm; means for providing the generated answer to the user; means including a terminal and a web browser or dedicated application for the user to view the answer; means for using a BERT model or GPT model in natural language processing; and means for using a database to search past statements and business strategies based on analyzed keywords. This enables users to quickly obtain specific advice based on a sophisticated decision-making process like that of a leader.

[0451] "User" refers to a user who can input questions or issues into the system and receive answers.

[0452] "Terminal" refers to a hardware device, such as a PC, smartphone, or tablet, through which a user enters questions or tasks and receives answers.

[0453] "Server" refers to a central system that receives questions or challenges sent by users, performs natural language processing, searches a database for relevant information, generates answers, and provides them to users.

[0454] "Natural language processing" refers to the technology that enables computers to understand and process human language, including analyzing text and identifying intent.

[0455] The "BERT model" is a type of natural language processing algorithm based on transformer technology, and is particularly good at analyzing text taking context into account.

[0456] The "GPT model" is a type of natural language processing algorithm that uses generative techniques, and is a technology that generates language based on large amounts of text data.

[0457] "Database" means a collection of information used by a system to store, search, and retrieve information, including but not limited to SQL Server and NoSQL databases.

[0458] "Questions and issues" refer to specific problems or doubts that users input into the system and seek to resolve.

[0459] "Identifying intent" refers to the process of using natural language processing technology to clarify the user's requirements and goals behind the entered question or task.

[0460] "Algorithms that mimic decision-making processes" refers to computational methods that derive optimal answers based on the past decision-making criteria and methods of leaders and CEOs.

[0461] "Generating an answer" refers to the process of creating appropriate advice or solutions to a user's questions or challenges based on analyzed information and decision-making processes.

[0462] A "web browser" refers to software that enables users to interact with servers over the Internet, and includes browsers such as Chrome and Firefox.

[0463] "Purpose-built application" refers to software developed for a specific purpose, to facilitate user access to a system.

[0464] MODE FOR CARRYING OUT THE INVENTION

[0465] This invention provides a system that mimics the decision-making process of corporate leaders. This system analyzes questions and issues entered by users, generates optimal answers based on related information, and provides them to the users. In this system, the server handles the main processing, and the terminal provides the interface with the user.

[0466] First, the user uses their own device to input a question or problem. Specifically, they enter the question into a text input field in a web browser or a dedicated application. This question is specific and based on the user's concerns or problems. For example, "I'm wondering whether to enter a new market. What should I do?" Once the input is complete, the user clicks the send button, and the content is sent to the server.

[0467] Next, the server receives the submitted question data. The server uses natural language processing techniques such as Google's BERT model or OpenAI's GPT model to analyze the intent of the question. This analysis begins with normalizing and tokenizing the sentence (dividing it into words), and then extracting keywords and related information. For example, keywords such as "entering new markets" and "project delays" are extracted.

[0468] The server then runs an algorithm that mimics the decision-making process of a company leader based on the extracted keywords and contextual information. The algorithm includes logic to derive the optimal answer by referencing a database containing past statements and business strategies. Specifically, the database contains information such as books, interviews, and business strategy information, and is managed using SQL Server or a NoSQL database.

[0469] After the algorithm is executed, the server generates a specific answer to the question, such as advice such as "research market demand, evaluate risk and return, and consider partnerships." Finally, the server sends the answer to the user's device, which displays it to the user, either by refreshing the web page or by displaying a dedicated application pop-up.

[0470] ---

[0471] Examples:

[0472] The user types into the device, "I'm wondering whether to enter a new market. What should I do?" The device sends this question to the server. The server receives the question and uses natural language processing to extract the keyword "enter a new market." It then searches a database for related past statements and strategies and runs an algorithm that mimics the decision-making process of a corporate leader. As a result, specific advice is generated: "Research market demand, evaluate risks and returns, and consider partnerships." The server sends this answer to the device, which displays it to the user.

[0473] ---

[0474] Examples of prompts:

[0475] 1. "What is the best way to go to market?"

[0476] 2. "What is the best way to address a delayed project?"

[0477] As described above, this system is able to provide prompt and appropriate advice in response to user questions and issues, allowing users to obtain specific advice based on a high-level decision-making process similar to that of a leader, thereby improving the efficiency of the entire company.

[0478] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0479] Step 1: Accepting user questions

[0480] A user uses a terminal to input a question or problem. Specifically, the user enters the question in a text input field in a web browser or a dedicated application and clicks the send button. This sends the question data in text format to the server. The input might be, for example, "I'm wondering whether to enter a new market. What should I do?" and the output is the text data to be sent.

[0481] Step 2: Question analysis and information extraction

[0482] The server receives the question data sent by the user. The server analyzes the text using a natural language processing model (BERT model or GPT model). Specific analysis operations include normalizing the text (removing unnecessary spaces and symbols), tokenizing (dividing it into words), and stemming (reducing words to their original form). The text data received in step 1 is given as input, and the extracted keywords and contextual information (e.g., entering a new market) are obtained as output.

[0483] Step 3: Mimic the decision-making process

[0484] The server runs an algorithm that mimics the decision-making process based on the keywords and contextual information obtained in step 2. This algorithm references a database that stores past statements and business strategies to retrieve relevant information. Specifically, it searches the database for the required information using SQL or NoSQL queries. The input is the extracted keywords (e.g., "enter a new market"), and the output is relevant information for decision-making (e.g., past market analysis data, risk assessment, etc.).

[0485] Step 4: Answer Generation

[0486] The server generates the optimal answer to the user's question based on the related information obtained in step 3. For generation, a natural language generation model (such as a GPT model) is again used. Specifically, the related information is provided as input data, and the generation model uses it to generate a natural, contextual answer. The input is the related information and the prompt sentence of the generation AI model, and the output is the generated specific answer text.

[0487] Step 5: Provide your answers

[0488] The server sends the answer generated in step 4 to the user's device. The device analyzes the received answer and displays it to the user. Specifically, the answer is displayed by updating the web page or by displaying a popup in a dedicated application. The input is the generated answer text, and the output is the answer content displayed on the user's screen.

[0489] The above is a specific description of each processing step of this system, including input, data processing, output, and specific operations at each step.

[0490] (Application example 1)

[0491] 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."

[0492] Providing specific, practical advice to help store managers and administrators make quick and accurate decisions in the daily tasks they face is not easy. Optimal advice based on experience and past data is particularly required for a wide range of tasks, such as inventory management, staff shift management, and new product introductions, but there is no established method for providing this advice.

[0493] 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.

[0494] In this invention, the server includes means for receiving a question or task input by a user, means for analyzing the question or task using natural language processing to identify the intent, means for searching a database for related information based on the analysis result, means for executing an algorithm that mimics the decision-making process of the leader, means for generating an answer based on the result of the algorithm, means for providing the generated answer to the user, means for using information context to provide advice on various tasks, and means for generating optimal advice using a generative AI model. This makes it possible to provide quick and specific advice for the daily tasks faced by managers and store managers of brick-and-mortar stores.

[0495] The "means for receiving questions and assignments entered by the user" refers to an interface and interactive communication function for receiving questions and assignments in text format entered by the user through a terminal.

[0496] "Means of analyzing and identifying intent using natural language processing" refers to an analytical technology that recognizes questions or tasks entered in text form by users and understands their meaning and purpose.

[0497] "Means for searching for relevant information from a database" refers to a technology that identifies the necessary data based on the intent of the analyzed question or task, and retrieves the appropriate information from the database that stores that data.

[0498] "Means for implementing algorithms that mimic the decision-making process of leaders" refers to technology that uses similar algorithms to make optimal decisions based on the decision-making processes used by corporate leaders in the past.

[0499] "Answer generation means" refers to techniques for creating specific answers to user questions or challenges based on acquired information and simulated decision-making processes.

[0500] The "means for providing the generated answer to the user" refers to an interface and communication technology for transmitting the generated answer to the user terminal and displaying the result to the user.

[0501] "Means using information context to provide advice on various operations" refers to means for providing advice using specific and detailed information on various operations related to managing a physical store (e.g., inventory management, staff management, new product introduction, etc.).

[0502] "Means for generating optimal advice using generative AI models" refers to technology that utilizes artificial intelligence technology to generate the most appropriate advice or answer to a user's question or issue.

[0503] This invention provides a support tool for store managers and administrators to instantly make optimal decisions in their daily work. Specifically, it is implemented as a smartphone application that provides quick and accurate answers based on user input.

[0504] The system consists of a user terminal (a smartphone in this case) and a server. The system includes the following main functional blocks:

[0505] User device functions

[0506] An interface is implemented on the user terminal for users to input questions and tasks. The user inputs a question in text format and sends it to the server.

[0507] Server Features

[0508] The server is responsible for the main data processing and response generation. It performs the following tasks:

[0509] 1. Question analysis:

[0510] The server analyzes the user-submitted question using natural language processing techniques (e.g., the transformers library), which perform topic modeling and keyword extraction to identify the intent of the question.

[0511] 2. Information Search:

[0512] Based on the intent of the question, relevant information (past statements, business strategies, operational know-how, etc.) is searched from a database.

[0513] 3. Answer generation:

[0514] It uses algorithms that mimic the decision-making process of leaders and generative AI models (e.g., transformers' question-answering pipeline) to generate optimal answers, leveraging diverse business context in the process.

[0515] 4. Provide answers:

[0516] The generated answer is sent to the user terminal and finally displayed to the user.

[0517] Specific use cases

[0518] For example, if a store manager were to enter a question through the app such as, "Which products would you recommend for this weekend's sale?", the following process would take place:

[0519] 1. The user terminal receives the query and sends it to the server.

[0520] 2. The server analyzes the question and extracts keywords such as "sale" and "recommended products."

[0521] 3. Search the database for relevant past sales data and competitive information on the product.

[0522] 4. Using a generative AI model, mimicking the leader's decision-making process, generate the answer "Provide a list of products with high sales performance."

[0523] 5. The server sends this response to the user's terminal and displays it to the user.

[0524] Prompt Sentence Examples

[0525] "Please give me some advice on inventory management."

[0526] "What items would you recommend in this weekend's sale?"

[0527] This system will enable store managers and supervisors to receive prompt and specific advice on a wide range of tasks.

[0528] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0529] Step 1:

[0530] The user inputs a question or task. Specifically, the question is entered in text format through a dedicated smartphone application, and is sent to the server by pressing the send button. An example of input in this case would be "Which products do you recommend for this weekend's sale?" The output is text data from the user.

[0531] Step 2:

[0532] The terminal sends the question entered by the user to the server, where the text data entered by the user is converted into packets and sent to the server via Internet communication. The input is the text data from the user, and the output is the transmitted packets.

[0533] Step 3:

[0534] The server analyzes the received question. Specifically, it uses natural language processing technology to analyze the question and performs topic modeling and keyword extraction. Here, keywords such as "sale" and "recommended products" are extracted, for example. The input is the user's text data, and the output is the extracted keywords and intent.

[0535] Step 4:

[0536] The server searches the database based on the analysis results. Specifically, it searches the database for relevant past data (e.g., past statements, business strategies, operational know-how, etc.) based on the extracted keywords and intent. The input is the extracted keywords and intent, and the output is a list of related information.

[0537] Step 5:

[0538] The server runs an algorithm that mimics the leader's decision-making process. Specifically, it uses relevant information to run the decision-making algorithm and generate an appropriate answer. The input is a list of relevant information, and the output is the generated answer.

[0539] Step 6:

[0540] The server generates optimal advice using a generative AI model (e.g., a question-answering pipeline in transformers) to generate specific advice. The input is the result of the decision-making algorithm, and the output is the final generated advice.

[0541] Step 7:

[0542] The server sends the generated answer to the user terminal. Specifically, it converts the generated advice in text format into packets and sends them to the user terminal via Internet communication. The input is the generated advice, and the output is the transmitted packets.

[0543] Step 8:

[0544] The terminal receives advice from the server and displays it to the user. Specifically, it converts the received packets into text data and displays it through a user interface. The input is the received packets, and the output is the display on the user interface.

[0545] 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.

[0546] This invention combines a system that mimics the decision-making process of corporate leaders with an emotion engine that recognizes user emotions. The program processing of this system is explained in natural language below. The program is executed through interaction between the server, terminals, and users.

[0547] Program Overview

[0548] This system analyzes questions and issues entered by users, generates optimal answers based on relevant information and emotional data, and provides them to the users. The server handles the main processing, while the terminal provides the interface with the user.

[0549] Processing flow (overview)

[0550] 1. Accepting user questions

[0551] Users input questions and tasks in text format through the terminal.

[0552] 2. Question analysis and information extraction

[0553] The server receives the question sent from the terminal and analyzes the intent of the question using natural language processing.

[0554] Based on the analysis results, the server searches the database for relevant information.

[0555] 3. Emotion recognition

[0556] The server uses an emotion engine to extract emotion data from the user's input text, for example, to determine whether the user is feeling anxious or excited.

[0557] 4. Imitating the decision-making process

[0558] The server runs an algorithm that mimics the CEO's decision-making process, including the extracted emotional data, to generate the optimal answer.

[0559] 5. Answer Generation and Delivery

[0560] The server formats the generated responses, adjusting the tone and content based on the emotional data, and provides them to the user.

[0561] Specific examples

[0562] Example 1: New market entry question

[0563] The user types into the terminal, "I'm wondering whether to enter a new market. What should I do?" The terminal sends this question to the server.

[0564] The server receives the question and uses natural language processing to extract the keyword "entering new markets." It then searches a database for related past statements and strategies. It then uses an emotion engine to recognize the emotion "worried" from the user's text. The server then takes this emotion data into account and runs an algorithm that mimics a CEO's decision-making process. As a result, it generates specific advice: "Research market demand, evaluate risks and rewards, and consider partnerships." The answer includes emotionally sensitive language: "We understand your concerns. To alleviate them, it's important to conduct thorough market research and risk assessment." The server then sends this answer to the device, which displays it to the user.

[0565] Example 2: Project Delay Question

[0566] The user types into the terminal, "What would you do if the project was delayed?" The terminal sends this question to the server.

[0567] The server receives the question and uses natural language processing to extract the keyword "project delay." It then searches a database for related past statements and strategies. It then uses an emotion engine to recognize the emotion of "impatience" from the user's text. The server then takes this emotion data into account and runs an algorithm that mimics a CEO's decision-making process. As a result, it generates specific advice: "Quickly identify the cause of the delay, reallocate resources, review priorities, and strengthen communication." The response includes a tone that takes emotion into consideration: "We understand your current impatience. To respond calmly, please prioritize identifying the cause of the delay." The server then sends this response to the device, which displays it to the user.

[0568] This system is designed to help employees improve their decision-making skills and contribute to the development of the company. It provides quick answers to users' questions and issues, and by combining the CEO's decision-making process with emotion recognition, it ensures consistency of knowledge across the company and mental health care for employees.

[0569] The processing flow will be explained below.

[0570] Step 1:

[0571] A user types a question or challenge into the device in text format, for example, "I'm wondering whether to expand into a new market. What should I do?"

[0572] Step 2:

[0573] The terminal receives the user's input and sends the data to the server in text format.

[0574] Step 3:

[0575] The server checks the query data received from the terminal and adjusts the format appropriately for internal processing.

[0576] Step 4:

[0577] The server applies natural language processing (NLP) modules to analyze the question text, including topic modeling and keyword extraction.

[0578] Step 5:

[0579] The server uses the analysis results to identify the subject and intent of the question, for example extracting the main theme of "entering new markets."

[0580] Step 6:

[0581] Based on the specified intent, the server searches a database of relevant information, including information on past statements, books, interviews, and business strategies.

[0582] Step 7:

[0583] The server uses an emotion engine to extract emotion data from the user's input text, for example, to recognize whether the user is feeling "anxious."

[0584] Step 8:

[0585] The server runs an algorithm to mimic the leader's decision-making process, integrating the identified intent with the extracted emotional data to generate the optimal answer.

[0586] Step 9:

[0587] The server then formats the generated responses, adjusting the tone and content based on the user's emotions. For example, if a user is feeling anxious, reassuring language will be added.

[0588] Step 10:

[0589] The server then sends the formatted answer data to the terminal in a format that is easy for the user to understand.

[0590] Step 11:

[0591] The device displays the answer received from the server to the user. For example, it might say, "When entering a new market, it is important to thoroughly research the target market's demand and evaluate the risks and rewards. It would also be a good idea to consider collaborating with partner companies. We understand your concerns. To alleviate them, it is important to conduct thorough market research and risk assessment."

[0592] Example 2

[0593] 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."

[0594] In modern companies, quick and accurate decision-making is required, but few systems provide responses that appropriately consider the user's emotions during the decision-making process. In particular, there is a need for a system that can generate answers that reflect the user's emotions while mimicking the decision-making process of a leader.

[0595] 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.

[0596] In this invention, the server includes means for receiving a question or task input by a user, means for analyzing the question or task using natural language processing to identify the intent, means for searching a database for related information based on the analysis results, means for extracting emotional data from the user's input, means for executing an algorithm that mimics a CEO's decision-making process based on the analysis results including the emotional data, means for generating an answer that takes the emotional data into consideration based on the results of the algorithm, and means for providing the generated answer to the user. This makes it possible to provide an appropriate answer that takes the user's emotions into consideration while mimicking a leader's decision-making process.

[0597] "User" refers to a person who uses the system to enter questions or issues and receive answers.

[0598] "Terminal" refers to a device that provides an interface for users to access the system and input questions or tasks. Examples include personal computers and smartphones.

[0599] "Question or Problem" refers to a textual inquiry that a user enters into the system seeking a solution.

[0600] "Natural language processing" refers to the technology for analyzing user-entered text and understanding its intent and sentiment. Specifically, it includes topic modeling and keyword extraction.

[0601] "Database" refers to a collection of information that the system references, including past statements, books, interviews, and business strategies.

[0602] "Emotion engine" refers to technology for extracting emotional data from user input, such as a sentiment analysis API.

[0603] "Emotion data" refers to emotional state information extracted from text entered by a user, including, for example, feelings of anxiety or impatience.

[0604] An "algorithm" is a set of computational steps to solve a specific problem or perform a computation, in this case to mimic the decision-making process of a CEO.

[0605] "Answer" refers to a response from the system to a user's question or problem, containing appropriate information and taking into account the user's feelings.

[0606] "Means for providing" refers to the technical means by which the server displays the answer to the user, specifically including sending the answer to the terminal.

[0607] This invention is a system that mimics the decision-making process of corporate leaders and recognizes user emotions. The main processing is handled by the server, and the user and terminal provide the interface.

[0608] Program processing overview

[0609] This system analyzes questions and issues entered by users, generates optimal answers based on relevant information and emotional data, and provides them to users. The main technologies and the hardware and software used are described below.

[0610] 1. Accepting user questions

[0611] The user enters a question in text format using a device, such as a PC or smartphone.

[0612] Example: User types, "I'm wondering whether to expand into a new market. What should I do?"

[0613] 2. Question analysis and information extraction

[0614] The server receives the question sent from the terminal and analyzes the intent of the question using natural language processing.

[0615] In this case, natural language processing libraries such as SpaCy and NLTK are used.

[0616] The server searches for relevant information from a database (e.g., MySQL, PostgreSQL, etc.) based on the analyzed keywords.

[0617] 3. Emotion recognition

[0618] The server uses an emotion engine to extract emotion data from the user's input text.

[0619] Specifically, it uses the sentiment analysis API of Microsoft Azure's Cognitive Services.

[0620] The server recognizes emotions such as "worried" and adds them to the analysis results.

[0621] 4. Imitating the decision-making process

[0622] The server then runs an algorithm that mimics the CEO's decision-making process, including the extracted emotional data.

[0623] For example, using machine learning models such as TensorFlow or Scikit-learn.

[0624] 5. Answer Generation and Delivery

[0625] The server formats the responses it generates, adjusting the tone and content based on emotional data.

[0626] The server converts the final response into JSON format and sends it to the terminal.

[0627] The terminal parses the received JSON data and displays it to the user.

[0628] Specific examples

[0629] Example 1: New market entry question

[0630] A user types into their terminal, "I'm wondering whether to expand into a new market. What should I do?"

[0631] The terminal sends this question to the server.

[0632] The server receives the question and uses natural language processing to extract the keyword "entering new markets."

[0633] Next, the database is searched for relevant past statements and strategies.

[0634] An emotion engine is used to recognize the emotion of "worried" from the user's text.

[0635] The server then takes this emotional data into account and runs an algorithm that mimics the CEO's decision-making process.

[0636] The result is specific advice on "market demand research, risk and return assessment, and partnership considerations."

[0637] The response includes sensitive language such as, "We understand your concerns. To alleviate them, it is important to conduct thorough market research and risk assessment."

[0638] The server sends this response to the terminal, which displays it to the user.

[0639] This system is designed to improve users' decision-making ability and contribute to the development of the company. It provides quick answers to users' questions and issues, and by combining the CEO's decision-making process with emotion recognition, it can ensure consistency of knowledge across the company and mental health care for employees.

[0640] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0641] Step 1: Accepting user questions

[0642] Specific actions

[0643] The user enters a question in text format using a terminal.

[0644] For example, a user might type, "I'm wondering whether to expand into a new market. What should I do?"

[0645] The terminal interface has an input field and a "Submit" button, which the user presses to send the question to the server.

[0646] input

[0647] Text data entered by the user into the terminal.

[0648] output

[0649] The text data sent to the server.

[0650] Step 2: Question analysis and information extraction

[0651] Specific actions

[0652] The server receives the question sent from the terminal and analyzes the text data.

[0653] The intent of the question is analyzed using natural language processing technology, for example using libraries such as SpaCy and NLTK.

[0654] The server extracts keywords such as "entering new markets" from the analysis results.

[0655] Based on the extracted keywords, the server retrieves relevant information from a database (e.g., MySQL or PostgreSQL) and temporarily stores it.

[0656] input

[0657] The text data received by the server.

[0658] output

[0659] Data and related information extracted as keywords.

[0660] Step 3: Emotion Recognition

[0661] Specific actions

[0662] The server uses an emotion engine to extract emotion data from the user's input text.

[0663] Specifically, it calls the sentiment analysis API of Microsoft Azure's Cognitive Services and sends text data.

[0664] Based on the received emotion data, emotions such as "worried" or "anxious" are recognized from the user's text.

[0665] The server adds this emotion data to the previously extracted keywords and related information.

[0666] input

[0667] Text data and already extracted keywords.

[0668] output

[0669] Analysis results with added emotion data.

[0670] Step 4: Imitate the decision-making process

[0671] Specific actions

[0672] The server runs an algorithm that mimics the CEO's decision-making process based on the analysis results, including the extracted emotional data.

[0673] For example, use machine learning models such as TensorFlow or Scikit-learn and load pre-trained algorithms.

[0674] The server inputs the analysis results and emotional data into an algorithm to generate the optimal answer.

[0675] The answers generated include specific advice such as "research market demand, assess risks, and consider partnerships."

[0676] input

[0677] Analysis results with added emotion data.

[0678] output

[0679] Algorithmically generated answers.

[0680] Step 5: Generate and provide answers

[0681] Specific actions

[0682] The server formats the generated responses, adjusting the tone and content based on the emotional data.

[0683] Specifically, the generated answers will be enhanced with emotionally sensitive language such as, "We understand your concerns. To alleviate them, it is important to conduct thorough market research and risk assessments."

[0684] The final answer is converted to JSON format and sent to the terminal.

[0685] The terminal parses the received JSON data and displays it to the user.

[0686] input

[0687] Algorithmically generated answers.

[0688] output

[0689] The final answer provided to the user.

[0690] (Application example 2)

[0691] 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."

[0692] Conventionally, security services have lacked systems that can quickly and accurately respond when users feel anxious or worried. As a result, it is difficult for users to find an appropriate solution, which can lead to a decline in the quality of security services. Furthermore, the inability to respond appropriately to users' emotions can further increase anxiety and impatience. The present invention aims to solve these problems.

[0693] 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 or task entered by a user, means for analyzing the question or task using natural language processing and identifying the intent, means for recognizing emotions from the entered text, means for searching a database for related information based on the analysis results and emotions, means for executing an algorithm that mimics the decision-making process, means for generating an answer that takes emotions into consideration based on the results of the algorithm, and means for providing the generated answer to the user. This enables a quick and accurate response when a user of a security service feels anxious or concerned. Furthermore, generating an answer that takes the user's emotions into consideration can improve the user's sense of security.

[0694] A "question" is text entered by a user regarding a particular problem or question.

[0695] A "problem" refers to a particular problem situation or challenge that a user wishes to solve.

[0696] "Natural language processing" is a general term for technology that allows computers to understand, analyze, and generate human language.

[0697] "Emotion" refers to a psychological state extracted from the text entered by the user, such as anxiety or impatience.

[0698] A "database" is a collection of related information organized for efficient searching and retrieval.

[0699] An "algorithm that mimics the decision-making process" is a computational procedure that replicates the decision-making process of corporate leaders.

[0700] An "answer" is a response generated by the server in response to a user's question or task.

[0701] "Relevant information" refers to data or documents that are directly related to the question or issue.

[0702] "Emotion recognition" refers to the technology of identifying a user's psychological state from their input text.

[0703] "Means for providing to the user" refers to the interface or method for showing the generated answer to the user.

[0704] This system analyzes questions and issues entered by users, generates and provides optimal answers based on related emotional data, and is implemented through interactions between the server, terminals, and users.

[0705] The server is the main processing unit and includes the following elements:

[0706] A way to receive questions and assignments

[0707] A means of analyzing questions and issues using natural language processing

[0708] A method for recognizing emotions from input text

[0709] A means of searching for relevant information from a database based on analysis results and sentiment

[0710] A means of implementing algorithms that mimic decision-making processes

[0711] A means of generating answers based on the results of an algorithm

[0712] A means of providing the generated answer to the user

[0713] Hardware and Software Configuration

[0714] Hardware:

[0715] Smartphone (user device)

[0716] Server (main processing and database management)

[0717] software:

[0718] Amazon Web Services (AWS) Lambda (serverless computing)

[0719] Google Cloud Natural Language API (Natural Language Processing)

[0720] IBM Watson Emotion Analysis

[0721] Python (programming language)

[0722] Data processing and calculation

[0723] 1. Receiving questions and assignments:

[0724] A user uses a smartphone to input a question or problem, for example, "My home security system has detected an abnormality. I'm worried. What should I do?"

[0725] 2. Analysis of questions and issues:

[0726] The server uses the Google Cloud Natural Language API to analyze the user's question or issue and extract key keywords (e.g., "security system," "anomaly").

[0727] 3. Emotion recognition:

[0728] The server uses IBM Watson Emotion Analysis to identify emotions from the user's input text (e.g., "anxiety").

[0729] 4. Information Search:

[0730] The server searches the database for relevant information based on the analyzed keywords and emotional data.

[0731] 5. Imitating the decision-making process:

[0732] The server runs an algorithm that mimics the decision-making process of a company leader, combining relevant information and emotional data to generate the best answer.

[0733] 6. Generate and provide answers:

[0734] The server adjusts the generated answer taking into account the user's emotions and displays it on the smartphone (e.g., "If an abnormality is detected, first remain calm and call your emergency contact or the nearest police station.").

[0735] Prompt Sentence Examples

[0736] User Question: "My home security system is detecting something abnormal. I'm worried. What should I do?"

[0737] Analyzed keywords: "security system", "abnormality"

[0738] Recognized emotion: "Anxiety"

[0739] Generated advice: "If an abnormality is detected, first remain calm and call your emergency contact or the nearest police station. Also, check the system logs and gather as much information as possible."

[0740] This system can provide users with optimal means to quickly and accurately resolve security-related issues and concerns. In particular, by taking emotional data into consideration, it can provide solutions that are suited to the psychological state of each individual user.

[0741] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0742] Step 1:

[0743] A user inputs a question or problem into their smartphone. For example, they input text like, "My home security system has detected an abnormality. I'm worried. What should I do?" This text is then sent from the device to the server. The input data is the user text, and the output data is the raw text sent to the server.

[0744] Step 2:

[0745] The server sends the received text to the Google Cloud Natural Language API and analyzes it using natural language processing. Specifically, the server extracts key keywords from the text. For example, the keywords "security system" and "abnormal" are extracted. The input data is the raw text, and the output data is the analyzed keywords.

[0746] Step 3:

[0747] The server uses IBM Watson Emotion Analysis to recognize emotions from the user's text based on the extracted keywords. Specifically, the raw text is sent to the emotion recognition engine, and the emotion "anxiety" is extracted as a result. The input data is the raw text and keywords, and the output data is the recognized emotion.

[0748] Step 4:

[0749] The server searches a database for relevant information based on the analyzed keywords and emotions. For example, past documents and advice on how to respond to security system anomalies are searched for. The input data is keyword and emotion data, and the output data is a set of related information.

[0750] Step 5:

[0751] The server runs an algorithm that mimics the decision-making process based on relevant information and emotional data. Specifically, it mimics past decisions made by company leaders and generates appropriate advice. The input data is relevant information and emotional data, and the output data is the generated advice.

[0752] Step 6:

[0753] The server adjusts the content and tone of the generated advice to provide it to the user based on the emotional data. For example, it uses language that alleviates anxiety. The input data are the generated advice and emotional data, and the output data is the optimized advice.

[0754] Step 7:

[0755] The device displays the optimized advice to the user, allowing the user to act based on the advice. Specifically, the advice is displayed on the smartphone screen. The input data is the optimized advice, and the output data is displayed to the user.

[0756] 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.

[0757] 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.

[0758] 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.

[0759] [Third embodiment]

[0760] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0761] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0762] 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).

[0763] 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.

[0764] 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.

[0765] 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).

[0766] 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.

[0767] 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.

[0768] 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.

[0769] 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.

[0770] 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.

[0771] 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."

[0772] This invention provides a system that mimics the decision-making process of corporate leaders. Specifically, it analyzes questions and issues entered by users, generates optimal answers based on related information, and provides them to the users. We generate a program for this system and explain its processing in natural language.

[0773] Program Overview

[0774] The system analyzes questions and issues entered by users and generates answers based on the leader's past statements and business strategies. The server handles the main processing, while the terminal provides the interface with the user.

[0775] Processing flow (overview)

[0776] 1. Accepting user questions

[0777] Users input questions and tasks in text format through the terminal.

[0778] 2. Question analysis and information extraction

[0779] The server receives the question sent from the terminal and analyzes the intent of the question using natural language processing.

[0780] Based on the analysis results, the server searches the database for relevant information.

[0781] 3. Imitating the decision-making process

[0782] The server runs an algorithm that mimics the CEO's decision-making process and generates the optimal answer.

[0783] 4. Answer generation and provision

[0784] The server sends the generated answer to the terminal, which displays the answer to the user.

[0785] Specific examples

[0786] Example 1: New market entry question

[0787] The user types into the terminal, "I'm wondering whether to enter a new market. What should I do?" The terminal sends this question to the server.

[0788] The server receives the question and uses natural language processing to extract the keyword "enter new markets." It then searches a database for relevant past statements and strategies and runs an algorithm that mimics a CEO's decision-making process. The resulting advice is specific: "Research market demand, evaluate risks and rewards, and consider partnerships." The server then sends the answer to the device, which displays it to the user.

[0789] Example 2: Project Delay Question

[0790] The user types into the terminal, "What would you do if the project was delayed?" The terminal sends this question to the server.

[0791] The server receives the question and uses natural language processing to extract the keyword "project delay." It then searches a database for relevant past statements and strategies and runs an algorithm that mimics the CEO's decision-making process. The result is specific advice: "Quickly identify the cause of the delay, reallocate resources, review priorities, and strengthen communication." The server sends this answer to the device, which displays it to the user.

[0792] The system is designed to help employees improve their decision-making skills and contribute to the company's growth. It provides quick answers to users' questions and issues, and shares the CEO's decision-making process, ensuring consistency of knowledge across the company.

[0793] The processing flow will be explained below.

[0794] Step 1:

[0795] The user enters a question or problem in text format into the terminal. For example, they enter a question like, "I'm wondering whether to enter a new market. What should I do?"

[0796] Step 2:

[0797] The terminal checks the user's question data and sends it to the server in text format.

[0798] Step 3:

[0799] The server receives the question data sent from the terminal and converts the received text data into a format for internal processing.

[0800] Step 4:

[0801] The server uses a natural language processing (NLP) module to analyze the question text, including topic modeling and keyword extraction.

[0802] Step 5:

[0803] The server identifies the user's intent based on the analysis of the question text. For example, if the keyword "entering a new market" is extracted, the server identifies the intent as "decision-making regarding market expansion."

[0804] Step 6:

[0805] Based on the specified intent, the server searches a database for relevant information, including information on the CEO's past statements, books, interviews, and business strategies.

[0806] Step 7:

[0807] The server retrieves the relevant information and runs an algorithm that mimics the CEO's decision-making process, taking into account past successes and failures to arrive at the optimal answer.

[0808] Step 8:

[0809] The server formats the generated answer and converts it into an output format for presentation to the user.

[0810] Step 9:

[0811] The server sends the formatted response to the terminal. The response data is formatted to be easy for the user to understand.

[0812] Step 10:

[0813] The device will then display the response data received from the server to the user, and provide specific advice such as, "When entering a new market, it is important to thoroughly research the target market's demand and evaluate the risks and rewards. It would also be a good idea to consider collaborating with partner companies."

[0814] Example 1

[0815] 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."

[0816] In modern business, employees need to have strong leadership skills and a wealth of knowledge to make appropriate and prompt decisions. However, not all employees have the decision-making ability of a leader, which can result in poor judgment and a decline in overall corporate performance. If there were a system that could mimic a leader's decision-making process and provide appropriate advice, it would be possible to improve employees' decision-making skills and increase the efficiency of the entire company. Against this background, the present invention aims to provide a system that mimics a leader's decision-making process and quickly provides optimal answers to users.

[0817] 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.

[0818] In this invention, the server includes: means for receiving a question or task entered by a user; means for analyzing the question or task using natural language processing to identify the intent; means for searching a database for related information based on the analysis results; means for executing an algorithm that mimics the decision-making process; means for generating an answer based on the result of the algorithm; means for providing the generated answer to the user; means including a terminal and a web browser or dedicated application for the user to view the answer; means for using a BERT model or GPT model in natural language processing; and means for using a database to search past statements and business strategies based on analyzed keywords. This enables users to quickly obtain specific advice based on a sophisticated decision-making process like that of a leader.

[0819] "User" refers to a user who can input questions or issues into the system and receive answers.

[0820] "Terminal" refers to a hardware device, such as a PC, smartphone, or tablet, through which a user enters questions or tasks and receives answers.

[0821] "Server" refers to a central system that receives questions or challenges sent by users, performs natural language processing, searches a database for relevant information, generates answers, and provides them to users.

[0822] "Natural language processing" refers to the technology that enables computers to understand and process human language, including analyzing text and identifying intent.

[0823] The "BERT model" is a type of natural language processing algorithm based on transformer technology, and is particularly good at analyzing text taking context into account.

[0824] The "GPT model" is a type of natural language processing algorithm that uses generative techniques, and is a technology that generates language based on large amounts of text data.

[0825] "Database" means a collection of information used by a system to store, search, and retrieve information, including but not limited to SQL Server and NoSQL databases.

[0826] "Questions and issues" refer to specific problems or doubts that users input into the system and seek to resolve.

[0827] "Identifying intent" refers to the process of using natural language processing technology to clarify the user's requirements and goals behind the entered question or task.

[0828] "Algorithms that mimic decision-making processes" refers to computational methods that derive optimal answers based on the past decision-making criteria and methods of leaders and CEOs.

[0829] "Generating an answer" refers to the process of creating appropriate advice or solutions to a user's questions or challenges based on analyzed information and decision-making processes.

[0830] A "web browser" refers to software that enables users to interact with servers over the Internet, and includes browsers such as Chrome and Firefox.

[0831] "Purpose-built application" refers to software developed for a specific purpose, to facilitate user access to a system.

[0832] MODE FOR CARRYING OUT THE INVENTION

[0833] This invention provides a system that mimics the decision-making process of corporate leaders. This system analyzes questions and issues entered by users, generates optimal answers based on related information, and provides them to the users. In this system, the server handles the main processing, and the terminal provides the interface with the user.

[0834] First, the user uses their own device to input a question or problem. Specifically, they enter the question into a text input field in a web browser or a dedicated application. This question is specific and based on the user's concerns or problems. For example, "I'm wondering whether to enter a new market. What should I do?" Once the input is complete, the user clicks the send button, and the content is sent to the server.

[0835] Next, the server receives the submitted question data. The server uses natural language processing techniques such as Google's BERT model or OpenAI's GPT model to analyze the intent of the question. This analysis begins with normalizing and tokenizing the sentence (dividing it into words), and then extracting keywords and related information. For example, keywords such as "entering new markets" and "project delays" are extracted.

[0836] The server then runs an algorithm that mimics the decision-making process of a company leader based on the extracted keywords and contextual information. The algorithm includes logic to derive the optimal answer by referencing a database containing past statements and business strategies. Specifically, the database contains information such as books, interviews, and business strategy information, and is managed using SQL Server or a NoSQL database.

[0837] After the algorithm is executed, the server generates a specific answer to the question, such as advice such as "research market demand, evaluate risk and return, and consider partnerships." Finally, the server sends the answer to the user's device, which displays it to the user, either by refreshing the web page or by displaying a dedicated application pop-up.

[0838] ---

[0839] Examples:

[0840] The user types into the device, "I'm wondering whether to enter a new market. What should I do?" The device sends this question to the server. The server receives the question and uses natural language processing to extract the keyword "enter a new market." It then searches a database for related past statements and strategies and runs an algorithm that mimics the decision-making process of a corporate leader. As a result, specific advice is generated: "Research market demand, evaluate risks and returns, and consider partnerships." The server sends this answer to the device, which displays it to the user.

[0841] ---

[0842] Examples of prompts:

[0843] 1. "What is the best way to go to market?"

[0844] 2. "What is the best way to address a delayed project?"

[0845] As described above, this system is able to provide prompt and appropriate advice in response to user questions and issues, allowing users to obtain specific advice based on a high-level decision-making process similar to that of a leader, thereby improving the efficiency of the entire company.

[0846] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0847] Step 1: Accepting user questions

[0848] A user uses a terminal to input a question or problem. Specifically, the user enters the question in a text input field in a web browser or a dedicated application and clicks the send button. This sends the question data in text format to the server. The input might be, for example, "I'm wondering whether to enter a new market. What should I do?" and the output is the text data to be sent.

[0849] Step 2: Question analysis and information extraction

[0850] The server receives the question data sent by the user. The server analyzes the text using a natural language processing model (BERT model or GPT model). Specific analysis operations include normalizing the text (removing unnecessary spaces and symbols), tokenizing (dividing it into words), and stemming (reducing words to their original form). The text data received in step 1 is given as input, and the extracted keywords and contextual information (e.g., entering a new market) are obtained as output.

[0851] Step 3: Mimic the decision-making process

[0852] The server runs an algorithm that mimics the decision-making process based on the keywords and contextual information obtained in step 2. This algorithm references a database that stores past statements and business strategies to retrieve relevant information. Specifically, it searches the database for the required information using SQL or NoSQL queries. The input is the extracted keywords (e.g., "enter a new market"), and the output is relevant information for decision-making (e.g., past market analysis data, risk assessment, etc.).

[0853] Step 4: Answer Generation

[0854] The server generates the optimal answer to the user's question based on the related information obtained in step 3. For generation, a natural language generation model (such as a GPT model) is again used. Specifically, the related information is provided as input data, and the generation model uses it to generate a natural, contextual answer. The input is the related information and the prompt sentence of the generation AI model, and the output is the generated specific answer text.

[0855] Step 5: Provide your answers

[0856] The server sends the answer generated in step 4 to the user's device. The device analyzes the received answer and displays it to the user. Specifically, the answer is displayed by updating the web page or by displaying a popup in a dedicated application. The input is the generated answer text, and the output is the answer content displayed on the user's screen.

[0857] The above is a specific description of each processing step of this system, including input, data processing, output, and specific operations at each step.

[0858] (Application example 1)

[0859] 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."

[0860] Providing specific, practical advice to help store managers and administrators make quick and accurate decisions in the daily tasks they face is not easy. Optimal advice based on experience and past data is particularly required for a wide range of tasks, such as inventory management, staff shift management, and new product introductions, but there is no established method for providing this advice.

[0861] 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.

[0862] In this invention, the server includes means for receiving a question or task input by a user, means for analyzing the question or task using natural language processing to identify the intent, means for searching a database for related information based on the analysis result, means for executing an algorithm that mimics the decision-making process of the leader, means for generating an answer based on the result of the algorithm, means for providing the generated answer to the user, means for using information context to provide advice on various tasks, and means for generating optimal advice using a generative AI model. This makes it possible to provide quick and specific advice for the daily tasks faced by managers and store managers of brick-and-mortar stores.

[0863] The "means for receiving questions and assignments entered by the user" refers to an interface and interactive communication function for receiving questions and assignments in text format entered by the user through a terminal.

[0864] "Means of analyzing and identifying intent using natural language processing" refers to an analytical technology that recognizes questions or tasks entered in text form by users and understands their meaning and purpose.

[0865] "Means for searching for relevant information from a database" refers to a technology that identifies the necessary data based on the intent of the analyzed question or task, and retrieves the appropriate information from the database that stores that data.

[0866] "Means for implementing algorithms that mimic the decision-making process of leaders" refers to technology that uses similar algorithms to make optimal decisions based on the decision-making processes used by corporate leaders in the past.

[0867] "Answer generation means" refers to techniques for creating specific answers to user questions or challenges based on acquired information and simulated decision-making processes.

[0868] The "means for providing the generated answer to the user" refers to an interface and communication technology for transmitting the generated answer to the user terminal and displaying the result to the user.

[0869] "Means using information context to provide advice on various operations" refers to means for providing advice using specific and detailed information on various operations related to managing a physical store (e.g., inventory management, staff management, new product introduction, etc.).

[0870] "Means for generating optimal advice using generative AI models" refers to technology that utilizes artificial intelligence technology to generate the most appropriate advice or answer to a user's question or issue.

[0871] This invention provides a support tool for store managers and administrators to instantly make optimal decisions in their daily work. Specifically, it is implemented as a smartphone application that provides quick and accurate answers based on user input.

[0872] The system consists of a user terminal (a smartphone in this case) and a server. The system includes the following main functional blocks:

[0873] User device functions

[0874] An interface is implemented on the user terminal for users to input questions and tasks. The user inputs a question in text format and sends it to the server.

[0875] Server Features

[0876] The server is responsible for the main data processing and response generation. It performs the following tasks:

[0877] 1. Question analysis:

[0878] The server analyzes the user-submitted question using natural language processing techniques (e.g., the transformers library), which perform topic modeling and keyword extraction to identify the intent of the question.

[0879] 2. Information Search:

[0880] Based on the intent of the question, relevant information (past statements, business strategies, operational know-how, etc.) is searched from a database.

[0881] 3. Answer generation:

[0882] It uses algorithms that mimic the decision-making process of leaders and generative AI models (e.g., transformers' question-answering pipeline) to generate optimal answers, leveraging diverse business context in the process.

[0883] 4. Provide answers:

[0884] The generated answer is sent to the user terminal and finally displayed to the user.

[0885] Specific use cases

[0886] For example, if a store manager were to enter a question through the app such as, "Which products would you recommend for this weekend's sale?", the following process would take place:

[0887] 1. The user terminal receives the query and sends it to the server.

[0888] 2. The server analyzes the question and extracts keywords such as "sale" and "recommended products."

[0889] 3. Search the database for relevant past sales data and competitive information on the product.

[0890] 4. Using a generative AI model, mimicking the leader's decision-making process, generate the answer "Provide a list of products with high sales performance."

[0891] 5. The server sends this response to the user's terminal and displays it to the user.

[0892] Prompt Sentence Examples

[0893] "Please give me some advice on inventory management."

[0894] "What items would you recommend in this weekend's sale?"

[0895] This system will enable store managers and supervisors to receive prompt and specific advice on a wide range of tasks.

[0896] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0897] Step 1:

[0898] The user inputs a question or task. Specifically, the question is entered in text format through a dedicated smartphone application, and is sent to the server by pressing the send button. An example of input in this case would be "Which products do you recommend for this weekend's sale?" The output is text data from the user.

[0899] Step 2:

[0900] The terminal sends the question entered by the user to the server, where the text data entered by the user is converted into packets and sent to the server via Internet communication. The input is the text data from the user, and the output is the transmitted packets.

[0901] Step 3:

[0902] The server analyzes the received question. Specifically, it uses natural language processing technology to analyze the question and performs topic modeling and keyword extraction. Here, keywords such as "sale" and "recommended products" are extracted, for example. The input is the user's text data, and the output is the extracted keywords and intent.

[0903] Step 4:

[0904] The server searches the database based on the analysis results. Specifically, it searches the database for relevant past data (e.g., past statements, business strategies, operational know-how, etc.) based on the extracted keywords and intent. The input is the extracted keywords and intent, and the output is a list of related information.

[0905] Step 5:

[0906] The server runs an algorithm that mimics the leader's decision-making process. Specifically, it uses relevant information to run the decision-making algorithm and generate an appropriate answer. The input is a list of relevant information, and the output is the generated answer.

[0907] Step 6:

[0908] The server generates optimal advice using a generative AI model (e.g., a question-answering pipeline in transformers) to generate specific advice. The input is the result of the decision-making algorithm, and the output is the final generated advice.

[0909] Step 7:

[0910] The server sends the generated answer to the user terminal. Specifically, it converts the generated advice in text format into packets and sends them to the user terminal via Internet communication. The input is the generated advice, and the output is the transmitted packets.

[0911] Step 8:

[0912] The terminal receives advice from the server and displays it to the user. Specifically, it converts the received packets into text data and displays it through a user interface. The input is the received packets, and the output is the display on the user interface.

[0913] 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.

[0914] This invention combines a system that mimics the decision-making process of corporate leaders with an emotion engine that recognizes user emotions. The program processing of this system is explained in natural language below. The program is executed through interaction between the server, terminals, and users.

[0915] Program Overview

[0916] This system analyzes questions and issues entered by users, generates optimal answers based on relevant information and emotional data, and provides them to the users. The server handles the main processing, while the terminal provides the interface with the user.

[0917] Processing flow (overview)

[0918] 1. Accepting user questions

[0919] Users input questions and tasks in text format through the terminal.

[0920] 2. Question analysis and information extraction

[0921] The server receives the question sent from the terminal and analyzes the intent of the question using natural language processing.

[0922] Based on the analysis results, the server searches the database for relevant information.

[0923] 3. Emotion recognition

[0924] The server uses an emotion engine to extract emotion data from the user's input text, for example, to determine whether the user is feeling anxious or excited.

[0925] 4. Imitating the decision-making process

[0926] The server runs an algorithm that mimics the CEO's decision-making process, including the extracted emotional data, to generate the optimal answer.

[0927] 5. Answer Generation and Delivery

[0928] The server formats the generated responses, adjusting the tone and content based on the emotional data, and provides them to the user.

[0929] Specific examples

[0930] Example 1: New market entry question

[0931] The user types into the terminal, "I'm wondering whether to enter a new market. What should I do?" The terminal sends this question to the server.

[0932] The server receives the question and uses natural language processing to extract the keyword "entering new markets." It then searches a database for related past statements and strategies. It then uses an emotion engine to recognize the emotion "worried" from the user's text. The server then takes this emotion data into account and runs an algorithm that mimics a CEO's decision-making process. As a result, it generates specific advice: "Research market demand, evaluate risks and rewards, and consider partnerships." The answer includes emotionally sensitive language: "We understand your concerns. To alleviate them, it's important to conduct thorough market research and risk assessment." The server then sends this answer to the device, which displays it to the user.

[0933] Example 2: Project Delay Question

[0934] The user types into the terminal, "What would you do if the project was delayed?" The terminal sends this question to the server.

[0935] The server receives the question and uses natural language processing to extract the keyword "project delay." It then searches a database for related past statements and strategies. It then uses an emotion engine to recognize the emotion of "impatience" from the user's text. The server then takes this emotion data into account and runs an algorithm that mimics a CEO's decision-making process. As a result, it generates specific advice: "Quickly identify the cause of the delay, reallocate resources, review priorities, and strengthen communication." The response includes a tone that takes emotion into consideration: "We understand your current impatience. To respond calmly, please prioritize identifying the cause of the delay." The server then sends this response to the device, which displays it to the user.

[0936] This system is designed to help employees improve their decision-making skills and contribute to the development of the company. It provides quick answers to users' questions and issues, and by combining the CEO's decision-making process with emotion recognition, it ensures consistency of knowledge across the company and mental health care for employees.

[0937] The processing flow will be explained below.

[0938] Step 1:

[0939] A user types a question or challenge into the device in text format, for example, "I'm wondering whether to expand into a new market. What should I do?"

[0940] Step 2:

[0941] The terminal receives the user's input and sends the data to the server in text format.

[0942] Step 3:

[0943] The server checks the query data received from the terminal and adjusts the format appropriately for internal processing.

[0944] Step 4:

[0945] The server applies natural language processing (NLP) modules to analyze the question text, including topic modeling and keyword extraction.

[0946] Step 5:

[0947] The server uses the analysis results to identify the subject and intent of the question, for example extracting the main theme of "entering new markets."

[0948] Step 6:

[0949] Based on the specified intent, the server searches a database of relevant information, including information on past statements, books, interviews, and business strategies.

[0950] Step 7:

[0951] The server uses an emotion engine to extract emotion data from the user's input text, for example, to recognize whether the user is feeling "anxious."

[0952] Step 8:

[0953] The server runs an algorithm to mimic the leader's decision-making process, integrating the identified intent with the extracted emotional data to generate the optimal answer.

[0954] Step 9:

[0955] The server then formats the generated responses, adjusting the tone and content based on the user's emotions. For example, if a user is feeling anxious, reassuring language will be added.

[0956] Step 10:

[0957] The server then sends the formatted answer data to the terminal in a format that is easy for the user to understand.

[0958] Step 11:

[0959] The device displays the answer received from the server to the user. For example, it might say, "When entering a new market, it is important to thoroughly research the target market's demand and evaluate the risks and rewards. It would also be a good idea to consider collaborating with partner companies. We understand your concerns. To alleviate them, it is important to conduct thorough market research and risk assessment."

[0960] Example 2

[0961] 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."

[0962] In modern companies, quick and accurate decision-making is required, but few systems provide responses that appropriately consider the user's emotions during the decision-making process. In particular, there is a need for a system that can generate answers that reflect the user's emotions while mimicking the decision-making process of a leader.

[0963] 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.

[0964] In this invention, the server includes means for receiving a question or task input by a user, means for analyzing the question or task using natural language processing to identify the intent, means for searching a database for related information based on the analysis results, means for extracting emotional data from the user's input, means for executing an algorithm that mimics a CEO's decision-making process based on the analysis results including the emotional data, means for generating an answer that takes the emotional data into consideration based on the results of the algorithm, and means for providing the generated answer to the user. This makes it possible to provide an appropriate answer that takes the user's emotions into consideration while mimicking a leader's decision-making process.

[0965] "User" refers to a person who uses the system to enter questions or issues and receive answers.

[0966] "Terminal" refers to a device that provides an interface for users to access the system and input questions or tasks. Examples include personal computers and smartphones.

[0967] "Question or Problem" refers to a textual inquiry that a user enters into the system seeking a solution.

[0968] "Natural language processing" refers to the technology for analyzing user-entered text and understanding its intent and sentiment. Specifically, it includes topic modeling and keyword extraction.

[0969] "Database" refers to a collection of information that the system references, including past statements, books, interviews, and business strategies.

[0970] "Emotion engine" refers to technology for extracting emotional data from user input, such as a sentiment analysis API.

[0971] "Emotion data" refers to emotional state information extracted from text entered by a user, including, for example, feelings of anxiety or impatience.

[0972] An "algorithm" is a set of computational steps to solve a specific problem or perform a computation, in this case to mimic the decision-making process of a CEO.

[0973] "Answer" refers to a response from the system to a user's question or problem, containing appropriate information and taking into account the user's feelings.

[0974] "Means for providing" refers to the technical means by which the server displays the answer to the user, specifically including sending the answer to the terminal.

[0975] This invention is a system that mimics the decision-making process of corporate leaders and recognizes user emotions. The main processing is handled by the server, and the user and terminal provide the interface.

[0976] Program processing overview

[0977] This system analyzes questions and issues entered by users, generates optimal answers based on relevant information and emotional data, and provides them to users. The main technologies and the hardware and software used are described below.

[0978] 1. Accepting user questions

[0979] The user enters a question in text format using a device, such as a PC or smartphone.

[0980] Example: User types, "I'm wondering whether to expand into a new market. What should I do?"

[0981] 2. Question analysis and information extraction

[0982] The server receives the question sent from the terminal and analyzes the intent of the question using natural language processing.

[0983] In this case, natural language processing libraries such as SpaCy and NLTK are used.

[0984] The server searches for relevant information from a database (e.g., MySQL, PostgreSQL, etc.) based on the analyzed keywords.

[0985] 3. Emotion recognition

[0986] The server uses an emotion engine to extract emotion data from the user's input text.

[0987] Specifically, it uses the sentiment analysis API of Microsoft Azure's Cognitive Services.

[0988] The server recognizes emotions such as "worried" and adds them to the analysis results.

[0989] 4. Imitating the decision-making process

[0990] The server then runs an algorithm that mimics the CEO's decision-making process, including the extracted emotional data.

[0991] For example, using machine learning models such as TensorFlow or Scikit-learn.

[0992] 5. Answer Generation and Delivery

[0993] The server formats the responses it generates, adjusting the tone and content based on emotional data.

[0994] The server converts the final response into JSON format and sends it to the terminal.

[0995] The terminal parses the received JSON data and displays it to the user.

[0996] Specific examples

[0997] Example 1: New market entry question

[0998] A user types into their terminal, "I'm wondering whether to expand into a new market. What should I do?"

[0999] The terminal sends this question to the server.

[1000] The server receives the question and uses natural language processing to extract the keyword "entering new markets."

[1001] Next, the database is searched for relevant past statements and strategies.

[1002] An emotion engine is used to recognize the emotion of "worried" from the user's text.

[1003] The server then takes this emotional data into account and runs an algorithm that mimics the CEO's decision-making process.

[1004] The result is specific advice on "market demand research, risk and return assessment, and partnership considerations."

[1005] The response includes sensitive language such as, "We understand your concerns. To alleviate them, it is important to conduct thorough market research and risk assessment."

[1006] The server sends this response to the terminal, which displays it to the user.

[1007] This system is designed to improve users' decision-making ability and contribute to the development of the company. It provides quick answers to users' questions and issues, and by combining the CEO's decision-making process with emotion recognition, it can ensure consistency of knowledge across the company and mental health care for employees.

[1008] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1009] Step 1: Accepting user questions

[1010] Specific actions

[1011] The user enters a question in text format using a terminal.

[1012] For example, a user might type, "I'm wondering whether to expand into a new market. What should I do?"

[1013] The terminal interface has an input field and a "Submit" button, which the user presses to send the question to the server.

[1014] input

[1015] Text data entered by the user into the terminal.

[1016] output

[1017] The text data sent to the server.

[1018] Step 2: Question analysis and information extraction

[1019] Specific actions

[1020] The server receives the question sent from the terminal and analyzes the text data.

[1021] The intent of the question is analyzed using natural language processing technology, for example using libraries such as SpaCy and NLTK.

[1022] The server extracts keywords such as "entering new markets" from the analysis results.

[1023] Based on the extracted keywords, the server retrieves relevant information from a database (e.g., MySQL or PostgreSQL) and temporarily stores it.

[1024] input

[1025] The text data received by the server.

[1026] output

[1027] Data and related information extracted as keywords.

[1028] Step 3: Emotion Recognition

[1029] Specific actions

[1030] The server uses an emotion engine to extract emotion data from the user's input text.

[1031] Specifically, it calls the sentiment analysis API of Microsoft Azure's Cognitive Services and sends text data.

[1032] Based on the received emotion data, emotions such as "worried" or "anxious" are recognized from the user's text.

[1033] The server adds this emotion data to the previously extracted keywords and related information.

[1034] input

[1035] Text data and already extracted keywords.

[1036] output

[1037] Analysis results with added emotion data.

[1038] Step 4: Imitate the decision-making process

[1039] Specific actions

[1040] The server runs an algorithm that mimics the CEO's decision-making process based on the analysis results, including the extracted emotional data.

[1041] For example, use machine learning models such as TensorFlow or Scikit-learn and load pre-trained algorithms.

[1042] The server inputs the analysis results and emotional data into an algorithm to generate the optimal answer.

[1043] The answers generated include specific advice such as "research market demand, assess risks, and consider partnerships."

[1044] input

[1045] Analysis results with added emotion data.

[1046] output

[1047] Algorithmically generated answers.

[1048] Step 5: Generate and provide answers

[1049] Specific actions

[1050] The server formats the generated responses, adjusting the tone and content based on the emotional data.

[1051] Specifically, the generated answers will be enhanced with emotionally sensitive language such as, "We understand your concerns. To alleviate them, it is important to conduct thorough market research and risk assessments."

[1052] The final answer is converted to JSON format and sent to the terminal.

[1053] The terminal parses the received JSON data and displays it to the user.

[1054] input

[1055] Algorithmically generated answers.

[1056] output

[1057] The final answer provided to the user.

[1058] (Application example 2)

[1059] 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."

[1060] Conventionally, security services have lacked systems that can quickly and accurately respond when users feel anxious or worried. As a result, it is difficult for users to find an appropriate solution, which can lead to a decline in the quality of security services. Furthermore, the inability to respond appropriately to users' emotions can further increase anxiety and impatience. The present invention aims to solve these problems.

[1061] 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 or task entered by a user, means for analyzing the question or task using natural language processing and identifying the intent, means for recognizing emotions from the entered text, means for searching a database for related information based on the analysis results and emotions, means for executing an algorithm that mimics the decision-making process, means for generating an answer that takes emotions into consideration based on the results of the algorithm, and means for providing the generated answer to the user. This enables a quick and accurate response when a user of a security service feels anxious or concerned. Furthermore, generating an answer that takes the user's emotions into consideration can improve the user's sense of security.

[1062] A "question" is text entered by a user regarding a particular problem or question.

[1063] A "problem" refers to a particular problem situation or challenge that a user wishes to solve.

[1064] "Natural language processing" is a general term for technology that allows computers to understand, analyze, and generate human language.

[1065] "Emotion" refers to a psychological state extracted from the text entered by the user, such as anxiety or impatience.

[1066] A "database" is a collection of related information organized for efficient searching and retrieval.

[1067] An "algorithm that mimics the decision-making process" is a computational procedure that replicates the decision-making process of corporate leaders.

[1068] An "answer" is a response generated by the server in response to a user's question or task.

[1069] "Relevant information" refers to data or documents that are directly related to the question or issue.

[1070] "Emotion recognition" refers to the technology of identifying a user's psychological state from their input text.

[1071] "Means for providing to the user" refers to the interface or method for showing the generated answer to the user.

[1072] This system analyzes questions and issues entered by users, generates and provides optimal answers based on related emotional data, and is implemented through interactions between the server, terminals, and users.

[1073] The server is the main processing unit and includes the following elements:

[1074] A way to receive questions and assignments

[1075] A means of analyzing questions and issues using natural language processing

[1076] A method for recognizing emotions from input text

[1077] A means of searching for relevant information from a database based on analysis results and sentiment

[1078] A means of implementing algorithms that mimic decision-making processes

[1079] A means of generating answers based on the results of an algorithm

[1080] A means of providing the generated answer to the user

[1081] Hardware and Software Configuration

[1082] Hardware:

[1083] Smartphone (user device)

[1084] Server (main processing and database management)

[1085] software:

[1086] Amazon Web Services (AWS) Lambda (serverless computing)

[1087] Google Cloud Natural Language API (Natural Language Processing)

[1088] IBM Watson Emotion Analysis

[1089] Python (programming language)

[1090] Data processing and calculation

[1091] 1. Receiving questions and assignments:

[1092] A user uses a smartphone to input a question or problem, for example, "My home security system has detected an abnormality. I'm worried. What should I do?"

[1093] 2. Analysis of questions and issues:

[1094] The server uses the Google Cloud Natural Language API to analyze the user's question or issue and extract key keywords (e.g., "security system," "anomaly").

[1095] 3. Emotion recognition:

[1096] The server uses IBM Watson Emotion Analysis to identify emotions from the user's input text (e.g., "anxiety").

[1097] 4. Information Search:

[1098] The server searches the database for relevant information based on the analyzed keywords and emotional data.

[1099] 5. Imitating the decision-making process:

[1100] The server runs an algorithm that mimics the decision-making process of a company leader, combining relevant information and emotional data to generate the best answer.

[1101] 6. Generate and provide answers:

[1102] The server adjusts the generated answer taking into account the user's emotions and displays it on the smartphone (e.g., "If an abnormality is detected, first remain calm and call your emergency contact or the nearest police station.").

[1103] Prompt Sentence Examples

[1104] User Question: "My home security system is detecting something abnormal. I'm worried. What should I do?"

[1105] Analyzed keywords: "security system", "abnormality"

[1106] Recognized emotion: "Anxiety"

[1107] Generated advice: "If an abnormality is detected, first remain calm and call your emergency contact or the nearest police station. Also, check the system logs and gather as much information as possible."

[1108] This system can provide users with optimal means to quickly and accurately resolve security-related issues and concerns. In particular, by taking emotional data into consideration, it can provide solutions that are suited to the psychological state of each individual user.

[1109] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1110] Step 1:

[1111] A user inputs a question or problem into their smartphone. For example, they input text like, "My home security system has detected an abnormality. I'm worried. What should I do?" This text is then sent from the device to the server. The input data is the user text, and the output data is the raw text sent to the server.

[1112] Step 2:

[1113] The server sends the received text to the Google Cloud Natural Language API and analyzes it using natural language processing. Specifically, the server extracts key keywords from the text. For example, the keywords "security system" and "abnormal" are extracted. The input data is the raw text, and the output data is the analyzed keywords.

[1114] Step 3:

[1115] The server uses IBM Watson Emotion Analysis to recognize emotions from the user's text based on the extracted keywords. Specifically, the raw text is sent to the emotion recognition engine, and the emotion "anxiety" is extracted as a result. The input data is the raw text and keywords, and the output data is the recognized emotion.

[1116] Step 4:

[1117] The server searches a database for relevant information based on the analyzed keywords and emotions. For example, past documents and advice on how to respond to security system anomalies are searched for. The input data is keyword and emotion data, and the output data is a set of related information.

[1118] Step 5:

[1119] The server runs an algorithm that mimics the decision-making process based on relevant information and emotional data. Specifically, it mimics past decisions made by company leaders and generates appropriate advice. The input data is relevant information and emotional data, and the output data is the generated advice.

[1120] Step 6:

[1121] The server adjusts the content and tone of the generated advice to provide it to the user based on the emotional data. For example, it uses language that alleviates anxiety. The input data are the generated advice and emotional data, and the output data is the optimized advice.

[1122] Step 7:

[1123] The device displays the optimized advice to the user, allowing the user to act based on the advice. Specifically, the advice is displayed on the smartphone screen. The input data is the optimized advice, and the output data is displayed to the user.

[1124] 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.

[1125] 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.

[1126] 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.

[1127] [Fourth embodiment]

[1128] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1129] 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.

[1130] 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).

[1131] 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.

[1132] 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.

[1133] 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).

[1134] 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.

[1135] 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.

[1136] 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.

[1137] 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.

[1138] 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.

[1139] 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.

[1140] 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."

[1141] This invention provides a system that mimics the decision-making process of corporate leaders. Specifically, it analyzes questions and issues entered by users, generates optimal answers based on related information, and provides them to the users. We generate a program for this system and explain its processing in natural language.

[1142] Program Overview

[1143] The system analyzes questions and issues entered by users and generates answers based on the leader's past statements and business strategies. The server handles the main processing, while the terminal provides the interface with the user.

[1144] Processing flow (overview)

[1145] 1. Accepting user questions

[1146] Users input questions and tasks in text format through the terminal.

[1147] 2. Question analysis and information extraction

[1148] The server receives the question sent from the terminal and analyzes the intent of the question using natural language processing.

[1149] Based on the analysis results, the server searches the database for relevant information.

[1150] 3. Imitating the decision-making process

[1151] The server runs an algorithm that mimics the CEO's decision-making process and generates the optimal answer.

[1152] 4. Answer generation and provision

[1153] The server sends the generated answer to the terminal, which displays the answer to the user.

[1154] Specific examples

[1155] Example 1: New market entry question

[1156] The user types into the terminal, "I'm wondering whether to enter a new market. What should I do?" The terminal sends this question to the server.

[1157] The server receives the question and uses natural language processing to extract the keyword "enter new markets." It then searches a database for relevant past statements and strategies and runs an algorithm that mimics a CEO's decision-making process. The resulting advice is specific: "Research market demand, evaluate risks and rewards, and consider partnerships." The server then sends the answer to the device, which displays it to the user.

[1158] Example 2: Project Delay Question

[1159] The user types into the terminal, "What would you do if the project was delayed?" The terminal sends this question to the server.

[1160] The server receives the question and uses natural language processing to extract the keyword "project delay." It then searches a database for relevant past statements and strategies and runs an algorithm that mimics the CEO's decision-making process. The result is specific advice: "Quickly identify the cause of the delay, reallocate resources, review priorities, and strengthen communication." The server sends this answer to the device, which displays it to the user.

[1161] The system is designed to help employees improve their decision-making skills and contribute to the company's growth. It provides quick answers to users' questions and issues, and shares the CEO's decision-making process, ensuring consistency of knowledge across the company.

[1162] The processing flow will be explained below.

[1163] Step 1:

[1164] The user enters a question or problem in text format into the terminal. For example, they enter a question like, "I'm wondering whether to enter a new market. What should I do?"

[1165] Step 2:

[1166] The terminal checks the user's question data and sends it to the server in text format.

[1167] Step 3:

[1168] The server receives the question data sent from the terminal and converts the received text data into a format for internal processing.

[1169] Step 4:

[1170] The server uses a natural language processing (NLP) module to analyze the question text, including topic modeling and keyword extraction.

[1171] Step 5:

[1172] The server identifies the user's intent based on the analysis of the question text. For example, if the keyword "entering a new market" is extracted, the server identifies the intent as "decision-making regarding market expansion."

[1173] Step 6:

[1174] Based on the specified intent, the server searches a database for relevant information, including information on the CEO's past statements, books, interviews, and business strategies.

[1175] Step 7:

[1176] The server retrieves the relevant information and runs an algorithm that mimics the CEO's decision-making process, taking into account past successes and failures to arrive at the optimal answer.

[1177] Step 8:

[1178] The server formats the generated answer and converts it into an output format for presentation to the user.

[1179] Step 9:

[1180] The server sends the formatted response to the terminal. The response data is formatted to be easy for the user to understand.

[1181] Step 10:

[1182] The device will then display the response data received from the server to the user, and provide specific advice such as, "When entering a new market, it is important to thoroughly research the target market's demand and evaluate the risks and rewards. It would also be a good idea to consider collaborating with partner companies."

[1183] Example 1

[1184] 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."

[1185] In modern business, employees need to have strong leadership skills and a wealth of knowledge to make appropriate and prompt decisions. However, not all employees have the decision-making ability of a leader, which can result in poor judgment and a decline in overall corporate performance. If there were a system that could mimic a leader's decision-making process and provide appropriate advice, it would be possible to improve employees' decision-making skills and increase the efficiency of the entire company. Against this background, the present invention aims to provide a system that mimics a leader's decision-making process and quickly provides optimal answers to users.

[1186] 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.

[1187] In this invention, the server includes: means for receiving a question or task entered by a user; means for analyzing the question or task using natural language processing to identify the intent; means for searching a database for related information based on the analysis results; means for executing an algorithm that mimics the decision-making process; means for generating an answer based on the result of the algorithm; means for providing the generated answer to the user; means including a terminal and a web browser or dedicated application for the user to view the answer; means for using a BERT model or GPT model in natural language processing; and means for using a database to search past statements and business strategies based on analyzed keywords. This enables users to quickly obtain specific advice based on a sophisticated decision-making process like that of a leader.

[1188] "User" refers to a user who can input questions or issues into the system and receive answers.

[1189] "Terminal" refers to a hardware device, such as a PC, smartphone, or tablet, through which a user enters questions or tasks and receives answers.

[1190] "Server" refers to a central system that receives questions or challenges sent by users, performs natural language processing, searches a database for relevant information, generates answers, and provides them to users.

[1191] "Natural language processing" refers to the technology that enables computers to understand and process human language, including analyzing text and identifying intent.

[1192] The "BERT model" is a type of natural language processing algorithm based on transformer technology, and is particularly good at analyzing text taking context into account.

[1193] The "GPT model" is a type of natural language processing algorithm that uses generative techniques, and is a technology that generates language based on large amounts of text data.

[1194] "Database" means a collection of information used by a system to store, search, and retrieve information, including but not limited to SQL Server and NoSQL databases.

[1195] "Questions and issues" refer to specific problems or doubts that users input into the system and seek to resolve.

[1196] "Identifying intent" refers to the process of using natural language processing technology to clarify the user's requirements and goals behind the entered question or task.

[1197] "Algorithms that mimic decision-making processes" refers to computational methods that derive optimal answers based on the past decision-making criteria and methods of leaders and CEOs.

[1198] "Generating an answer" refers to the process of creating appropriate advice or solutions to a user's questions or challenges based on analyzed information and decision-making processes.

[1199] A "web browser" refers to software that enables users to interact with servers over the Internet, and includes browsers such as Chrome and Firefox.

[1200] "Purpose-built application" refers to software developed for a specific purpose, to facilitate user access to a system.

[1201] MODE FOR CARRYING OUT THE INVENTION

[1202] This invention provides a system that mimics the decision-making process of corporate leaders. This system analyzes questions and issues entered by users, generates optimal answers based on related information, and provides them to the users. In this system, the server handles the main processing, and the terminal provides the interface with the user.

[1203] First, the user uses their own device to input a question or problem. Specifically, they enter the question into a text input field in a web browser or a dedicated application. This question is specific and based on the user's concerns or problems. For example, "I'm wondering whether to enter a new market. What should I do?" Once the input is complete, the user clicks the send button, and the content is sent to the server.

[1204] Next, the server receives the submitted question data. The server uses natural language processing techniques such as Google's BERT model or OpenAI's GPT model to analyze the intent of the question. This analysis begins with normalizing and tokenizing the sentence (dividing it into words), and then extracting keywords and related information. For example, keywords such as "entering new markets" and "project delays" are extracted.

[1205] The server then runs an algorithm that mimics the decision-making process of a company leader based on the extracted keywords and contextual information. The algorithm includes logic to derive the optimal answer by referencing a database containing past statements and business strategies. Specifically, the database contains information such as books, interviews, and business strategy information, and is managed using SQL Server or a NoSQL database.

[1206] After the algorithm is executed, the server generates a specific answer to the question, such as advice such as "research market demand, evaluate risk and return, and consider partnerships." Finally, the server sends the answer to the user's device, which displays it to the user, either by refreshing the web page or by displaying a dedicated application pop-up.

[1207] ---

[1208] Examples:

[1209] The user types into the device, "I'm wondering whether to enter a new market. What should I do?" The device sends this question to the server. The server receives the question and uses natural language processing to extract the keyword "enter a new market." It then searches a database for related past statements and strategies and runs an algorithm that mimics the decision-making process of a corporate leader. As a result, specific advice is generated: "Research market demand, evaluate risks and returns, and consider partnerships." The server sends this answer to the device, which displays it to the user.

[1210] ---

[1211] Examples of prompts:

[1212] 1. "What is the best way to go to market?"

[1213] 2. "What is the best way to address a delayed project?"

[1214] As described above, this system is able to provide prompt and appropriate advice in response to user questions and issues, allowing users to obtain specific advice based on a high-level decision-making process similar to that of a leader, thereby improving the efficiency of the entire company.

[1215] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1216] Step 1: Accepting user questions

[1217] A user uses a terminal to input a question or problem. Specifically, the user enters the question in a text input field in a web browser or a dedicated application and clicks the send button. This sends the question data in text format to the server. The input might be, for example, "I'm wondering whether to enter a new market. What should I do?" and the output is the text data to be sent.

[1218] Step 2: Question analysis and information extraction

[1219] The server receives the question data sent by the user. The server analyzes the text using a natural language processing model (BERT model or GPT model). Specific analysis operations include normalizing the text (removing unnecessary spaces and symbols), tokenizing (dividing it into words), and stemming (reducing words to their original form). The text data received in step 1 is given as input, and the extracted keywords and contextual information (e.g., entering a new market) are obtained as output.

[1220] Step 3: Mimic the decision-making process

[1221] The server runs an algorithm that mimics the decision-making process based on the keywords and contextual information obtained in step 2. This algorithm references a database that stores past statements and business strategies to retrieve relevant information. Specifically, it searches the database for the required information using SQL or NoSQL queries. The input is the extracted keywords (e.g., "enter a new market"), and the output is relevant information for decision-making (e.g., past market analysis data, risk assessment, etc.).

[1222] Step 4: Answer Generation

[1223] The server generates the optimal answer to the user's question based on the related information obtained in step 3. For generation, a natural language generation model (such as a GPT model) is again used. Specifically, the related information is provided as input data, and the generation model uses it to generate a natural, contextual answer. The input is the related information and the prompt sentence of the generation AI model, and the output is the generated specific answer text.

[1224] Step 5: Provide your answers

[1225] The server sends the answer generated in step 4 to the user's device. The device analyzes the received answer and displays it to the user. Specifically, the answer is displayed by updating the web page or by displaying a popup in a dedicated application. The input is the generated answer text, and the output is the answer content displayed on the user's screen.

[1226] The above is a specific description of each processing step of this system, including input, data processing, output, and specific operations at each step.

[1227] (Application example 1)

[1228] 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."

[1229] Providing specific, practical advice to help store managers and administrators make quick and accurate decisions in the daily tasks they face is not easy. Optimal advice based on experience and past data is particularly required for a wide range of tasks, such as inventory management, staff shift management, and new product introductions, but there is no established method for providing this advice.

[1230] 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.

[1231] In this invention, the server includes means for receiving a question or task input by a user, means for analyzing the question or task using natural language processing to identify the intent, means for searching a database for related information based on the analysis result, means for executing an algorithm that mimics the decision-making process of the leader, means for generating an answer based on the result of the algorithm, means for providing the generated answer to the user, means for using information context to provide advice on various tasks, and means for generating optimal advice using a generative AI model. This makes it possible to provide quick and specific advice for the daily tasks faced by managers and store managers of brick-and-mortar stores.

[1232] The "means for receiving questions and assignments entered by the user" refers to an interface and interactive communication function for receiving questions and assignments in text format entered by the user through a terminal.

[1233] "Means of analyzing and identifying intent using natural language processing" refers to an analytical technology that recognizes questions or tasks entered in text form by users and understands their meaning and purpose.

[1234] "Means for searching for relevant information from a database" refers to a technology that identifies the necessary data based on the intent of the analyzed question or task, and retrieves the appropriate information from the database that stores that data.

[1235] "Means for implementing algorithms that mimic the decision-making process of leaders" refers to technology that uses similar algorithms to make optimal decisions based on the decision-making processes used by corporate leaders in the past.

[1236] "Answer generation means" refers to techniques for creating specific answers to user questions or challenges based on acquired information and simulated decision-making processes.

[1237] The "means for providing the generated answer to the user" refers to an interface and communication technology for transmitting the generated answer to the user terminal and displaying the result to the user.

[1238] "Means using information context to provide advice on various operations" refers to means for providing advice using specific and detailed information on various operations related to managing a physical store (e.g., inventory management, staff management, new product introduction, etc.).

[1239] "Means for generating optimal advice using generative AI models" refers to technology that utilizes artificial intelligence technology to generate the most appropriate advice or answer to a user's question or issue.

[1240] This invention provides a support tool for store managers and administrators to instantly make optimal decisions in their daily work. Specifically, it is implemented as a smartphone application that provides quick and accurate answers based on user input.

[1241] The system consists of a user terminal (a smartphone in this case) and a server. The system includes the following main functional blocks:

[1242] User device functions

[1243] An interface is implemented on the user terminal for users to input questions and tasks. The user inputs a question in text format and sends it to the server.

[1244] Server Features

[1245] The server is responsible for the main data processing and response generation. It performs the following tasks:

[1246] 1. Question analysis:

[1247] The server analyzes the user-submitted question using natural language processing techniques (e.g., the transformers library), which perform topic modeling and keyword extraction to identify the intent of the question.

[1248] 2. Information Search:

[1249] Based on the intent of the question, relevant information (past statements, business strategies, operational know-how, etc.) is searched from a database.

[1250] 3. Answer generation:

[1251] It uses algorithms that mimic the decision-making process of leaders and generative AI models (e.g., transformers' question-answering pipeline) to generate optimal answers, leveraging diverse business context in the process.

[1252] 4. Provide answers:

[1253] The generated answer is sent to the user terminal and finally displayed to the user.

[1254] Specific use cases

[1255] For example, if a store manager were to enter a question through the app such as, "Which products would you recommend for this weekend's sale?", the following process would take place:

[1256] 1. The user terminal receives the query and sends it to the server.

[1257] 2. The server analyzes the question and extracts keywords such as "sale" and "recommended products."

[1258] 3. Search the database for relevant past sales data and competitive information on the product.

[1259] 4. Using a generative AI model, mimicking the leader's decision-making process, generate the answer "Provide a list of products with high sales performance."

[1260] 5. The server sends this response to the user's terminal and displays it to the user.

[1261] Prompt Sentence Examples

[1262] "Please give me some advice on inventory management."

[1263] "What items would you recommend in this weekend's sale?"

[1264] This system will enable store managers and supervisors to receive prompt and specific advice on a wide range of tasks.

[1265] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1266] Step 1:

[1267] The user inputs a question or task. Specifically, the question is entered in text format through a dedicated smartphone application, and is sent to the server by pressing the send button. An example of input in this case would be "Which products do you recommend for this weekend's sale?" The output is text data from the user.

[1268] Step 2:

[1269] The terminal sends the question entered by the user to the server, where the text data entered by the user is converted into packets and sent to the server via Internet communication. The input is the text data from the user, and the output is the transmitted packets.

[1270] Step 3:

[1271] The server analyzes the received question. Specifically, it uses natural language processing technology to analyze the question and performs topic modeling and keyword extraction. Here, keywords such as "sale" and "recommended products" are extracted, for example. The input is the user's text data, and the output is the extracted keywords and intent.

[1272] Step 4:

[1273] The server searches the database based on the analysis results. Specifically, it searches the database for relevant past data (e.g., past statements, business strategies, operational know-how, etc.) based on the extracted keywords and intent. The input is the extracted keywords and intent, and the output is a list of related information.

[1274] Step 5:

[1275] The server runs an algorithm that mimics the leader's decision-making process. Specifically, it uses relevant information to run the decision-making algorithm and generate an appropriate answer. The input is a list of relevant information, and the output is the generated answer.

[1276] Step 6:

[1277] The server generates optimal advice using a generative AI model (e.g., a question-answering pipeline in transformers) to generate specific advice. The input is the result of the decision-making algorithm, and the output is the final generated advice.

[1278] Step 7:

[1279] The server sends the generated answer to the user terminal. Specifically, it converts the generated advice in text format into packets and sends them to the user terminal via Internet communication. The input is the generated advice, and the output is the transmitted packets.

[1280] Step 8:

[1281] The terminal receives advice from the server and displays it to the user. Specifically, it converts the received packets into text data and displays it through a user interface. The input is the received packets, and the output is the display on the user interface.

[1282] 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.

[1283] This invention combines a system that mimics the decision-making process of corporate leaders with an emotion engine that recognizes user emotions. The program processing of this system is explained in natural language below. The program is executed through interaction between the server, terminals, and users.

[1284] Program Overview

[1285] This system analyzes questions and issues entered by users, generates optimal answers based on relevant information and emotional data, and provides them to the users. The server handles the main processing, while the terminal provides the interface with the user.

[1286] Processing flow (overview)

[1287] 1. Accepting user questions

[1288] Users input questions and tasks in text format through the terminal.

[1289] 2. Question analysis and information extraction

[1290] The server receives the question sent from the terminal and analyzes the intent of the question using natural language processing.

[1291] Based on the analysis results, the server searches the database for relevant information.

[1292] 3. Emotion recognition

[1293] The server uses an emotion engine to extract emotion data from the user's input text, for example, to determine whether the user is feeling anxious or excited.

[1294] 4. Imitating the decision-making process

[1295] The server runs an algorithm that mimics the CEO's decision-making process, including the extracted emotional data, to generate the optimal answer.

[1296] 5. Answer Generation and Delivery

[1297] The server formats the generated responses, adjusting the tone and content based on the emotional data, and provides them to the user.

[1298] Specific examples

[1299] Example 1: New market entry question

[1300] The user types into the terminal, "I'm wondering whether to enter a new market. What should I do?" The terminal sends this question to the server.

[1301] The server receives the question and uses natural language processing to extract the keyword "entering new markets." It then searches a database for related past statements and strategies. It then uses an emotion engine to recognize the emotion "worried" from the user's text. The server then takes this emotion data into account and runs an algorithm that mimics a CEO's decision-making process. As a result, it generates specific advice: "Research market demand, evaluate risks and rewards, and consider partnerships." The answer includes emotionally sensitive language: "We understand your concerns. To alleviate them, it's important to conduct thorough market research and risk assessment." The server then sends this answer to the device, which displays it to the user.

[1302] Example 2: Project Delay Question

[1303] The user types into the terminal, "What would you do if the project was delayed?" The terminal sends this question to the server.

[1304] The server receives the question and uses natural language processing to extract the keyword "project delay." It then searches a database for related past statements and strategies. It then uses an emotion engine to recognize the emotion of "impatience" from the user's text. The server then takes this emotion data into account and runs an algorithm that mimics a CEO's decision-making process. As a result, it generates specific advice: "Quickly identify the cause of the delay, reallocate resources, review priorities, and strengthen communication." The response includes a tone that takes emotion into consideration: "We understand your current impatience. To respond calmly, please prioritize identifying the cause of the delay." The server then sends this response to the device, which displays it to the user.

[1305] This system is designed to help employees improve their decision-making skills and contribute to the development of the company. It provides quick answers to users' questions and issues, and by combining the CEO's decision-making process with emotion recognition, it ensures consistency of knowledge across the company and mental health care for employees.

[1306] The processing flow will be explained below.

[1307] Step 1:

[1308] A user types a question or challenge into the device in text format, for example, "I'm wondering whether to expand into a new market. What should I do?"

[1309] Step 2:

[1310] The terminal receives the user's input and sends the data to the server in text format.

[1311] Step 3:

[1312] The server checks the query data received from the terminal and adjusts the format appropriately for internal processing.

[1313] Step 4:

[1314] The server applies natural language processing (NLP) modules to analyze the question text, including topic modeling and keyword extraction.

[1315] Step 5:

[1316] The server uses the analysis results to identify the subject and intent of the question, for example extracting the main theme of "entering new markets."

[1317] Step 6:

[1318] Based on the specified intent, the server searches a database of relevant information, including information on past statements, books, interviews, and business strategies.

[1319] Step 7:

[1320] The server uses an emotion engine to extract emotion data from the user's input text, for example, to recognize whether the user is feeling "anxious."

[1321] Step 8:

[1322] The server runs an algorithm to mimic the leader's decision-making process, integrating the identified intent with the extracted emotional data to generate the optimal answer.

[1323] Step 9:

[1324] The server then formats the generated responses, adjusting the tone and content based on the user's emotions. For example, if a user is feeling anxious, reassuring language will be added.

[1325] Step 10:

[1326] The server then sends the formatted answer data to the terminal in a format that is easy for the user to understand.

[1327] Step 11:

[1328] The device displays the answer received from the server to the user. For example, it might say, "When entering a new market, it is important to thoroughly research the target market's demand and evaluate the risks and rewards. It would also be a good idea to consider collaborating with partner companies. We understand your concerns. To alleviate them, it is important to conduct thorough market research and risk assessment."

[1329] Example 2

[1330] 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."

[1331] In modern companies, quick and accurate decision-making is required, but few systems provide responses that appropriately consider the user's emotions during the decision-making process. In particular, there is a need for a system that can generate answers that reflect the user's emotions while mimicking the decision-making process of a leader.

[1332] 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.

[1333] In this invention, the server includes means for receiving a question or task input by a user, means for analyzing the question or task using natural language processing to identify the intent, means for searching a database for related information based on the analysis results, means for extracting emotional data from the user's input, means for executing an algorithm that mimics a CEO's decision-making process based on the analysis results including the emotional data, means for generating an answer that takes the emotional data into consideration based on the results of the algorithm, and means for providing the generated answer to the user. This makes it possible to provide an appropriate answer that takes the user's emotions into consideration while mimicking a leader's decision-making process.

[1334] "User" refers to a person who uses the system to enter questions or issues and receive answers.

[1335] "Terminal" refers to a device that provides an interface for users to access the system and input questions or tasks. Examples include personal computers and smartphones.

[1336] "Question or Problem" refers to a textual inquiry that a user enters into the system seeking a solution.

[1337] "Natural language processing" refers to the technology for analyzing user-entered text and understanding its intent and sentiment. Specifically, it includes topic modeling and keyword extraction.

[1338] "Database" refers to a collection of information that the system references, including past statements, books, interviews, and business strategies.

[1339] "Emotion engine" refers to technology for extracting emotional data from user input, such as a sentiment analysis API.

[1340] "Emotion data" refers to emotional state information extracted from text entered by a user, including, for example, feelings of anxiety or impatience.

[1341] An "algorithm" is a set of computational steps to solve a specific problem or perform a computation, in this case to mimic the decision-making process of a CEO.

[1342] "Answer" refers to a response from the system to a user's question or problem, containing appropriate information and taking into account the user's feelings.

[1343] "Means for providing" refers to the technical means by which the server displays the answer to the user, specifically including sending the answer to the terminal.

[1344] This invention is a system that mimics the decision-making process of corporate leaders and recognizes user emotions. The main processing is handled by the server, and the user and terminal provide the interface.

[1345] Program processing overview

[1346] This system analyzes questions and issues entered by users, generates optimal answers based on relevant information and emotional data, and provides them to users. The main technologies and the hardware and software used are described below.

[1347] 1. Accepting user questions

[1348] The user enters a question in text format using a device, such as a PC or smartphone.

[1349] Example: User types, "I'm wondering whether to expand into a new market. What should I do?"

[1350] 2. Question analysis and information extraction

[1351] The server receives the question sent from the terminal and analyzes the intent of the question using natural language processing.

[1352] In this case, natural language processing libraries such as SpaCy and NLTK are used.

[1353] The server searches for relevant information from a database (e.g., MySQL, PostgreSQL, etc.) based on the analyzed keywords.

[1354] 3. Emotion recognition

[1355] The server uses an emotion engine to extract emotion data from the user's input text.

[1356] Specifically, it uses the sentiment analysis API of Microsoft Azure's Cognitive Services.

[1357] The server recognizes emotions such as "worried" and adds them to the analysis results.

[1358] 4. Imitating the decision-making process

[1359] The server then runs an algorithm that mimics the CEO's decision-making process, including the extracted emotional data.

[1360] For example, using machine learning models such as TensorFlow or Scikit-learn.

[1361] 5. Answer Generation and Delivery

[1362] The server formats the responses it generates, adjusting the tone and content based on emotional data.

[1363] The server converts the final response into JSON format and sends it to the terminal.

[1364] The terminal parses the received JSON data and displays it to the user.

[1365] Specific examples

[1366] Example 1: New market entry question

[1367] A user types into their terminal, "I'm wondering whether to expand into a new market. What should I do?"

[1368] The terminal sends this question to the server.

[1369] The server receives the question and uses natural language processing to extract the keyword "entering new markets."

[1370] Next, the database is searched for relevant past statements and strategies.

[1371] An emotion engine is used to recognize the emotion of "worried" from the user's text.

[1372] The server then takes this emotional data into account and runs an algorithm that mimics the CEO's decision-making process.

[1373] The result is specific advice on "market demand research, risk and return assessment, and partnership considerations."

[1374] The response includes sensitive language such as, "We understand your concerns. To alleviate them, it is important to conduct thorough market research and risk assessment."

[1375] The server sends this response to the terminal, which displays it to the user.

[1376] This system is designed to improve users' decision-making ability and contribute to the development of the company. It provides quick answers to users' questions and issues, and by combining the CEO's decision-making process with emotion recognition, it can ensure consistency of knowledge across the company and mental health care for employees.

[1377] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1378] Step 1: Accepting user questions

[1379] Specific actions

[1380] The user enters a question in text format using a terminal.

[1381] For example, a user might type, "I'm wondering whether to expand into a new market. What should I do?"

[1382] The terminal interface has an input field and a "Submit" button, which the user presses to send the question to the server.

[1383] input

[1384] Text data entered by the user into the terminal.

[1385] output

[1386] The text data sent to the server.

[1387] Step 2: Question analysis and information extraction

[1388] Specific actions

[1389] The server receives the question sent from the terminal and analyzes the text data.

[1390] The intent of the question is analyzed using natural language processing technology, for example using libraries such as SpaCy and NLTK.

[1391] The server extracts keywords such as "entering new markets" from the analysis results.

[1392] Based on the extracted keywords, the server retrieves relevant information from a database (e.g., MySQL or PostgreSQL) and temporarily stores it.

[1393] input

[1394] The text data received by the server.

[1395] output

[1396] Data and related information extracted as keywords.

[1397] Step 3: Emotion Recognition

[1398] Specific actions

[1399] The server uses an emotion engine to extract emotion data from the user's input text.

[1400] Specifically, it calls the sentiment analysis API of Microsoft Azure's Cognitive Services and sends text data.

[1401] Based on the received emotion data, emotions such as "worried" or "anxious" are recognized from the user's text.

[1402] The server adds this emotion data to the previously extracted keywords and related information.

[1403] input

[1404] Text data and already extracted keywords.

[1405] output

[1406] Analysis results with added emotion data.

[1407] Step 4: Imitate the decision-making process

[1408] Specific actions

[1409] The server runs an algorithm that mimics the CEO's decision-making process based on the analysis results, including the extracted emotional data.

[1410] For example, use machine learning models such as TensorFlow or Scikit-learn and load pre-trained algorithms.

[1411] The server inputs the analysis results and emotional data into an algorithm to generate the optimal answer.

[1412] The answers generated include specific advice such as "research market demand, assess risks, and consider partnerships."

[1413] input

[1414] Analysis results with added emotion data.

[1415] output

[1416] Algorithmically generated answers.

[1417] Step 5: Generate and provide answers

[1418] Specific actions

[1419] The server formats the generated responses, adjusting the tone and content based on the emotional data.

[1420] Specifically, the generated answers will be enhanced with emotionally sensitive language such as, "We understand your concerns. To alleviate them, it is important to conduct thorough market research and risk assessments."

[1421] The final answer is converted to JSON format and sent to the terminal.

[1422] The terminal parses the received JSON data and displays it to the user.

[1423] input

[1424] Algorithmically generated answers.

[1425] output

[1426] The final answer provided to the user.

[1427] (Application example 2)

[1428] 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."

[1429] Conventionally, security services have lacked systems that can quickly and accurately respond when users feel anxious or worried. As a result, it is difficult for users to find an appropriate solution, which can lead to a decline in the quality of security services. Furthermore, the inability to respond appropriately to users' emotions can further increase anxiety and impatience. The present invention aims to solve these problems.

[1430] 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 or task entered by a user, means for analyzing the question or task using natural language processing and identifying the intent, means for recognizing emotions from the entered text, means for searching a database for related information based on the analysis results and emotions, means for executing an algorithm that mimics the decision-making process, means for generating an answer that takes emotions into consideration based on the results of the algorithm, and means for providing the generated answer to the user. This enables a quick and accurate response when a user of a security service feels anxious or concerned. Furthermore, generating an answer that takes the user's emotions into consideration can improve the user's sense of security.

[1431] A "question" is text entered by a user regarding a particular problem or question.

[1432] A "problem" refers to a particular problem situation or challenge that a user wishes to solve.

[1433] "Natural language processing" is a general term for technology that allows computers to understand, analyze, and generate human language.

[1434] "Emotion" refers to a psychological state extracted from the text entered by the user, such as anxiety or impatience.

[1435] A "database" is a collection of related information organized for efficient searching and retrieval.

[1436] An "algorithm that mimics the decision-making process" is a computational procedure that replicates the decision-making process of corporate leaders.

[1437] An "answer" is a response generated by the server in response to a user's question or task.

[1438] "Relevant information" refers to data or documents that are directly related to the question or issue.

[1439] "Emotion recognition" refers to the technology of identifying a user's psychological state from their input text.

[1440] "Means for providing to the user" refers to the interface or method for showing the generated answer to the user.

[1441] This system analyzes questions and issues entered by users, generates and provides optimal answers based on related emotional data, and is implemented through interactions between the server, terminals, and users.

[1442] The server is the main processing unit and includes the following elements:

[1443] A way to receive questions and assignments

[1444] A means of analyzing questions and issues using natural language processing

[1445] A method for recognizing emotions from input text

[1446] A means of searching for relevant information from a database based on analysis results and sentiment

[1447] A means of implementing algorithms that mimic decision-making processes

[1448] A means of generating answers based on the results of an algorithm

[1449] A means of providing the generated answer to the user

[1450] Hardware and Software Configuration

[1451] Hardware:

[1452] Smartphone (user device)

[1453] Server (main processing and database management)

[1454] software:

[1455] Amazon Web Services (AWS) Lambda (serverless computing)

[1456] Google Cloud Natural Language API (Natural Language Processing)

[1457] IBM Watson Emotion Analysis

[1458] Python (programming language)

[1459] Data processing and calculation

[1460] 1. Receiving questions and assignments:

[1461] A user uses a smartphone to input a question or problem, for example, "My home security system has detected an abnormality. I'm worried. What should I do?"

[1462] 2. Analysis of questions and issues:

[1463] The server uses the Google Cloud Natural Language API to analyze the user's question or issue and extract key keywords (e.g., "security system," "anomaly").

[1464] 3. Emotion recognition:

[1465] The server uses IBM Watson Emotion Analysis to identify emotions from the user's input text (e.g., "anxiety").

[1466] 4. Information Search:

[1467] The server searches the database for relevant information based on the analyzed keywords and emotional data.

[1468] 5. Imitating the decision-making process:

[1469] The server runs an algorithm that mimics the decision-making process of a company leader, combining relevant information and emotional data to generate the best answer.

[1470] 6. Generate and provide answers:

[1471] The server adjusts the generated answer taking into account the user's emotions and displays it on the smartphone (e.g., "If an abnormality is detected, first remain calm and call your emergency contact or the nearest police station.").

[1472] Prompt Sentence Examples

[1473] User Question: "My home security system is detecting something abnormal. I'm worried. What should I do?"

[1474] Analyzed keywords: "security system", "abnormality"

[1475] Recognized emotion: "Anxiety"

[1476] Generated advice: "If an abnormality is detected, first remain calm and call your emergency contact or the nearest police station. Also, check the system logs and gather as much information as possible."

[1477] This system can provide users with optimal means to quickly and accurately resolve security-related issues and concerns. In particular, by taking emotional data into consideration, it can provide solutions that are suited to the psychological state of each individual user.

[1478] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1479] Step 1:

[1480] A user inputs a question or problem into their smartphone. For example, they input text like, "My home security system has detected an abnormality. I'm worried. What should I do?" This text is then sent from the device to the server. The input data is the user text, and the output data is the raw text sent to the server.

[1481] Step 2:

[1482] The server sends the received text to the Google Cloud Natural Language API and analyzes it using natural language processing. Specifically, the server extracts key keywords from the text. For example, the keywords "security system" and "abnormal" are extracted. The input data is the raw text, and the output data is the analyzed keywords.

[1483] Step 3:

[1484] The server uses IBM Watson Emotion Analysis to recognize emotions from the user's text based on the extracted keywords. Specifically, the raw text is sent to the emotion recognition engine, and the emotion "anxiety" is extracted as a result. The input data is the raw text and keywords, and the output data is the recognized emotion.

[1485] Step 4:

[1486] The server searches a database for relevant information based on the analyzed keywords and emotions. For example, past documents and advice on how to respond to security system anomalies are searched for. The input data is keyword and emotion data, and the output data is a set of related information.

[1487] Step 5:

[1488] The server runs an algorithm that mimics the decision-making process based on relevant information and emotional data. Specifically, it mimics past decisions made by company leaders and generates appropriate advice. The input data is relevant information and emotional data, and the output data is the generated advice.

[1489] Step 6:

[1490] The server adjusts the content and tone of the generated advice to provide it to the user based on the emotional data. For example, it uses language that alleviates anxiety. The input data are the generated advice and emotional data, and the output data is the optimized advice.

[1491] Step 7:

[1492] The device displays the optimized advice to the user, allowing the user to act based on the advice. Specifically, the advice is displayed on the smartphone screen. The input data is the optimized advice, and the output data is displayed to the user.

[1493] 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.

[1494] 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.

[1495] 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.

[1496] 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.

[1497] 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.

[1498] 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.

[1499] 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).

[1500] 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.

[1501] 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."

[1502] 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.

[1503] 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).

[1504] 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.

[1505] 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.

[1506] 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.

[1507] 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.

[1508] 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.

[1509] 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.

[1510] 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.

[1511] 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.

[1512] 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.

[1513] 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.

[1514] The following is further disclosed regarding the above embodiment.

[1515] (Claim 1)

[1516] means for receiving user-entered questions or assignments;

[1517] A means for analyzing the question or problem using natural language processing and identifying the intent;

[1518] a means for searching a database for related information based on the analysis results;

[1519] means for executing an algorithm that mimics the decision-making process of said CEO;

[1520] means for generating an answer based on the results of said algorithm;

[1521] means for providing the generated answer to a user;

[1522] A system including:

[1523] (Claim 2)

[1524] 10. The system of claim 1, wherein the database includes information about past statements, books, interviews, and business strategies.

[1525] (Claim 3)

[1526] 10. The system of claim 1, wherein the natural language processing includes topic modeling and keyword extraction.

[1527] "Example 1"

[1528] (Claim 1)

[1529] means for receiving user-entered questions or assignments;

[1530] A means for analyzing the question or problem using natural language processing and identifying the intent;

[1531] a means for searching a database for related information based on the analysis results;

[1532] means for executing an algorithm that mimics said decision-making process;

[1533] means for generating an answer based on the results of said algorithm;

[1534] means for providing the generated answer to a user;

[1535] means for a user to view answers, the means including a terminal and a web browser or dedicated application;

[1536] A means of using BERT or GPT models in natural language processing;

[1537] A method that uses a database to search past statements and business strategies based on analyzed keywords, and

[1538] A system including:

[1539] (Claim 2)

[1540] 10. The system of claim 1, wherein the database includes information about past statements, books, interviews, and business strategies.

[1541] (Claim 3)

[1542] 10. The system of claim 1, wherein the natural language processing includes topic modeling and keyword extraction.

[1543] "Application Example 1"

[1544] (Claim 1)

[1545] means for receiving user-entered questions or assignments;

[1546] A means for analyzing the question or problem using natural language processing and identifying the intent;

[1547] a means for searching a database for related information based on the analysis results;

[1548] means for executing an algorithm that mimics the decision-making process of said leader;

[1549] means for generating an answer based on the results of said algorithm;

[1550] means for providing the generated answer to a user;

[1551] a means for using information context to provide advice on various business matters;

[1552] a means for generating optimal advice using a generative AI model; and

[1553] A system including:

[1554] (Claim 2)

[1555] 2. The system of claim 1, wherein the database includes information on past statements, books, interviews, business strategies, and operational know-how.

[1556] (Claim 3)

[1557] 2. The system of claim 1, wherein the natural language processing includes topic modeling and keyword extraction, and further generates prompt sentences in response to user questions.

[1558] "Example 2: Combining Emotion Engines"

[1559] (Claim 1)

[1560] means for receiving user-entered questions or assignments;

[1561] A means for analyzing the question or problem using natural language processing and identifying the intent;

[1562] a means for searching a database for related information based on the analysis results;

[1563] means for extracting emotion data from a user's input;

[1564] means for executing an algorithm that mimics the decision-making process of a CEO based on the analysis results including the emotion data;

[1565] A means for generating an answer that takes emotion data into consideration based on the result of the algorithm;

[1566] means for providing the generated answer to a user;

[1567] A system including:

[1568] (Claim 2)

[1569] The database includes information on past statements, books, interviews, and business strategies.

[1570] 10. The system of claim 1.

[1571] (Claim 3)

[1572] The natural language processing includes topic modeling and keyword extraction.

[1573] 10. The system of claim 1.

[1574] "Application example 2 when combining emotion engines"

[1575] (Claim 1)

[1576] means for receiving user-entered questions or assignments;

[1577] A means for analyzing the question or problem using natural language processing and identifying the intent;

[1578] means for recognizing emotions from the input text;

[1579] a means for searching a database for relevant information based on the analysis result and the emotion;

[1580] means for executing an algorithm that mimics said decision-making process;

[1581] means for generating an emotion-sensitive answer based on the results of said algorithm;

[1582] means for providing the generated answer to a user;

[1583] A system including:

[1584] (Claim 2)

[1585] 10. The system of claim 1, wherein the database includes information about past statements, literature, interviews, and strategies.

[1586] (Claim 3)

[1587] 10. The system of claim 1, wherein the natural language processing includes topic modeling and keyword extraction. [Explanation of symbols]

[1588] 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 user-entered questions or assignments; A means for analyzing the question or problem using natural language processing and identifying the intent; a means for searching a database for related information based on the analysis results; means for executing an algorithm that mimics the decision-making process of said CEO; means for generating an answer based on the results of said algorithm; means for providing the generated answer to a user; A system including:

2. 2. The system of claim 1, wherein the database includes information about past statements, books, interviews, and business strategies.

3. 10. The system of claim 1, wherein the natural language processing includes topic modeling and keyword extraction.

Images