System

Abstract

A system is provided.SOLUTION: A system including means for collecting information related to a task or a project that a retiree was in charge of and storing the information in a database, means for performing text analysis on the collected information and extracting a keyword or an important phrase, means for causing a generative AI model to learn based on the extracted keyword or phrase, and means for receiving a question from a user and answering the question using the generative AI model.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] Recent organizational changes have resulted in an increase in employee turnover, leaving the knowledge and tasks of certain employees unorganized. This lack of personal information and problems with organization has led to frequent delays and errors in work. Therefore, there is a need to efficiently organize the knowledge of those who have left, so that new employees can access that knowledge quickly and accurately to avoid work delays and errors. [Means for solving the problem]

[0005] The present invention solves the above problem by providing a system that includes a means for collecting information related to the work and projects that former employees were in charge of and storing it in a database, a means for performing text analysis of the collected information and extracting keywords and important phrases, a means for training a generative AI model based on the extracted keywords and phrases, and a means for accepting questions from users and answering the questions using the generative AI model.

[0006] A "former employee" is an employee who was in charge of a particular task or project but is leaving the organization.

[0007] "Work" refers to the set of tasks or activities that employees perform to achieve organizational goals.

[0008] A "project" is a temporary collection of activities designed to achieve a specific goal.

[0009] "Information" refers to knowledge or data that exists in the form of documents, emails, chat logs, etc.

[0010] "Collection" refers to the act of gathering and organizing information needed for a specific purpose.

[0011] A "database" is a system that can efficiently store, retrieve, and manage information.

[0012] "Storage" refers to the act of recording collected information in a database or other recording medium so that it can be accessed at a later date.

[0013] "Text analysis" refers to the technology of processing natural language text and analyzing its structure and meaning.

[0014] "Keywords" are words or phrases in a text that have particular significance.

[0015] A "significant phrase" is a series of consecutive words that contain specific meaning or information, extracted through text analysis.

[0016] A "generative AI model" is a machine learning model that learns from specific data and generates appropriate answers to questions.

[0017] "Learning" is the process by which a generative AI model recognizes patterns and rules based on input data and improves its performance.

[0018] "User" means an end user who utilizes the system to obtain information or answer questions. [Brief explanation of the drawings]

[0019] [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

[0020] 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.

[0021] First, the terms used in the following description will be explained.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 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.

[0030] 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).

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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."

[0040] This invention relates to a system that collects information related to the work and projects that former employees were in charge of, analyzes the text, and trains a generative AI model to quickly and appropriately answer questions from users. This system consists of three main components: a server, a terminal, and a user.

[0041] server

[0042] The server first collects information related to the work and projects that the former employee was in charge of. The collected information is then stored in a database. The collected information is then analyzed using natural language processing technology to extract keywords and important phrases. A generative AI model learns from this extracted information. This model is then used to generate appropriate answers to user questions.

[0043] Terminal

[0044] The terminal is the interface through which the user inputs questions and sends them to the server. The terminal also formats the questions input by the user and sends them to the server. It also plays a role in displaying the answers returned by the server to the user. In this way, the terminal is a tool for facilitating communication between the user and the server.

[0045] User

[0046] Users use the system to enter questions related to their work and receive appropriate answers. For example, if a user wants to know the progress of a promotional campaign for a new product, they enter that specific question into their terminal. When they press the send button, the question is sent from the terminal to the server.

[0047] The server receives the question, uses the generative AI model to generate the optimal answer, and sends this answer back to the device. The device then displays the answer to the user, who can then use it to carry out tasks or solve problems.

[0048] Specific examples

[0049] Let's say Tanaka from the marketing department wants to check the status of a new product promotion campaign. Tanaka types "Please tell me about the progress of the new product promotion campaign" into the interface on his device and clicks the send button. The question is sent from the device to the server, which queries the question with the generative AI model. The generative AI model generates an appropriate answer based on information related to past promotional campaigns, and returns an answer such as "The new product promotion campaign is currently in its third phase and is 70% complete" to Tanaka's device. Tanaka can then review the displayed answer and plan the next steps for his work.

[0050] In this way, the system of the present invention effectively organizes the knowledge possessed by former employees and allows them to access the necessary information quickly and accurately, thereby avoiding delays and errors in work.

[0051] The processing flow will be explained below.

[0052] Step 1:

[0053] The server collects documents, emails, chat logs, and other information related to the work and projects that former employees were in charge of. This information collection is done periodically using automated scripts and APIs.

[0054] Step 2:

[0055] The server stores the collected information in a database, and when storing it, it adds metadata to each piece of information to make it easier to organize and search for the information later.

[0056] Step 3:

[0057] The server performs text analysis of the stored information, using tools that use natural language processing technology to perform morphological and grammatical analysis.

[0058] Step 4:

[0059] The server extracts keywords and important phrases from the results of text analysis, which are then used to train the generative AI model.

[0060] Step 5:

[0061] The server then trains the generative AI model with the extracted information, a process that improves its ability to recognize patterns and rules from past data and generate appropriate answers to questions.

[0062] Step 6:

[0063] The user inputs a business-related question into the terminal interface. For example, if the user wants to check the progress of a promotional campaign for a new product, the user inputs a specific question.

[0064] Step 7:

[0065] The terminal sends the user-entered question to the server, where the question is formatted using a protocol such as an HTTP request.

[0066] Step 8:

[0067] The server receives the question from the terminal and analyzes the content of the question using natural language processing technology.

[0068] Step 9:

[0069] The server then queries the generative AI model based on the analysis results, and the model uses the learned data to generate an appropriate answer.

[0070] Step 10:

[0071] The server then returns the generated answer to the device in a data format such as JSON or XML.

[0072] Step 11:

[0073] The terminal displays the answer received from the server on the user interface in a format that is easily understandable to the user.

[0074] Step 12:

[0075] Users can review the displayed answers and use them to complete tasks or solve problems, for example, to plan the next steps for a sales campaign based on the information provided.

[0076] Example 1

[0077] 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."

[0078] When an employee in charge of an important task or project leaves a company, the loss of that knowledge and information can disrupt business continuity. In particular, if the employee was performing tasks that require specific knowledge and experience, such as project management or marketing activities, it can be difficult for the new employee who takes over to smoothly adapt and continue performing those tasks. This also increases the likelihood of operational delays and errors, so there is a need for a method to efficiently collect and analyze information and obtain the necessary information quickly and accurately.

[0079] 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.

[0080] In this invention, the server includes means for collecting and storing information related to the work and projects that former employees were in charge of in a database, means for analyzing the collected information using natural language processing technology and extracting keywords and important phrases, means for training a generative AI model based on the extracted keywords and phrases, means for accepting questions from users and answering the questions using the generative AI model, means for formatting the questions from users using a terminal and sending them to the server, and means for displaying the answers returned from the server to the user on the terminal. This makes it possible to efficiently collect and analyze the knowledge and information held by former employees and quickly and accurately access the necessary information.

[0081] "Ex-employees" refers to employees who have left the company.

[0082] "Work" refers to specific job functions and routine tasks within a company.

[0083] A "project" is a set of activities designed to achieve a specific purpose.

[0084] "Information" refers to a collection of general knowledge such as data, knowledge, reports, emails, etc.

[0085] A "database" refers to a system for organizing and storing collected information.

[0086] "Natural language processing technology" refers to the technology that allows computers to understand and analyze human language.

[0087] "Keywords" refer to important words or phrases within a document.

[0088] A "phrase" refers to a group of words that have meaning and are made up of multiple words.

[0089] A "generative AI model" refers to a model that uses artificial intelligence to generate text and answer questions.

[0090] A "question" refers to a query entered by a user seeking specific information.

[0091] "Answer" refers to the information provided by a generative AI model in response to a question.

[0092] "Terminal" refers to a device through which a user accesses the system and inputs questions.

[0093] "User" refers to the employees and personnel who use this system.

[0094] "Formalization" refers to the process of converting an input question into a certain format.

[0095] "Server" refers to a computer that performs the main processing of the entire system.

[0096] Including "communication" refers to the process of sending and receiving information or data.

[0097] "Interface" refers to the means by which a user interacts with a system.

[0098] This invention relates to a system that collects information related to the work and projects that former employees were in charge of, analyzes the text, and trains a generative AI model to quickly and appropriately answer questions from users. This system consists of three main components: a server, a terminal, and a user.

[0099] server

[0100] The server has the function of collecting information related to the work and projects of former employees. The information is obtained from the company's document management system and mail server and stored in a database such as MongoDB. The data is then analyzed using natural language processing technologies such as SpaCy and NLTK to extract keywords and important phrases. This extracted information is used to train a generative AI model (e.g., OpenAI's GPT-4). This generative AI model is responsible for generating appropriate answers to user questions. The server also trains the generative AI model using TensorFlow and PyTorch.

[0101] Terminal

[0102] The terminal is an interface through which the user inputs a question and sends it to the server. The terminal can operate as a web browser, desktop application, or mobile application. For example, the web application is implemented using "React.js" and has a question input field and a submit button. The question input by the user is formatted by the terminal and sent to the server via "REST API." The answer returned from the server is also displayed to the user on the terminal.

[0103] User

[0104] Users use their devices to input questions related to their work and receive appropriate answers. For example, if a marketing department employee wants to know the progress of a new product promotion campaign, they can input "Please tell me about the progress of the new product promotion campaign" into their device and send it. The question is sent from the device to the server and queried by the generative AI model. The generative AI model generates an appropriate answer based on information related to past promotional campaigns, and returns an answer such as "The new product promotion campaign is currently in its third phase and is 70% complete" to the user's device. The user can use this information to plan the next steps in their work.

[0105] Specific examples

[0106] An example of a prompt phrase used is, "Please tell me about the progress of the promotional campaign for the new product." The system uses a generative AI model to generate an answer to this question and displays it to the user on the device. In this way, the knowledge and information possessed by former employees can be efficiently organized, allowing users to access the information they need quickly and accurately, thereby avoiding work delays and errors.

[0107] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0108] Step 1: Gather information

[0109] The server collects information related to the former employee's work and projects, specifically reports, emails, and project management tool data from the company's document management system and email server.

[0110] Input: Document management system, mail server

[0111] Output: Retrieved work and project-related information (text format)

[0112] Step 2: Saving to the database

[0113] The server stores the collected information in a database such as MongoDB, which allows the data to be systematically managed for later analysis and retrieval.

[0114] Input: Work and project related information captured

[0115] Output: Information stored in the database

[0116] Step 3: Natural Language Processing Analysis

[0117] The server uses natural language processing techniques (e.g., SpaCy, NLTK) to analyze the stored information, specifically extracting keywords and important phrases from the text.

[0118] Input: Information stored in a database

[0119] Output: Extracted keywords and important phrases

[0120] Step 4: Training the generative AI model

[0121] The server trains a generative AI model (e.g., OpenAI's GPT-4) based on the extracted keywords and phrases. During this process, the model is trained using a machine learning framework (e.g., TensorFlow, PyTorch).

[0122] Input: Extracted keywords or key phrases

[0123] Output: Trained generative AI model

[0124] Step 5: Enter and format your question

[0125] The user uses the device to enter a question, which is then formatted and sent to the server via a REST API request. Specifically, the user enters a question in a text box and clicks the submit button.

[0126] Input: Question from the user (prompt sentence)

[0127] Output: Formatted question (HTTP request)

[0128] Step 6: Submit and receive your question

[0129] The device sends a formulated question to the server, which accepts the question and prepares the data to query the generative AI model.

[0130] Input: A formatted question (HTTP request)

[0131] Output: The question sent to the server

[0132] Step 7: Generate an answer

[0133] The server uses the generative AI model to generate the optimal answer for the received question. Specifically, the server automatically creates an answer based on the question entered into the generative AI model.

[0134] Input: The question sent to the server

[0135] Output: The generated answer

[0136] Step 8: Return and view your responses

[0137] The server returns the generated answer to the terminal, which then displays the received answer to the user. Specifically, the generated answer is displayed on the user interface.

[0138] Input: Generated answer (HTTP response)

[0139] Output: Answer displayed on terminal

[0140] Step 9: What happens next for the user?

[0141] Based on the displayed answers, users can plan and execute the next steps in their business. For example, they can decide on the next marketing strategy based on the answers.

[0142] Input: Answer displayed on the terminal

[0143] Output: User's action plan

[0144] In this way, each component of the system works together to carry out processing and provide users with prompt and appropriate information.

[0145] (Application example 1)

[0146] 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."

[0147] There is a problem that valuable knowledge about the work and projects that former employees were in charge of is not passed on, resulting in delays and errors by remaining employees.In addition, information on transaction history and payment status for electronic payment services needs to be provided quickly and appropriately.A system is needed to solve these problems and ensure work efficiency and transparency in the payment process.

[0148] 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.

[0149] In this invention, the server includes means for collecting and storing information related to the work and projects that former employees were in charge of in a database, means for performing text analysis of the collected information and extracting keywords and important phrases, means for training a generative AI model based on the extracted keywords and phrases, means for providing appropriate answers based on information including transaction history and payment status related to electronic payments, and means for accepting questions from users and answering the questions using the generative AI model. This makes it possible to effectively utilize the knowledge of former employees, speed up operations, and improve the efficiency of information provision in the electronic payment process.

[0150] "Ex-employees" are employees who have left a particular company or organization.

[0151] "Work" refers to the specific work or tasks that an employee is responsible for within an organization or company.

[0152] A "project" is a set of planned activities to achieve a specific purpose within a certain period of time.

[0153] "Information" refers to data and knowledge related to a business or project.

[0154] A "database" is a system that centrally stores and manages various types of data.

[0155] "Text analysis" is a technique for extracting and analyzing specific information from text data.

[0156] "Keywords" are words or phrases that play an important role in a piece of text.

[0157] A "generative AI model" is an artificial intelligence that uses machine learning technology to automatically generate appropriate answers to questions.

[0158] "Electronic payment" refers to payment transactions conducted over the Internet or electronic devices.

[0159] "Transaction History" means a record of past payment activity and transactions.

[0160] "Payment Status" means the progress or completion state of a particular payment activity.

[0161] An "answer" is the information that a generative AI model outputs in response to a user's question.

[0162] "User" refers to an individual or organization that uses the system to ask a question.

[0163] "Server" means a computer system for collecting, analyzing, storing data, and running the generative AI model.

[0164] A "question" is a query that a user enters into the system to obtain specific information.

[0165] Explanation of program processing

[0166] Hardware and Software Use

[0167] server:

[0168] Hardware: The server uses a high-performance computer system to store and analyze the collected information and train the generative AI model.

[0169] Software: The server uses Python and natural language processing libraries such as Hugging Face Transformers. Specifically, the generative AI model is trained using the "deepset / roberta-base-squad2" model.

[0170] Device:

[0171] Hardware: The device, such as a smartphone or computer, used by the user to enter the question.

[0172] Software: A user interface for entering questions and an application for displaying answers from the server.

[0173] User:

[0174] Users use their devices to input questions, which are then sent to a server where a generative AI model generates an answer.

[0175] Data processing and calculation

[0176] The server first collects information related to the former employee's work and projects and stores it in a database. Next, the information is analyzed using natural language processing technology to extract keywords and important phrases. A generative AI model is trained based on this analyzed information.

[0177] The user's question is sent to the server via the device, and the server generates an answer using the generative AI model. The generated answer is then sent back to the device and displayed to the user.

[0178] Specific examples

[0179] Suppose a user asks, "What is the payment status of transaction ID: 12345?" The server extracts information such as transaction history and payment status from the database, and uses a generative AI model to generate an answer such as, "The current status of transaction ID: 12345 is complete. All approval processes have been completed." The answer is sent to the terminal and displayed to the user.

[0180] Prompt Sentence Examples

[0181] An example of a prompt entered by a user:

[0182] "What is the payment status for transaction ID: 12345?"

[0183] This invention effectively transfers the knowledge of former employees and trains it in a generative AI model, enabling users to quickly and accurately obtain information. It can also respond to specific questions about electronic payments, improving work efficiency and transparency in the payment process.

[0184] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0185] Step 1:

[0186] The server collects and stores in a database information related to the former employee's work and projects, including detailed project progress reports, transaction history, payment status, etc. The input data are documents, reports, and database entries, and the output is structured data that can be used for analysis and to train generative AI models.

[0187] Step 2:

[0188] The server uses natural language processing (NLP) techniques to analyze the collected information and extract keywords and important phrases. The input is raw information about tasks and projects stored in a database. The output is the analysis results, including keywords and important phrases. Specific NLP libraries (e.g., SpaCy and NLTK) are used to process the data.

[0189] Step 3:

[0190] The server trains a generative AI model (e.g., Hugging Face's "deepset / roberta-base-squad2") based on the text analysis results. The input is the key information extracted in step 2. The output is a generative AI model that can appropriately respond to the user's question. This generative AI model is trained using a large amount of text data to improve the accuracy of the model.

[0191] Step 4:

[0192] A user inputs a question using a device (such as a smartphone or computer). The device interface formats the question from the user and sends it to the server. The input is the user's question (prompt), and the output is the transfer of formatted data to the server.

[0193] Step 5:

[0194] The server inputs the received question into the generative AI model to generate an appropriate answer. The input is the question from the user, and the output is the answer generated by the generative AI model. The generative AI model analyzes related information in a database based on the question content and generates an answer that is useful to the user.

[0195] Step 6:

[0196] The server sends the generated answer to the terminal. The input is the generated answer, and the output is the transfer of the answer information to the terminal.

[0197] Step 7:

[0198] The terminal displays the answer received from the server to the user. The input is the answer information provided by the server, and the output is the answer displayed for the user on the terminal screen. This allows the user to quickly and accurately obtain the information they need, such as the progress of work or projects, or the payment status of transactions.

[0199] 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.

[0200] This invention relates to a system that collects information related to the work and projects that former employees were in charge of, analyzes the text, and trains a generative AI model to quickly and appropriately answer questions from users. This system consists of four main components: a server, a terminal, a user, and an emotion engine that recognizes the user's emotions.

[0201] server

[0202] The server first collects information related to the work and projects that the former employee was in charge of. The collected information is then stored in a database. When storing the information, metadata is added to each piece of information to facilitate organization and subsequent retrieval. The collected information is then analyzed using natural language processing technology to extract keywords and important phrases. A generative AI model trains based on this extracted information. This model is then used to generate appropriate answers to user questions.

[0203] Terminal

[0204] The terminal serves as an interface through which the user can input questions and send them to the server. It also simultaneously collects emotional data when the user asks a question. Emotional data is analyzed from the user's facial expression, tone of voice, and text content. The terminal formats the questions and emotional data input by the user and sends them to the server. It also plays a role in displaying the answers returned by the server to the user.

[0205] Emotion Engine

[0206] The emotion engine has the ability to analyze the user's emotions and adjust the generative AI model's responses based on that. Emotional data is analyzed in real time, and if the user is feeling stressed, for example, the tone and content of the response will be softened.

[0207] User

[0208] Users can use the system to input questions related to their work and receive appropriate answers. The device also automatically collects the emotions expressed at the time of the question. For example, if a user wants to know the progress of a new product promotion campaign and is feeling stressed, they can input that specific question and receive an answer that takes those emotions into consideration.

[0209] Specific examples

[0210] Suppose that Tanaka from the marketing department wants to check the status of a promotional campaign for a new product. He types "Please tell me about the progress of the promotional campaign for the new product" into the interface on his device. If the emotion engine detects stress while Tanaka is typing this question, the device will send the question to the server based on this emotion data.

[0211] The server queries the question to the AI ​​model, which generates an appropriate answer based on information related to past promotional campaigns. For example, the generated answer might be, "The promotional campaign for the new product is currently in its third phase and is 70% complete." The emotion engine then performs additional processing to soften the tone and content of the answer to reduce Tanaka's stress.

[0212] The server then adapts the generated answer to Tanaka's emotions and sends it back to his device. Tanaka's device displays the answer, allowing him to check the necessary information without feeling stressed.

[0213] In this way, the system of the present invention not only efficiently organizes the knowledge possessed by former employees and allows them to access the necessary information quickly and accurately, but also provides answers that take the user's emotions into consideration, thereby further preventing work delays and errors.

[0214] The processing flow will be explained below.

[0215] Step 1:

[0216] The server collects documents, emails, chat logs, and other information related to the work and projects that former employees were in charge of. This information collection is done periodically using automated scripts and APIs.

[0217] Step 2:

[0218] The server stores the collected information in a database, and when storing it, it adds metadata to each piece of information to make it easier to organize and search for the information later.

[0219] Step 3:

[0220] The server performs text analysis of the stored information, using tools that use natural language processing technology to perform morphological and grammatical analysis.

[0221] Step 4:

[0222] The server extracts keywords and important phrases from the results of text analysis, which are then used to train the generative AI model.

[0223] Step 5:

[0224] The server trains the generative AI model based on the extracted information, a process that improves its ability to recognize patterns and rules from past data and generate appropriate answers to questions.

[0225] Step 6:

[0226] The user inputs a business-related question into the terminal interface. For example, if the user wants to check the progress of a promotional campaign for a new product, the user inputs that specific question.

[0227] Step 7:

[0228] In addition to the user's input, the device uses facial expression recognition and voice analysis to obtain emotional data about the user. It analyzes the user's emotional state when entering a question and collects emotional data such as stress, joy, and confusion.

[0229] Step 8:

[0230] The device sends the collected questions and emotion data to the server, where the data is formatted using a protocol such as an HTTP request.

[0231] Step 9:

[0232] The server receives the question and emotion data from the device and analyzes the content of the question using natural language processing technology.

[0233] Step 10:

[0234] The server then queries the generative AI model based on the analysis results, and the model uses the learned data to generate an appropriate answer.

[0235] Step 11:

[0236] The emotion engine analyzes the user's emotional data and adjusts the tone and content of the generated response. For example, if the user is feeling stressed, the tone of the response will be softened.

[0237] Step 12:

[0238] The server adjusts the generated answers using the emotion engine and then sends them back to the device in a data format such as JSON or XML.

[0239] Step 13:

[0240] The terminal displays the adjusted answers received from the server on a user interface in a format that is easily understandable to the user.

[0241] Step 14:

[0242] Users can review the displayed answers and use them to carry out tasks or solve problems, and can use the information they need to plan the next steps in their sales campaigns.

[0243] Example 2

[0244] 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."

[0245] In modern companies, the loss of important knowledge and information held by employees who leave the company is a major problem. While there is also a need to quickly and appropriately retrieve work-related information, insufficient access can lead to reduced work efficiency and errors. Furthermore, it is important to consider the user's emotions when retrieving information, and it is desirable to receive answers without feeling stressed. A system that solves these problems is needed.

[0246] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting and storing information related to the work and projects that the former employee was in charge of in a database, means for performing text analysis of the collected information and extracting keywords and important phrases, means for training a generative AI model based on the extracted keywords and phrases, means for accepting questions from users and answering the questions using the generative AI model, means for collecting and analyzing user emotion data, and means for adjusting the generated answers based on the analyzed emotion data. This makes it possible to effectively store and utilize the knowledge and information of former employees, provide appropriate answers when users ask questions, and respond in a way that takes the user's emotions into consideration.

[0247] "Ex-employees" refer to former employees who have left a company or organization.

[0248] "Work" refers to the tasks and responsibilities performed within a company or organization.

[0249] A "project" is a set of activities or tasks planned to achieve a specific purpose.

[0250] "Information" refers to data and knowledge related to a business or project.

[0251] A "database" refers to a system for organizing and storing information.

[0252] "Text analytics" refers to the process of analyzing natural language text and extracting useful information from it.

[0253] "Keywords" are words or phrases that are particularly important in a piece of text.

[0254] A "phrase" is an expression made up of multiple words that have a specific meaning.

[0255] A "generative AI model" refers to an artificial intelligence model that uses machine learning algorithms to generate output from input data.

[0256] "User" refers to a person who uses the system.

[0257] A "question" refers to an action in which a user asks the system for information they want to know.

[0258] "Emotional data" refers to various data that indicate the user's emotional state (facial expressions, tone of voice, text content, etc.).

[0259] "Analysis" refers to the process of examining the contents of data to extract specific information.

[0260] "Adjustment" refers to the act of changing content or methods to suit specific conditions.

[0261] A "system" refers to a mechanism in which multiple components work together to achieve a set of functions.

[0262] "Metadata" refers to data that provides information about other data.

[0263] "Natural language processing technology" refers to computer science technology for understanding, interpreting, and generating human language.

[0264] In this invention, the server, terminal, and user components cooperate to collect and analyze the knowledge and information possessed by former employees, and provide a system that uses a generative AI model to provide appropriate answers to user questions.

[0265] server

[0266] The server automatically collects information related to the work and projects that former employees were in charge of. This information is collected from sources such as network communications, emails, and internal chats. Programming languages ​​such as Python, web scraping technology, and APIs are used to collect the information. The collected information is stored in a database such as MySQL along with metadata.

[0267] The server then analyzes the collected information using natural language processing techniques (e.g., Python's NLTK or spaCy) to extract keywords and important phrases. This information is used to train a generative AI model (e.g., OpenAI's GPT-3). The server then optimizes the generative AI model using a deep learning framework (e.g., TensorFlow or PyTorch).

[0268] Terminal

[0269] The device provides an interface for users to interact with the system. Users type questions into the device, and the data is sent to the server. The device is equipped with a webcam and microphone to collect the user's facial expressions and tone of voice in real time. This emotional data is analyzed using Azure Cognitive Services and Google Cloud's Natural Language API.

[0270] Emotion Engine

[0271] The emotion engine analyzes collected emotion data in real time to understand the user's emotional state. It uses libraries such as OpenCV and TensorFlow for emotion analysis and adjusts the output of the generative AI model based on the analysis results. This adjustment results in softer responses if the user is feeling stressed.

[0272] User

[0273] Users can input questions related to their work into the terminal interface and receive appropriate answers from the server. For example, a user might ask, "Please tell me about the progress of the promotional campaign for a new product." The user's input is then subjected to real-time emotion analysis to determine whether they are feeling stressed.

[0274] As a concrete example, if a member of the marketing department wants to check the progress of a promotional campaign for a new product, the user inputs the question "Please tell me about the progress of the promotional campaign for the new product" into the device. Along with this input information, the emotion engine analyzes the user's facial expressions and voice and sends the emotion data to the server. The server then sends the following prompt to the generative AI model:

[0275] Example prompt sentence:

[0276] Please tell us about the progress of the promotional campaign for the new product.

[0277] The server uses a generative AI model to generate an appropriate response and adjusts the response based on the analysis results of the emotion engine. For example, if the response generated is, "The promotional campaign for our new product is currently in its third phase and is 70% complete," the emotion engine softens the tone by adding, "Don't worry, everything is going smoothly."

[0278] In this way, the user can quickly and appropriately obtain the necessary information without feeling stressed. In this way, this invention is a system that effectively utilizes the knowledge and information of former employees and provides appropriate answers that take into consideration the feelings of the user.

[0279] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0280] Step 1:

[0281] The server collects information related to the work and projects that former employees were in charge of and stores it in a database. Specifically, it uses Python scripts to collect data from sources such as network communications, emails, and internal chats, and stores the data in a MySQL database. The collected data is assigned metadata such as date and time and related projects, allowing for efficient search and management. The input is text data obtained from each source, and the output is stored in the database as information with metadata.

[0282] Step 2:

[0283] The server performs text analysis of the stored information using natural language processing technology. Specifically, it uses Python's NLTK and spaCy to analyze the text data retrieved from the database and extract important keywords and phrases. The input is the text data stored in the database, and the output is the keywords and important phrases that are the analysis results. These results are then stored back in the database.

[0284] Step 3:

[0285] The server trains a generative AI model based on the extracted keywords and phrases. Specifically, it uses the extracted data to train a generative AI model (e.g., GPT-3) using a deep learning framework (e.g., TensorFlow or PyTorch). The input is a dataset consisting of keywords and important phrases, and the output is a generative AI model optimized for answer generation.

[0286] Step 4:

[0287] The terminal receives a question entered by the user. Specifically, the user enters the question into a form using a web browser or a dedicated application, and then sends the data to the server. The input is the text question entered by the user, and the output is an HTTP POST request sent to the server.

[0288] Step 5:

[0289] The device collects and analyzes the user's emotional data. Specifically, it uses a webcam and microphone to collect the user's facial expressions and voice, and performs emotional analysis using Azure Cognitive Services and Google Cloud's Natural Language API. The input is image and audio data collected in real time, and the output is text data representing the results of the emotional analysis. This data is also sent to the server.

[0290] Step 6:

[0291] The server receives the user's question and emotion data and generates an answer to the question using a generative AI model. Specifically, the user's question is input to the generative AI model as a prompt sentence, and the answer obtained from the model is obtained. The input is the user's question and the emotion analysis results, and the output is the answer text obtained from the generative AI model.

[0292] Step 7:

[0293] The server adjusts the answer based on the emotional data. Specifically, it modifies the generated answer text to soften the tone and be more considerate according to the results of the emotional analysis. The input is the answer obtained from the generative AI model and the results of the emotional analysis, and the output is the adjusted answer text.

[0294] Step 8:

[0295] The terminal displays the adjusted answer to the user. Specifically, it dynamically generates an HTML format from the text received from the server and displays it on the user's display. The input is the adjusted answer text, and the output is the answer displayed to the user.

[0296] (Application example 2)

[0297] 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."

[0298] Losing knowledge about the work and projects that former employees were in charge of is a major problem for companies. Particularly in on-site areas such as logistics centers, the experience and know-how of former employees is directly linked to operational efficiency and problem-solving. However, it is difficult to pass on the knowledge of former employees to successors, which can result in delays and errors. Furthermore, when on-site staff have questions about work or processes, they often cannot quickly obtain appropriate answers. Furthermore, a system is needed that reduces the stress staff feel when seeking answers and allows them to carry out their work more comfortably.

[0299] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0300] In this invention, the server includes means for collecting and storing information related to the work and projects that the former employee was in charge of in a database, means for performing text analysis of the collected information and extracting keywords and important phrases, means for training a generative AI model based on the extracted keywords and phrases, means for accepting user questions and answering the questions using the generative AI model, and means for recognizing the user's emotions and adjusting the answers of the generative AI model based on the emotions. This allows the knowledge of the former employee to be efficiently organized, enabling logistics center staff to obtain quick and appropriate answers. Providing answers that take emotions into consideration can prevent work delays and errors and reduce staff stress.

[0301] "Ex-employees" are former employees who have left a company or organization.

[0302] "Business" refers to the specific work or tasks that a company or organization performs to achieve its goals.

[0303] A "project" is a set of planned tasks with a set deadline and deliverables that are designed to achieve a specific goal.

[0304] "Information" refers to data, knowledge, know-how, etc. related to business or projects.

[0305] A "database" is a digital recording system that organizes and stores information so that it can be easily retrieved.

[0306] "Text analysis" is the technology of processing text written in natural language and extracting meaningful patterns and information.

[0307] "Keywords" are important words or phrases extracted through text analysis.

[0308] A "generative AI model" is an algorithm trained using artificial intelligence that generates new data and answers based on accumulated information.

[0309] "Emotion recognition" is a technology that analyzes a user's emotions from their facial expressions, voice, and text, and identifies their state.

[0310] "Response adjustment" refers to the process of changing the tone and expression of the generated response based on the user's emotional data obtained through emotion recognition.

[0311] This invention is a system that effectively utilizes information about work and projects held by former employees at a logistics center, enabling on-site staff to receive prompt and appropriate answers. This system consists of four main components: a server, terminals, users, and an emotion engine.

[0312] server

[0313] The server first collects information related to the work and projects that the former employee was in charge of and stores it in a database. At the same time, it adds metadata to the information to facilitate organization and subsequent searches. Next, it uses technology to analyze the collected information and extract keywords and important phrases from the text. This analysis uses natural language processing (NLP) technology. For example, it uses Python's Transformers library to train a generative AI model. The trained model runs on the server and provides quick and appropriate answers to user questions.

[0314] Terminal

[0315] The terminal provides an interface for logistics center staff to input questions and send them to the server. This interface uses a smartphone. When a user inputs a question, the terminal collects the question and also the user's emotional data. This emotional data is analyzed from the user's facial expressions, voice, and text content.

[0316] Emotion Engine

[0317] The emotion engine analyzes the user's emotional data sent from the device and adjusts the generative AI model's responses based on that data. For example, if the user is feeling stressed, the tone and content of the response will be adjusted to be gentler. This allows the user to receive the response without feeling stressed.

[0318] User

[0319] Using this system, users input questions related to the operations and processes of the logistics center. For example, when a question is input, such as "Please tell me the progress of the new shipping process," the question and the user's emotional data are sent to the server. The server queries the question with a generative AI model and generates an appropriate answer. The emotion engine adjusts the answer according to the user's emotion and sends the answer back to the terminal.

[0320] Specific examples

[0321] When a logistics center employee asks about the progress of the new shipping process, the following prompt is used:

[0322] Q: How is the new shipping process progressing?

[0323] Emotion detected: Stress

[0324] Context: Historical data and process information from your distribution center

[0325] A: Don't worry, we've checked and the new shipping process is currently in its second phase and is 80% complete.

[0326] In this way, the system of the present invention efficiently organizes the knowledge of former employees, allowing logistics center staff to quickly and accurately access the information they need. Furthermore, by using an emotion engine, it is possible to provide appropriate answers that take into consideration the user's emotions, thereby preventing work delays and errors.

[0327] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0328] Step 1:

[0329] Gather information related to the tasks and projects the former employee was involved in.

[0330] The server collects information about the work and projects of former employees and stores it in a database. Specifically, it obtains data from interview sheets, work reports, and project management tools. The server adds metadata to the collected information, allowing for efficient searching and organization.

[0331] Input: Interview sheets, work reports, project management tools

[0332] Output: A database containing the information along with metadata

[0333] Step 2:

[0334] The collected information is subjected to text analysis to extract keywords and important phrases.

[0335] The server uses natural language processing (NLP) techniques to analyze the information in the database, such as using Python's Transformers library to process the text and extract key keywords and phrases, providing the data needed to train the generative AI model.

[0336] Input: Information in the database

[0337] Output: Extracted keywords and important phrases

[0338] Step 3:

[0339] A generative AI model is trained based on the extracted keywords and phrases.

[0340] The server trains a generative AI model based on the extracted keywords and phrases. This training process uses past data to optimize the model's performance. The machine learning algorithm is implemented using Python's Transformers library.

[0341] Input: Extracted keywords or phrases

[0342] Output: A trained generative AI model

[0343] Step 4:

[0344] The user inputs a question into the terminal and sends it to the server.

[0345] Users use their smartphones to input questions about the operations and processes of the logistics center. The questions are sent from the device to the server, and emotion data is also collected. For example, voice input and text input are possible, and the emotion engine analyzes the user's facial expressions, voice, and text content.

[0346] Input: User questions, emotion data

[0347] Output: Questions and sentiment data sent to the server

[0348] Step 5:

[0349] The server uses a generative AI model to generate answers to questions.

[0350] The server passes the question sent by the user to the generative AI model, which generates an appropriate answer based on past data. This allows for quick and accurate answers to the user's questions. For example, in response to the question "What is the progress of the new shipping process?", a specific answer such as "The new shipping process is currently in its second phase and is 80% complete" is generated.

[0351] Input: User question

[0352] Output: The generated answer

[0353] Step 6:

[0354] An emotion engine adjusts the generated answers based on the user's emotions.

[0355] The server uses an emotion engine to analyze the user's emotional data and adjust the generated responses accordingly. For example, if the user is feeling stressed, the server will change the tone and content of the response to be gentler.

[0356] Input: User emotion data, generated answers

[0357] Output: Adjusted answer

[0358] Step 7:

[0359] The server sends the adjusted answer to the terminal for display to the user.

[0360] The server returns the adjusted answer to the device and displays it to the user, who can then view the emotion-sensitive answer through the device interface.

[0361] Input: Adjusted Answer

[0362] Output: Answer displayed on terminal

[0363] Examples:

[0364] Q: How is the new shipping process progressing?

[0365] Emotion detected: Stress

[0366] Context: Historical data and process information from your distribution center

[0367] A: Don't worry, we've checked and the new shipping process is currently in its second phase and is 80% complete.

[0368]

[0369] 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.

[0370] 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.

[0371] 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.

[0372] [Second embodiment]

[0373] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0374] 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.

[0375] 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).

[0376] 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.

[0377] 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.

[0378] 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).

[0379] 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.

[0380] 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.

[0381] 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.

[0382] 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.

[0383] 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.

[0384] 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."

[0385] This invention relates to a system that collects information related to the work and projects that former employees were in charge of, analyzes the text, and trains a generative AI model to quickly and appropriately answer questions from users. This system consists of three main components: a server, a terminal, and a user.

[0386] server

[0387] The server first collects information related to the work and projects that the former employee was in charge of. The collected information is then stored in a database. The collected information is then analyzed using natural language processing technology to extract keywords and important phrases. A generative AI model learns from this extracted information. This model is then used to generate appropriate answers to user questions.

[0388] Terminal

[0389] The terminal is the interface through which the user inputs questions and sends them to the server. The terminal also formats the questions input by the user and sends them to the server. It also plays a role in displaying the answers returned by the server to the user. In this way, the terminal is a tool for facilitating communication between the user and the server.

[0390] User

[0391] Users use the system to enter questions related to their work and receive appropriate answers. For example, if a user wants to know the progress of a promotional campaign for a new product, they enter that specific question into their terminal. When they press the send button, the question is sent from the terminal to the server.

[0392] The server receives the question, uses the generative AI model to generate the optimal answer, and sends this answer back to the device. The device then displays the answer to the user, who can then use it to carry out tasks or solve problems.

[0393] Specific examples

[0394] Let's say Tanaka from the marketing department wants to check the status of a new product promotion campaign. Tanaka types "Please tell me about the progress of the new product promotion campaign" into the interface on his device and clicks the send button. The question is sent from the device to the server, which queries the question with the generative AI model. The generative AI model generates an appropriate answer based on information related to past promotional campaigns, and returns an answer such as "The new product promotion campaign is currently in its third phase and is 70% complete" to Tanaka's device. Tanaka can then review the displayed answer and plan the next steps for his work.

[0395] In this way, the system of the present invention effectively organizes the knowledge possessed by former employees and allows them to access the necessary information quickly and accurately, thereby avoiding delays and errors in work.

[0396] The processing flow will be explained below.

[0397] Step 1:

[0398] The server collects documents, emails, chat logs, and other information related to the work and projects that former employees were in charge of. This information collection is done periodically using automated scripts and APIs.

[0399] Step 2:

[0400] The server stores the collected information in a database, and when storing it, it adds metadata to each piece of information to make it easier to organize and search for the information later.

[0401] Step 3:

[0402] The server performs text analysis of the stored information, using tools that use natural language processing technology to perform morphological and grammatical analysis.

[0403] Step 4:

[0404] The server extracts keywords and important phrases from the results of text analysis, which are then used to train the generative AI model.

[0405] Step 5:

[0406] The server then trains the generative AI model with the extracted information, a process that improves its ability to recognize patterns and rules from past data and generate appropriate answers to questions.

[0407] Step 6:

[0408] The user inputs a business-related question into the terminal interface. For example, if the user wants to check the progress of a promotional campaign for a new product, the user inputs a specific question.

[0409] Step 7:

[0410] The terminal sends the user-entered question to the server, where the question is formatted using a protocol such as an HTTP request.

[0411] Step 8:

[0412] The server receives the question from the terminal and analyzes the content of the question using natural language processing technology.

[0413] Step 9:

[0414] The server then queries the generative AI model based on the analysis results, and the model uses the learned data to generate an appropriate answer.

[0415] Step 10:

[0416] The server then returns the generated answer to the device in a data format such as JSON or XML.

[0417] Step 11:

[0418] The terminal displays the answer received from the server on the user interface in a format that is easily understandable to the user.

[0419] Step 12:

[0420] Users can review the displayed answers and use them to complete tasks or solve problems, for example, to plan the next steps for a sales campaign based on the information provided.

[0421] Example 1

[0422] 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."

[0423] When an employee in charge of an important task or project leaves a company, the loss of that knowledge and information can disrupt business continuity. In particular, if the employee was performing tasks that require specific knowledge and experience, such as project management or marketing activities, it can be difficult for the new employee who takes over to smoothly adapt and continue performing those tasks. This also increases the likelihood of operational delays and errors, so there is a need for a method to efficiently collect and analyze information and obtain the necessary information quickly and accurately.

[0424] 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.

[0425] In this invention, the server includes means for collecting and storing information related to the work and projects that former employees were in charge of in a database, means for analyzing the collected information using natural language processing technology and extracting keywords and important phrases, means for training a generative AI model based on the extracted keywords and phrases, means for accepting questions from users and answering the questions using the generative AI model, means for formatting the questions from users using a terminal and sending them to the server, and means for displaying the answers returned from the server to the user on the terminal. This makes it possible to efficiently collect and analyze the knowledge and information held by former employees and quickly and accurately access the necessary information.

[0426] "Ex-employees" refers to employees who have left the company.

[0427] "Work" refers to specific job functions and routine tasks within a company.

[0428] A "project" is a set of activities designed to achieve a specific purpose.

[0429] "Information" refers to a collection of general knowledge such as data, knowledge, reports, emails, etc.

[0430] A "database" refers to a system for organizing and storing collected information.

[0431] "Natural language processing technology" refers to the technology that allows computers to understand and analyze human language.

[0432] "Keywords" refer to important words or phrases within a document.

[0433] A "phrase" refers to a group of words that have meaning and are made up of multiple words.

[0434] A "generative AI model" refers to a model that uses artificial intelligence to generate text and answer questions.

[0435] A "question" refers to a query entered by a user seeking specific information.

[0436] "Answer" refers to the information provided by a generative AI model in response to a question.

[0437] "Terminal" refers to a device through which a user accesses the system and inputs questions.

[0438] "User" refers to the employees and personnel who use this system.

[0439] "Formalization" refers to the process of converting an input question into a certain format.

[0440] "Server" refers to a computer that performs the main processing of the entire system.

[0441] Including "communication" refers to the process of sending and receiving information or data.

[0442] "Interface" refers to the means by which a user interacts with a system.

[0443] This invention relates to a system that collects information related to the work and projects that former employees were in charge of, analyzes the text, and trains a generative AI model to quickly and appropriately answer questions from users. This system consists of three main components: a server, a terminal, and a user.

[0444] server

[0445] The server has the function of collecting information related to the work and projects of former employees. The information is obtained from the company's document management system and mail server and stored in a database such as MongoDB. The data is then analyzed using natural language processing technologies such as SpaCy and NLTK to extract keywords and important phrases. This extracted information is used to train a generative AI model (e.g., OpenAI's GPT-4). This generative AI model is responsible for generating appropriate answers to user questions. The server also trains the generative AI model using TensorFlow and PyTorch.

[0446] Terminal

[0447] The terminal is an interface through which the user inputs a question and sends it to the server. The terminal can operate as a web browser, desktop application, or mobile application. For example, the web application is implemented using "React.js" and has a question input field and a submit button. The question input by the user is formatted by the terminal and sent to the server via "REST API." The answer returned from the server is also displayed to the user on the terminal.

[0448] User

[0449] Users use their devices to input questions related to their work and receive appropriate answers. For example, if a marketing department employee wants to know the progress of a new product promotion campaign, they can input "Please tell me about the progress of the new product promotion campaign" into their device and send it. The question is sent from the device to the server and queried by the generative AI model. The generative AI model generates an appropriate answer based on information related to past promotional campaigns, and returns an answer such as "The new product promotion campaign is currently in its third phase and is 70% complete" to the user's device. The user can use this information to plan the next steps in their work.

[0450] Specific examples

[0451] An example of a prompt phrase used is, "Please tell me about the progress of the promotional campaign for the new product." The system uses a generative AI model to generate an answer to this question and displays it to the user on the device. In this way, the knowledge and information possessed by former employees can be efficiently organized, allowing users to access the information they need quickly and accurately, thereby avoiding work delays and errors.

[0452] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0453] Step 1: Gather information

[0454] The server collects information related to the former employee's work and projects, specifically reports, emails, and project management tool data from the company's document management system and email server.

[0455] Input: Document management system, mail server

[0456] Output: Retrieved work and project-related information (text format)

[0457] Step 2: Saving to the database

[0458] The server stores the collected information in a database such as MongoDB, which allows the data to be systematically managed for later analysis and retrieval.

[0459] Input: Work and project related information captured

[0460] Output: Information stored in the database

[0461] Step 3: Natural Language Processing Analysis

[0462] The server uses natural language processing techniques (e.g., SpaCy, NLTK) to analyze the stored information, specifically extracting keywords and important phrases from the text.

[0463] Input: Information stored in a database

[0464] Output: Extracted keywords and important phrases

[0465] Step 4: Training the generative AI model

[0466] The server trains a generative AI model (e.g., OpenAI's GPT-4) based on the extracted keywords and phrases. During this process, the model is trained using a machine learning framework (e.g., TensorFlow, PyTorch).

[0467] Input: Extracted keywords or key phrases

[0468] Output: Trained generative AI model

[0469] Step 5: Enter and format your question

[0470] The user uses the device to enter a question, which is then formatted and sent to the server via a REST API request. Specifically, the user enters a question in a text box and clicks the submit button.

[0471] Input: Question from the user (prompt sentence)

[0472] Output: Formatted question (HTTP request)

[0473] Step 6: Submit and receive your question

[0474] The device sends a formulated question to the server, which accepts the question and prepares the data to query the generative AI model.

[0475] Input: A formatted question (HTTP request)

[0476] Output: The question sent to the server

[0477] Step 7: Generate an answer

[0478] The server uses the generative AI model to generate the optimal answer for the received question. Specifically, the server automatically creates an answer based on the question entered into the generative AI model.

[0479] Input: The question sent to the server

[0480] Output: The generated answer

[0481] Step 8: Return and view your responses

[0482] The server returns the generated answer to the terminal, which then displays the received answer to the user. Specifically, the generated answer is displayed on the user interface.

[0483] Input: Generated answer (HTTP response)

[0484] Output: Answer displayed on terminal

[0485] Step 9: What happens next for the user?

[0486] Based on the displayed answers, users can plan and execute the next steps in their business. For example, they can decide on the next marketing strategy based on the answers.

[0487] Input: Answer displayed on the terminal

[0488] Output: User's action plan

[0489] In this way, each component of the system works together to carry out processing and provide users with prompt and appropriate information.

[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] There is a problem that valuable knowledge about the work and projects that former employees were in charge of is not passed on, resulting in delays and errors by remaining employees.In addition, information on transaction history and payment status for electronic payment services needs to be provided quickly and appropriately.A system is needed to solve these problems and ensure work efficiency and transparency in the payment process.

[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 collecting and storing information related to the work and projects that former employees were in charge of in a database, means for performing text analysis of the collected information and extracting keywords and important phrases, means for training a generative AI model based on the extracted keywords and phrases, means for providing appropriate answers based on information including transaction history and payment status related to electronic payments, and means for accepting questions from users and answering the questions using the generative AI model. This makes it possible to effectively utilize the knowledge of former employees, speed up operations, and improve the efficiency of information provision in the electronic payment process.

[0495] "Ex-employees" are employees who have left a particular company or organization.

[0496] "Work" refers to the specific work or tasks that an employee is responsible for within an organization or company.

[0497] A "project" is a set of planned activities to achieve a specific purpose within a certain period of time.

[0498] "Information" refers to data and knowledge related to a business or project.

[0499] A "database" is a system that centrally stores and manages various types of data.

[0500] "Text analysis" is a technique for extracting and analyzing specific information from text data.

[0501] "Keywords" are words or phrases that play an important role in a piece of text.

[0502] A "generative AI model" is an artificial intelligence that uses machine learning technology to automatically generate appropriate answers to questions.

[0503] "Electronic payment" refers to payment transactions conducted over the Internet or electronic devices.

[0504] "Transaction History" means a record of past payment activity and transactions.

[0505] "Payment Status" means the progress or completion state of a particular payment activity.

[0506] An "answer" is the information that a generative AI model outputs in response to a user's question.

[0507] "User" refers to an individual or organization that uses the system to ask a question.

[0508] "Server" means a computer system for collecting, analyzing, storing data, and running the generative AI model.

[0509] A "question" is a query that a user enters into the system to obtain specific information.

[0510] Explanation of program processing

[0511] Hardware and Software Use

[0512] server:

[0513] Hardware: The server uses a high-performance computer system to store and analyze the collected information and train the generative AI model.

[0514] Software: The server uses Python and natural language processing libraries such as Hugging Face Transformers. Specifically, the generative AI model is trained using the "deepset / roberta-base-squad2" model.

[0515] Device:

[0516] Hardware: The device, such as a smartphone or computer, used by the user to enter the question.

[0517] Software: A user interface for entering questions and an application for displaying answers from the server.

[0518] User:

[0519] Users use their devices to input questions, which are then sent to a server where a generative AI model generates an answer.

[0520] Data processing and calculation

[0521] The server first collects information related to the former employee's work and projects and stores it in a database. Next, the information is analyzed using natural language processing technology to extract keywords and important phrases. A generative AI model is trained based on this analyzed information.

[0522] The user's question is sent to the server via the device, and the server generates an answer using the generative AI model. The generated answer is then sent back to the device and displayed to the user.

[0523] Specific examples

[0524] Suppose a user asks, "What is the payment status of transaction ID: 12345?" The server extracts information such as transaction history and payment status from the database, and uses a generative AI model to generate an answer such as, "The current status of transaction ID: 12345 is complete. All approval processes have been completed." The answer is sent to the terminal and displayed to the user.

[0525] Prompt Sentence Examples

[0526] An example of a prompt entered by a user:

[0527] "What is the payment status for transaction ID: 12345?"

[0528] This invention effectively transfers the knowledge of former employees and trains it in a generative AI model, enabling users to quickly and accurately obtain information. It can also respond to specific questions about electronic payments, improving work efficiency and transparency in the payment process.

[0529] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0530] Step 1:

[0531] The server collects and stores in a database information related to the former employee's work and projects, including detailed project progress reports, transaction history, payment status, etc. The input data are documents, reports, and database entries, and the output is structured data that can be used for analysis and to train generative AI models.

[0532] Step 2:

[0533] The server uses natural language processing (NLP) techniques to analyze the collected information and extract keywords and important phrases. The input is raw information about tasks and projects stored in a database. The output is the analysis results, including keywords and important phrases. Specific NLP libraries (e.g., SpaCy and NLTK) are used to process the data.

[0534] Step 3:

[0535] The server trains a generative AI model (e.g., Hugging Face's "deepset / roberta-base-squad2") based on the text analysis results. The input is the key information extracted in step 2. The output is a generative AI model that can appropriately respond to the user's question. This generative AI model is trained using a large amount of text data to improve the accuracy of the model.

[0536] Step 4:

[0537] A user inputs a question using a device (such as a smartphone or computer). The device interface formats the question from the user and sends it to the server. The input is the user's question (prompt), and the output is the transfer of formatted data to the server.

[0538] Step 5:

[0539] The server inputs the received question into the generative AI model to generate an appropriate answer. The input is the question from the user, and the output is the answer generated by the generative AI model. The generative AI model analyzes related information in a database based on the question content and generates an answer that is useful to the user.

[0540] Step 6:

[0541] The server sends the generated answer to the terminal. The input is the generated answer, and the output is the transfer of the answer information to the terminal.

[0542] Step 7:

[0543] The terminal displays the answer received from the server to the user. The input is the answer information provided by the server, and the output is the answer displayed for the user on the terminal screen. This allows the user to quickly and accurately obtain the information they need, such as the progress of work or projects, or the payment status of transactions.

[0544] 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.

[0545] This invention relates to a system that collects information related to the work and projects that former employees were in charge of, analyzes the text, and trains a generative AI model to quickly and appropriately answer questions from users. This system consists of four main components: a server, a terminal, a user, and an emotion engine that recognizes the user's emotions.

[0546] server

[0547] The server first collects information related to the work and projects that the former employee was in charge of. The collected information is then stored in a database. When storing the information, metadata is added to each piece of information to facilitate organization and subsequent retrieval. The collected information is then analyzed using natural language processing technology to extract keywords and important phrases. A generative AI model trains based on this extracted information. This model is then used to generate appropriate answers to user questions.

[0548] Terminal

[0549] The terminal serves as an interface through which the user can input questions and send them to the server. It also simultaneously collects emotional data when the user asks a question. Emotional data is analyzed from the user's facial expression, tone of voice, and text content. The terminal formats the questions and emotional data input by the user and sends them to the server. It also plays a role in displaying the answers returned by the server to the user.

[0550] Emotion Engine

[0551] The emotion engine has the ability to analyze the user's emotions and adjust the generative AI model's responses based on that. Emotional data is analyzed in real time, and if the user is feeling stressed, for example, the tone and content of the response will be softened.

[0552] User

[0553] Users can use the system to input questions related to their work and receive appropriate answers. The device also automatically collects the emotions expressed at the time of the question. For example, if a user wants to know the progress of a new product promotion campaign and is feeling stressed, they can input that specific question and receive an answer that takes those emotions into consideration.

[0554] Specific examples

[0555] Suppose that Tanaka from the marketing department wants to check the status of a promotional campaign for a new product. He types "Please tell me about the progress of the promotional campaign for the new product" into the interface on his device. If the emotion engine detects stress while Tanaka is typing this question, the device will send the question to the server based on this emotion data.

[0556] The server queries the question to the AI ​​model, which generates an appropriate answer based on information related to past promotional campaigns. For example, the generated answer might be, "The promotional campaign for the new product is currently in its third phase and is 70% complete." The emotion engine then performs additional processing to soften the tone and content of the answer to reduce Tanaka's stress.

[0557] The server then adapts the generated answer to Tanaka's emotions and sends it back to his device. Tanaka's device displays the answer, allowing him to check the necessary information without feeling stressed.

[0558] In this way, the system of the present invention not only efficiently organizes the knowledge possessed by former employees and allows them to access the necessary information quickly and accurately, but also provides answers that take the user's emotions into consideration, thereby further preventing work delays and errors.

[0559] The processing flow will be explained below.

[0560] Step 1:

[0561] The server collects documents, emails, chat logs, and other information related to the work and projects that former employees were in charge of. This information collection is done periodically using automated scripts and APIs.

[0562] Step 2:

[0563] The server stores the collected information in a database, and when storing it, it adds metadata to each piece of information to make it easier to organize and search for the information later.

[0564] Step 3:

[0565] The server performs text analysis of the stored information, using tools that use natural language processing technology to perform morphological and grammatical analysis.

[0566] Step 4:

[0567] The server extracts keywords and important phrases from the results of text analysis, which are then used to train the generative AI model.

[0568] Step 5:

[0569] The server trains the generative AI model based on the extracted information, a process that improves its ability to recognize patterns and rules from past data and generate appropriate answers to questions.

[0570] Step 6:

[0571] The user inputs a business-related question into the terminal interface. For example, if the user wants to check the progress of a promotional campaign for a new product, the user inputs that specific question.

[0572] Step 7:

[0573] In addition to the user's input, the device uses facial expression recognition and voice analysis to obtain emotional data about the user. It analyzes the user's emotional state when entering a question and collects emotional data such as stress, joy, and confusion.

[0574] Step 8:

[0575] The device sends the collected questions and emotion data to the server, where the data is formatted using a protocol such as an HTTP request.

[0576] Step 9:

[0577] The server receives the question and emotion data from the device and analyzes the content of the question using natural language processing technology.

[0578] Step 10:

[0579] The server then queries the generative AI model based on the analysis results, and the model uses the learned data to generate an appropriate answer.

[0580] Step 11:

[0581] The emotion engine analyzes the user's emotional data and adjusts the tone and content of the generated response. For example, if the user is feeling stressed, the tone of the response will be softened.

[0582] Step 12:

[0583] The server adjusts the generated answers using the emotion engine and then sends them back to the device in a data format such as JSON or XML.

[0584] Step 13:

[0585] The terminal displays the adjusted answers received from the server on a user interface in a format that is easily understandable to the user.

[0586] Step 14:

[0587] Users can review the displayed answers and use them to carry out tasks or solve problems, and can use the information they need to plan the next steps in their sales campaigns.

[0588] Example 2

[0589] 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."

[0590] In modern companies, the loss of important knowledge and information held by employees who leave the company is a major problem. While there is also a need to quickly and appropriately retrieve work-related information, insufficient access can lead to reduced work efficiency and errors. Furthermore, it is important to consider the user's emotions when retrieving information, and it is desirable to receive answers without feeling stressed. A system that solves these problems is needed.

[0591] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting and storing information related to the work and projects that the former employee was in charge of in a database, means for performing text analysis of the collected information and extracting keywords and important phrases, means for training a generative AI model based on the extracted keywords and phrases, means for accepting questions from users and answering the questions using the generative AI model, means for collecting and analyzing user emotion data, and means for adjusting the generated answers based on the analyzed emotion data. This makes it possible to effectively store and utilize the knowledge and information of former employees, provide appropriate answers when users ask questions, and respond in a way that takes the user's emotions into consideration.

[0592] "Ex-employees" refer to former employees who have left a company or organization.

[0593] "Work" refers to the tasks and responsibilities performed within a company or organization.

[0594] A "project" is a set of activities or tasks planned to achieve a specific purpose.

[0595] "Information" refers to data and knowledge related to a business or project.

[0596] A "database" refers to a system for organizing and storing information.

[0597] "Text analytics" refers to the process of analyzing natural language text and extracting useful information from it.

[0598] "Keywords" are words or phrases that are particularly important in a piece of text.

[0599] A "phrase" is an expression made up of multiple words that have a specific meaning.

[0600] A "generative AI model" refers to an artificial intelligence model that uses machine learning algorithms to generate output from input data.

[0601] "User" refers to a person who uses the system.

[0602] A "question" refers to an action in which a user asks the system for information they want to know.

[0603] "Emotional data" refers to various data that indicate the user's emotional state (facial expressions, tone of voice, text content, etc.).

[0604] "Analysis" refers to the process of examining the contents of data to extract specific information.

[0605] "Adjustment" refers to the act of changing content or methods to suit specific conditions.

[0606] A "system" refers to a mechanism in which multiple components work together to achieve a set of functions.

[0607] "Metadata" refers to data that provides information about other data.

[0608] "Natural language processing technology" refers to computer science technology for understanding, interpreting, and generating human language.

[0609] In this invention, the server, terminal, and user components cooperate to collect and analyze the knowledge and information possessed by former employees, and provide a system that uses a generative AI model to provide appropriate answers to user questions.

[0610] server

[0611] The server automatically collects information related to the work and projects that former employees were in charge of. This information is collected from sources such as network communications, emails, and internal chats. Programming languages ​​such as Python, web scraping technology, and APIs are used to collect the information. The collected information is stored in a database such as MySQL along with metadata.

[0612] The server then analyzes the collected information using natural language processing techniques (e.g., Python's NLTK or spaCy) to extract keywords and important phrases. This information is used to train a generative AI model (e.g., OpenAI's GPT-3). The server then optimizes the generative AI model using a deep learning framework (e.g., TensorFlow or PyTorch).

[0613] Terminal

[0614] The device provides an interface for users to interact with the system. Users type questions into the device, and the data is sent to the server. The device is equipped with a webcam and microphone to collect the user's facial expressions and tone of voice in real time. This emotional data is analyzed using Azure Cognitive Services and Google Cloud's Natural Language API.

[0615] Emotion Engine

[0616] The emotion engine analyzes collected emotion data in real time to understand the user's emotional state. It uses libraries such as OpenCV and TensorFlow for emotion analysis and adjusts the output of the generative AI model based on the analysis results. This adjustment results in softer responses if the user is feeling stressed.

[0617] User

[0618] Users can input questions related to their work into the terminal interface and receive appropriate answers from the server. For example, a user might ask, "Please tell me about the progress of the promotional campaign for a new product." The user's input is then subjected to real-time emotion analysis to determine whether they are feeling stressed.

[0619] As a concrete example, if a member of the marketing department wants to check the progress of a promotional campaign for a new product, the user inputs the question "Please tell me about the progress of the promotional campaign for the new product" into the device. Along with this input information, the emotion engine analyzes the user's facial expressions and voice and sends the emotion data to the server. The server then sends the following prompt to the generative AI model:

[0620] Example prompt sentence:

[0621] Please tell us about the progress of the promotional campaign for the new product.

[0622] The server uses a generative AI model to generate an appropriate response and adjusts the response based on the analysis results of the emotion engine. For example, if the response generated is, "The promotional campaign for our new product is currently in its third phase and is 70% complete," the emotion engine softens the tone by adding, "Don't worry, everything is going smoothly."

[0623] In this way, the user can quickly and appropriately obtain the necessary information without feeling stressed. In this way, this invention is a system that effectively utilizes the knowledge and information of former employees and provides appropriate answers that take into consideration the feelings of the user.

[0624] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0625] Step 1:

[0626] The server collects information related to the work and projects that former employees were in charge of and stores it in a database. Specifically, it uses Python scripts to collect data from sources such as network communications, emails, and internal chats, and stores the data in a MySQL database. The collected data is assigned metadata such as date and time and related projects, allowing for efficient search and management. The input is text data obtained from each source, and the output is stored in the database as information with metadata.

[0627] Step 2:

[0628] The server performs text analysis of the stored information using natural language processing technology. Specifically, it uses Python's NLTK and spaCy to analyze the text data retrieved from the database and extract important keywords and phrases. The input is the text data stored in the database, and the output is the keywords and important phrases that are the analysis results. These results are then stored back in the database.

[0629] Step 3:

[0630] The server trains a generative AI model based on the extracted keywords and phrases. Specifically, it uses the extracted data to train a generative AI model (e.g., GPT-3) using a deep learning framework (e.g., TensorFlow or PyTorch). The input is a dataset consisting of keywords and important phrases, and the output is a generative AI model optimized for answer generation.

[0631] Step 4:

[0632] The terminal receives a question entered by the user. Specifically, the user enters the question into a form using a web browser or a dedicated application, and then sends the data to the server. The input is the text question entered by the user, and the output is an HTTP POST request sent to the server.

[0633] Step 5:

[0634] The device collects and analyzes the user's emotional data. Specifically, it uses a webcam and microphone to collect the user's facial expressions and voice, and performs emotional analysis using Azure Cognitive Services and Google Cloud's Natural Language API. The input is image and audio data collected in real time, and the output is text data representing the results of the emotional analysis. This data is also sent to the server.

[0635] Step 6:

[0636] The server receives the user's question and emotion data and generates an answer to the question using a generative AI model. Specifically, the user's question is input to the generative AI model as a prompt sentence, and the answer obtained from the model is obtained. The input is the user's question and the emotion analysis results, and the output is the answer text obtained from the generative AI model.

[0637] Step 7:

[0638] The server adjusts the answer based on the emotional data. Specifically, it modifies the generated answer text to soften the tone and be more considerate according to the results of the emotional analysis. The input is the answer obtained from the generative AI model and the results of the emotional analysis, and the output is the adjusted answer text.

[0639] Step 8:

[0640] The terminal displays the adjusted answer to the user. Specifically, it dynamically generates an HTML format from the text received from the server and displays it on the user's display. The input is the adjusted answer text, and the output is the answer displayed to the user.

[0641] (Application example 2)

[0642] 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."

[0643] Losing knowledge about the work and projects that former employees were in charge of is a major problem for companies. Particularly in on-site areas such as logistics centers, the experience and know-how of former employees is directly linked to operational efficiency and problem-solving. However, it is difficult to pass on the knowledge of former employees to successors, which can result in delays and errors. Furthermore, when on-site staff have questions about work or processes, they often cannot quickly obtain appropriate answers. Furthermore, a system is needed that reduces the stress staff feel when seeking answers and allows them to carry out their work more comfortably.

[0644] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0645] In this invention, the server includes means for collecting and storing information related to the work and projects that the former employee was in charge of in a database, means for performing text analysis of the collected information and extracting keywords and important phrases, means for training a generative AI model based on the extracted keywords and phrases, means for accepting user questions and answering the questions using the generative AI model, and means for recognizing the user's emotions and adjusting the answers of the generative AI model based on the emotions. This allows the knowledge of the former employee to be efficiently organized, enabling logistics center staff to obtain quick and appropriate answers. Providing answers that take emotions into consideration can prevent work delays and errors and reduce staff stress.

[0646] "Ex-employees" are former employees who have left a company or organization.

[0647] "Business" refers to the specific work or tasks that a company or organization performs to achieve its goals.

[0648] A "project" is a set of planned tasks with a set deadline and deliverables that are designed to achieve a specific goal.

[0649] "Information" refers to data, knowledge, know-how, etc. related to business or projects.

[0650] A "database" is a digital recording system that organizes and stores information so that it can be easily retrieved.

[0651] "Text analysis" is the technology of processing text written in natural language and extracting meaningful patterns and information.

[0652] "Keywords" are important words or phrases extracted through text analysis.

[0653] A "generative AI model" is an algorithm trained using artificial intelligence that generates new data and answers based on accumulated information.

[0654] "Emotion recognition" is a technology that analyzes a user's emotions from their facial expressions, voice, and text, and identifies their state.

[0655] "Response adjustment" refers to the process of changing the tone and expression of the generated response based on the user's emotional data obtained through emotion recognition.

[0656] This invention is a system that effectively utilizes information about work and projects held by former employees at a logistics center, enabling on-site staff to receive prompt and appropriate answers. This system consists of four main components: a server, terminals, users, and an emotion engine.

[0657] server

[0658] The server first collects information related to the work and projects that the former employee was in charge of and stores it in a database. At the same time, it adds metadata to the information to facilitate organization and subsequent searches. Next, it uses technology to analyze the collected information and extract keywords and important phrases from the text. This analysis uses natural language processing (NLP) technology. For example, it uses Python's Transformers library to train a generative AI model. The trained model runs on the server and provides quick and appropriate answers to user questions.

[0659] Terminal

[0660] The terminal provides an interface for logistics center staff to input questions and send them to the server. This interface uses a smartphone. When a user inputs a question, the terminal collects the question and also the user's emotional data. This emotional data is analyzed from the user's facial expressions, voice, and text content.

[0661] Emotion Engine

[0662] The emotion engine analyzes the user's emotional data sent from the device and adjusts the generative AI model's responses based on that data. For example, if the user is feeling stressed, the tone and content of the response will be adjusted to be gentler. This allows the user to receive the response without feeling stressed.

[0663] User

[0664] Using this system, users input questions related to the operations and processes of the logistics center. For example, when a question is input, such as "Please tell me the progress of the new shipping process," the question and the user's emotional data are sent to the server. The server queries the question with a generative AI model and generates an appropriate answer. The emotion engine adjusts the answer according to the user's emotion and sends the answer back to the terminal.

[0665] Specific examples

[0666] When a logistics center employee asks about the progress of the new shipping process, the following prompt is used:

[0667] Q: How is the new shipping process progressing?

[0668] Emotion detected: Stress

[0669] Context: Historical data and process information from your distribution center

[0670] A: Don't worry, we've checked and the new shipping process is currently in its second phase and is 80% complete.

[0671] In this way, the system of the present invention efficiently organizes the knowledge of former employees, allowing logistics center staff to quickly and accurately access the information they need. Furthermore, by using an emotion engine, it is possible to provide appropriate answers that take into consideration the user's emotions, thereby preventing work delays and errors.

[0672] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0673] Step 1:

[0674] Gather information related to the tasks and projects the former employee was involved in.

[0675] The server collects information about the work and projects of former employees and stores it in a database. Specifically, it obtains data from interview sheets, work reports, and project management tools. The server adds metadata to the collected information, allowing for efficient searching and organization.

[0676] Input: Interview sheets, work reports, project management tools

[0677] Output: A database containing the information along with metadata

[0678] Step 2:

[0679] The collected information is subjected to text analysis to extract keywords and important phrases.

[0680] The server uses natural language processing (NLP) techniques to analyze the information in the database, such as using Python's Transformers library to process the text and extract key keywords and phrases, providing the data needed to train the generative AI model.

[0681] Input: Information in the database

[0682] Output: Extracted keywords and important phrases

[0683] Step 3:

[0684] A generative AI model is trained based on the extracted keywords and phrases.

[0685] The server trains a generative AI model based on the extracted keywords and phrases. This training process uses past data to optimize the model's performance. The machine learning algorithm is implemented using Python's Transformers library.

[0686] Input: Extracted keywords or phrases

[0687] Output: A trained generative AI model

[0688] Step 4:

[0689] The user inputs a question into the terminal and sends it to the server.

[0690] Users use their smartphones to input questions about the operations and processes of the logistics center. The questions are sent from the device to the server, and emotion data is also collected. For example, voice input and text input are possible, and the emotion engine analyzes the user's facial expressions, voice, and text content.

[0691] Input: User questions, emotion data

[0692] Output: Questions and sentiment data sent to the server

[0693] Step 5:

[0694] The server uses a generative AI model to generate answers to questions.

[0695] The server passes the question sent by the user to the generative AI model, which generates an appropriate answer based on past data. This allows for quick and accurate answers to the user's questions. For example, in response to the question "What is the progress of the new shipping process?", a specific answer such as "The new shipping process is currently in its second phase and is 80% complete" is generated.

[0696] Input: User question

[0697] Output: The generated answer

[0698] Step 6:

[0699] An emotion engine adjusts the generated answers based on the user's emotions.

[0700] The server uses an emotion engine to analyze the user's emotional data and adjust the generated responses accordingly. For example, if the user is feeling stressed, the server will change the tone and content of the response to be gentler.

[0701] Input: User emotion data, generated answers

[0702] Output: Adjusted answer

[0703] Step 7:

[0704] The server sends the adjusted answer to the terminal for display to the user.

[0705] The server returns the adjusted answer to the device and displays it to the user, who can then view the emotion-sensitive answer through the device interface.

[0706] Input: Adjusted Answer

[0707] Output: Answer displayed on terminal

[0708] Examples:

[0709] Q: How is the new shipping process progressing?

[0710] Emotion detected: Stress

[0711] Context: Historical data and process information from your distribution center

[0712] A: Don't worry, we've checked and the new shipping process is currently in its second phase and is 80% complete.

[0713]

[0714] 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.

[0715] 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.

[0716] 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.

[0717] [Third embodiment]

[0718] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0719] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0720] 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).

[0721] 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.

[0722] 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.

[0723] 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).

[0724] 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.

[0725] 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.

[0726] 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.

[0727] 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.

[0728] 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.

[0729] 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."

[0730] This invention relates to a system that collects information related to the work and projects that former employees were in charge of, analyzes the text, and trains a generative AI model to quickly and appropriately answer questions from users. This system consists of three main components: a server, a terminal, and a user.

[0731] server

[0732] The server first collects information related to the work and projects that the former employee was in charge of. The collected information is then stored in a database. The collected information is then analyzed using natural language processing technology to extract keywords and important phrases. A generative AI model learns from this extracted information. This model is then used to generate appropriate answers to user questions.

[0733] Terminal

[0734] The terminal is the interface through which the user inputs questions and sends them to the server. The terminal also formats the questions input by the user and sends them to the server. It also plays a role in displaying the answers returned by the server to the user. In this way, the terminal is a tool for facilitating communication between the user and the server.

[0735] User

[0736] Users use the system to enter questions related to their work and receive appropriate answers. For example, if a user wants to know the progress of a promotional campaign for a new product, they enter that specific question into their terminal. When they press the send button, the question is sent from the terminal to the server.

[0737] The server receives the question, uses the generative AI model to generate the optimal answer, and sends this answer back to the device. The device then displays the answer to the user, who can then use it to carry out tasks or solve problems.

[0738] Specific examples

[0739] Let's say Tanaka from the marketing department wants to check the status of a new product promotion campaign. Tanaka types "Please tell me about the progress of the new product promotion campaign" into the interface on his device and clicks the send button. The question is sent from the device to the server, which queries the question with the generative AI model. The generative AI model generates an appropriate answer based on information related to past promotional campaigns, and returns an answer such as "The new product promotion campaign is currently in its third phase and is 70% complete" to Tanaka's device. Tanaka can then review the displayed answer and plan the next steps for his work.

[0740] In this way, the system of the present invention effectively organizes the knowledge possessed by former employees and allows them to access the necessary information quickly and accurately, thereby avoiding delays and errors in work.

[0741] The processing flow will be explained below.

[0742] Step 1:

[0743] The server collects documents, emails, chat logs, and other information related to the work and projects that former employees were in charge of. This information collection is done periodically using automated scripts and APIs.

[0744] Step 2:

[0745] The server stores the collected information in a database, and when storing it, it adds metadata to each piece of information to make it easier to organize and search for the information later.

[0746] Step 3:

[0747] The server performs text analysis of the stored information, using tools that use natural language processing technology to perform morphological and grammatical analysis.

[0748] Step 4:

[0749] The server extracts keywords and important phrases from the results of text analysis, which are then used to train the generative AI model.

[0750] Step 5:

[0751] The server then trains the generative AI model with the extracted information, a process that improves its ability to recognize patterns and rules from past data and generate appropriate answers to questions.

[0752] Step 6:

[0753] The user inputs a business-related question into the terminal interface. For example, if the user wants to check the progress of a promotional campaign for a new product, the user inputs a specific question.

[0754] Step 7:

[0755] The terminal sends the user-entered question to the server, where the question is formatted using a protocol such as an HTTP request.

[0756] Step 8:

[0757] The server receives the question from the terminal and analyzes the content of the question using natural language processing technology.

[0758] Step 9:

[0759] The server then queries the generative AI model based on the analysis results, and the model uses the learned data to generate an appropriate answer.

[0760] Step 10:

[0761] The server then returns the generated answer to the device in a data format such as JSON or XML.

[0762] Step 11:

[0763] The terminal displays the answer received from the server on the user interface in a format that is easily understandable to the user.

[0764] Step 12:

[0765] Users can review the displayed answers and use them to complete tasks or solve problems, for example, to plan the next steps for a sales campaign based on the information provided.

[0766] Example 1

[0767] 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."

[0768] When an employee in charge of an important task or project leaves a company, the loss of that knowledge and information can disrupt business continuity. In particular, if the employee was performing tasks that require specific knowledge and experience, such as project management or marketing activities, it can be difficult for the new employee who takes over to smoothly adapt and continue performing those tasks. This also increases the likelihood of operational delays and errors, so there is a need for a method to efficiently collect and analyze information and obtain the necessary information quickly and accurately.

[0769] 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.

[0770] In this invention, the server includes means for collecting and storing information related to the work and projects that former employees were in charge of in a database, means for analyzing the collected information using natural language processing technology and extracting keywords and important phrases, means for training a generative AI model based on the extracted keywords and phrases, means for accepting questions from users and answering the questions using the generative AI model, means for formatting the questions from users using a terminal and sending them to the server, and means for displaying the answers returned from the server to the user on the terminal. This makes it possible to efficiently collect and analyze the knowledge and information held by former employees and quickly and accurately access the necessary information.

[0771] "Ex-employees" refers to employees who have left the company.

[0772] "Work" refers to specific job functions and routine tasks within a company.

[0773] A "project" is a set of activities designed to achieve a specific purpose.

[0774] "Information" refers to a collection of general knowledge such as data, knowledge, reports, emails, etc.

[0775] A "database" refers to a system for organizing and storing collected information.

[0776] "Natural language processing technology" refers to the technology that allows computers to understand and analyze human language.

[0777] "Keywords" refer to important words or phrases within a document.

[0778] A "phrase" refers to a group of words that have meaning and are made up of multiple words.

[0779] A "generative AI model" refers to a model that uses artificial intelligence to generate text and answer questions.

[0780] A "question" refers to a query entered by a user seeking specific information.

[0781] "Answer" refers to the information provided by a generative AI model in response to a question.

[0782] "Terminal" refers to a device through which a user accesses the system and inputs questions.

[0783] "User" refers to the employees and personnel who use this system.

[0784] "Formalization" refers to the process of converting an input question into a certain format.

[0785] "Server" refers to a computer that performs the main processing of the entire system.

[0786] Including "communication" refers to the process of sending and receiving information or data.

[0787] "Interface" refers to the means by which a user interacts with a system.

[0788] This invention relates to a system that collects information related to the work and projects that former employees were in charge of, analyzes the text, and trains a generative AI model to quickly and appropriately answer questions from users. This system consists of three main components: a server, a terminal, and a user.

[0789] server

[0790] The server has the function of collecting information related to the work and projects of former employees. The information is obtained from the company's document management system and mail server and stored in a database such as MongoDB. The data is then analyzed using natural language processing technologies such as SpaCy and NLTK to extract keywords and important phrases. This extracted information is used to train a generative AI model (e.g., OpenAI's GPT-4). This generative AI model is responsible for generating appropriate answers to user questions. The server also trains the generative AI model using TensorFlow and PyTorch.

[0791] Terminal

[0792] The terminal is an interface through which the user inputs a question and sends it to the server. The terminal can operate as a web browser, desktop application, or mobile application. For example, the web application is implemented using "React.js" and has a question input field and a submit button. The question input by the user is formatted by the terminal and sent to the server via "REST API." The answer returned from the server is also displayed to the user on the terminal.

[0793] User

[0794] Users use their devices to input questions related to their work and receive appropriate answers. For example, if a marketing department employee wants to know the progress of a new product promotion campaign, they can input "Please tell me about the progress of the new product promotion campaign" into their device and send it. The question is sent from the device to the server and queried by the generative AI model. The generative AI model generates an appropriate answer based on information related to past promotional campaigns, and returns an answer such as "The new product promotion campaign is currently in its third phase and is 70% complete" to the user's device. The user can use this information to plan the next steps in their work.

[0795] Specific examples

[0796] An example of a prompt phrase used is, "Please tell me about the progress of the promotional campaign for the new product." The system uses a generative AI model to generate an answer to this question and displays it to the user on the device. In this way, the knowledge and information possessed by former employees can be efficiently organized, allowing users to access the information they need quickly and accurately, thereby avoiding work delays and errors.

[0797] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0798] Step 1: Gather information

[0799] The server collects information related to the former employee's work and projects, specifically reports, emails, and project management tool data from the company's document management system and email server.

[0800] Input: Document management system, mail server

[0801] Output: Retrieved work and project-related information (text format)

[0802] Step 2: Saving to the database

[0803] The server stores the collected information in a database such as MongoDB, which allows the data to be systematically managed for later analysis and retrieval.

[0804] Input: Work and project related information captured

[0805] Output: Information stored in the database

[0806] Step 3: Natural Language Processing Analysis

[0807] The server uses natural language processing techniques (e.g., SpaCy, NLTK) to analyze the stored information, specifically extracting keywords and important phrases from the text.

[0808] Input: Information stored in a database

[0809] Output: Extracted keywords and important phrases

[0810] Step 4: Training the generative AI model

[0811] The server trains a generative AI model (e.g., OpenAI's GPT-4) based on the extracted keywords and phrases. During this process, the model is trained using a machine learning framework (e.g., TensorFlow, PyTorch).

[0812] Input: Extracted keywords or key phrases

[0813] Output: Trained generative AI model

[0814] Step 5: Enter and format your question

[0815] The user uses the device to enter a question, which is then formatted and sent to the server via a REST API request. Specifically, the user enters a question in a text box and clicks the submit button.

[0816] Input: Question from the user (prompt sentence)

[0817] Output: Formatted question (HTTP request)

[0818] Step 6: Submit and receive your question

[0819] The device sends a formulated question to the server, which accepts the question and prepares the data to query the generative AI model.

[0820] Input: A formatted question (HTTP request)

[0821] Output: The question sent to the server

[0822] Step 7: Generate an answer

[0823] The server uses the generative AI model to generate the optimal answer for the received question. Specifically, the server automatically creates an answer based on the question entered into the generative AI model.

[0824] Input: The question sent to the server

[0825] Output: The generated answer

[0826] Step 8: Return and view your responses

[0827] The server returns the generated answer to the terminal, which then displays the received answer to the user. Specifically, the generated answer is displayed on the user interface.

[0828] Input: Generated answer (HTTP response)

[0829] Output: Answer displayed on terminal

[0830] Step 9: What happens next for the user?

[0831] Based on the displayed answers, users can plan and execute the next steps in their business. For example, they can decide on the next marketing strategy based on the answers.

[0832] Input: Answer displayed on the terminal

[0833] Output: User's action plan

[0834] In this way, each component of the system works together to carry out processing and provide users with prompt and appropriate information.

[0835] (Application example 1)

[0836] 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."

[0837] There is a problem that valuable knowledge about the work and projects that former employees were in charge of is not passed on, resulting in delays and errors by remaining employees.In addition, information on transaction history and payment status for electronic payment services needs to be provided quickly and appropriately.A system is needed to solve these problems and ensure work efficiency and transparency in the payment process.

[0838] 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.

[0839] In this invention, the server includes means for collecting and storing information related to the work and projects that former employees were in charge of in a database, means for performing text analysis of the collected information and extracting keywords and important phrases, means for training a generative AI model based on the extracted keywords and phrases, means for providing appropriate answers based on information including transaction history and payment status related to electronic payments, and means for accepting questions from users and answering the questions using the generative AI model. This makes it possible to effectively utilize the knowledge of former employees, speed up operations, and improve the efficiency of information provision in the electronic payment process.

[0840] "Ex-employees" are employees who have left a particular company or organization.

[0841] "Work" refers to the specific work or tasks that an employee is responsible for within an organization or company.

[0842] A "project" is a set of planned activities to achieve a specific purpose within a certain period of time.

[0843] "Information" refers to data and knowledge related to a business or project.

[0844] A "database" is a system that centrally stores and manages various types of data.

[0845] "Text analysis" is a technique for extracting and analyzing specific information from text data.

[0846] "Keywords" are words or phrases that play an important role in a piece of text.

[0847] A "generative AI model" is an artificial intelligence that uses machine learning technology to automatically generate appropriate answers to questions.

[0848] "Electronic payment" refers to payment transactions conducted over the Internet or electronic devices.

[0849] "Transaction History" means a record of past payment activity and transactions.

[0850] "Payment Status" means the progress or completion state of a particular payment activity.

[0851] An "answer" is the information that a generative AI model outputs in response to a user's question.

[0852] "User" refers to an individual or organization that uses the system to ask a question.

[0853] "Server" means a computer system for collecting, analyzing, storing data, and running the generative AI model.

[0854] A "question" is a query that a user enters into the system to obtain specific information.

[0855] Explanation of program processing

[0856] Hardware and Software Use

[0857] server:

[0858] Hardware: The server uses a high-performance computer system to store and analyze the collected information and train the generative AI model.

[0859] Software: The server uses Python and natural language processing libraries such as Hugging Face Transformers. Specifically, the generative AI model is trained using the "deepset / roberta-base-squad2" model.

[0860] Device:

[0861] Hardware: The device, such as a smartphone or computer, used by the user to enter the question.

[0862] Software: A user interface for entering questions and an application for displaying answers from the server.

[0863] User:

[0864] Users use their devices to input questions, which are then sent to a server where a generative AI model generates an answer.

[0865] Data processing and calculation

[0866] The server first collects information related to the former employee's work and projects and stores it in a database. Next, the information is analyzed using natural language processing technology to extract keywords and important phrases. A generative AI model is trained based on this analyzed information.

[0867] The user's question is sent to the server via the device, and the server generates an answer using the generative AI model. The generated answer is then sent back to the device and displayed to the user.

[0868] Specific examples

[0869] Suppose a user asks, "What is the payment status of transaction ID: 12345?" The server extracts information such as transaction history and payment status from the database, and uses a generative AI model to generate an answer such as, "The current status of transaction ID: 12345 is complete. All approval processes have been completed." The answer is sent to the terminal and displayed to the user.

[0870] Prompt Sentence Examples

[0871] An example of a prompt entered by a user:

[0872] "What is the payment status for transaction ID: 12345?"

[0873] This invention effectively transfers the knowledge of former employees and trains it in a generative AI model, enabling users to quickly and accurately obtain information. It can also respond to specific questions about electronic payments, improving work efficiency and transparency in the payment process.

[0874] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0875] Step 1:

[0876] The server collects and stores in a database information related to the former employee's work and projects, including detailed project progress reports, transaction history, payment status, etc. The input data are documents, reports, and database entries, and the output is structured data that can be used for analysis and to train generative AI models.

[0877] Step 2:

[0878] The server uses natural language processing (NLP) techniques to analyze the collected information and extract keywords and important phrases. The input is raw information about tasks and projects stored in a database. The output is the analysis results, including keywords and important phrases. Specific NLP libraries (e.g., SpaCy and NLTK) are used to process the data.

[0879] Step 3:

[0880] The server trains a generative AI model (e.g., Hugging Face's "deepset / roberta-base-squad2") based on the text analysis results. The input is the key information extracted in step 2. The output is a generative AI model that can appropriately respond to the user's question. This generative AI model is trained using a large amount of text data to improve the accuracy of the model.

[0881] Step 4:

[0882] A user inputs a question using a device (such as a smartphone or computer). The device interface formats the question from the user and sends it to the server. The input is the user's question (prompt), and the output is the transfer of formatted data to the server.

[0883] Step 5:

[0884] The server inputs the received question into the generative AI model to generate an appropriate answer. The input is the question from the user, and the output is the answer generated by the generative AI model. The generative AI model analyzes related information in a database based on the question content and generates an answer that is useful to the user.

[0885] Step 6:

[0886] The server sends the generated answer to the terminal. The input is the generated answer, and the output is the transfer of the answer information to the terminal.

[0887] Step 7:

[0888] The terminal displays the answer received from the server to the user. The input is the answer information provided by the server, and the output is the answer displayed for the user on the terminal screen. This allows the user to quickly and accurately obtain the information they need, such as the progress of work or projects, or the payment status of transactions.

[0889] 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.

[0890] This invention relates to a system that collects information related to the work and projects that former employees were in charge of, analyzes the text, and trains a generative AI model to quickly and appropriately answer questions from users. This system consists of four main components: a server, a terminal, a user, and an emotion engine that recognizes the user's emotions.

[0891] server

[0892] The server first collects information related to the work and projects that the former employee was in charge of. The collected information is then stored in a database. When storing the information, metadata is added to each piece of information to facilitate organization and subsequent retrieval. The collected information is then analyzed using natural language processing technology to extract keywords and important phrases. A generative AI model trains based on this extracted information. This model is then used to generate appropriate answers to user questions.

[0893] Terminal

[0894] The terminal serves as an interface through which the user can input questions and send them to the server. It also simultaneously collects emotional data when the user asks a question. Emotional data is analyzed from the user's facial expression, tone of voice, and text content. The terminal formats the questions and emotional data input by the user and sends them to the server. It also plays a role in displaying the answers returned by the server to the user.

[0895] Emotion Engine

[0896] The emotion engine has the ability to analyze the user's emotions and adjust the generative AI model's responses based on that. Emotional data is analyzed in real time, and if the user is feeling stressed, for example, the tone and content of the response will be softened.

[0897] User

[0898] Users can use the system to input questions related to their work and receive appropriate answers. The device also automatically collects the emotions expressed at the time of the question. For example, if a user wants to know the progress of a new product promotion campaign and is feeling stressed, they can input that specific question and receive an answer that takes those emotions into consideration.

[0899] Specific examples

[0900] Suppose that Tanaka from the marketing department wants to check the status of a promotional campaign for a new product. He types "Please tell me about the progress of the promotional campaign for the new product" into the interface on his device. If the emotion engine detects stress while Tanaka is typing this question, the device will send the question to the server based on this emotion data.

[0901] The server queries the question to the AI ​​model, which generates an appropriate answer based on information related to past promotional campaigns. For example, the generated answer might be, "The promotional campaign for the new product is currently in its third phase and is 70% complete." The emotion engine then performs additional processing to soften the tone and content of the answer to reduce Tanaka's stress.

[0902] The server then adapts the generated answer to Tanaka's emotions and sends it back to his device. Tanaka's device displays the answer, allowing him to check the necessary information without feeling stressed.

[0903] In this way, the system of the present invention not only efficiently organizes the knowledge possessed by former employees and allows them to access the necessary information quickly and accurately, but also provides answers that take the user's emotions into consideration, thereby further preventing work delays and errors.

[0904] The processing flow will be explained below.

[0905] Step 1:

[0906] The server collects documents, emails, chat logs, and other information related to the work and projects that former employees were in charge of. This information collection is done periodically using automated scripts and APIs.

[0907] Step 2:

[0908] The server stores the collected information in a database, and when storing it, it adds metadata to each piece of information to make it easier to organize and search for the information later.

[0909] Step 3:

[0910] The server performs text analysis of the stored information, using tools that use natural language processing technology to perform morphological and grammatical analysis.

[0911] Step 4:

[0912] The server extracts keywords and important phrases from the results of text analysis, which are then used to train the generative AI model.

[0913] Step 5:

[0914] The server trains the generative AI model based on the extracted information, a process that improves its ability to recognize patterns and rules from past data and generate appropriate answers to questions.

[0915] Step 6:

[0916] The user inputs a business-related question into the terminal interface. For example, if the user wants to check the progress of a promotional campaign for a new product, the user inputs that specific question.

[0917] Step 7:

[0918] In addition to the user's input, the device uses facial expression recognition and voice analysis to obtain emotional data about the user. It analyzes the user's emotional state when entering a question and collects emotional data such as stress, joy, and confusion.

[0919] Step 8:

[0920] The device sends the collected questions and emotion data to the server, where the data is formatted using a protocol such as an HTTP request.

[0921] Step 9:

[0922] The server receives the question and emotion data from the device and analyzes the content of the question using natural language processing technology.

[0923] Step 10:

[0924] The server then queries the generative AI model based on the analysis results, and the model uses the learned data to generate an appropriate answer.

[0925] Step 11:

[0926] The emotion engine analyzes the user's emotional data and adjusts the tone and content of the generated response. For example, if the user is feeling stressed, the tone of the response will be softened.

[0927] Step 12:

[0928] The server adjusts the generated answers using the emotion engine and then sends them back to the device in a data format such as JSON or XML.

[0929] Step 13:

[0930] The terminal displays the adjusted answers received from the server on a user interface in a format that is easily understandable to the user.

[0931] Step 14:

[0932] Users can review the displayed answers and use them to carry out tasks or solve problems, and can use the information they need to plan the next steps in their sales campaigns.

[0933] Example 2

[0934] 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."

[0935] In modern companies, the loss of important knowledge and information held by employees who leave the company is a major problem. While there is also a need to quickly and appropriately retrieve work-related information, insufficient access can lead to reduced work efficiency and errors. Furthermore, it is important to consider the user's emotions when retrieving information, and it is desirable to receive answers without feeling stressed. A system that solves these problems is needed.

[0936] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting and storing information related to the work and projects that the former employee was in charge of in a database, means for performing text analysis of the collected information and extracting keywords and important phrases, means for training a generative AI model based on the extracted keywords and phrases, means for accepting questions from users and answering the questions using the generative AI model, means for collecting and analyzing user emotion data, and means for adjusting the generated answers based on the analyzed emotion data. This makes it possible to effectively store and utilize the knowledge and information of former employees, provide appropriate answers when users ask questions, and respond in a way that takes the user's emotions into consideration.

[0937] "Ex-employees" refer to former employees who have left a company or organization.

[0938] "Work" refers to the tasks and responsibilities performed within a company or organization.

[0939] A "project" is a set of activities or tasks planned to achieve a specific purpose.

[0940] "Information" refers to data and knowledge related to a business or project.

[0941] A "database" refers to a system for organizing and storing information.

[0942] "Text analytics" refers to the process of analyzing natural language text and extracting useful information from it.

[0943] "Keywords" are words or phrases that are particularly important in a piece of text.

[0944] A "phrase" is an expression made up of multiple words that have a specific meaning.

[0945] A "generative AI model" refers to an artificial intelligence model that uses machine learning algorithms to generate output from input data.

[0946] "User" refers to a person who uses the system.

[0947] A "question" refers to an action in which a user asks the system for information they want to know.

[0948] "Emotional data" refers to various data that indicate the user's emotional state (facial expressions, tone of voice, text content, etc.).

[0949] "Analysis" refers to the process of examining the contents of data to extract specific information.

[0950] "Adjustment" refers to the act of changing content or methods to suit specific conditions.

[0951] A "system" refers to a mechanism in which multiple components work together to achieve a set of functions.

[0952] "Metadata" refers to data that provides information about other data.

[0953] "Natural language processing technology" refers to computer science technology for understanding, interpreting, and generating human language.

[0954] In this invention, the server, terminal, and user components cooperate to collect and analyze the knowledge and information possessed by former employees, and provide a system that uses a generative AI model to provide appropriate answers to user questions.

[0955] server

[0956] The server automatically collects information related to the work and projects that former employees were in charge of. This information is collected from sources such as network communications, emails, and internal chats. Programming languages ​​such as Python, web scraping technology, and APIs are used to collect the information. The collected information is stored in a database such as MySQL along with metadata.

[0957] The server then analyzes the collected information using natural language processing techniques (e.g., Python's NLTK or spaCy) to extract keywords and important phrases. This information is used to train a generative AI model (e.g., OpenAI's GPT-3). The server then optimizes the generative AI model using a deep learning framework (e.g., TensorFlow or PyTorch).

[0958] Terminal

[0959] The device provides an interface for users to interact with the system. Users type questions into the device, and the data is sent to the server. The device is equipped with a webcam and microphone to collect the user's facial expressions and tone of voice in real time. This emotional data is analyzed using Azure Cognitive Services and Google Cloud's Natural Language API.

[0960] Emotion Engine

[0961] The emotion engine analyzes collected emotion data in real time to understand the user's emotional state. It uses libraries such as OpenCV and TensorFlow for emotion analysis and adjusts the output of the generative AI model based on the analysis results. This adjustment results in softer responses if the user is feeling stressed.

[0962] User

[0963] Users can input questions related to their work into the terminal interface and receive appropriate answers from the server. For example, a user might ask, "Please tell me about the progress of the promotional campaign for a new product." The user's input is then subjected to real-time emotion analysis to determine whether they are feeling stressed.

[0964] As a concrete example, if a member of the marketing department wants to check the progress of a promotional campaign for a new product, the user inputs the question "Please tell me about the progress of the promotional campaign for the new product" into the device. Along with this input information, the emotion engine analyzes the user's facial expressions and voice and sends the emotion data to the server. The server then sends the following prompt to the generative AI model:

[0965] Example prompt sentence:

[0966] Please tell us about the progress of the promotional campaign for the new product.

[0967] The server uses a generative AI model to generate an appropriate response and adjusts the response based on the analysis results of the emotion engine. For example, if the response generated is, "The promotional campaign for our new product is currently in its third phase and is 70% complete," the emotion engine softens the tone by adding, "Don't worry, everything is going smoothly."

[0968] In this way, the user can quickly and appropriately obtain the necessary information without feeling stressed. In this way, this invention is a system that effectively utilizes the knowledge and information of former employees and provides appropriate answers that take into consideration the feelings of the user.

[0969] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0970] Step 1:

[0971] The server collects information related to the work and projects that former employees were in charge of and stores it in a database. Specifically, it uses Python scripts to collect data from sources such as network communications, emails, and internal chats, and stores the data in a MySQL database. The collected data is assigned metadata such as date and time and related projects, allowing for efficient search and management. The input is text data obtained from each source, and the output is stored in the database as information with metadata.

[0972] Step 2:

[0973] The server performs text analysis of the stored information using natural language processing technology. Specifically, it uses Python's NLTK and spaCy to analyze the text data retrieved from the database and extract important keywords and phrases. The input is the text data stored in the database, and the output is the keywords and important phrases that are the analysis results. These results are then stored back in the database.

[0974] Step 3:

[0975] The server trains a generative AI model based on the extracted keywords and phrases. Specifically, it uses the extracted data to train a generative AI model (e.g., GPT-3) using a deep learning framework (e.g., TensorFlow or PyTorch). The input is a dataset consisting of keywords and important phrases, and the output is a generative AI model optimized for answer generation.

[0976] Step 4:

[0977] The terminal receives a question entered by the user. Specifically, the user enters the question into a form using a web browser or a dedicated application, and then sends the data to the server. The input is the text question entered by the user, and the output is an HTTP POST request sent to the server.

[0978] Step 5:

[0979] The device collects and analyzes the user's emotional data. Specifically, it uses a webcam and microphone to collect the user's facial expressions and voice, and performs emotional analysis using Azure Cognitive Services and Google Cloud's Natural Language API. The input is image and audio data collected in real time, and the output is text data representing the results of the emotional analysis. This data is also sent to the server.

[0980] Step 6:

[0981] The server receives the user's question and emotion data and generates an answer to the question using a generative AI model. Specifically, the user's question is input to the generative AI model as a prompt sentence, and the answer obtained from the model is obtained. The input is the user's question and the emotion analysis results, and the output is the answer text obtained from the generative AI model.

[0982] Step 7:

[0983] The server adjusts the answer based on the emotional data. Specifically, it modifies the generated answer text to soften the tone and be more considerate according to the results of the emotional analysis. The input is the answer obtained from the generative AI model and the results of the emotional analysis, and the output is the adjusted answer text.

[0984] Step 8:

[0985] The terminal displays the adjusted answer to the user. Specifically, it dynamically generates an HTML format from the text received from the server and displays it on the user's display. The input is the adjusted answer text, and the output is the answer displayed to the user.

[0986] (Application example 2)

[0987] 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."

[0988] Losing knowledge about the work and projects that former employees were in charge of is a major problem for companies. Particularly in on-site areas such as logistics centers, the experience and know-how of former employees is directly linked to operational efficiency and problem-solving. However, it is difficult to pass on the knowledge of former employees to successors, which can result in delays and errors. Furthermore, when on-site staff have questions about work or processes, they often cannot quickly obtain appropriate answers. Furthermore, a system is needed that reduces the stress staff feel when seeking answers and allows them to carry out their work more comfortably.

[0989] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0990] In this invention, the server includes means for collecting and storing information related to the work and projects that the former employee was in charge of in a database, means for performing text analysis of the collected information and extracting keywords and important phrases, means for training a generative AI model based on the extracted keywords and phrases, means for accepting user questions and answering the questions using the generative AI model, and means for recognizing the user's emotions and adjusting the answers of the generative AI model based on the emotions. This allows the knowledge of the former employee to be efficiently organized, enabling logistics center staff to obtain quick and appropriate answers. Providing answers that take emotions into consideration can prevent work delays and errors and reduce staff stress.

[0991] "Ex-employees" are former employees who have left a company or organization.

[0992] "Business" refers to the specific work or tasks that a company or organization performs to achieve its goals.

[0993] A "project" is a set of planned tasks with a set deadline and deliverables that are designed to achieve a specific goal.

[0994] "Information" refers to data, knowledge, know-how, etc. related to business or projects.

[0995] A "database" is a digital recording system that organizes and stores information so that it can be easily retrieved.

[0996] "Text analysis" is the technology of processing text written in natural language and extracting meaningful patterns and information.

[0997] "Keywords" are important words or phrases extracted through text analysis.

[0998] A "generative AI model" is an algorithm trained using artificial intelligence that generates new data and answers based on accumulated information.

[0999] "Emotion recognition" is a technology that analyzes a user's emotions from their facial expressions, voice, and text, and identifies their state.

[1000] "Response adjustment" refers to the process of changing the tone and expression of the generated response based on the user's emotional data obtained through emotion recognition.

[1001] This invention is a system that effectively utilizes information about work and projects held by former employees at a logistics center, enabling on-site staff to receive prompt and appropriate answers. This system consists of four main components: a server, terminals, users, and an emotion engine.

[1002] server

[1003] The server first collects information related to the work and projects that the former employee was in charge of and stores it in a database. At the same time, it adds metadata to the information to facilitate organization and subsequent searches. Next, it uses technology to analyze the collected information and extract keywords and important phrases from the text. This analysis uses natural language processing (NLP) technology. For example, it uses Python's Transformers library to train a generative AI model. The trained model runs on the server and provides quick and appropriate answers to user questions.

[1004] Terminal

[1005] The terminal provides an interface for logistics center staff to input questions and send them to the server. This interface uses a smartphone. When a user inputs a question, the terminal collects the question and also the user's emotional data. This emotional data is analyzed from the user's facial expressions, voice, and text content.

[1006] Emotion Engine

[1007] The emotion engine analyzes the user's emotional data sent from the device and adjusts the generative AI model's responses based on that data. For example, if the user is feeling stressed, the tone and content of the response will be adjusted to be gentler. This allows the user to receive the response without feeling stressed.

[1008] User

[1009] Using this system, users input questions related to the operations and processes of the logistics center. For example, when a question is input, such as "Please tell me the progress of the new shipping process," the question and the user's emotional data are sent to the server. The server queries the question with a generative AI model and generates an appropriate answer. The emotion engine adjusts the answer according to the user's emotion and sends the answer back to the terminal.

[1010] Specific examples

[1011] When a logistics center employee asks about the progress of the new shipping process, the following prompt is used:

[1012] Q: How is the new shipping process progressing?

[1013] Emotion detected: Stress

[1014] Context: Historical data and process information from your distribution center

[1015] A: Don't worry, we've checked and the new shipping process is currently in its second phase and is 80% complete.

[1016] In this way, the system of the present invention efficiently organizes the knowledge of former employees, allowing logistics center staff to quickly and accurately access the information they need. Furthermore, by using an emotion engine, it is possible to provide appropriate answers that take into consideration the user's emotions, thereby preventing work delays and errors.

[1017] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1018] Step 1:

[1019] Gather information related to the tasks and projects the former employee was involved in.

[1020] The server collects information about the work and projects of former employees and stores it in a database. Specifically, it obtains data from interview sheets, work reports, and project management tools. The server adds metadata to the collected information, allowing for efficient searching and organization.

[1021] Input: Interview sheets, work reports, project management tools

[1022] Output: A database containing the information along with metadata

[1023] Step 2:

[1024] The collected information is subjected to text analysis to extract keywords and important phrases.

[1025] The server uses natural language processing (NLP) techniques to analyze the information in the database, such as using Python's Transformers library to process the text and extract key keywords and phrases, providing the data needed to train the generative AI model.

[1026] Input: Information in the database

[1027] Output: Extracted keywords and important phrases

[1028] Step 3:

[1029] A generative AI model is trained based on the extracted keywords and phrases.

[1030] The server trains a generative AI model based on the extracted keywords and phrases. This training process uses past data to optimize the model's performance. The machine learning algorithm is implemented using Python's Transformers library.

[1031] Input: Extracted keywords or phrases

[1032] Output: A trained generative AI model

[1033] Step 4:

[1034] The user inputs a question into the terminal and sends it to the server.

[1035] Users use their smartphones to input questions about the operations and processes of the logistics center. The questions are sent from the device to the server, and emotion data is also collected. For example, voice input and text input are possible, and the emotion engine analyzes the user's facial expressions, voice, and text content.

[1036] Input: User questions, emotion data

[1037] Output: Questions and sentiment data sent to the server

[1038] Step 5:

[1039] The server uses a generative AI model to generate answers to questions.

[1040] The server passes the question sent by the user to the generative AI model, which generates an appropriate answer based on past data. This allows for quick and accurate answers to the user's questions. For example, in response to the question "What is the progress of the new shipping process?", a specific answer such as "The new shipping process is currently in its second phase and is 80% complete" is generated.

[1041] Input: User question

[1042] Output: The generated answer

[1043] Step 6:

[1044] An emotion engine adjusts the generated answers based on the user's emotions.

[1045] The server uses an emotion engine to analyze the user's emotional data and adjust the generated responses accordingly. For example, if the user is feeling stressed, the server will change the tone and content of the response to be gentler.

[1046] Input: User emotion data, generated answers

[1047] Output: Adjusted answer

[1048] Step 7:

[1049] The server sends the adjusted answer to the terminal for display to the user.

[1050] The server returns the adjusted answer to the device and displays it to the user, who can then view the emotion-sensitive answer through the device interface.

[1051] Input: Adjusted Answer

[1052] Output: Answer displayed on terminal

[1053] Examples:

[1054] Q: How is the new shipping process progressing?

[1055] Emotion detected: Stress

[1056] Context: Historical data and process information from your distribution center

[1057] A: Don't worry, we've checked and the new shipping process is currently in its second phase and is 80% complete.

[1058]

[1059] 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.

[1060] 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.

[1061] 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.

[1062] [Fourth embodiment]

[1063] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1064] 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.

[1065] 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).

[1066] 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.

[1067] 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.

[1068] 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).

[1069] 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.

[1070] 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.

[1071] 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.

[1072] 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.

[1073] 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.

[1074] 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.

[1075] 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."

[1076] This invention relates to a system that collects information related to the work and projects that former employees were in charge of, analyzes the text, and trains a generative AI model to quickly and appropriately answer questions from users. This system consists of three main components: a server, a terminal, and a user.

[1077] server

[1078] The server first collects information related to the work and projects that the former employee was in charge of. The collected information is then stored in a database. The collected information is then analyzed using natural language processing technology to extract keywords and important phrases. A generative AI model learns from this extracted information. This model is then used to generate appropriate answers to user questions.

[1079] Terminal

[1080] The terminal is the interface through which the user inputs questions and sends them to the server. The terminal also formats the questions input by the user and sends them to the server. It also plays a role in displaying the answers returned by the server to the user. In this way, the terminal is a tool for facilitating communication between the user and the server.

[1081] User

[1082] Users use the system to enter questions related to their work and receive appropriate answers. For example, if a user wants to know the progress of a promotional campaign for a new product, they enter that specific question into their terminal. When they press the send button, the question is sent from the terminal to the server.

[1083] The server receives the question, uses the generative AI model to generate the optimal answer, and sends this answer back to the device. The device then displays the answer to the user, who can then use it to carry out tasks or solve problems.

[1084] Specific examples

[1085] Let's say Tanaka from the marketing department wants to check the status of a new product promotion campaign. Tanaka types "Please tell me about the progress of the new product promotion campaign" into the interface on his device and clicks the send button. The question is sent from the device to the server, which queries the question with the generative AI model. The generative AI model generates an appropriate answer based on information related to past promotional campaigns, and returns an answer such as "The new product promotion campaign is currently in its third phase and is 70% complete" to Tanaka's device. Tanaka can then review the displayed answer and plan the next steps for his work.

[1086] In this way, the system of the present invention effectively organizes the knowledge possessed by former employees and allows them to access the necessary information quickly and accurately, thereby avoiding delays and errors in work.

[1087] The processing flow will be explained below.

[1088] Step 1:

[1089] The server collects documents, emails, chat logs, and other information related to the work and projects that former employees were in charge of. This information collection is done periodically using automated scripts and APIs.

[1090] Step 2:

[1091] The server stores the collected information in a database, and when storing it, it adds metadata to each piece of information to make it easier to organize and search for the information later.

[1092] Step 3:

[1093] The server performs text analysis of the stored information, using tools that use natural language processing technology to perform morphological and grammatical analysis.

[1094] Step 4:

[1095] The server extracts keywords and important phrases from the results of text analysis, which are then used to train the generative AI model.

[1096] Step 5:

[1097] The server then trains the generative AI model with the extracted information, a process that improves its ability to recognize patterns and rules from past data and generate appropriate answers to questions.

[1098] Step 6:

[1099] The user inputs a business-related question into the terminal interface. For example, if the user wants to check the progress of a promotional campaign for a new product, the user inputs a specific question.

[1100] Step 7:

[1101] The terminal sends the user-entered question to the server, where the question is formatted using a protocol such as an HTTP request.

[1102] Step 8:

[1103] The server receives the question from the terminal and analyzes the content of the question using natural language processing technology.

[1104] Step 9:

[1105] The server then queries the generative AI model based on the analysis results, and the model uses the learned data to generate an appropriate answer.

[1106] Step 10:

[1107] The server then returns the generated answer to the device in a data format such as JSON or XML.

[1108] Step 11:

[1109] The terminal displays the answer received from the server on the user interface in a format that is easily understandable to the user.

[1110] Step 12:

[1111] Users can review the displayed answers and use them to complete tasks or solve problems, for example, to plan the next steps for a sales campaign based on the information provided.

[1112] Example 1

[1113] 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."

[1114] When an employee in charge of an important task or project leaves a company, the loss of that knowledge and information can disrupt business continuity. In particular, if the employee was performing tasks that require specific knowledge and experience, such as project management or marketing activities, it can be difficult for the new employee who takes over to smoothly adapt and continue performing those tasks. This also increases the likelihood of operational delays and errors, so there is a need for a method to efficiently collect and analyze information and obtain the necessary information quickly and accurately.

[1115] 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.

[1116] In this invention, the server includes means for collecting and storing information related to the work and projects that former employees were in charge of in a database, means for analyzing the collected information using natural language processing technology and extracting keywords and important phrases, means for training a generative AI model based on the extracted keywords and phrases, means for accepting questions from users and answering the questions using the generative AI model, means for formatting the questions from users using a terminal and sending them to the server, and means for displaying the answers returned from the server to the user on the terminal. This makes it possible to efficiently collect and analyze the knowledge and information held by former employees and quickly and accurately access the necessary information.

[1117] "Ex-employees" refers to employees who have left the company.

[1118] "Work" refers to specific job functions and routine tasks within a company.

[1119] A "project" is a set of activities designed to achieve a specific purpose.

[1120] "Information" refers to a collection of general knowledge such as data, knowledge, reports, emails, etc.

[1121] A "database" refers to a system for organizing and storing collected information.

[1122] "Natural language processing technology" refers to the technology that allows computers to understand and analyze human language.

[1123] "Keywords" refer to important words or phrases within a document.

[1124] A "phrase" refers to a group of words that have meaning and are made up of multiple words.

[1125] A "generative AI model" refers to a model that uses artificial intelligence to generate text and answer questions.

[1126] A "question" refers to a query entered by a user seeking specific information.

[1127] "Answer" refers to the information provided by a generative AI model in response to a question.

[1128] "Terminal" refers to a device through which a user accesses the system and inputs questions.

[1129] "User" refers to the employees and personnel who use this system.

[1130] "Formalization" refers to the process of converting an input question into a certain format.

[1131] "Server" refers to a computer that performs the main processing of the entire system.

[1132] Including "communication" refers to the process of sending and receiving information or data.

[1133] "Interface" refers to the means by which a user interacts with a system.

[1134] This invention relates to a system that collects information related to the work and projects that former employees were in charge of, analyzes the text, and trains a generative AI model to quickly and appropriately answer questions from users. This system consists of three main components: a server, a terminal, and a user.

[1135] server

[1136] The server has the function of collecting information related to the work and projects of former employees. The information is obtained from the company's document management system and mail server and stored in a database such as MongoDB. The data is then analyzed using natural language processing technologies such as SpaCy and NLTK to extract keywords and important phrases. This extracted information is used to train a generative AI model (e.g., OpenAI's GPT-4). This generative AI model is responsible for generating appropriate answers to user questions. The server also trains the generative AI model using TensorFlow and PyTorch.

[1137] Terminal

[1138] The terminal is an interface through which the user inputs a question and sends it to the server. The terminal can operate as a web browser, desktop application, or mobile application. For example, the web application is implemented using "React.js" and has a question input field and a submit button. The question input by the user is formatted by the terminal and sent to the server via "REST API." The answer returned from the server is also displayed to the user on the terminal.

[1139] User

[1140] Users use their devices to input questions related to their work and receive appropriate answers. For example, if a marketing department employee wants to know the progress of a new product promotion campaign, they can input "Please tell me about the progress of the new product promotion campaign" into their device and send it. The question is sent from the device to the server and queried by the generative AI model. The generative AI model generates an appropriate answer based on information related to past promotional campaigns, and returns an answer such as "The new product promotion campaign is currently in its third phase and is 70% complete" to the user's device. The user can use this information to plan the next steps in their work.

[1141] Specific examples

[1142] An example of a prompt phrase used is, "Please tell me about the progress of the promotional campaign for the new product." The system uses a generative AI model to generate an answer to this question and displays it to the user on the device. In this way, the knowledge and information possessed by former employees can be efficiently organized, allowing users to access the information they need quickly and accurately, thereby avoiding work delays and errors.

[1143] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1144] Step 1: Gather information

[1145] The server collects information related to the former employee's work and projects, specifically reports, emails, and project management tool data from the company's document management system and email server.

[1146] Input: Document management system, mail server

[1147] Output: Retrieved work and project-related information (text format)

[1148] Step 2: Saving to the database

[1149] The server stores the collected information in a database such as MongoDB, which allows the data to be systematically managed for later analysis and retrieval.

[1150] Input: Work and project related information captured

[1151] Output: Information stored in the database

[1152] Step 3: Natural Language Processing Analysis

[1153] The server uses natural language processing techniques (e.g., SpaCy, NLTK) to analyze the stored information, specifically extracting keywords and important phrases from the text.

[1154] Input: Information stored in a database

[1155] Output: Extracted keywords and important phrases

[1156] Step 4: Training the generative AI model

[1157] The server trains a generative AI model (e.g., OpenAI's GPT-4) based on the extracted keywords and phrases. During this process, the model is trained using a machine learning framework (e.g., TensorFlow, PyTorch).

[1158] Input: Extracted keywords or key phrases

[1159] Output: Trained generative AI model

[1160] Step 5: Enter and format your question

[1161] The user uses the device to enter a question, which is then formatted and sent to the server via a REST API request. Specifically, the user enters a question in a text box and clicks the submit button.

[1162] Input: Question from the user (prompt sentence)

[1163] Output: Formatted question (HTTP request)

[1164] Step 6: Submit and receive your question

[1165] The device sends a formulated question to the server, which accepts the question and prepares the data to query the generative AI model.

[1166] Input: A formatted question (HTTP request)

[1167] Output: The question sent to the server

[1168] Step 7: Generate an answer

[1169] The server uses the generative AI model to generate the optimal answer for the received question. Specifically, the server automatically creates an answer based on the question entered into the generative AI model.

[1170] Input: The question sent to the server

[1171] Output: The generated answer

[1172] Step 8: Return and view your responses

[1173] The server returns the generated answer to the terminal, which then displays the received answer to the user. Specifically, the generated answer is displayed on the user interface.

[1174] Input: Generated answer (HTTP response)

[1175] Output: Answer displayed on terminal

[1176] Step 9: What happens next for the user?

[1177] Based on the displayed answers, users can plan and execute the next steps in their business. For example, they can decide on the next marketing strategy based on the answers.

[1178] Input: Answer displayed on the terminal

[1179] Output: User's action plan

[1180] In this way, each component of the system works together to carry out processing and provide users with prompt and appropriate information.

[1181] (Application example 1)

[1182] 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."

[1183] There is a problem that valuable knowledge about the work and projects that former employees were in charge of is not passed on, resulting in delays and errors by remaining employees.In addition, information on transaction history and payment status for electronic payment services needs to be provided quickly and appropriately.A system is needed to solve these problems and ensure work efficiency and transparency in the payment process.

[1184] 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.

[1185] In this invention, the server includes means for collecting and storing information related to the work and projects that former employees were in charge of in a database, means for performing text analysis of the collected information and extracting keywords and important phrases, means for training a generative AI model based on the extracted keywords and phrases, means for providing appropriate answers based on information including transaction history and payment status related to electronic payments, and means for accepting questions from users and answering the questions using the generative AI model. This makes it possible to effectively utilize the knowledge of former employees, speed up operations, and improve the efficiency of information provision in the electronic payment process.

[1186] "Ex-employees" are employees who have left a particular company or organization.

[1187] "Work" refers to the specific work or tasks that an employee is responsible for within an organization or company.

[1188] A "project" is a set of planned activities to achieve a specific purpose within a certain period of time.

[1189] "Information" refers to data and knowledge related to a business or project.

[1190] A "database" is a system that centrally stores and manages various types of data.

[1191] "Text analysis" is a technique for extracting and analyzing specific information from text data.

[1192] "Keywords" are words or phrases that play an important role in a piece of text.

[1193] A "generative AI model" is an artificial intelligence that uses machine learning technology to automatically generate appropriate answers to questions.

[1194] "Electronic payment" refers to payment transactions conducted over the Internet or electronic devices.

[1195] "Transaction History" means a record of past payment activity and transactions.

[1196] "Payment Status" means the progress or completion state of a particular payment activity.

[1197] An "answer" is the information that a generative AI model outputs in response to a user's question.

[1198] "User" refers to an individual or organization that uses the system to ask a question.

[1199] "Server" means a computer system for collecting, analyzing, storing data, and running the generative AI model.

[1200] A "question" is a query that a user enters into the system to obtain specific information.

[1201] Explanation of program processing

[1202] Hardware and Software Use

[1203] server:

[1204] Hardware: The server uses a high-performance computer system to store and analyze the collected information and train the generative AI model.

[1205] Software: The server uses Python and natural language processing libraries such as Hugging Face Transformers. Specifically, the generative AI model is trained using the "deepset / roberta-base-squad2" model.

[1206] Device:

[1207] Hardware: The device, such as a smartphone or computer, used by the user to enter the question.

[1208] Software: A user interface for entering questions and an application for displaying answers from the server.

[1209] User:

[1210] Users use their devices to input questions, which are then sent to a server where a generative AI model generates an answer.

[1211] Data processing and calculation

[1212] The server first collects information related to the former employee's work and projects and stores it in a database. Next, the information is analyzed using natural language processing technology to extract keywords and important phrases. A generative AI model is trained based on this analyzed information.

[1213] The user's question is sent to the server via the device, and the server generates an answer using the generative AI model. The generated answer is then sent back to the device and displayed to the user.

[1214] Specific examples

[1215] Suppose a user asks, "What is the payment status of transaction ID: 12345?" The server extracts information such as transaction history and payment status from the database, and uses a generative AI model to generate an answer such as, "The current status of transaction ID: 12345 is complete. All approval processes have been completed." The answer is sent to the terminal and displayed to the user.

[1216] Prompt Sentence Examples

[1217] An example of a prompt entered by a user:

[1218] "What is the payment status for transaction ID: 12345?"

[1219] This invention effectively transfers the knowledge of former employees and trains it in a generative AI model, enabling users to quickly and accurately obtain information. It can also respond to specific questions about electronic payments, improving work efficiency and transparency in the payment process.

[1220] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1221] Step 1:

[1222] The server collects and stores in a database information related to the former employee's work and projects, including detailed project progress reports, transaction history, payment status, etc. The input data are documents, reports, and database entries, and the output is structured data that can be used for analysis and to train generative AI models.

[1223] Step 2:

[1224] The server uses natural language processing (NLP) techniques to analyze the collected information and extract keywords and important phrases. The input is raw information about tasks and projects stored in a database. The output is the analysis results, including keywords and important phrases. Specific NLP libraries (e.g., SpaCy and NLTK) are used to process the data.

[1225] Step 3:

[1226] The server trains a generative AI model (e.g., Hugging Face's "deepset / roberta-base-squad2") based on the text analysis results. The input is the key information extracted in step 2. The output is a generative AI model that can appropriately respond to the user's question. This generative AI model is trained using a large amount of text data to improve the accuracy of the model.

[1227] Step 4:

[1228] A user inputs a question using a device (such as a smartphone or computer). The device interface formats the question from the user and sends it to the server. The input is the user's question (prompt), and the output is the transfer of formatted data to the server.

[1229] Step 5:

[1230] The server inputs the received question into the generative AI model to generate an appropriate answer. The input is the question from the user, and the output is the answer generated by the generative AI model. The generative AI model analyzes related information in a database based on the question content and generates an answer that is useful to the user.

[1231] Step 6:

[1232] The server sends the generated answer to the terminal. The input is the generated answer, and the output is the transfer of the answer information to the terminal.

[1233] Step 7:

[1234] The terminal displays the answer received from the server to the user. The input is the answer information provided by the server, and the output is the answer displayed for the user on the terminal screen. This allows the user to quickly and accurately obtain the information they need, such as the progress of work or projects, or the payment status of transactions.

[1235] 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.

[1236] This invention relates to a system that collects information related to the work and projects that former employees were in charge of, analyzes the text, and trains a generative AI model to quickly and appropriately answer questions from users. This system consists of four main components: a server, a terminal, a user, and an emotion engine that recognizes the user's emotions.

[1237] server

[1238] The server first collects information related to the work and projects that the former employee was in charge of. The collected information is then stored in a database. When storing the information, metadata is added to each piece of information to facilitate organization and subsequent retrieval. The collected information is then analyzed using natural language processing technology to extract keywords and important phrases. A generative AI model trains based on this extracted information. This model is then used to generate appropriate answers to user questions.

[1239] Terminal

[1240] The terminal serves as an interface through which the user can input questions and send them to the server. It also simultaneously collects emotional data when the user asks a question. Emotional data is analyzed from the user's facial expression, tone of voice, and text content. The terminal formats the questions and emotional data input by the user and sends them to the server. It also plays a role in displaying the answers returned by the server to the user.

[1241] Emotion Engine

[1242] The emotion engine has the ability to analyze the user's emotions and adjust the generative AI model's responses based on that. Emotional data is analyzed in real time, and if the user is feeling stressed, for example, the tone and content of the response will be softened.

[1243] User

[1244] Users can use the system to input questions related to their work and receive appropriate answers. The device also automatically collects the emotions expressed at the time of the question. For example, if a user wants to know the progress of a new product promotion campaign and is feeling stressed, they can input that specific question and receive an answer that takes those emotions into consideration.

[1245] Specific examples

[1246] Suppose that Tanaka from the marketing department wants to check the status of a promotional campaign for a new product. He types "Please tell me about the progress of the promotional campaign for the new product" into the interface on his device. If the emotion engine detects stress while Tanaka is typing this question, the device will send the question to the server based on this emotion data.

[1247] The server queries the question to the AI ​​model, which generates an appropriate answer based on information related to past promotional campaigns. For example, the generated answer might be, "The promotional campaign for the new product is currently in its third phase and is 70% complete." The emotion engine then performs additional processing to soften the tone and content of the answer to reduce Tanaka's stress.

[1248] The server then adapts the generated answer to Tanaka's emotions and sends it back to his device. Tanaka's device displays the answer, allowing him to check the necessary information without feeling stressed.

[1249] In this way, the system of the present invention not only efficiently organizes the knowledge possessed by former employees and allows them to access the necessary information quickly and accurately, but also provides answers that take the user's emotions into consideration, thereby further preventing work delays and errors.

[1250] The processing flow will be explained below.

[1251] Step 1:

[1252] The server collects documents, emails, chat logs, and other information related to the work and projects that former employees were in charge of. This information collection is done periodically using automated scripts and APIs.

[1253] Step 2:

[1254] The server stores the collected information in a database, and when storing it, it adds metadata to each piece of information to make it easier to organize and search for the information later.

[1255] Step 3:

[1256] The server performs text analysis of the stored information, using tools that use natural language processing technology to perform morphological and grammatical analysis.

[1257] Step 4:

[1258] The server extracts keywords and important phrases from the results of text analysis, which are then used to train the generative AI model.

[1259] Step 5:

[1260] The server trains the generative AI model based on the extracted information, a process that improves its ability to recognize patterns and rules from past data and generate appropriate answers to questions.

[1261] Step 6:

[1262] The user inputs a business-related question into the terminal interface. For example, if the user wants to check the progress of a promotional campaign for a new product, the user inputs that specific question.

[1263] Step 7:

[1264] In addition to the user's input, the device uses facial expression recognition and voice analysis to obtain emotional data about the user. It analyzes the user's emotional state when entering a question and collects emotional data such as stress, joy, and confusion.

[1265] Step 8:

[1266] The device sends the collected questions and emotion data to the server, where the data is formatted using a protocol such as an HTTP request.

[1267] Step 9:

[1268] The server receives the question and emotion data from the device and analyzes the content of the question using natural language processing technology.

[1269] Step 10:

[1270] The server then queries the generative AI model based on the analysis results, and the model uses the learned data to generate an appropriate answer.

[1271] Step 11:

[1272] The emotion engine analyzes the user's emotional data and adjusts the tone and content of the generated response. For example, if the user is feeling stressed, the tone of the response will be softened.

[1273] Step 12:

[1274] The server adjusts the generated answers using the emotion engine and then sends them back to the device in a data format such as JSON or XML.

[1275] Step 13:

[1276] The terminal displays the adjusted answers received from the server on a user interface in a format that is easily understandable to the user.

[1277] Step 14:

[1278] Users can review the displayed answers and use them to carry out tasks or solve problems, and can use the information they need to plan the next steps in their sales campaigns.

[1279] Example 2

[1280] 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."

[1281] In modern companies, the loss of important knowledge and information held by employees who leave the company is a major problem. While there is also a need to quickly and appropriately retrieve work-related information, insufficient access can lead to reduced work efficiency and errors. Furthermore, it is important to consider the user's emotions when retrieving information, and it is desirable to receive answers without feeling stressed. A system that solves these problems is needed.

[1282] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting and storing information related to the work and projects that the former employee was in charge of in a database, means for performing text analysis of the collected information and extracting keywords and important phrases, means for training a generative AI model based on the extracted keywords and phrases, means for accepting questions from users and answering the questions using the generative AI model, means for collecting and analyzing user emotion data, and means for adjusting the generated answers based on the analyzed emotion data. This makes it possible to effectively store and utilize the knowledge and information of former employees, provide appropriate answers when users ask questions, and respond in a way that takes the user's emotions into consideration.

[1283] "Ex-employees" refer to former employees who have left a company or organization.

[1284] "Work" refers to the tasks and responsibilities performed within a company or organization.

[1285] A "project" is a set of activities or tasks planned to achieve a specific purpose.

[1286] "Information" refers to data and knowledge related to a business or project.

[1287] A "database" refers to a system for organizing and storing information.

[1288] "Text analytics" refers to the process of analyzing natural language text and extracting useful information from it.

[1289] "Keywords" are words or phrases that are particularly important in a piece of text.

[1290] A "phrase" is an expression made up of multiple words that have a specific meaning.

[1291] A "generative AI model" refers to an artificial intelligence model that uses machine learning algorithms to generate output from input data.

[1292] "User" refers to a person who uses the system.

[1293] A "question" refers to an action in which a user asks the system for information they want to know.

[1294] "Emotional data" refers to various data that indicate the user's emotional state (facial expressions, tone of voice, text content, etc.).

[1295] "Analysis" refers to the process of examining the contents of data to extract specific information.

[1296] "Adjustment" refers to the act of changing content or methods to suit specific conditions.

[1297] A "system" refers to a mechanism in which multiple components work together to achieve a set of functions.

[1298] "Metadata" refers to data that provides information about other data.

[1299] "Natural language processing technology" refers to computer science technology for understanding, interpreting, and generating human language.

[1300] In this invention, the server, terminal, and user components cooperate to collect and analyze the knowledge and information possessed by former employees, and provide a system that uses a generative AI model to provide appropriate answers to user questions.

[1301] server

[1302] The server automatically collects information related to the work and projects that former employees were in charge of. This information is collected from sources such as network communications, emails, and internal chats. Programming languages ​​such as Python, web scraping technology, and APIs are used to collect the information. The collected information is stored in a database such as MySQL along with metadata.

[1303] The server then analyzes the collected information using natural language processing techniques (e.g., Python's NLTK or spaCy) to extract keywords and important phrases. This information is used to train a generative AI model (e.g., OpenAI's GPT-3). The server then optimizes the generative AI model using a deep learning framework (e.g., TensorFlow or PyTorch).

[1304] Terminal

[1305] The device provides an interface for users to interact with the system. Users type questions into the device, and the data is sent to the server. The device is equipped with a webcam and microphone to collect the user's facial expressions and tone of voice in real time. This emotional data is analyzed using Azure Cognitive Services and Google Cloud's Natural Language API.

[1306] Emotion Engine

[1307] The emotion engine analyzes collected emotion data in real time to understand the user's emotional state. It uses libraries such as OpenCV and TensorFlow for emotion analysis and adjusts the output of the generative AI model based on the analysis results. This adjustment results in softer responses if the user is feeling stressed.

[1308] User

[1309] Users can input questions related to their work into the terminal interface and receive appropriate answers from the server. For example, a user might ask, "Please tell me about the progress of the promotional campaign for a new product." The user's input is then subjected to real-time emotion analysis to determine whether they are feeling stressed.

[1310] As a concrete example, if a member of the marketing department wants to check the progress of a promotional campaign for a new product, the user inputs the question "Please tell me about the progress of the promotional campaign for the new product" into the device. Along with this input information, the emotion engine analyzes the user's facial expressions and voice and sends the emotion data to the server. The server then sends the following prompt to the generative AI model:

[1311] Example prompt sentence:

[1312] Please tell us about the progress of the promotional campaign for the new product.

[1313] The server uses a generative AI model to generate an appropriate response and adjusts the response based on the analysis results of the emotion engine. For example, if the response generated is, "The promotional campaign for our new product is currently in its third phase and is 70% complete," the emotion engine softens the tone by adding, "Don't worry, everything is going smoothly."

[1314] In this way, the user can quickly and appropriately obtain the necessary information without feeling stressed. In this way, this invention is a system that effectively utilizes the knowledge and information of former employees and provides appropriate answers that take into consideration the feelings of the user.

[1315] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1316] Step 1:

[1317] The server collects information related to the work and projects that former employees were in charge of and stores it in a database. Specifically, it uses Python scripts to collect data from sources such as network communications, emails, and internal chats, and stores the data in a MySQL database. The collected data is assigned metadata such as date and time and related projects, allowing for efficient search and management. The input is text data obtained from each source, and the output is stored in the database as information with metadata.

[1318] Step 2:

[1319] The server performs text analysis of the stored information using natural language processing technology. Specifically, it uses Python's NLTK and spaCy to analyze the text data retrieved from the database and extract important keywords and phrases. The input is the text data stored in the database, and the output is the keywords and important phrases that are the analysis results. These results are then stored back in the database.

[1320] Step 3:

[1321] The server trains a generative AI model based on the extracted keywords and phrases. Specifically, it uses the extracted data to train a generative AI model (e.g., GPT-3) using a deep learning framework (e.g., TensorFlow or PyTorch). The input is a dataset consisting of keywords and important phrases, and the output is a generative AI model optimized for answer generation.

[1322] Step 4:

[1323] The terminal receives a question entered by the user. Specifically, the user enters the question into a form using a web browser or a dedicated application, and then sends the data to the server. The input is the text question entered by the user, and the output is an HTTP POST request sent to the server.

[1324] Step 5:

[1325] The device collects and analyzes the user's emotional data. Specifically, it uses a webcam and microphone to collect the user's facial expressions and voice, and performs emotional analysis using Azure Cognitive Services and Google Cloud's Natural Language API. The input is image and audio data collected in real time, and the output is text data representing the results of the emotional analysis. This data is also sent to the server.

[1326] Step 6:

[1327] The server receives the user's question and emotion data and generates an answer to the question using a generative AI model. Specifically, the user's question is input to the generative AI model as a prompt sentence, and the answer obtained from the model is obtained. The input is the user's question and the emotion analysis results, and the output is the answer text obtained from the generative AI model.

[1328] Step 7:

[1329] The server adjusts the answer based on the emotional data. Specifically, it modifies the generated answer text to soften the tone and be more considerate according to the results of the emotional analysis. The input is the answer obtained from the generative AI model and the results of the emotional analysis, and the output is the adjusted answer text.

[1330] Step 8:

[1331] The terminal displays the adjusted answer to the user. Specifically, it dynamically generates an HTML format from the text received from the server and displays it on the user's display. The input is the adjusted answer text, and the output is the answer displayed to the user.

[1332] (Application example 2)

[1333] 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."

[1334] Losing knowledge about the work and projects that former employees were in charge of is a major problem for companies. Particularly in on-site areas such as logistics centers, the experience and know-how of former employees is directly linked to operational efficiency and problem-solving. However, it is difficult to pass on the knowledge of former employees to successors, which can result in delays and errors. Furthermore, when on-site staff have questions about work or processes, they often cannot quickly obtain appropriate answers. Furthermore, a system is needed that reduces the stress staff feel when seeking answers and allows them to carry out their work more comfortably.

[1335] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1336] In this invention, the server includes means for collecting and storing information related to the work and projects that the former employee was in charge of in a database, means for performing text analysis of the collected information and extracting keywords and important phrases, means for training a generative AI model based on the extracted keywords and phrases, means for accepting user questions and answering the questions using the generative AI model, and means for recognizing the user's emotions and adjusting the answers of the generative AI model based on the emotions. This allows the knowledge of the former employee to be efficiently organized, enabling logistics center staff to obtain quick and appropriate answers. Providing answers that take emotions into consideration can prevent work delays and errors and reduce staff stress.

[1337] "Ex-employees" are former employees who have left a company or organization.

[1338] "Business" refers to the specific work or tasks that a company or organization performs to achieve its goals.

[1339] A "project" is a set of planned tasks with a set deadline and deliverables that are designed to achieve a specific goal.

[1340] "Information" refers to data, knowledge, know-how, etc. related to business or projects.

[1341] A "database" is a digital recording system that organizes and stores information so that it can be easily retrieved.

[1342] "Text analysis" is the technology of processing text written in natural language and extracting meaningful patterns and information.

[1343] "Keywords" are important words or phrases extracted through text analysis.

[1344] A "generative AI model" is an algorithm trained using artificial intelligence that generates new data and answers based on accumulated information.

[1345] "Emotion recognition" is a technology that analyzes a user's emotions from their facial expressions, voice, and text, and identifies their state.

[1346] "Response adjustment" refers to the process of changing the tone and expression of the generated response based on the user's emotional data obtained through emotion recognition.

[1347] This invention is a system that effectively utilizes information about work and projects held by former employees at a logistics center, enabling on-site staff to receive prompt and appropriate answers. This system consists of four main components: a server, terminals, users, and an emotion engine.

[1348] server

[1349] The server first collects information related to the work and projects that the former employee was in charge of and stores it in a database. At the same time, it adds metadata to the information to facilitate organization and subsequent searches. Next, it uses technology to analyze the collected information and extract keywords and important phrases from the text. This analysis uses natural language processing (NLP) technology. For example, it uses Python's Transformers library to train a generative AI model. The trained model runs on the server and provides quick and appropriate answers to user questions.

[1350] Terminal

[1351] The terminal provides an interface for logistics center staff to input questions and send them to the server. This interface uses a smartphone. When a user inputs a question, the terminal collects the question and also the user's emotional data. This emotional data is analyzed from the user's facial expressions, voice, and text content.

[1352] Emotion Engine

[1353] The emotion engine analyzes the user's emotional data sent from the device and adjusts the generative AI model's responses based on that data. For example, if the user is feeling stressed, the tone and content of the response will be adjusted to be gentler. This allows the user to receive the response without feeling stressed.

[1354] User

[1355] Using this system, users input questions related to the operations and processes of the logistics center. For example, when a question is input, such as "Please tell me the progress of the new shipping process," the question and the user's emotional data are sent to the server. The server queries the question with a generative AI model and generates an appropriate answer. The emotion engine adjusts the answer according to the user's emotion and sends the answer back to the terminal.

[1356] Specific examples

[1357] When a logistics center employee asks about the progress of the new shipping process, the following prompt is used:

[1358] Q: How is the new shipping process progressing?

[1359] Emotion detected: Stress

[1360] Context: Historical data and process information from your distribution center

[1361] A: Don't worry, we've checked and the new shipping process is currently in its second phase and is 80% complete.

[1362] In this way, the system of the present invention efficiently organizes the knowledge of former employees, allowing logistics center staff to quickly and accurately access the information they need. Furthermore, by using an emotion engine, it is possible to provide appropriate answers that take into consideration the user's emotions, thereby preventing work delays and errors.

[1363] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1364] Step 1:

[1365] Gather information related to the tasks and projects the former employee was involved in.

[1366] The server collects information about the work and projects of former employees and stores it in a database. Specifically, it obtains data from interview sheets, work reports, and project management tools. The server adds metadata to the collected information, allowing for efficient searching and organization.

[1367] Input: Interview sheets, work reports, project management tools

[1368] Output: A database containing the information along with metadata

[1369] Step 2:

[1370] The collected information is subjected to text analysis to extract keywords and important phrases.

[1371] The server uses natural language processing (NLP) techniques to analyze the information in the database, such as using Python's Transformers library to process the text and extract key keywords and phrases, providing the data needed to train the generative AI model.

[1372] Input: Information in the database

[1373] Output: Extracted keywords and important phrases

[1374] Step 3:

[1375] A generative AI model is trained based on the extracted keywords and phrases.

[1376] The server trains a generative AI model based on the extracted keywords and phrases. This training process uses past data to optimize the model's performance. The machine learning algorithm is implemented using Python's Transformers library.

[1377] Input: Extracted keywords or phrases

[1378] Output: A trained generative AI model

[1379] Step 4:

[1380] The user inputs a question into the terminal and sends it to the server.

[1381] Users use their smartphones to input questions about the operations and processes of the logistics center. The questions are sent from the device to the server, and emotion data is also collected. For example, voice input and text input are possible, and the emotion engine analyzes the user's facial expressions, voice, and text content.

[1382] Input: User questions, emotion data

[1383] Output: Questions and sentiment data sent to the server

[1384] Step 5:

[1385] The server uses a generative AI model to generate answers to questions.

[1386] The server passes the question sent by the user to the generative AI model, which generates an appropriate answer based on past data. This allows for quick and accurate answers to the user's questions. For example, in response to the question "What is the progress of the new shipping process?", a specific answer such as "The new shipping process is currently in its second phase and is 80% complete" is generated.

[1387] Input: User question

[1388] Output: The generated answer

[1389] Step 6:

[1390] An emotion engine adjusts the generated answers based on the user's emotions.

[1391] The server uses an emotion engine to analyze the user's emotional data and adjust the generated responses accordingly. For example, if the user is feeling stressed, the server will change the tone and content of the response to be gentler.

[1392] Input: User emotion data, generated answers

[1393] Output: Adjusted answer

[1394] Step 7:

[1395] The server sends the adjusted answer to the terminal for display to the user.

[1396] The server returns the adjusted answer to the device and displays it to the user, who can then view the emotion-sensitive answer through the device interface.

[1397] Input: Adjusted Answer

[1398] Output: Answer displayed on terminal

[1399] Examples:

[1400] Q: How is the new shipping process progressing?

[1401] Emotion detected: Stress

[1402] Context: Historical data and process information from your distribution center

[1403] A: Don't worry, we've checked and the new shipping process is currently in its second phase and is 80% complete.

[1404]

[1405] 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.

[1406] 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.

[1407] 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 robot 414.

[1408] 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.

[1409] FIG. 9 illustrates 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 behaviors 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.

[1410] 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.

[1411] 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).

[1412] 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.

[1413] 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."

[1414] 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.

[1415] 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).

[1416] 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.

[1417] 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.

[1418] 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.

[1419] 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.

[1420] 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.

[1421] 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.

[1422] 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.

[1423] 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.

[1424] 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.

[1425] 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.

[1426] The following is further disclosed regarding the above embodiment.

[1427] (Claim 1)

[1428] A means of collecting and storing information related to the work and projects that former employees were involved in in a database;

[1429] A means of analyzing the collected information and extracting keywords and important phrases.

[1430] A means to train a generative AI model based on extracted keywords and phrases, and

[1431] A system that includes a means for accepting questions from users and answering the questions using a generative AI model.

[1432] (Claim 2)

[1433] 2. The system according to claim 1, wherein the collected information is organized with metadata and stored in a database.

[1434] (Claim 3)

[1435] The system of claim 1, wherein natural language processing technology is used in training the generative AI model.

[1436] "Example 1"

[1437] (Claim 1)

[1438] A means of collecting and storing information related to the work and projects that former employees were involved in in a database;

[1439] Analyzing the collected information using natural language processing technology to extract keywords and important phrases,

[1440] A means to train a generative AI model based on extracted keywords and phrases, and

[1441] A means for accepting questions from users and answering the questions using a generative AI model;

[1442] means for formulating a question from a user using a terminal and transmitting the question to a server;

[1443] means for displaying the response returned by the server to the user at the terminal;

[1444] A system including:

[1445] (Claim 2)

[1446] 2. The system according to claim 1, wherein the collected information is organized with metadata and stored in a database.

[1447] (Claim 3)

[1448] The system of claim 1, wherein natural language processing technology is used in training the generative AI model.

[1449] "Application Example 1"

[1450] (Claim 1)

[1451] A means of collecting and storing information related to the work and projects that former employees were involved in in a database;

[1452] A means of analyzing the collected information and extracting keywords and important phrases.

[1453] A means to train a generative AI model based on extracted keywords and phrases, and

[1454] A means for accepting questions from users and answering the questions using a generative AI model;

[1455] A system that includes a means for providing appropriate responses based on information about electronic payments, including transaction history and payment status.

[1456] (Claim 2)

[1457] 2. The system according to claim 1, wherein the collected information is organized with metadata and stored in a database.

[1458] (Claim 3)

[1459] The system of claim 1, wherein natural language processing technology is used in training the generative AI model.

[1460] "Example 2: Combining Emotion Engines"

[1461] (Claim 1)

[1462] A means of collecting and storing information related to the work and projects that former employees were involved in in a database;

[1463] A means of analyzing the collected information and extracting keywords and important phrases.

[1464] A means to train a generative AI model based on extracted keywords and phrases, and

[1465] A means for accepting questions from users and answering the questions using a generative AI model;

[1466] means for collecting and analyzing user emotion data;

[1467] The system includes means for adjusting the generated response based on the analyzed sentiment data.

[1468] (Claim 2)

[1469] 2. The system according to claim 1, wherein the collected information is organized with metadata and stored in a database.

[1470] (Claim 3)

[1471] The system of claim 1, wherein natural language processing technology is used in training the generative AI model.

[1472] "Application example 2 when combining emotion engines"

[1473] (Claim 1)

[1474] A means of collecting and storing information related to the work and projects that former employees were involved in in a database;

[1475] A means of analyzing the collected information and extracting keywords and important phrases.

[1476] A means to train a generative AI model based on extracted keywords and phrases, and

[1477] A means for accepting questions from users and answering the questions using a generative AI model;

[1478] A system that includes a means for recognizing a user's emotions and adjusting the answers of a generative AI model based on those emotions.

[1479] (Claim 2)

[1480] 2. The system according to claim 1, wherein the collected information is organized with metadata and stored in a database.

[1481] (Claim 3)

[1482] The system of claim 1, wherein natural language processing technology is used in training the generative AI model. [Explanation of symbols]

[1483] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting and storing information related to the work and projects that former employees were involved in in a database; A means of analyzing the collected information and extracting keywords and important phrases. A means to train a generative AI model based on extracted keywords and phrases, and A system that includes a means for accepting questions from users and answering the questions using a generative AI model.

2. 2. The system according to claim 1, wherein the collected information is organized with metadata and stored in a database.

3. The system of claim 1, wherein natural language processing techniques are used in training the generative AI model.

Images