system

Abstract

Provide a system. 【Solution means】Means for collecting skill data of all employees, Means for collecting MBO data of all employees, Means for collecting customer information, Means for collecting project information, Means for collecting product information, Means for preprocessing the collected data, Means for inputting the preprocessed data into a generative AI model, Means for receiving user questions, Means for generating an answer by the generative AI model based on the received question, A system including means for presenting the generated answer to the user.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In a modern corporate environment, there is a variety of data such as employees' skills, MBO (management by objectives), customer information, project information, product information, etc. However, it is difficult to effectively integrate this information and build a mechanism that is useful for employees' work. In particular, each employee cannot quickly find other employees with appropriate skills in their work, the optimal project, customers, etc., resulting in problems such as reduced efficiency and productivity. To solve such problems, a system that integrates and provides this information is required.

Means for Solving the Problems

[0005] This invention provides a means for collecting skill data, MBO data, customer information, project information, and product information of all employees, and for integrating and pre-processing this information. Furthermore, it provides a system that includes means for feeding the pre-processed data into a generative AI model for training, and means for receiving user questions, having the generative AI model generate answers based on the received questions, and presenting them to the user. This system allows each employee to quickly obtain the necessary information and improve work efficiency. In addition, it prevents information leakage by handling highly confidential company information securely in a closed environment.

[0006] "Skill data" refers to information about the abilities, expertise, and experience that employees possess.

[0007] "MBO data" refers to information about the goals set by employees based on management by objectives and the status of their achievement.

[0008] "Customer information" refers to information about external organizations and business partners with which a company engages in its commercial activities.

[0009] "Project information" refers to information about specific projects carried out within a company, including objectives, schedules, resources, and progress.

[0010] "Product information" refers to information about the products and services that a company offers.

[0011] "Preprocessing" refers to processes such as data cleaning, normalization, and format conversion performed to transform raw data into a format that can be analyzed.

[0012] A "generative AI model" is an artificial intelligence model that can learn from large-scale data and generate or predict new data.

[0013] A "closed environment" refers to a closed system or network that cannot be accessed from the outside, and is an environment where settings are made to maintain information security. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0018] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] As shown in Figure 1, the 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.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0028] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] This invention is a system that integrates all employees' skill data, MBO data, customer information, project information, and product information to provide information useful for each employee's work. This system consists of three main components: a server, a terminal, and a user, each performing a specific function.

[0036] server

[0037] The server collects necessary information from multiple data sources and performs preprocessing. Then, it inputs the data into a generative AI model (e.g., GPT) to allow it to learn.

[0038] Data Collection: The server retrieves skill data for all employees from the HR database. Next, it retrieves MBO data from the performance management system and customer information from the CRM system. It also retrieves project information from the project management system and product information from the product database.

[0039] Preprocessing: Normalize the acquired data, removing unnecessary line breaks and special characters. Unify the format and convert it to a format suitable for AI models (e.g., JSON format).

[0040] Input to the AI ​​model: Preprocessed data is input into a generative AI model, and the necessary training is performed.

[0041] terminal

[0042] The terminal provides an interface for users to input questions into the system and view the results. It is typically implemented as a web application or desktop application.

[0043] Interface provision: The terminal provides a form where the user can enter a question. For example, it can accept questions such as, "Who is the best employee for the next project?"

[0044] Data transmission: The terminal sends the user's question to the server.

[0045] User

[0046] Users can use this system to quickly obtain information related to their work.

[0047] Question Input: Enter specific work-related questions into the terminal. For example, "Who is the best employee for the next project?"

[0048] Specific example of processing

[0049] The following is a concrete example of how the system generates answers to specific questions.

[0050] 1. User: Enters the question "Who is the best employee for the next project?" into the terminal.

[0051] 2. Terminal: Receives questions and sends their contents to the server.

[0052] 3. Server: Receives questions and inputs them into the generative AI model.

[0053] 4. AI Model: Generates the best answer to a question based on training data (e.g., Employee A, Employee B).

[0054] 5. Server: Receives the generated response and formats it into a format to be returned to the user.

[0055] 6. Terminal: Displays formatted answers to the user.

[0056] As a result, users can instantly obtain information on the best employees for their next project, improving work efficiency and productivity.

[0057] security

[0058] Because the system handles highly confidential company information, it operates in a closed environment. This environment is designed to restrict external access and minimize the risk of information leakage.

[0059] Based on the above, the present invention provides specific means for each employee to quickly acquire information necessary for their work and to improve work efficiency.

[0060] The following describes the processing flow.

[0061] Step 1:

[0062] The server retrieves all employees' skill data from the HR database. Specifically, it executes an SQL query to retrieve the skill information of all employees.

[0063] Step 2:

[0064] The server retrieves MBO data from the performance management system. This uses API requests to retrieve each employee's goals and their achievement status.

[0065] Step 3:

[0066] The server retrieves customer information from the CRM system. A RESTful API is used to extract customer information from the existing CRM system.

[0067] Step 4:

[0068] The server retrieves project information from the project management system. It collects information about the project's objectives, schedule, and resources via an API.

[0069] Step 5:

[0070] The server retrieves product information from the product database. It obtains data such as product specifications, release schedules, and related projects.

[0071] Step 6:

[0072] All data acquired by the server is preprocessed. This includes normalizing text data, converting formats, and supplementing missing data.

[0073] Step 7:

[0074] The server inputs pre-processed data into a generative AI model. The data is converted to JSON format and loaded into the AI ​​model as training data.

[0075] Step 8:

[0076] The server begins training the generative AI model. The AI ​​model is trained using data to acquire the necessary predictive capabilities.

[0077] Step 9:

[0078] The device provides an interface for the user to input questions. It displays input fields for web forms and desktop applications.

[0079] Step 10:

[0080] The user enters a work-related question into the terminal. For example, they might enter, "Who is the best employee for the next project?"

[0081] Step 11:

[0082] The terminal sends the user's question to the server. RESTful APIs or message queues are used to send user queries to the server.

[0083] Step 12:

[0084] The server inputs the received question into a generative AI model. The AI ​​model is then called to analyze the question and generate an appropriate answer.

[0085] Step 13:

[0086] The AI ​​model generates answers based on the input questions. For example, based on the training data, it might recommend "Ichiro Tanaka and Jiro Suzuki are the best employees for the next project."

[0087] Step 14:

[0088] The server formats the generated response, converting it into a user-friendly format and adding necessary information.

[0089] Step 15:

[0090] The device displays formatted answers to the user. The results are displayed in a visually easy-to-understand interface.

[0091] The above outlines the specific process by which the system generates and provides the optimal answer to a user's question.

[0092] (Example 1)

[0093] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0094] Traditional systems made it difficult to integrate and manage skill data, MBO data, customer information, project information, and product information for all employees of a company. Furthermore, there was insufficient means to quickly provide information useful for each employee's work based on this data, hindering operational efficiency. In addition, because this data includes highly confidential information, appropriate security measures are necessary.

[0095] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0096] In this invention, the server includes means for collecting skill data of all employees, means for collecting MBO data of all employees, means for collecting customer information, means for collecting project information, means for collecting product information, means for normalizing the collected data and removing unnecessary line breaks and special characters, means for converting the preprocessed data into a unified format, means for inputting the data converted into a unified format into a generative AI model, means for receiving user questions, means for transmitting the received questions to the server, means for the server to generate answers based on the received questions using the generative AI model, and means for formatting the generated answers and presenting them to the user. This makes it possible to integrate individual data and provide information quickly and accurately using a generative AI model, thereby improving operational efficiency and ensuring security.

[0097] "Skill data" refers to information about the skills and abilities that employees possess.

[0098] "MBO data" refers to data related to the goals and results achieved by employees based on the Management by Objectives (MBO) system.

[0099] "Customer information" refers to information about customers and partners with whom a company conducts business.

[0100] "Project information" refers to data about ongoing projects within a company, including project progress and information about the members involved.

[0101] "Product information" refers to information about the products and services that a company offers.

[0102] "Preprocessing" is the process of normalizing collected data and removing unnecessary line breaks and special characters.

[0103] "Unified formatting" refers to the process of converting information obtained from different data sources into a consistent format.

[0104] A "generative AI model" is an artificial intelligence model that generates text based on a large amount of data, such as GPT.

[0105] "Question reception" refers to the process of receiving inquiries from users.

[0106] "Submitting a question" refers to the act of sending a user's question to the server.

[0107] "Answer generation" refers to the act of generating appropriate answers based on received questions using a generative AI model.

[0108] "Answer formatting" is the process of preparing the generated answers into a format that can be presented to the user.

[0109] This invention integrates all employees' skill data, MBO data, customer information, project information, and product information to provide information useful for each employee's work. This system consists of three main components: a server, a terminal, and a user, each performing a specific function.

[0110] server

[0111] The server collects necessary information from multiple data sources and performs preprocessing. It also analyzes the data using generative AI models to generate optimal answers to user questions.

[0112] Data Collection: The server retrieves skill data for all employees from the HR database. It also retrieves MBO data from the performance management system, customer information from the CRM system, project information from the project management system, and product information from the product database.

[0113] Hardware / software used: AWS® EC2, AWS RDS

[0114] Specific examples of operation:

[0115] SQL query: SELECT FROM skills WHERE employee_id IS NOT NULL;

[0116] API call: curl -X GET https: / / api.example.com / mbo-data

[0117] Preprocessing: The acquired data is normalized, and unnecessary line breaks and special characters are removed. Then, the data format is standardized and converted to, for example, JSON format.

[0118] Hardware / software used: Python script

[0119] Specific examples of operation:

[0120] Special character removal: str.replace('\n', ' ').replace('\t', ' ')

[0121] JSON conversion: json.dumps(data)

[0122] AI model training: Preprocessed data is input into a generative AI model (e.g., GPT) to train the model.

[0123] Hardware / software used: OpenAI® GPT-3®, Python script

[0124] Specific examples of operation:

[0125] Execute the script: python train_model.py --data<path_to_preprocessed_data>

[0126] terminal

[0127] The terminal provides an interface for users to input questions into the system and view the results. It is typically implemented as a web application or desktop application.

[0128] Interface provision: The terminal provides a form where the user can enter a question. For example, it can accept questions such as, "Who is the best employee for the next project?"

[0129] Hardware / software used: HTML, JavaScript (registered trademark)

[0130] Specific examples of operation:

[0131] Question form: <input type="text" id="userQuestion">

[0132] Send event: document.getElementById('sendButton').onclick = sendQuestion;

[0133] Data transmission: The terminal sends the user's question to the server.

[0134] Hardware / software used: Fetch API, JSON

[0135] Specific examples of operation:

[0136] Converting the question to JSON: let questionData = JSON.stringify({ question: userQuestion});

[0137] HTTP POST request: fetch(' / api / questions', { method: 'POST', body: questionData});

[0138] User

[0139] Users can use this system to quickly obtain information related to their work.

[0140] Question Input: Enter specific work-related questions into the terminal. For example, "Who is the best employee for the next project?"

[0141] Specific example of operation: Enter "Who is the best employee for the next project?" into the inquiry form and click the submit button.

[0142] Example of question and answer processing

[0143] 1. User: Enters the question "Who is the best employee for the next project?" into the terminal.

[0144] 2. Terminal: Receives questions and sends their contents to the server.

[0145] 3. Server: Receives questions and inputs them into the generative AI model.

[0146] 4. AI Model: Generates the best answer to a question based on training data (e.g., Employee A, Employee B).

[0147] 5. Server: Receives the generated response and formats it into a format to be returned to the user.

[0148] 6. Terminal: Displays formatted answers to the user.

[0149] This system will allow users to quickly obtain information useful for their work, and is expected to improve work efficiency.

[0150] security

[0151] Because the system handles highly confidential company information, it operates in a closed environment. This environment restricts external access and is designed to minimize the risk of information leakage. Specifically, this includes firewall configuration and the regular application of security patches.

[0152] Based on the above, the present invention provides specific means for each employee to quickly acquire information necessary for their work and to improve work efficiency.

[0153] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0154] Step 1:

[0155] The server collects skill data for all employees from the HR database. The server issues SQL queries to retrieve the skill data and converts this dataset into a list of skills for each employee. The input to this process is the HR database, and the output is a list of skill data.

[0156] Specific example of operation: SELECT FROM skills WHERE employee_id IS NOT NULL;

[0157] Step 2:

[0158] The server calls the performance management system's API to collect MBO data. The MBO information is retrieved via the API call and organized as performance data for each employee. The input to this process is the performance management system's API endpoint, and the output is a list of MBO data.

[0159] Specific example of operation: curl -X GET https: / / api.example.com / mbo-data

[0160] Step 3:

[0161] The server interacts with the CRM system to collect customer information. The server retrieves customer information via an API and stores that data in a database. The input to this process is the CRM system's API, and the output is a list of customer information.

[0162] Specific example of operation: curl -X GET https: / / api.example.com / clients

[0163] Step 4:

[0164] The server retrieves project information from the project management system's database. It issues SQL queries to obtain the project information and converts it into a list format. The input to this process is the project management system's database, and the output is a list of project information.

[0165] Specific example of operation: SELECT FROM projects WHERE status='active';

[0166] Step 5:

[0167] The server accesses the product database and collects product information. It issues SQL queries to retrieve product information and converts the data into a list format. The input to this process is the product database, and the output is a list of product information.

[0168] Specific example of operation: SELECT FROM products;

[0169] Step 6:

[0170] The server normalizes the collected data and removes unnecessary line breaks and special characters. A Python script is used to perform the data cleaning. The input to this process is the various collected data, and the output is the normalized dataset.

[0171] Specific example of operation: str.replace('\n', ' ').replace('\t', ' ')

[0172] Step 7:

[0173] The server converts the preprocessed data into a unified format (e.g., JSON). A Python script is used to perform this data format conversion. The input to this process is the preprocessed data, and the output is a unified format dataset.

[0174] Specific example of operation: json.dumps(data)

[0175] Step 8:

[0176] The server inputs data converted to a unified format into a generative AI model (e.g., GPT) and trains the model. It runs a training script and provides data to ensure the model performs optimally. The input to this process is a dataset in a unified format, and the output is a trained AI model.

[0177] Specific example of operation: python train_model.py --data<path_to_preprocessed_data>

[0178] Step 9:

[0179] Users enter specific business-related questions through a web form. The entered questions are converted to JSON format and sent from the terminal to the server. The input for this process is the user's questions, and the output is the question data sent to the server.

[0180] Specific example of operation: let questionData = JSON.stringify({ question: userQuestion});

[0181] Step 10:

[0182] The terminal receives the user's question and sends its contents to the server. The question data is sent to the server using an HTTP POST request. The input to this process is the question data in JSON format, and the output is the request sent to the server.

[0183] Specific example of operation: fetch(' / api / questions', { method: 'POST', body: questionData});

[0184] Step 11:

[0185] The server inputs the received question into a generative AI model and generates the optimal answer. The AI ​​model generates the answer based on the training data and returns the result to the server. The input to this process is the user's question data, and the output is the generated answer.

[0186] Specific example of operation: let formattedQuestion = formatForAIModel(questionData);

[0187] Step 12:

[0188] The server receives the generated response and formats it for presentation to the user. The formatted response is returned to the terminal as an HTTP response. The input to this process is the generated response, and the output is the response presented to the user.

[0189] Specific example of operation: let jsonResponse = JSON.stringify({ answer: generatedAnswer});

[0190] Step 13:

[0191] The terminal displays the responses received from the server to the user. The generated responses are visualized through a web interface. The input to this process is the response data from the server, and the output is the information presented to the user.

[0192] Specific example of operation: document.getElementById('answerDisplay').innerText = response.answer;

[0193] Step 14:

[0194] The server manages the system to ensure it operates in a closed environment. It regularly performs firewall configuration and applies security patches. The input to this process is the configuration information of the operating environment, and the output is a secure system state.

[0195] Specific example of operation: iptables -A INPUT -p tcp --dport 80 -j ACCEPT

[0196] (Application Example 1)

[0197] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0198] Modern factories require improved efficiency in each work area and the overall system, while simultaneously enabling rapid responses to anomalies. Monitoring robot status, managing work progress, and identifying necessary actions are particularly crucial for on-site technicians. However, there is a lack of systems that adequately collect and analyze this data and provide the necessary information immediately. Existing systems struggle with centralized data management and anomaly detection, potentially delaying rapid responses. Therefore, a system is needed that supports efficient factory operations and enables rapid responses to anomalies.

[0199] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0200] In this invention, the server includes means for collecting skill data of all employees, means for collecting MBO data of all employees, means for collecting customer information, means for collecting project information, means for collecting product information, means for preprocessing the collected data, means for inputting the preprocessed data into a generative artificial intelligence model, means for receiving user questions, means for the generative artificial intelligence model to generate answers based on the received questions, means for presenting the generated answers to the user, means for on-site workers to check the status of robots and work progress in real time through smart glasses, means for providing optimal actions to each robot and worker, and means for immediately notifying and proposing countermeasures in the event of an anomaly. This makes it possible to centrally manage various data within the factory, grasp the situation on-site in real time, and propose the optimal work to be done next. Furthermore, it is possible to respond quickly in the event of an anomaly and improve the efficiency of the entire factory.

[0201] "All employee skill data" refers to data on the skills, expertise, qualifications, and experience of all employees throughout the company.

[0202] "MBO data for all employees" refers to data related to achievement targets and performance evaluations based on the goal management system for all employees.

[0203] "Customer information" refers to information about customers and partner companies with which a company does business.

[0204] "Project information" refers to information about each project, such as its progress, assigned personnel, schedule, and resources.

[0205] "Product information" refers to information about the products and services that a company handles.

[0206] A "generative artificial intelligence model" is an artificial intelligence model that uses natural language processing technology to generate appropriate answers and suggestions based on input data.

[0207] "Means of receiving user questions" refers to interfaces or devices that allow users to input questions into the system.

[0208] "Means for generating answers" refers to a mechanism that uses a generative artificial intelligence model to generate the optimal answer to a user's question.

[0209] "Means of presenting answers to users" refers to a mechanism that provides the generated answers to users in an easy-to-read format.

[0210] "Smart glasses" are wearable devices that have the function of integrating and displaying digital information in addition to information from the real world.

[0211] "Methods for real-time monitoring" refer to technologies and interfaces that instantly acquire on-site conditions and data, and provide users with the necessary information on the spot.

[0212] "Means for immediate notification and proposal of countermeasures in the event of an anomaly" refers to a mechanism for promptly issuing a warning and proposing necessary countermeasures when an anomaly is detected within the factory.

[0213] This invention is a system that integrates all employees' skill data, MBO data, customer information, project information, and product information to provide information useful for the work of each employee and field worker. This system consists of three main components: a server, terminals, and users.

[0214] server

[0215] The server collects necessary information from multiple data sources and performs preprocessing. Then, it inputs the data into a generative artificial intelligence model (e.g., GPT) to allow it to learn.

[0216] 1. Data Collection

[0217] The server retrieves skill data for all employees from the HR database and MBO data from the performance management system. It also retrieves customer information from the CRM system, project information from the project management system, and product information from the product database.

[0218] 2. Preprocessing

[0219] The acquired data is normalized, removing unnecessary line breaks and special characters. The format is standardized and converted to a format suitable for artificial intelligence models (e.g., JSON). This ensures data consistency and accuracy. Specifically, numerical data is standardized using libraries such as StandardScaler.

[0220] 3. Input to the AI ​​model

[0221] Preprocessed data is input into a generative artificial intelligence model, and the necessary training is performed. Examples of generative AI models used include GPT-2 and GPT-3. Examples of prompts include, "Who is the best employee for the next project?" and "What is the best action for the robot at this point?"

[0222] terminal

[0223] The terminal provides an interface for users to input questions into the system and view the results.

[0224] 1. Interface provision

[0225] The terminal provides a form where users can enter questions. For example, it might accept questions such as, "Who is the best employee for the next project?"

[0226] 2. Data transmission

[0227] The terminal sends the user's question to the server.

[0228] 3. Display results

[0229] The generated responses are displayed in a user-friendly format. When using smart glasses, the status of robots in the factory and the progress of their work can be checked in real time. A user interface (UI) for this purpose is included.

[0230] User

[0231] Users can use this system to quickly obtain information related to their work.

[0232] 1. Enter your question

[0233] Users input specific, work-related questions into the terminal. For example, they might ask questions like, "Who is the best employee for the next project?" or "What is the current status of the robots on site?"

[0234] 2. Check the results

[0235] Review the generated results and decide on the next action. For example, you can determine the optimal employee allocation or the next work instructions for the robots.

[0236] Specific example

[0237] For example, if a user asks, "Who is the best employee for the next project?", the server inputs pre-processed data into a generative artificial intelligence model and generates the optimal answer. This answer is then presented to the user via a terminal. Similarly, if a field worker uses smart glasses to ask, "What is the best action for the robot at this moment?", the server can use the generative artificial intelligence model based on real-time data to provide the optimal work instructions.

[0238] As described above, this invention is a system that enables on-site workers to obtain appropriate information in real time and respond quickly.

[0239] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0240] Step 1:

[0241] The server collects data from various data sources. Specifically, it retrieves skill data for all employees from the HR database and MBO data from the performance management system. It also retrieves customer information from the CRM system and project information from the project management system. Furthermore, it retrieves product information from the product database. The input data consists of data from various systems, and the output is a dictionary-format dataset containing the respective data.

[0242] Step 2:

[0243] The server preprocesses the collected data. Specifically, it normalizes skill data, MBO data, customer information, project information, and product information. During this process, unnecessary line breaks and special characters are removed from text data, and numerical data is standardized using StandardScaler. The input is the raw data collected in step 1, and the output is the preprocessed, clean data.

[0244] Step 3:

[0245] The server inputs preprocessed data into a generative artificial intelligence model. Specifically, this data is converted to JSON format and input into the AI ​​model (e.g., GPT-2 or GPT-3). Here, the input is preprocessed data, and the output is the trained dataset in the generative artificial intelligence model.

[0246] Step 4:

[0247] The terminal accepts user questions. When a user enters a question into the terminal's input form, it accepts questions such as, "Who is the best employee for the next project?" The input is the user's question, and the output is the string data of that question.

[0248] Step 5:

[0249] The terminal sends the user's question to the server. The input is the user's question text, and the output is the question data sent to the server.

[0250] Step 6:

[0251] The server inputs a question into a generative artificial intelligence model and generates an answer. Specifically, the server combines collected preprocessed data with the user's question and inputs it into the AI ​​model to generate the optimal answer. The input consists of the user's question and preprocessed data, while the output is the generated answer text.

[0252] Step 7:

[0253] The server formats the generated response and returns it to the terminal. Specifically, it receives the output from the AI ​​model and formats it into a format that is easy for the user to understand. The input is the output text from the AI ​​model, and the output is the formatted response text.

[0254] Step 8:

[0255] The terminal presents the formatted response to the user. When using smart glasses, this response is displayed so that field workers can view it in real time. The input is the formatted response text, and the output is the display data shown to the user.

[0256] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0257] This invention provides a system that integrates all employees' skill data, MBO data, customer information, project information, and product information to provide information useful for each employee's work, and combines this with an emotion engine to recognize user emotions, thereby providing even more comprehensive feedback and support. This system consists of three main components: a server, a terminal, and a user, each performing a specific function.

[0258] server

[0259] The server collects necessary information from multiple data sources and performs preprocessing. It then inputs this data into a generative AI model for training. Furthermore, it recognizes user emotions and provides appropriate feedback and support information.

[0260] Data Collection and Preprocessing: Skill data for all employees is obtained from the HR database, MBO data from the performance management system, customer information from the CRM system, project information from the project management system, and product information from the product database. After normalizing and standardizing the format of this data, it is input into a generative AI model.

[0261] Inputting and training the AI ​​model: Preprocessed data is input into the generative AI model, and the necessary learning is performed.

[0262] Emotion Engine: Analyzes user input and performs emotion recognition.

[0263] terminal

[0264] The terminal provides an interface for users to input questions into the system and view the results. It is typically implemented as a web application or desktop application.

[0265] Interface provision: The device provides a form where the user can enter a question, and the emotion engine recognizes the user's emotions as they enter the question.

[0266] Data transmission: The terminal sends the user's questions and the results of the sentiment engine's recognition to the server.

[0267] User

[0268] Users can use this system to quickly obtain information about their work and receive emotion-based feedback and support.

[0269] Question Input: Enter specific, work-related questions into the terminal. For example, "Who is the best employee for the next project?" The user's emotions are also recognized during this process.

[0270] Specific example of processing

[0271] The following are specific examples of how the system generates answers to particular questions and provides appropriate feedback.

[0272] 1. User: When entering the question, "Who is the best employee for the next project?", if the user is feeling anxious, the emotion engine will recognize that emotion based on facial recognition and text analysis technology.

[0273] 2. Terminal: Sends sentiment data to the server along with the question.

[0274] 3. Server: Receives questions and sentiment data and inputs them into a generative AI model.

[0275] 4. AI Model: Based on the learning data, it generates the optimal answer to the question and adjusts the feedback content based on the recognized emotion. For example, when the answer is "The optimal candidates for the next project are Ichiro Tanaka and Jiro Suzuki", additional encouragement and support information are also provided to users who recognize an uneasy emotion.

[0276] 5. Server: Formats the generated answer and the adjusted feedback and returns them to the terminal.

[0277] 6. Terminal: Displays the formatted answer and feedback to the user.

[0278] As a result, the user can quickly obtain information about the optimal employees for the next project and also receive appropriate support based on their emotion.

[0279] Security

[0280] To handle company-confidential information, the system is operated in a closed environment. In this environment, external access is restricted and it is designed to minimize the risk of information leakage.

[0281] As described above, the present invention provides specific means for each employee to quickly obtain the information necessary for their work and further provide feedback and support based on the user's emotion.

[0282] The following describes the processing flow.

[0283] Step 1:

[0284] The server retrieves the skill data of all employees from the personnel database. Specifically, it executes an SQL query to obtain the skill information of all employees.

[0285] Step 2:

[0286] The server retrieves MBO data from the performance management system. This uses an API request to obtain the goals and achievement status of each employee.

[0287] Step 3:

[0288] The server retrieves customer information from the CRM system. A RESTful API is used to extract information about customers from the existing CRM system.

[0289] Step 4:

[0290] The server retrieves project information from the project management system. Information about the project's objectives, schedule, and resources is collected via the API.

[0291] <00009​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​Step 9:

[0300] The terminal provides an interface for the user to input questions. It displays web forms and input fields of desktop applications.

[0301] Step 10:

[0302] The user inputs a work-related question into the terminal. For example, input "Who is the most suitable employee for the next project?"

[0303] Step 11:

[0304] When the terminal receives the user's question, it analyzes the user's emotion with an emotion engine. This is done using face recognition and text analysis.

[0305] Step 12:

[0306] When the terminal receives the question and emotion data, it sends them to the server. It uses a RESTful API or a message queue to send the user's query and emotion data to the server.

[0307] Step 13:

[0308] The server inputs the received question and emotion data into a generative AI model. It calls the AI model to generate an answer based on the question content and emotion data.

[0309] Step 14:

[0310] The AI model generates an answer based on the input question and emotion. For example, based on the training data, it recommends "Ichiro Tanaka and Jiro Suzuki are the most suitable employees for the next project."

[0311] Step 15:

[0312] The server formats the generated response, converting it into a user-friendly format and adding necessary information. It also provides additional encouragement and support based on the user's sentiment.

[0313] Step 16:

[0314] The device displays formatted answers to the user. The results are displayed in a visually easy-to-understand interface.

[0315] The above outlines the specific process flow from when the system generates and provides the optimal answer and feedback based on the user's questions and emotions.

[0316] (Example 2)

[0317] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0318] In today's business environment, there is a need for a system that can comprehensively manage and quickly access employee skills, performance evaluations, business partner information, project information, and product information. However, current systems manage this information in a dispersed manner, making it difficult to provide necessary information quickly and appropriately. Furthermore, they cannot provide feedback that responds to user emotions, limiting their ability to improve user satisfaction. Therefore, a system that combines integrated information management with emotion recognition capabilities is necessary.

[0319] The specific processing performed by the specific 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 skill data of all employees, means for collecting performance evaluation data of all employees, means for collecting business partner information, means for preprocessing the collected data, means for inputting the preprocessed data into a generative AI model, means for recognizing the user's emotions, means for receiving questions from the user, means for the generative AI model to generate answers based on the received questions, means for adjusting feedback based on the recognized emotions, and means for presenting the generated answers and adjusted feedback to the user. This makes it possible not only to generate quick and appropriate answers based on aggregated data, but also to provide feedback that is in line with the user's emotions.

[0320] "Skill data" refers to information about the specialized knowledge and skills that employees possess.

[0321] "Performance evaluation data" refers to information about an employee's past performance and achievements.

[0322] "Business partner information" refers to information about business partners and customers.

[0323] "Project information" refers to information about ongoing or completed projects.

[0324] "Product information" refers to information about products that the company manufactures and sells.

[0325] "Preprocessing" is the process of converting raw data into a format that can be used by the AI ​​model.

[0326] A "generative AI model" is an artificial intelligence model that generates natural language based on input data.

[0327] "Emotion recognition" is a technology that identifies emotions from a user's facial expressions or input text.

[0328] "Feedback" refers to supplementary information and advice provided in addition to the answers to user questions.

[0329] A "closed environment" is a secure operating environment where external access is restricted.

[0330] This invention is a system that integrates all employees' skill data, performance evaluation data, business partner information, project information, and product information to provide information useful for each employee's work. Furthermore, by incorporating an emotion engine to recognize user emotions, it provides more comprehensive feedback and support. This system consists of three main components: a server, a terminal, and a user, each performing a specific function.

[0331] server

[0332] The server's role is to collect information from multiple data sources and preprocess it. Specifically, it retrieves data from HR databases, performance management systems, CRM systems, project management systems, and product databases. This data is normalized into a unified format using libraries such as Pandas. Next, the preprocessed data is input into a generative AI model for training. Natural language generation models such as GPT-3 are used as generative AI models.

[0333] Furthermore, the emotion recognition engine installed on the server analyzes user input and recognizes the user's emotions. A specific emotion recognition API is used for this emotion recognition.

[0334] terminal

[0335] The terminal provides an interface for users to input questions into the system and view the results. It is typically implemented as a web or desktop application. It uses HTML or JavaScript to display user input forms and sends the user's questions to the server along with sentiment data analyzed by an emotion engine. As the user inputs a question, the emotion recognition engine analyzes the user's emotions and determines what kind of feedback is appropriate.

[0336] User

[0337] This system allows users to quickly obtain information about their work and receive emotion-based feedback and support. Specifically, they can input questions to identify the best employee for the next project. For example, they might input a question like, "Who is the best employee for the next project?" The system also automatically recognizes the user's emotions during this process.

[0338] Specific example

[0339] The following are specific examples of how the system generates answers to particular questions and provides appropriate feedback.

[0340] 1. User: When entering the question, "Who is the best employee for the next project?", if the user is feeling anxious, the emotion recognition API will analyze that emotion.

[0341] 2. Terminal: Sends recognized emotion data along with the question to the server.

[0342] 3. Server: Receives questions and sentiment data, inputs them into a generative AI model to generate answers, and adds encouraging feedback to address user anxieties.

[0343] 4. Server: Returns the generated response and adjusted feedback to the terminal.

[0344] 5. Device: Displays the received responses and feedback to the user.

[0345] In this way, users can quickly obtain useful information related to their work and receive appropriate support tailored to their needs.

[0346] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0347] Step 1:

[0348] Data Acquisition and Preprocessing

[0349] The server collects necessary information from various data sources. It retrieves skill data from the HR database and performance evaluation data from the performance management system. It also retrieves business partner information from the CRM system and project and product information from their respective systems.

[0350] Specifically, the server collects data and preprocesses it as follows:

[0351] Inputs: HR database, performance management system, CRM system, project management system, product database

[0352] Data Retrieval: Data is retrieved using SQL queries, RESTful APIs, and SOAP APIs. Examples: SQL query "SELECT FROM skills_table", RESTful API "GET / mbo-data", SOAP API query

[0353] Preprocessing: Normalize the collected data and convert it to a unified format using the Pandas library.

[0354] Output: Preprocessed dataset

[0355] Step 2:

[0356] emotion recognition

[0357] The server activates the emotion recognition engine and analyzes the user's input data. The emotion recognition engine analyzes the text and facial images entered by the user on the device to recognize the user's emotions.

[0358] Specifically, the server recognizes emotions in the following way:

[0359] Input: User text input, face image

[0360] Emotion recognition processing: Perform text analysis using "sentiment = model.predict(user_input_text)" and face recognition using "emotion = model.recognize(face_image)".

[0361] Output: User sentiment data

[0362] Step 3:

[0363] Receiving and sending user input data

[0364] The device collects questions from the user and sends them to the server along with sentiment data. The device uses HTML and JavaScript to display input forms for the user and collects the entered data.

[0365] Specifically, the terminal collects and transmits data in the following manner:

[0366] Input: User questions, sentiment data

[0367] Data transmission: Using JavaScript, user questions and sentiment data are sent to the server via AJAX requests.

[0368] Output: Question and sentiment data sent to the server

[0369] Step 4:

[0370] AI model-based question answer generation

[0371] The server inputs the received question and sentiment data into a generative AI model to generate an answer. The generative AI model generates the optimal answer based on the pre-processed data.

[0372] Specifically, the server generates the response as follows:

[0373] Input: User questions, sentiment data, preprocessed dataset

[0374] Model Input: Input the received data into the generative AI model. Example: "response = gpt3.generate(prompt)"

[0375] Output: Generated answer

[0376] Step 5:

[0377] Emotion-based feedback adjustment

[0378] The server reviews the generated responses and adjusts the feedback based on sentiment data. For example, if the user is feeling anxious, it adds an encouraging message to alleviate that anxiety.

[0379] Specifically, the server adjusts the feedback as follows:

[0380] Input: Generated responses, sentiment data

[0381] Feedback adjustment: "if user_emotion == 'anxiety': response += 'We will provide reassuring information to address your anxiety.'"

[0382] Output: Adjusted feedback

[0383] Step 6:

[0384] Send and view responses and feedback

[0385] The server sends the generated response and adjusted feedback to the device. The device then displays it to the user.

[0386] Specifically, the server and terminal send and display data in the following manner.

[0387] Input: Adjusted feedback

[0388] Data formatting and transmission: Execute "json_response = jsonify(response_data)" and return it as the API response.

[0389] Output: Responses and feedback displayed to the user

[0390] (Application Example 2)

[0391] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0392] In today's increasingly diverse work environment, there is a need to efficiently integrate vast amounts of data, such as employee skill data, performance data, client information, project information, and product information, and to provide appropriate feedback. Furthermore, it is necessary to recognize user emotions and provide feedback tailored to those situations in order to improve work efficiency and employee mental support. Since such a system does not exist, the objective of this invention is to provide a means to solve this problem.

[0393] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0394] In this invention, the server includes means for collecting skill data of all employees, means for collecting MBO data of all employees, means for collecting customer information, means for collecting project information, means for collecting product information, means for preprocessing the collected data, means for inputting the preprocessed data into a generative AI model, means for receiving user questions, means for the generative AI model to generate answers based on the received questions, means for presenting the generated answers to the user, means for recognizing the user's emotions, means for providing emotion-based feedback, and means for providing information to the user through various devices (including smart glasses). This makes it possible to efficiently utilize integrated data and provide appropriate answers to user questions and emotion-based feedback in real time.

[0395] "Means of collecting skill data for all employees" refers to a method for systematically acquiring and storing in a database the specialized knowledge, abilities, and work experience of all employees.

[0396] "Means for collecting MBO data from all employees" refers to methods for obtaining and recording the goal achievement status and evaluation results of all employees.

[0397] "Means of collecting customer information" refers to methods for acquiring and managing information about a company's business partners.

[0398] "Means of collecting project information" refers to methods for obtaining and storing detailed information about ongoing or past projects.

[0399] "Means of collecting product information" refers to methods for obtaining and managing detailed product information and performance data.

[0400] "Means for preprocessing collected data" refers to methods for normalizing information obtained from various data sources and converting it into a consistent format.

[0401] "Means for inputting pre-processed data into a generative AI model" refers to a method of inputting normalized data into an AI model and training the model.

[0402] "Means for receiving user inquiries" refers to an interface that accepts user inquiries and questions in an input format.

[0403] "A means by which a generative AI model generates an answer based on a received question" refers to a method for an AI model to generate an appropriate answer based on a question received from a user.

[0404] "Means of presenting generated answers to the user" refers to an interface for displaying answers generated by an AI model to the user.

[0405] "Means of recognizing user emotions" refers to methods for analyzing a user's facial expressions and tone of voice to determine their emotional state.

[0406] "Means of providing emotion-based feedback" refers to methods for providing appropriate feedback and support messages in accordance with the recognized emotions of the user.

[0407] "Means of providing information to users through various devices (including smart glasses)" refers to methods of providing information to users in real time using smart glasses or other wearable devices.

[0408] This invention is a system that integrates employee skill data, MBO data, customer information, project information, and product information, and combines them with an emotion recognition engine to provide comprehensive feedback and support. This system mainly consists of three main components: a server, a terminal, and a user.

[0409] server

[0410] The server plays the role of collecting necessary information from multiple data sources and performing preprocessing. The hardware used includes common cloud servers (e.g., AWS, Azure®). The collected data is then input into a generative AI model (e.g., OpenAI's GPT-4®) for training. Furthermore, an emotion engine (e.g., Affectiva, IBM Watson®) that analyzes user input and performs emotion recognition is also incorporated into the server. This enables the server to generate optimal answers to questions related to the user's work and provide appropriate, emotion-based feedback.

[0411] For example, the server performs the following data processing:

[0412] 1. Data Collection: Obtain skill data for all employees from the human resources management system, MBO data from the performance management system, customer information from the customer relationship management system, project information from the project management system, and product information from the product database.

[0413] 2. Data preprocessing: Normalize the acquired data and convert it into a consistent format.

[0414] 3. AI Model Input and Training: Preprocessed data is input into the generative AI model for training.

[0415] 4. Emotion Recognition: Analyzes user input and recognizes their emotional state.

[0416] terminal

[0417] The terminal plays the role of providing an interface for users to input questions into the system. While typically implemented as a web or desktop application, it can also be compatible with wearable devices such as smart glasses. The terminal sends the user's questions and their emotional data to the server, and displays the server's responses and feedback to the user.

[0418] As a concrete example, in a factory work support application using smart glasses, workers can wear the smart glasses and receive work instructions and encouraging messages in real time. For example, feedback such as, "The next task is to install part A. The necessary tools are a screwdriver and screws. If you are feeling stressed, please stay calm and proceed with the work," may be provided.

[0419] User

[0420] Users can use the system to quickly obtain work-related information and receive emotion-based feedback and support. When a question is entered, the system recognizes the user's emotions along with the question, resulting in more accurate feedback.

[0421] For example, if a user is feeling anxious when entering the question, "Who are the best employees for the next project?", they will be provided with feedback such as, "You have excellent team members. There's no need to worry."

[0422] Example of a prompt

[0423] Question: "What is the next task?"

[0424] Emotions: Stress

[0425] The generated message is: "The next task is to install part A. The necessary tools are a screwdriver and screws. Please proceed calmly."

[0426] The above describes the embodiments of the present invention. This system enables users to efficiently utilize integrated data and receive appropriate answers to work-related questions and sentiment-based feedback in real time.

[0427] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0428] Step 1:

[0429] The server collects employee skill data, MBO data, customer information, project information, and product information from multiple data sources. Inputs are from each data source, and output is an integrated dataset. Specifically, it retrieves data from human resources management systems, performance management systems, customer relationship management systems, project management systems, and product databases.

[0430] Step 2:

[0431] The server preprocesses the collected data. The input is an integrated dataset, and the output is normalized data. Specific operations include standardizing data formats and imputing missing values. Through this preprocessing, the data is transformed into a format suitable for generative AI models.

[0432] Step 3:

[0433] The server inputs pre-processed data into a generative AI model and trains the AI ​​model. The input is normalized data, and the output is the trained AI model. Specifically, data is fed into a generative AI model (e.g., OpenAI's GPT-4) to train it so that it can generate appropriate feedback and responses.

[0434] Step 4:

[0435] The user inputs a question into the system via a terminal. The input is the user's question, and the output is question data. The terminal uses an emotion engine to recognize the user's emotions in response to the question and generates question data and emotion data.

[0436] Step 5:

[0437] The terminal sends question data and sentiment data to the server. The input is question data and sentiment data, and the output is the server's reception. Specifically, data is sent to the server through the terminal's interface.

[0438] Step 6:

[0439] The server inputs the received question data and sentiment data into a generative AI model. The input consists of question data and sentiment data, and the output is the generated answer and appropriately adjusted feedback. The AI ​​model generates the optimal answer to the question, along with sentiment-based feedback.

[0440] Step 7:

[0441] The server formats the generated responses and feedback and sends them to the terminal. The input is the generated responses and feedback, and the output is the formatted data. Specifically, it reformats it into a user-friendly format.

[0442] Step 8:

[0443] The device displays formatted responses and feedback to the user. The input is formatted data, and the output is information provided to the user. Specifically, the information is displayed using smart glasses or other device displays.

[0444] As a concrete example, the following describes the behavior when a user asks, "Who is the best employee for the next project?" and is feeling anxious:

[0445] In Step 1, information is collected from each data source.

[0446] In step 2, the data is preprocessed.

[0447] In step 3, the generative AI model is trained.

[0448] In step 4, the user enters the question.

[0449] In step 5, the device sends the question and sentiment data to the server.

[0450] In step 6, the AI ​​model generates appropriate answers and emotion-based feedback.

[0451] In step 7, the server formats the data.

[0452] In step 8, the device displays the following message to the user: "Tanaka is the most suitable employee, and you can entrust the matter to him with confidence. Please do not worry."

[0453] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0454] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0455] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0456] [Second Embodiment]

[0457] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0458] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0459] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0460] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0461] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0462] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0463] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0464] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0465] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0466] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0467] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0468] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0469] This invention is a system that integrates all employees' skill data, MBO data, customer information, project information, and product information to provide information useful for each employee's work. This system consists of three main components: a server, a terminal, and a user, each performing a specific function.

[0470] server

[0471] The server collects necessary information from multiple data sources and performs preprocessing. Then, it inputs the data into a generative AI model (e.g., GPT) to allow it to learn.

[0472] Data Collection: The server retrieves skill data for all employees from the HR database. Next, it retrieves MBO data from the performance management system and customer information from the CRM system. It also retrieves project information from the project management system and product information from the product database.

[0473] Preprocessing: Normalize the acquired data, removing unnecessary line breaks and special characters. Unify the format and convert it to a format suitable for AI models (e.g., JSON format).

[0474] Input to the AI ​​model: Preprocessed data is input into a generative AI model, and the necessary training is performed.

[0475] terminal

[0476] The terminal provides an interface for users to input questions into the system and view the results. It is typically implemented as a web application or desktop application.

[0477] Interface provision: The terminal provides a form where the user can enter a question. For example, it can accept questions such as, "Who is the best employee for the next project?"

[0478] Data transmission: The terminal sends the user's question to the server.

[0479] User

[0480] Users can use this system to quickly obtain information related to their work.

[0481] Question Input: Enter specific work-related questions into the terminal. For example, "Who is the best employee for the next project?"

[0482] Specific example of processing

[0483] The following is a concrete example of how the system generates answers to specific questions.

[0484] 1. User: Enters the question "Who is the best employee for the next project?" into the terminal.

[0485] 2. Terminal: Receives questions and sends their contents to the server.

[0486] 3. Server: Receives questions and inputs them into the generative AI model.

[0487] 4. AI Model: Generates the best answer to a question based on training data (e.g., Employee A, Employee B).

[0488] 5. Server: Receives the generated response and formats it into a format to be returned to the user.

[0489] 6. Terminal: Displays formatted answers to the user.

[0490] As a result, users can instantly obtain information on the best employees for their next project, improving work efficiency and productivity.

[0491] security

[0492] Because the system handles highly confidential company information, it operates in a closed environment. This environment is designed to restrict external access and minimize the risk of information leakage.

[0493] Based on the above, the present invention provides specific means for each employee to quickly acquire information necessary for their work and to improve work efficiency.

[0494] The following describes the processing flow.

[0495] Step 1:

[0496] The server retrieves all employees' skill data from the HR database. Specifically, it executes an SQL query to retrieve the skill information of all employees.

[0497] Step 2:

[0498] The server retrieves MBO data from the performance management system. This uses API requests to retrieve each employee's goals and their achievement status.

[0499] Step 3:

[0500] The server retrieves customer information from the CRM system. A RESTful API is used to extract customer information from the existing CRM system.

[0501] Step 4:

[0502] The server retrieves project information from the project management system. It collects information about the project's objectives, schedule, and resources via an API.

[0503] Step 5:

[0504] The server retrieves product information from the product database. It obtains data such as product specifications, release schedules, and related projects.

[0505] Step 6:

[0506] All data acquired by the server is preprocessed. This includes normalizing text data, converting formats, and supplementing missing data.

[0507] Step 7:

[0508] The server inputs pre-processed data into a generative AI model. The data is converted to JSON format and loaded into the AI ​​model as training data.

[0509] Step 8:

[0510] The server begins training the generative AI model. The AI ​​model is trained using data to acquire the necessary predictive capabilities.

[0511] Step 9:

[0512] The device provides an interface for the user to input questions. It displays input fields for web forms and desktop applications.

[0513] Step 10:

[0514] The user enters a work-related question into the terminal. For example, they might enter, "Who is the best employee for the next project?"

[0515] Step 11:

[0516] The terminal sends the user's question to the server. RESTful APIs or message queues are used to send user queries to the server.

[0517] Step 12:

[0518] The server inputs the received question into a generative AI model. The AI ​​model is then called to analyze the question and generate an appropriate answer.

[0519] Step 13:

[0520] The AI ​​model generates answers based on the input questions. For example, based on the training data, it might recommend "Ichiro Tanaka and Jiro Suzuki are the best employees for the next project."

[0521] Step 14:

[0522] The server formats the generated response, converting it into a user-friendly format and adding necessary information.

[0523] Step 15:

[0524] The device displays formatted answers to the user. The results are displayed in a visually easy-to-understand interface.

[0525] The above outlines the specific process by which the system generates and provides the optimal answer to a user's question.

[0526] (Example 1)

[0527] Next, we will describe Example 1. 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."

[0528] Traditional systems made it difficult to integrate and manage skill data, MBO data, customer information, project information, and product information for all employees of a company. Furthermore, there was insufficient means to quickly provide information useful for each employee's work based on this data, hindering operational efficiency. In addition, because this data includes highly confidential information, appropriate security measures are necessary.

[0529] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0530] In this invention, the server includes means for collecting skill data of all employees, means for collecting MBO data of all employees, means for collecting customer information, means for collecting project information, means for collecting product information, means for normalizing the collected data and removing unnecessary line breaks and special characters, means for converting the preprocessed data into a unified format, means for inputting the data converted into a unified format into a generative AI model, means for receiving user questions, means for transmitting the received questions to the server, means for the server to generate answers based on the received questions using the generative AI model, and means for formatting the generated answers and presenting them to the user. This makes it possible to integrate individual data and provide information quickly and accurately using a generative AI model, thereby improving operational efficiency and ensuring security.

[0531] "Skill data" refers to information about the skills and abilities that employees possess.

[0532] "MBO data" refers to data related to the goals and results achieved by employees based on the Management by Objectives (MBO) system.

[0533] "Customer information" refers to information about customers and partners with whom a company conducts business.

[0534] "Project information" refers to data about ongoing projects within a company, including project progress and information about the members involved.

[0535] "Product information" refers to information about the products and services that a company offers.

[0536] "Preprocessing" is the process of normalizing collected data and removing unnecessary line breaks and special characters.

[0537] "Unified formatting" refers to the process of converting information obtained from different data sources into a consistent format.

[0538] A "generative AI model" is an artificial intelligence model that generates text based on a large amount of data, such as GPT.

[0539] "Question reception" refers to the process of receiving inquiries from users.

[0540] "Submitting a question" refers to the act of sending a user's question to the server.

[0541] "Answer generation" refers to the act of generating appropriate answers based on received questions using a generative AI model.

[0542] "Answer formatting" is the process of preparing the generated answers into a format that can be presented to the user.

[0543] This invention integrates all employees' skill data, MBO data, customer information, project information, and product information to provide information useful for each employee's work. This system consists of three main components: a server, a terminal, and a user, each performing a specific function.

[0544] server

[0545] The server collects necessary information from multiple data sources and performs preprocessing. It also analyzes the data using generative AI models to generate optimal answers to user questions.

[0546] Data Collection: The server retrieves skill data for all employees from the HR database. It also retrieves MBO data from the performance management system, customer information from the CRM system, project information from the project management system, and product information from the product database.

[0547] Hardware / software used: AWS EC2, AWS RDS

[0548] Specific examples of operation:

[0549] SQL query: SELECT FROM skills WHERE employee_id IS NOT NULL;

[0550] API call: curl -X GET https: / / api.example.com / mbo-data

[0551] Preprocessing: The acquired data is normalized, and unnecessary line breaks and special characters are removed. Then, the data format is standardized and converted to, for example, JSON format.

[0552] Hardware / software used: Python script

[0553] Specific examples of operation:

[0554] Special character removal: str.replace('\n', ' ').replace('\t', ' ')

[0555] JSON conversion: json.dumps(data)

[0556] AI model training: Preprocessed data is input into a generative AI model (e.g., GPT) to train the model.

[0557] Hardware / software used: OpenAI GPT-3, Python scripts

[0558] Specific examples of operation:

[0559] Execute the script: python train_model.py --data<path_to_preprocessed_data>

[0560] terminal

[0561] The terminal provides an interface for users to input questions into the system and view the results. It is typically implemented as a web application or desktop application.

[0562] Interface provision: The terminal provides a form where the user can enter a question. For example, it can accept questions such as, "Who is the best employee for the next project?"

[0563] Hardware / software used: HTML, JavaScript

[0564] Specific examples of operation:

[0565] Question form: <input type="text" id="userQuestion">

[0566] Send event: document.getElementById('sendButton').onclick = sendQuestion;

[0567] Data transmission: The terminal sends the user's question to the server.

[0568] Hardware / software used: Fetch API, JSON

[0569] Specific examples of operation:

[0570] Converting the question to JSON: let questionData = JSON.stringify({ question: userQuestion});

[0571] HTTP POST request: fetch(' / api / questions', { method: 'POST', body: questionData});

[0572] User

[0573] Users can use this system to quickly obtain information related to their work.

[0574] Question Input: Enter specific work-related questions into the terminal. For example, "Who is the best employee for the next project?"

[0575] Specific example of operation: Enter "Who is the best employee for the next project?" into the inquiry form and click the submit button.

[0576] Example of question and answer processing

[0577] 1. User: Enters the question "Who is the best employee for the next project?" into the terminal.

[0578] 2. Terminal: Receives questions and sends their contents to the server.

[0579] 3. Server: Receives questions and inputs them into the generative AI model.

[0580] 4. AI Model: Generates the best answer to a question based on training data (e.g., Employee A, Employee B).

[0581] 5. Server: Receives the generated response and formats it into a format to be returned to the user.

[0582] 6. Terminal: Displays formatted answers to the user.

[0583] This system will allow users to quickly obtain information useful for their work, and is expected to improve work efficiency.

[0584] security

[0585] Because the system handles highly confidential company information, it operates in a closed environment. This environment restricts external access and is designed to minimize the risk of information leakage. Specifically, this includes firewall configuration and the regular application of security patches.

[0586] Based on the above, the present invention provides specific means for each employee to quickly acquire information necessary for their work and to improve work efficiency.

[0587] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0588] Step 1:

[0589] The server collects skill data for all employees from the HR database. The server issues SQL queries to retrieve the skill data and converts this dataset into a list of skills for each employee. The input to this process is the HR database, and the output is a list of skill data.

[0590] Specific example of operation: SELECT FROM skills WHERE employee_id IS NOT NULL;

[0591] Step 2:

[0592] The server calls the performance management system's API to collect MBO data. The MBO information is retrieved via the API call and organized as performance data for each employee. The input to this process is the performance management system's API endpoint, and the output is a list of MBO data.

[0593] Specific example of operation: curl -X GET https: / / api.example.com / mbo-data

[0594] Step 3:

[0595] The server interacts with the CRM system to collect customer information. The server retrieves customer information via an API and stores that data in a database. The input to this process is the CRM system's API, and the output is a list of customer information.

[0596] Specific example of operation: curl -X GET https: / / api.example.com / clients

[0597] Step 4:

[0598] The server retrieves project information from the project management system's database. It issues SQL queries to obtain the project information and converts it into a list format. The input to this process is the project management system's database, and the output is a list of project information.

[0599] Specific example of operation: SELECT FROM projects WHERE status='active';

[0600] Step 5:

[0601] The server accesses the product database and collects product information. It issues SQL queries to retrieve product information and converts the data into a list format. The input to this process is the product database, and the output is a list of product information.

[0602] Specific example of operation: SELECT FROM products;

[0603] Step 6:

[0604] The server normalizes the collected data and removes unnecessary line breaks and special characters. A Python script is used to perform the data cleaning. The input to this process is the various collected data, and the output is the normalized dataset.

[0605] Specific example of operation: str.replace('\n', ' ').replace('\t', ' ')

[0606] Step 7:

[0607] The server converts the preprocessed data into a unified format (e.g., JSON). A Python script is used to perform this data format conversion. The input to this process is the preprocessed data, and the output is a unified format dataset.

[0608] Specific example of operation: json.dumps(data)

[0609] Step 8:

[0610] The server inputs data converted to a unified format into a generative AI model (e.g., GPT) and trains the model. It runs a training script and provides data to ensure the model performs optimally. The input to this process is a dataset in a unified format, and the output is a trained AI model.

[0611] Specific example of operation: python train_model.py --data<path_to_preprocessed_data>

[0612] Step 9:

[0613] Users enter specific business-related questions through a web form. The entered questions are converted to JSON format and sent from the terminal to the server. The input for this process is the user's questions, and the output is the question data sent to the server.

[0614] Specific example of operation: let questionData = JSON.stringify({ question: userQuestion});

[0615] Step 10:

[0616] The terminal receives the user's question and sends its contents to the server. The question data is sent to the server using an HTTP POST request. The input to this process is the question data in JSON format, and the output is the request sent to the server.

[0617] Specific example of operation: fetch(' / api / questions', { method: 'POST', body: questionData});

[0618] Step 11:

[0619] The server inputs the received question into a generative AI model and generates the optimal answer. The AI ​​model generates the answer based on the training data and returns the result to the server. The input to this process is the user's question data, and the output is the generated answer.

[0620] Specific example of operation: let formattedQuestion = formatForAIModel(questionData);

[0621] Step 12:

[0622] The server receives the generated response and formats it for presentation to the user. The formatted response is returned to the terminal as an HTTP response. The input to this process is the generated response, and the output is the response presented to the user.

[0623] Specific example of operation: let jsonResponse = JSON.stringify({ answer: generatedAnswer});

[0624] Step 13:

[0625] The terminal displays the responses received from the server to the user. The generated responses are visualized through a web interface. The input to this process is the response data from the server, and the output is the information presented to the user.

[0626] Specific example of operation: document.getElementById('answerDisplay').innerText = response.answer;

[0627] Step 14:

[0628] The server manages the system to ensure it operates in a closed environment. It regularly performs firewall configuration and applies security patches. The input to this process is the configuration information of the operating environment, and the output is a secure system state.

[0629] Specific example of operation: iptables -A INPUT -p tcp --dport 80 -j ACCEPT

[0630] (Application Example 1)

[0631] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0632] Modern factories require improved efficiency in each work area and the overall system, while simultaneously enabling rapid responses to anomalies. Monitoring robot status, managing work progress, and identifying necessary actions are particularly crucial for on-site technicians. However, there is a lack of systems that adequately collect and analyze this data and provide the necessary information immediately. Existing systems struggle with centralized data management and anomaly detection, potentially delaying rapid responses. Therefore, a system is needed that supports efficient factory operations and enables rapid responses to anomalies.

[0633] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0634] In this invention, the server includes means for collecting skill data of all employees, means for collecting MBO data of all employees, means for collecting customer information, means for collecting project information, means for collecting product information, means for preprocessing the collected data, means for inputting the preprocessed data into a generative artificial intelligence model, means for receiving user questions, means for the generative artificial intelligence model to generate answers based on the received questions, means for presenting the generated answers to the user, means for on-site workers to check the status of robots and work progress in real time through smart glasses, means for providing optimal actions to each robot and worker, and means for immediately notifying and proposing countermeasures in the event of an anomaly. This makes it possible to centrally manage various data within the factory, grasp the situation on-site in real time, and propose the optimal work to be done next. Furthermore, it is possible to respond quickly in the event of an anomaly and improve the efficiency of the entire factory.

[0635] "All employee skill data" refers to data on the skills, expertise, qualifications, and experience of all employees throughout the company.

[0636] "MBO data for all employees" refers to data related to achievement targets and performance evaluations based on the goal management system for all employees.

[0637] "Customer information" refers to information about customers and partner companies with which a company does business.

[0638] "Project information" refers to information about each project, such as its progress, assigned personnel, schedule, and resources.

[0639] "Product information" refers to information about the products and services that a company handles.

[0640] A "generative artificial intelligence model" is an artificial intelligence model that uses natural language processing technology to generate appropriate answers and suggestions based on input data.

[0641] "Means of receiving user questions" refers to interfaces or devices that allow users to input questions into the system.

[0642] "Means for generating answers" refers to a mechanism that uses a generative artificial intelligence model to generate the optimal answer to a user's question.

[0643] "Means of presenting answers to users" refers to a mechanism that provides the generated answers to users in an easy-to-read format.

[0644] "Smart glasses" are wearable devices that have the function of integrating and displaying digital information in addition to information from the real world.

[0645] "Methods for real-time monitoring" refer to technologies and interfaces that instantly acquire on-site conditions and data, and provide users with the necessary information on the spot.

[0646] "Means for immediate notification and proposal of countermeasures in the event of an anomaly" refers to a mechanism for promptly issuing a warning and proposing necessary countermeasures when an anomaly is detected within the factory.

[0647] This invention is a system that integrates all employees' skill data, MBO data, customer information, project information, and product information to provide information useful for the work of each employee and field worker. This system consists of three main components: a server, terminals, and users.

[0648] server

[0649] The server collects necessary information from multiple data sources and performs preprocessing. Then, it inputs the data into a generative artificial intelligence model (e.g., GPT) to allow it to learn.

[0650] 1. Data Collection

[0651] The server retrieves skill data for all employees from the HR database and MBO data from the performance management system. It also retrieves customer information from the CRM system, project information from the project management system, and product information from the product database.

[0652] 2. Preprocessing

[0653] The acquired data is normalized, removing unnecessary line breaks and special characters. The format is standardized and converted to a format suitable for artificial intelligence models (e.g., JSON). This ensures data consistency and accuracy. Specifically, numerical data is standardized using libraries such as StandardScaler.

[0654] 3. Input to the AI ​​model

[0655] Preprocessed data is input into a generative artificial intelligence model, and the necessary training is performed. Examples of generative AI models used include GPT-2 and GPT-3. Examples of prompts include, "Who is the best employee for the next project?" and "What is the best action for the robot at this point?"

[0656] terminal

[0657] The terminal provides an interface for users to input questions into the system and view the results.

[0658] 1. Interface provision

[0659] The terminal provides a form where users can enter questions. For example, it might accept questions such as, "Who is the best employee for the next project?"

[0660] 2. Data transmission

[0661] The terminal sends the user's question to the server.

[0662] 3. Display results

[0663] The generated responses are displayed in a user-friendly format. When using smart glasses, the status of robots in the factory and the progress of their work can be checked in real time. A user interface (UI) for this purpose is included.

[0664] User

[0665] Users can use this system to quickly obtain information related to their work.

[0666] 1. Enter your question

[0667] Users input specific, work-related questions into the terminal. For example, they might ask questions like, "Who is the best employee for the next project?" or "What is the current status of the robots on site?"

[0668] 2. Check the results

[0669] Review the generated results and decide on the next action. For example, you can determine the optimal employee allocation or the next work instructions for the robots.

[0670] Specific example

[0671] For example, if a user asks, "Who is the best employee for the next project?", the server inputs pre-processed data into a generative artificial intelligence model and generates the optimal answer. This answer is then presented to the user via a terminal. Similarly, if a field worker uses smart glasses to ask, "What is the best action for the robot at this moment?", the server can use the generative artificial intelligence model based on real-time data to provide the optimal work instructions.

[0672] As described above, this invention is a system that enables on-site workers to obtain appropriate information in real time and respond quickly.

[0673] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0674] Step 1:

[0675] The server collects data from various data sources. Specifically, it retrieves skill data for all employees from the HR database and MBO data from the performance management system. It also retrieves customer information from the CRM system and project information from the project management system. Furthermore, it retrieves product information from the product database. The input data consists of data from various systems, and the output is a dictionary-format dataset containing the respective data.

[0676] Step 2:

[0677] The server preprocesses the collected data. Specifically, it normalizes skill data, MBO data, customer information, project information, and product information. During this process, unnecessary line breaks and special characters are removed from text data, and numerical data is standardized using StandardScaler. The input is the raw data collected in step 1, and the output is the preprocessed, clean data.

[0678] Step 3:

[0679] The server inputs preprocessed data into a generative artificial intelligence model. Specifically, this data is converted to JSON format and input into the AI ​​model (e.g., GPT-2 or GPT-3). Here, the input is preprocessed data, and the output is the trained dataset in the generative artificial intelligence model.

[0680] Step 4:

[0681] The terminal accepts user questions. When a user enters a question into the terminal's input form, it accepts questions such as, "Who is the best employee for the next project?" The input is the user's question, and the output is the string data of that question.

[0682] Step 5:

[0683] The terminal sends the user's question to the server. The input is the user's question text, and the output is the question data sent to the server.

[0684] Step 6:

[0685] The server inputs a question into a generative artificial intelligence model and generates an answer. Specifically, the server combines collected preprocessed data with the user's question and inputs it into the AI ​​model to generate the optimal answer. The input consists of the user's question and preprocessed data, while the output is the generated answer text.

[0686] Step 7:

[0687] The server formats the generated response and returns it to the terminal. Specifically, it receives the output from the AI ​​model and formats it into a format that is easy for the user to understand. The input is the output text from the AI ​​model, and the output is the formatted response text.

[0688] Step 8:

[0689] The terminal presents the formatted response to the user. When using smart glasses, this response is displayed so that field workers can view it in real time. The input is the formatted response text, and the output is the display data shown to the user.

[0690] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0691] This invention provides a system that integrates all employees' skill data, MBO data, customer information, project information, and product information to provide information useful for each employee's work, and combines this with an emotion engine to recognize user emotions, thereby providing even more comprehensive feedback and support. This system consists of three main components: a server, a terminal, and a user, each performing a specific function.

[0692] server

[0693] The server collects necessary information from multiple data sources and performs preprocessing. It then inputs this data into a generative AI model for training. Furthermore, it recognizes user emotions and provides appropriate feedback and support information.

[0694] Data Collection and Preprocessing: Skill data for all employees is obtained from the HR database, MBO data from the performance management system, customer information from the CRM system, project information from the project management system, and product information from the product database. After normalizing and standardizing the format of this data, it is input into a generative AI model.

[0695] Inputting and training the AI ​​model: Preprocessed data is input into the generative AI model, and the necessary learning is performed.

[0696] Emotion Engine: Analyzes user input and performs emotion recognition.

[0697] terminal

[0698] The terminal provides an interface for users to input questions into the system and view the results. It is typically implemented as a web application or desktop application.

[0699] Interface provision: The device provides a form where the user can enter a question, and the emotion engine recognizes the user's emotions as they enter the question.

[0700] Data transmission: The terminal sends the user's questions and the results of the sentiment engine's recognition to the server.

[0701] User

[0702] Users can use this system to quickly obtain information about their work and receive emotion-based feedback and support.

[0703] Question Input: Enter specific, work-related questions into the terminal. For example, "Who is the best employee for the next project?" The user's emotions are also recognized during this process.

[0704] Specific example of processing

[0705] The following are specific examples of how the system generates answers to particular questions and provides appropriate feedback.

[0706] 1. User: When entering the question, "Who is the best employee for the next project?", if the user is feeling anxious, the emotion engine will recognize that emotion based on facial recognition and text analysis technology.

[0707] 2. Terminal: Sends sentiment data to the server along with the question.

[0708] 3. Server: Receives questions and sentiment data and inputs them into a generative AI model.

[0709] 4. AI Model: Based on training data, it generates the best possible answers to questions and adjusts the feedback based on recognized emotions. For example, if the answer is "The best candidates for the next project are Ichiro Tanaka and Jiro Suzuki," it will also provide additional encouragement and support information to users who are perceived as feeling anxious.

[0710] 5. Server: Formats the generated responses and adjusted feedback and returns them to the terminal.

[0711] 6. Terminal: Displays formatted answers and feedback to the user.

[0712] As a result, users can quickly obtain information on the best employees for their next project, and also receive appropriate support based on their emotions.

[0713] security

[0714] Because the system handles highly confidential company information, it operates in a closed environment. This environment is designed to restrict external access and minimize the risk of information leakage.

[0715] Based on the above, the present invention provides specific means for each employee to quickly acquire information necessary for their work, and further to provide feedback and support based on user emotions.

[0716] The following describes the processing flow.

[0717] Step 1:

[0718] The server retrieves skill data for all employees from the HR database. Specifically, it executes an SQL query to retrieve skill information for all employees.

[0719] Step 2:

[0720] The server retrieves MBO data from the performance management system. This uses API requests to retrieve each employee's goals and their achievement status.

[0721] Step 3:

[0722] The server retrieves customer information from the CRM system. A RESTful API is used to extract customer information from the existing CRM system.

[0723] Step 4:

[0724] The server retrieves project information from the project management system. It collects information about the project's objectives, schedule, and resources via an API.

[0725] Step 5:

[0726] The server retrieves product information from the product database. It obtains data such as product specifications, release schedules, and related projects.

[0727] Step 6:

[0728] All data acquired by the server is preprocessed. This includes normalizing text data, converting formats, and supplementing missing data.

[0729] Step 7:

[0730] The server inputs pre-processed data into a generative AI model. The data is converted to JSON format and loaded into the AI ​​model as training data.

[0731] Step 8:

[0732] The server begins training the generative AI model. The AI ​​model is trained using data to acquire the necessary predictive capabilities.

[0733] Step 9:

[0734] The device provides an interface for the user to input questions. It displays input fields for web forms and desktop applications.

[0735] Step 10:

[0736] The user enters a work-related question into the terminal. For example, they might enter, "Who is the best employee for the next project?"

[0737] Step 11:

[0738] When the device receives a user's question, it analyzes the user's emotions using an emotion engine. This is done using facial recognition and text analysis.

[0739] Step 12:

[0740] The device sends questions and sentiment data to the server. RESTful APIs and message queues are used to send user queries and sentiment data to the server.

[0741] Step 13:

[0742] The server inputs the received question and sentiment data into a generative AI model. The AI ​​model is then invoked to generate an answer based on the question and sentiment data.

[0743] Step 14:

[0744] The AI ​​model generates answers based on the input question and its associated emotions. For example, based on the training data, it might recommend "Ichiro Tanaka and Jiro Suzuki are the best employees for the next project."

[0745] Step 15:

[0746] The server formats the generated response, converting it into a user-friendly format and adding necessary information. It also provides additional encouragement and support based on the user's sentiment.

[0747] Step 16:

[0748] The device displays formatted answers to the user. The results are displayed in a visually easy-to-understand interface.

[0749] The above outlines the specific process flow from when the system generates and provides the optimal answer and feedback based on the user's questions and emotions.

[0750] (Example 2)

[0751] Next, we will describe Example 2. 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".

[0752] In today's business environment, there is a need for a system that can comprehensively manage and quickly access employee skills, performance evaluations, business partner information, project information, and product information. However, current systems manage this information in a dispersed manner, making it difficult to provide necessary information quickly and appropriately. Furthermore, they cannot provide feedback that responds to user emotions, limiting their ability to improve user satisfaction. Therefore, a system that combines integrated information management with emotion recognition capabilities is necessary.

[0753] The specific processing performed by the specific 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 skill data of all employees, means for collecting performance evaluation data of all employees, means for collecting business partner information, means for preprocessing the collected data, means for inputting the preprocessed data into a generative AI model, means for recognizing the user's emotions, means for receiving questions from the user, means for the generative AI model to generate answers based on the received questions, means for adjusting feedback based on the recognized emotions, and means for presenting the generated answers and adjusted feedback to the user. This makes it possible not only to generate quick and appropriate answers based on aggregated data, but also to provide feedback that is in line with the user's emotions.

[0754] "Skill data" refers to information about the specialized knowledge and skills that employees possess.

[0755] "Performance evaluation data" refers to information about an employee's past performance and achievements.

[0756] "Business partner information" refers to information about business partners and customers.

[0757] "Project information" refers to information about ongoing or completed projects.

[0758] "Product information" refers to information about products that the company manufactures and sells.

[0759] "Preprocessing" is the process of converting raw data into a format that can be used by the AI ​​model.

[0760] A "generative AI model" is an artificial intelligence model that generates natural language based on input data.

[0761] "Emotion recognition" is a technology that identifies emotions from a user's facial expressions or input text.

[0762] "Feedback" refers to supplementary information and advice provided in addition to the answers to user questions.

[0763] A "closed environment" is a secure operating environment where external access is restricted.

[0764] This invention is a system that integrates all employees' skill data, performance evaluation data, business partner information, project information, and product information to provide information useful for each employee's work. Furthermore, by incorporating an emotion engine to recognize user emotions, it provides more comprehensive feedback and support. This system consists of three main components: a server, a terminal, and a user, each performing a specific function.

[0765] server

[0766] The server's role is to collect information from multiple data sources and preprocess it. Specifically, it retrieves data from HR databases, performance management systems, CRM systems, project management systems, and product databases. This data is normalized into a unified format using libraries such as Pandas. Next, the preprocessed data is input into a generative AI model for training. Natural language generation models such as GPT-3 are used as generative AI models.

[0767] Furthermore, the emotion recognition engine installed on the server analyzes user input and recognizes the user's emotions. A specific emotion recognition API is used for this emotion recognition.

[0768] terminal

[0769] The terminal provides an interface for users to input questions into the system and view the results. It is typically implemented as a web or desktop application. It uses HTML or JavaScript to display user input forms and sends the user's questions to the server along with sentiment data analyzed by an emotion engine. As the user inputs a question, the emotion recognition engine analyzes the user's emotions and determines what kind of feedback is appropriate.

[0770] User

[0771] This system allows users to quickly obtain information about their work and receive emotion-based feedback and support. Specifically, they can input questions to identify the best employee for the next project. For example, they might input a question like, "Who is the best employee for the next project?" The system also automatically recognizes the user's emotions during this process.

[0772] Specific example

[0773] The following are specific examples of how the system generates answers to particular questions and provides appropriate feedback.

[0774] 1. User: When entering the question, "Who is the best employee for the next project?", if the user is feeling anxious, the emotion recognition API will analyze that emotion.

[0775] 2. Terminal: Sends recognized emotion data along with the question to the server.

[0776] 3. Server: Receives questions and sentiment data, inputs them into a generative AI model to generate answers, and adds encouraging feedback to address user anxieties.

[0777] 4. Server: Returns the generated response and adjusted feedback to the terminal.

[0778] 5. Device: Displays the received responses and feedback to the user.

[0779] In this way, users can quickly obtain useful information related to their work and receive appropriate support tailored to their needs.

[0780] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0781] Step 1:

[0782] Data Acquisition and Preprocessing

[0783] The server collects necessary information from various data sources. It retrieves skill data from the HR database and performance evaluation data from the performance management system. It also retrieves business partner information from the CRM system and project and product information from their respective systems.

[0784] Specifically, the server collects data and preprocesses it as follows:

[0785] Inputs: HR database, performance management system, CRM system, project management system, product database

[0786] Data Retrieval: Data is retrieved using SQL queries, RESTful APIs, and SOAP APIs. Examples: SQL query "SELECT FROM skills_table", RESTful API "GET / mbo-data", SOAP API query

[0787] Preprocessing: Normalize the collected data and convert it to a unified format using the Pandas library.

[0788] Output: Preprocessed dataset

[0789] Step 2:

[0790] emotion recognition

[0791] The server activates the emotion recognition engine and analyzes the user's input data. The emotion recognition engine analyzes the text and facial images entered by the user on the device to recognize the user's emotions.

[0792] Specifically, the server recognizes emotions in the following way:

[0793] Input: User text input, face image

[0794] Emotion recognition processing: Perform text analysis using "sentiment = model.predict(user_input_text)" and face recognition using "emotion = model.recognize(face_image)".

[0795] Output: User sentiment data

[0796] Step 3:

[0797] Receiving and sending user input data

[0798] The device collects questions from the user and sends them to the server along with sentiment data. The device uses HTML and JavaScript to display input forms for the user and collects the entered data.

[0799] Specifically, the terminal collects and transmits data in the following manner:

[0800] Input: User questions, sentiment data

[0801] Data transmission: Using JavaScript, user questions and sentiment data are sent to the server via AJAX requests.

[0802] Output: Question and sentiment data sent to the server

[0803] Step 4:

[0804] AI model-based question answer generation

[0805] The server inputs the received question and sentiment data into a generative AI model to generate an answer. The generative AI model generates the optimal answer based on the pre-processed data.

[0806] Specifically, the server generates the response as follows:

[0807] Input: User questions, sentiment data, preprocessed dataset

[0808] Model Input: Input the received data into the generative AI model. Example: "response = gpt3.generate(prompt)"

[0809] Output: Generated answer

[0810] Step 5:

[0811] Emotion-based feedback adjustment

[0812] The server reviews the generated responses and adjusts the feedback based on sentiment data. For example, if the user is feeling anxious, it adds an encouraging message to alleviate that anxiety.

[0813] Specifically, the server adjusts the feedback as follows:

[0814] Input: Generated responses, sentiment data

[0815] Feedback adjustment: "if user_emotion == 'anxiety': response += 'We will provide reassuring information to address your anxiety.'"

[0816] Output: Adjusted feedback

[0817] Step 6:

[0818] Send and view responses and feedback

[0819] The server sends the generated response and adjusted feedback to the device. The device then displays it to the user.

[0820] Specifically, the server and terminal send and display data in the following manner.

[0821] Input: Adjusted feedback

[0822] Data formatting and transmission: Execute "json_response = jsonify(response_data)" and return it as the API response.

[0823] Output: Responses and feedback displayed to the user

[0824] (Application Example 2)

[0825] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0826] In today's increasingly diverse work environment, there is a need to efficiently integrate vast amounts of data, such as employee skill data, performance data, client information, project information, and product information, and to provide appropriate feedback. Furthermore, it is necessary to recognize user emotions and provide feedback tailored to those situations in order to improve work efficiency and employee mental support. Since such a system does not exist, the objective of this invention is to provide a means to solve this problem.

[0827] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0828] In this invention, the server includes means for collecting skill data of all employees, means for collecting MBO data of all employees, means for collecting customer information, means for collecting project information, means for collecting product information, means for preprocessing the collected data, means for inputting the preprocessed data into a generative AI model, means for receiving user questions, means for the generative AI model to generate answers based on the received questions, means for presenting the generated answers to the user, means for recognizing the user's emotions, means for providing emotion-based feedback, and means for providing information to the user through various devices (including smart glasses). This makes it possible to efficiently utilize integrated data and provide appropriate answers to user questions and emotion-based feedback in real time.

[0829] "Means of collecting skill data for all employees" refers to a method for systematically acquiring and storing in a database the specialized knowledge, abilities, and work experience of all employees.

[0830] "Means for collecting MBO data from all employees" refers to methods for obtaining and recording the goal achievement status and evaluation results of all employees.

[0831] "Means of collecting customer information" refers to methods for acquiring and managing information about a company's business partners.

[0832] "Means of collecting project information" refers to methods for obtaining and storing detailed information about ongoing or past projects.

[0833] "Means of collecting product information" refers to methods for obtaining and managing detailed product information and performance data.

[0834] "Means for preprocessing collected data" refers to methods for normalizing information obtained from various data sources and converting it into a consistent format.

[0835] "Means for inputting pre-processed data into a generative AI model" refers to a method of inputting normalized data into an AI model and training the model.

[0836] "Means for receiving user inquiries" refers to an interface that accepts user inquiries and questions in an input format.

[0837] "A means by which a generative AI model generates an answer based on a received question" refers to a method for an AI model to generate an appropriate answer based on a question received from a user.

[0838] "Means of presenting generated answers to the user" refers to an interface for displaying answers generated by an AI model to the user.

[0839] "Means of recognizing user emotions" refers to methods for analyzing a user's facial expressions and tone of voice to determine their emotional state.

[0840] "Means of providing emotion-based feedback" refers to methods for providing appropriate feedback and support messages in accordance with the recognized emotions of the user.

[0841] "Means of providing information to users through various devices (including smart glasses)" refers to methods of providing information to users in real time using smart glasses or other wearable devices.

[0842] This invention is a system that integrates employee skill data, MBO data, customer information, project information, and product information, and combines them with an emotion recognition engine to provide comprehensive feedback and support. This system mainly consists of three main components: a server, a terminal, and a user.

[0843] server

[0844] The server plays the role of collecting necessary information from multiple data sources and performing preprocessing. The hardware used includes common cloud servers (e.g., AWS, Azure). It also inputs the collected data into a generative AI model (e.g., OpenAI's GPT-4) for training. Furthermore, an emotion engine (e.g., Affectiva, IBM Watson) that analyzes user input and performs sentiment recognition is also incorporated into the server. This enables the server to generate optimal answers to user work-related questions and provide appropriate, emotion-based feedback.

[0845] For example, the server performs the following data processing:

[0846] 1. Data Collection: Obtain skill data for all employees from the human resources management system, MBO data from the performance management system, customer information from the customer relationship management system, project information from the project management system, and product information from the product database.

[0847] 2. Data preprocessing: Normalize the acquired data and convert it into a consistent format.

[0848] 3. AI Model Input and Training: Preprocessed data is input into the generative AI model for training.

[0849] 4. Emotion Recognition: Analyzes user input and recognizes their emotional state.

[0850] terminal

[0851] The terminal plays the role of providing an interface for users to input questions into the system. While typically implemented as a web or desktop application, it can also be compatible with wearable devices such as smart glasses. The terminal sends the user's questions and their emotional data to the server, and displays the server's responses and feedback to the user.

[0852] As a concrete example, in a factory work support application using smart glasses, workers can wear the smart glasses and receive work instructions and encouraging messages in real time. For example, feedback such as, "The next task is to install part A. The necessary tools are a screwdriver and screws. If you are feeling stressed, please stay calm and proceed with the work," may be provided.

[0853] User

[0854] Users can use the system to quickly obtain work-related information and receive emotion-based feedback and support. When a question is entered, the system recognizes the user's emotions along with the question, resulting in more accurate feedback.

[0855] For example, if a user is feeling anxious when entering the question, "Who are the best employees for the next project?", they will be provided with feedback such as, "You have excellent team members. There's no need to worry."

[0856] Example of a prompt

[0857] Question: "What is the next task?"

[0858] Emotions: Stress

[0859] The generated message is: "The next task is to install part A. The necessary tools are a screwdriver and screws. Please proceed calmly."

[0860] The above describes the embodiments of the present invention. This system enables users to efficiently utilize integrated data and receive appropriate answers to work-related questions and sentiment-based feedback in real time.

[0861] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0862] Step 1:

[0863] The server collects employee skill data, MBO data, customer information, project information, and product information from multiple data sources. Inputs are from each data source, and output is an integrated dataset. Specifically, it retrieves data from human resources management systems, performance management systems, customer relationship management systems, project management systems, and product databases.

[0864] Step 2:

[0865] The server preprocesses the collected data. The input is an integrated dataset, and the output is normalized data. Specific operations include standardizing data formats and imputing missing values. Through this preprocessing, the data is transformed into a format suitable for generative AI models.

[0866] Step 3:

[0867] The server inputs pre-processed data into a generative AI model and trains the AI ​​model. The input is normalized data, and the output is the trained AI model. Specifically, data is fed into a generative AI model (e.g., OpenAI's GPT-4) to train it so that it can generate appropriate feedback and responses.

[0868] Step 4:

[0869] The user inputs a question into the system via a terminal. The input is the user's question, and the output is question data. The terminal uses an emotion engine to recognize the user's emotions in response to the question and generates question data and emotion data.

[0870] Step 5:

[0871] The terminal sends question data and sentiment data to the server. The input is question data and sentiment data, and the output is the server's reception. Specifically, data is sent to the server through the terminal's interface.

[0872] Step 6:

[0873] The server inputs the received question data and sentiment data into a generative AI model. The input consists of question data and sentiment data, and the output is the generated answer and appropriately adjusted feedback. The AI ​​model generates the optimal answer to the question, along with sentiment-based feedback.

[0874] Step 7:

[0875] The server formats the generated responses and feedback and sends them to the terminal. The input is the generated responses and feedback, and the output is the formatted data. Specifically, it reformats it into a user-friendly format.

[0876] Step 8:

[0877] The device displays formatted responses and feedback to the user. The input is formatted data, and the output is information provided to the user. Specifically, the information is displayed using smart glasses or other device displays.

[0878] As a concrete example, the following describes the behavior when a user asks, "Who is the best employee for the next project?" and is feeling anxious:

[0879] In Step 1, information is collected from each data source.

[0880] In step 2, the data is preprocessed.

[0881] In step 3, the generative AI model is trained.

[0882] In step 4, the user enters the question.

[0883] In step 5, the device sends the question and sentiment data to the server.

[0884] In step 6, the AI ​​model generates appropriate answers and emotion-based feedback.

[0885] In step 7, the server formats the data.

[0886] In step 8, the device displays the following message to the user: "Tanaka is the most suitable employee, and you can entrust the matter to him with confidence. Please do not worry."

[0887] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0888] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0889] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0890] [Third Embodiment]

[0891] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0892] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0893] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0894] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0895] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0896] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0897] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0898] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0899] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0900] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0901] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0902] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0903] This invention is a system that integrates all employees' skill data, MBO data, customer information, project information, and product information to provide information useful for each employee's work. This system consists of three main components: a server, a terminal, and a user, each performing a specific function.

[0904] server

[0905] The server collects necessary information from multiple data sources and performs preprocessing. Then, it inputs the data into a generative AI model (e.g., GPT) to allow it to learn.

[0906] Data Collection: The server retrieves skill data for all employees from the HR database. Next, it retrieves MBO data from the performance management system and customer information from the CRM system. It also retrieves project information from the project management system and product information from the product database.

[0907] Preprocessing: Normalize the acquired data, removing unnecessary line breaks and special characters. Unify the format and convert it to a format suitable for AI models (e.g., JSON format).

[0908] Input to the AI ​​model: Preprocessed data is input into a generative AI model, and the necessary training is performed.

[0909] terminal

[0910] The terminal provides an interface for users to input questions into the system and view the results. It is typically implemented as a web application or desktop application.

[0911] Interface provision: The terminal provides a form where the user can enter a question. For example, it can accept questions such as, "Who is the best employee for the next project?"

[0912] Data transmission: The terminal sends the user's question to the server.

[0913] User

[0914] Users can use this system to quickly obtain information related to their work.

[0915] Question Input: Enter specific work-related questions into the terminal. For example, "Who is the best employee for the next project?"

[0916] Specific example of processing

[0917] The following is a concrete example of how the system generates answers to specific questions.

[0918] 1. User: Enters the question "Who is the best employee for the next project?" into the terminal.

[0919] 2. Terminal: Receives questions and sends their contents to the server.

[0920] 3. Server: Receives questions and inputs them into the generative AI model.

[0921] 4. AI Model: Generates the best answer to a question based on training data (e.g., Employee A, Employee B).

[0922] 5. Server: Receives the generated response and formats it into a format to be returned to the user.

[0923] 6. Terminal: Displays formatted answers to the user.

[0924] As a result, users can instantly obtain information on the best employees for their next project, improving work efficiency and productivity.

[0925] security

[0926] Because the system handles highly confidential company information, it operates in a closed environment. This environment is designed to restrict external access and minimize the risk of information leakage.

[0927] Based on the above, the present invention provides specific means for each employee to quickly acquire information necessary for their work and to improve work efficiency.

[0928] The following describes the processing flow.

[0929] Step 1:

[0930] The server retrieves all employees' skill data from the HR database. Specifically, it executes an SQL query to retrieve the skill information of all employees.

[0931] Step 2:

[0932] The server retrieves MBO data from the performance management system. This uses API requests to retrieve each employee's goals and their achievement status.

[0933] Step 3:

[0934] The server retrieves customer information from the CRM system. A RESTful API is used to extract customer information from the existing CRM system.

[0935] Step 4:

[0936] The server retrieves project information from the project management system. It collects information about the project's objectives, schedule, and resources via an API.

[0937] Step 5:

[0938] The server retrieves product information from the product database. It obtains data such as product specifications, release schedules, and related projects.

[0939] Step 6:

[0940] All data acquired by the server is preprocessed. This includes normalizing text data, converting formats, and supplementing missing data.

[0941] Step 7:

[0942] The server inputs pre-processed data into a generative AI model. The data is converted to JSON format and loaded into the AI ​​model as training data.

[0943] Step 8:

[0944] The server begins training the generative AI model. The AI ​​model is trained using data to acquire the necessary predictive capabilities.

[0945] Step 9:

[0946] The device provides an interface for the user to input questions. It displays input fields for web forms and desktop applications.

[0947] Step 10:

[0948] The user enters a work-related question into the terminal. For example, they might enter, "Who is the best employee for the next project?"

[0949] Step 11:

[0950] The terminal sends the user's question to the server. RESTful APIs or message queues are used to send user queries to the server.

[0951] Step 12:

[0952] The server inputs the received question into a generative AI model. The AI ​​model is then called to analyze the question and generate an appropriate answer.

[0953] Step 13:

[0954] The AI ​​model generates answers based on the input questions. For example, based on the training data, it might recommend "Ichiro Tanaka and Jiro Suzuki are the best employees for the next project."

[0955] Step 14:

[0956] The server formats the generated response, converting it into a user-friendly format and adding necessary information.

[0957] Step 15:

[0958] The device displays formatted answers to the user. The results are displayed in a visually easy-to-understand interface.

[0959] The above outlines the specific process by which the system generates and provides the optimal answer to a user's question.

[0960] (Example 1)

[0961] Next, we will describe Example 1. 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."

[0962] Traditional systems made it difficult to integrate and manage skill data, MBO data, customer information, project information, and product information for all employees of a company. Furthermore, there was insufficient means to quickly provide information useful for each employee's work based on this data, hindering operational efficiency. In addition, because this data includes highly confidential information, appropriate security measures are necessary.

[0963] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0964] In this invention, the server includes means for collecting skill data of all employees, means for collecting MBO data of all employees, means for collecting customer information, means for collecting project information, means for collecting product information, means for normalizing the collected data and removing unnecessary line breaks and special characters, means for converting the preprocessed data into a unified format, means for inputting the data converted into a unified format into a generative AI model, means for receiving user questions, means for transmitting the received questions to the server, means for the server to generate answers based on the received questions using the generative AI model, and means for formatting the generated answers and presenting them to the user. This makes it possible to integrate individual data and provide information quickly and accurately using a generative AI model, thereby improving operational efficiency and ensuring security.

[0965] "Skill data" refers to information about the skills and abilities that employees possess.

[0966] "MBO data" refers to data related to the goals and results achieved by employees based on the Management by Objectives (MBO) system.

[0967] "Customer information" refers to information about customers and partners with whom a company conducts business.

[0968] "Project information" refers to data about ongoing projects within a company, including project progress and information about the members involved.

[0969] "Product information" refers to information about the products and services that a company offers.

[0970] "Preprocessing" is the process of normalizing collected data and removing unnecessary line breaks and special characters.

[0971] "Unified formatting" refers to the process of converting information obtained from different data sources into a consistent format.

[0972] A "generative AI model" is an artificial intelligence model that generates text based on a large amount of data, such as GPT.

[0973] "Question reception" refers to the process of receiving inquiries from users.

[0974] "Submitting a question" refers to the act of sending a user's question to the server.

[0975] "Answer generation" refers to the act of generating appropriate answers based on received questions using a generative AI model.

[0976] "Answer formatting" is the process of preparing the generated answers into a format that can be presented to the user.

[0977] This invention integrates all employees' skill data, MBO data, customer information, project information, and product information to provide information useful for each employee's work. This system consists of three main components: a server, a terminal, and a user, each performing a specific function.

[0978] server

[0979] The server collects necessary information from multiple data sources and performs preprocessing. It also analyzes the data using generative AI models to generate optimal answers to user questions.

[0980] Data Collection: The server retrieves skill data for all employees from the HR database. It also retrieves MBO data from the performance management system, customer information from the CRM system, project information from the project management system, and product information from the product database.

[0981] Hardware / software used: AWS EC2, AWS RDS

[0982] Specific examples of operation:

[0983] SQL query: SELECT FROM skills WHERE employee_id IS NOT NULL;

[0984] API call: curl -X GET https: / / api.example.com / mbo-data

[0985] Preprocessing: The acquired data is normalized, and unnecessary line breaks and special characters are removed. Then, the data format is standardized and converted to, for example, JSON format.

[0986] Hardware / software used: Python script

[0987] Specific examples of operation:

[0988] Special character removal: str.replace('\n', ' ').replace('\t', ' ')

[0989] JSON conversion: json.dumps(data)

[0990] AI model training: Preprocessed data is input into a generative AI model (e.g., GPT) to train the model.

[0991] Hardware / software used: OpenAI GPT-3, Python scripts

[0992] Specific examples of operation:

[0993] Execute the script: python train_model.py --data<path_to_preprocessed_data>

[0994] terminal

[0995] The terminal provides an interface for users to input questions into the system and view the results. It is typically implemented as a web application or desktop application.

[0996] Interface provision: The terminal provides a form where the user can enter a question. For example, it can accept questions such as, "Who is the best employee for the next project?"

[0997] Hardware / software used: HTML, JavaScript

[0998] Specific examples of operation:

[0999] Question form: <input type="text" id="userQuestion">

[1000] Send event: document.getElementById('sendButton').onclick = sendQuestion;

[1001] Data transmission: The terminal sends the user's question to the server.

[1002] Hardware / software used: Fetch API, JSON

[1003] Specific examples of operation:

[1004] Converting the question to JSON: let questionData = JSON.stringify({ question: userQuestion});

[1005] HTTP POST request: fetch(' / api / questions', { method: 'POST', body: questionData});

[1006] User

[1007] Users can use this system to quickly obtain information related to their work.

[1008] Question Input: Enter specific work-related questions into the terminal. For example, "Who is the best employee for the next project?"

[1009] Specific example of operation: Enter "Who is the best employee for the next project?" into the inquiry form and click the submit button.

[1010] Example of question and answer processing

[1011] 1. User: Enters the question "Who is the best employee for the next project?" into the terminal.

[1012] 2. Terminal: Receives questions and sends their contents to the server.

[1013] 3. Server: Receives questions and inputs them into the generative AI model.

[1014] 4. AI Model: Generates the best answer to a question based on training data (e.g., Employee A, Employee B).

[1015] 5. Server: Receives the generated response and formats it into a format to be returned to the user.

[1016] 6. Terminal: Displays formatted answers to the user.

[1017] This system will allow users to quickly obtain information useful for their work, and is expected to improve work efficiency.

[1018] security

[1019] Because the system handles highly confidential company information, it operates in a closed environment. This environment restricts external access and is designed to minimize the risk of information leakage. Specifically, this includes firewall configuration and the regular application of security patches.

[1020] Based on the above, the present invention provides specific means for each employee to quickly acquire information necessary for their work and to improve work efficiency.

[1021] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1022] Step 1:

[1023] The server collects skill data for all employees from the HR database. The server issues SQL queries to retrieve the skill data and converts this dataset into a list of skills for each employee. The input to this process is the HR database, and the output is a list of skill data.

[1024] Specific example of operation: SELECT FROM skills WHERE employee_id IS NOT NULL;

[1025] Step 2:

[1026] The server calls the performance management system's API to collect MBO data. The MBO information is retrieved via the API call and organized as performance data for each employee. The input to this process is the performance management system's API endpoint, and the output is a list of MBO data.

[1027] Specific example of operation: curl -X GET https: / / api.example.com / mbo-data

[1028] Step 3:

[1029] The server interacts with the CRM system to collect customer information. The server retrieves customer information via an API and stores that data in a database. The input to this process is the CRM system's API, and the output is a list of customer information.

[1030] Specific example of operation: curl -X GET https: / / api.example.com / clients

[1031] Step 4:

[1032] The server retrieves project information from the project management system's database. It issues SQL queries to obtain the project information and converts it into a list format. The input to this process is the project management system's database, and the output is a list of project information.

[1033] Specific example of operation: SELECT FROM projects WHERE status='active';

[1034] Step 5:

[1035] The server accesses the product database and collects product information. It issues SQL queries to retrieve product information and converts the data into a list format. The input to this process is the product database, and the output is a list of product information.

[1036] Specific example of operation: SELECT FROM products;

[1037] Step 6:

[1038] The server normalizes the collected data and removes unnecessary line breaks and special characters. A Python script is used to perform the data cleaning. The input to this process is the various collected data, and the output is the normalized dataset.

[1039] Specific example of operation: str.replace('\n', ' ').replace('\t', ' ')

[1040] Step 7:

[1041] The server converts the preprocessed data into a unified format (e.g., JSON). A Python script is used to perform this data format conversion. The input to this process is the preprocessed data, and the output is a unified format dataset.

[1042] Specific example of operation: json.dumps(data)

[1043] Step 8:

[1044] The server inputs data converted to a unified format into a generative AI model (e.g., GPT) and trains the model. It runs a training script and provides data to ensure the model performs optimally. The input to this process is a dataset in a unified format, and the output is a trained AI model.

[1045] Specific example of operation: python train_model.py --data<path_to_preprocessed_data>

[1046] Step 9:

[1047] Users enter specific business-related questions through a web form. The entered questions are converted to JSON format and sent from the terminal to the server. The input for this process is the user's questions, and the output is the question data sent to the server.

[1048] Specific example of operation: let questionData = JSON.stringify({ question: userQuestion});

[1049] Step 10:

[1050] The terminal receives the user's question and sends its contents to the server. The question data is sent to the server using an HTTP POST request. The input to this process is the question data in JSON format, and the output is the request sent to the server.

[1051] Specific example of operation: fetch(' / api / questions', { method: 'POST', body: questionData});

[1052] Step 11:

[1053] The server inputs the received question into a generative AI model and generates the optimal answer. The AI ​​model generates the answer based on the training data and returns the result to the server. The input to this process is the user's question data, and the output is the generated answer.

[1054] Specific example of operation: let formattedQuestion = formatForAIModel(questionData);

[1055] Step 12:

[1056] The server receives the generated response and formats it for presentation to the user. The formatted response is returned to the terminal as an HTTP response. The input to this process is the generated response, and the output is the response presented to the user.

[1057] Specific example of operation: let jsonResponse = JSON.stringify({ answer: generatedAnswer});

[1058] Step 13:

[1059] The terminal displays the responses received from the server to the user. The generated responses are visualized through a web interface. The input to this process is the response data from the server, and the output is the information presented to the user.

[1060] Specific example of operation: document.getElementById('answerDisplay').innerText = response.answer;

[1061] Step 14:

[1062] The server manages the system to ensure it operates in a closed environment. It regularly performs firewall configuration and applies security patches. The input to this process is the configuration information of the operating environment, and the output is a secure system state.

[1063] Specific example of operation: iptables -A INPUT -p tcp --dport 80 -j ACCEPT

[1064] (Application Example 1)

[1065] Next, we will explain Application Example 1. In the following explanation, 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."

[1066] Modern factories require improved efficiency in each work area and the overall system, while simultaneously enabling rapid responses to anomalies. Monitoring robot status, managing work progress, and identifying necessary actions are particularly crucial for on-site technicians. However, there is a lack of systems that adequately collect and analyze this data and provide the necessary information immediately. Existing systems struggle with centralized data management and anomaly detection, potentially delaying rapid responses. Therefore, a system is needed that supports efficient factory operations and enables rapid responses to anomalies.

[1067] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1068] In this invention, the server includes means for collecting skill data of all employees, means for collecting MBO data of all employees, means for collecting customer information, means for collecting project information, means for collecting product information, means for preprocessing the collected data, means for inputting the preprocessed data into a generative artificial intelligence model, means for receiving user questions, means for the generative artificial intelligence model to generate answers based on the received questions, means for presenting the generated answers to the user, means for on-site workers to check the status of robots and work progress in real time through smart glasses, means for providing optimal actions to each robot and worker, and means for immediately notifying and proposing countermeasures in the event of an anomaly. This makes it possible to centrally manage various data within the factory, grasp the situation on-site in real time, and propose the optimal work to be done next. Furthermore, it is possible to respond quickly in the event of an anomaly and improve the efficiency of the entire factory.

[1069] "All employee skill data" refers to data on the skills, expertise, qualifications, and experience of all employees throughout the company.

[1070] "MBO data for all employees" refers to data related to achievement targets and performance evaluations based on the goal management system for all employees.

[1071] "Customer information" refers to information about customers and partner companies with which a company does business.

[1072] "Project information" refers to information about each project, such as its progress, assigned personnel, schedule, and resources.

[1073] "Product information" refers to information about the products and services that a company handles.

[1074] A "generative artificial intelligence model" is an artificial intelligence model that uses natural language processing technology to generate appropriate answers and suggestions based on input data.

[1075] "Means of receiving user questions" refers to interfaces or devices that allow users to input questions into the system.

[1076] "Means for generating answers" refers to a mechanism that uses a generative artificial intelligence model to generate the optimal answer to a user's question.

[1077] "Means of presenting answers to users" refers to a mechanism that provides the generated answers to users in an easy-to-read format.

[1078] "Smart glasses" are wearable devices that have the function of integrating and displaying digital information in addition to information from the real world.

[1079] "Methods for real-time monitoring" refer to technologies and interfaces that instantly acquire on-site conditions and data, and provide users with the necessary information on the spot.

[1080] "Means for immediate notification and proposal of countermeasures in the event of an anomaly" refers to a mechanism for promptly issuing a warning and proposing necessary countermeasures when an anomaly is detected within the factory.

[1081] This invention is a system that integrates all employees' skill data, MBO data, customer information, project information, and product information to provide information useful for the work of each employee and field worker. This system consists of three main components: a server, terminals, and users.

[1082] server

[1083] The server collects necessary information from multiple data sources and performs preprocessing. Then, it inputs the data into a generative artificial intelligence model (e.g., GPT) to allow it to learn.

[1084] 1. Data Collection

[1085] The server retrieves skill data for all employees from the HR database and MBO data from the performance management system. It also retrieves customer information from the CRM system, project information from the project management system, and product information from the product database.

[1086] 2. Preprocessing

[1087] The acquired data is normalized, removing unnecessary line breaks and special characters. The format is standardized and converted to a format suitable for artificial intelligence models (e.g., JSON). This ensures data consistency and accuracy. Specifically, numerical data is standardized using libraries such as StandardScaler.

[1088] 3. Input to the AI ​​model

[1089] Preprocessed data is input into a generative artificial intelligence model, and the necessary training is performed. Examples of generative AI models used include GPT-2 and GPT-3. Examples of prompts include, "Who is the best employee for the next project?" and "What is the best action for the robot at this point?"

[1090] terminal

[1091] The terminal provides an interface for users to input questions into the system and view the results.

[1092] 1. Interface provision

[1093] The terminal provides a form where users can enter questions. For example, it might accept questions such as, "Who is the best employee for the next project?"

[1094] 2. Data transmission

[1095] The terminal sends the user's question to the server.

[1096] 3. Display results

[1097] The generated responses are displayed in a user-friendly format. When using smart glasses, the status of robots in the factory and the progress of their work can be checked in real time. A user interface (UI) for this purpose is included.

[1098] User

[1099] Users can use this system to quickly obtain information related to their work.

[1100] 1. Enter your question

[1101] Users input specific, work-related questions into the terminal. For example, they might ask questions like, "Who is the best employee for the next project?" or "What is the current status of the robots on site?"

[1102] 2. Check the results

[1103] Review the generated results and decide on the next action. For example, you can determine the optimal employee allocation or the next work instructions for the robots.

[1104] Specific example

[1105] For example, if a user asks, "Who is the best employee for the next project?", the server inputs pre-processed data into a generative artificial intelligence model and generates the optimal answer. This answer is then presented to the user via a terminal. Similarly, if a field worker uses smart glasses to ask, "What is the best action for the robot at this moment?", the server can use the generative artificial intelligence model based on real-time data to provide the optimal work instructions.

[1106] As described above, this invention is a system that enables on-site workers to obtain appropriate information in real time and respond quickly.

[1107] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1108] Step 1:

[1109] The server collects data from various data sources. Specifically, it retrieves skill data for all employees from the HR database and MBO data from the performance management system. It also retrieves customer information from the CRM system and project information from the project management system. Furthermore, it retrieves product information from the product database. The input data consists of data from various systems, and the output is a dictionary-format dataset containing the respective data.

[1110] Step 2:

[1111] The server preprocesses the collected data. Specifically, it normalizes skill data, MBO data, customer information, project information, and product information. During this process, unnecessary line breaks and special characters are removed from text data, and numerical data is standardized using StandardScaler. The input is the raw data collected in step 1, and the output is the preprocessed, clean data.

[1112] Step 3:

[1113] The server inputs preprocessed data into a generative artificial intelligence model. Specifically, this data is converted to JSON format and input into the AI ​​model (e.g., GPT-2 or GPT-3). Here, the input is preprocessed data, and the output is the trained dataset in the generative artificial intelligence model.

[1114] Step 4:

[1115] The terminal accepts user questions. When a user enters a question into the terminal's input form, it accepts questions such as, "Who is the best employee for the next project?" The input is the user's question, and the output is the string data of that question.

[1116] Step 5:

[1117] The terminal sends the user's question to the server. The input is the user's question text, and the output is the question data sent to the server.

[1118] Step 6:

[1119] The server inputs a question into a generative artificial intelligence model and generates an answer. Specifically, the server combines collected preprocessed data with the user's question and inputs it into the AI ​​model to generate the optimal answer. The input consists of the user's question and preprocessed data, while the output is the generated answer text.

[1120] Step 7:

[1121] The server formats the generated response and returns it to the terminal. Specifically, it receives the output from the AI ​​model and formats it into a format that is easy for the user to understand. The input is the output text from the AI ​​model, and the output is the formatted response text.

[1122] Step 8:

[1123] The terminal presents the formatted response to the user. When using smart glasses, this response is displayed so that field workers can view it in real time. The input is the formatted response text, and the output is the display data shown to the user.

[1124] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1125] This invention provides a system that integrates all employees' skill data, MBO data, customer information, project information, and product information to provide information useful for each employee's work, and combines this with an emotion engine to recognize user emotions, thereby providing even more comprehensive feedback and support. This system consists of three main components: a server, a terminal, and a user, each performing a specific function.

[1126] server

[1127] The server collects necessary information from multiple data sources and performs preprocessing. It then inputs this data into a generative AI model for training. Furthermore, it recognizes user emotions and provides appropriate feedback and support information.

[1128] Data Collection and Preprocessing: Skill data for all employees is obtained from the HR database, MBO data from the performance management system, customer information from the CRM system, project information from the project management system, and product information from the product database. After normalizing and standardizing the format of this data, it is input into a generative AI model.

[1129] Inputting and training the AI ​​model: Preprocessed data is input into the generative AI model, and the necessary learning is performed.

[1130] Emotion Engine: Analyzes user input and performs emotion recognition.

[1131] terminal

[1132] The terminal provides an interface for users to input questions into the system and view the results. It is typically implemented as a web application or desktop application.

[1133] Interface provision: The device provides a form where the user can enter a question, and the emotion engine recognizes the user's emotions as they enter the question.

[1134] Data transmission: The terminal sends the user's questions and the results of the sentiment engine's recognition to the server.

[1135] User

[1136] Users can use this system to quickly obtain information about their work and receive emotion-based feedback and support.

[1137] Question Input: Enter specific, work-related questions into the terminal. For example, "Who is the best employee for the next project?" The user's emotions are also recognized during this process.

[1138] Specific example of processing

[1139] The following are specific examples of how the system generates answers to particular questions and provides appropriate feedback.

[1140] 1. User: When entering the question, "Who is the best employee for the next project?", if the user is feeling anxious, the emotion engine will recognize that emotion based on facial recognition and text analysis technology.

[1141] 2. Terminal: Sends sentiment data to the server along with the question.

[1142] 3. Server: Receives questions and sentiment data and inputs them into a generative AI model.

[1143] 4. AI Model: Based on training data, it generates the best possible answers to questions and adjusts the feedback based on recognized emotions. For example, if the answer is "The best candidates for the next project are Ichiro Tanaka and Jiro Suzuki," it will also provide additional encouragement and support information to users who are perceived as feeling anxious.

[1144] 5. Server: Formats the generated responses and adjusted feedback and returns them to the terminal.

[1145] 6. Terminal: Displays formatted answers and feedback to the user.

[1146] As a result, users can quickly obtain information on the best employees for their next project, and also receive appropriate support based on their emotions.

[1147] security

[1148] Because the system handles highly confidential company information, it operates in a closed environment. This environment is designed to restrict external access and minimize the risk of information leakage.

[1149] Based on the above, the present invention provides specific means for each employee to quickly acquire information necessary for their work, and further to provide feedback and support based on user emotions.

[1150] The following describes the processing flow.

[1151] Step 1:

[1152] The server retrieves skill data for all employees from the HR database. Specifically, it executes an SQL query to retrieve skill information for all employees.

[1153] Step 2:

[1154] The server retrieves MBO data from the performance management system. This uses API requests to retrieve each employee's goals and their achievement status.

[1155] Step 3:

[1156] The server retrieves customer information from the CRM system. A RESTful API is used to extract customer information from the existing CRM system.

[1157] Step 4:

[1158] The server retrieves project information from the project management system. It collects information about the project's objectives, schedule, and resources via an API.

[1159] Step 5:

[1160] The server retrieves product information from the product database. It obtains data such as product specifications, release schedules, and related projects.

[1161] Step 6:

[1162] All data acquired by the server is preprocessed. This includes normalizing text data, converting formats, and supplementing missing data.

[1163] Step 7:

[1164] The server inputs pre-processed data into a generative AI model. The data is converted to JSON format and loaded into the AI ​​model as training data.

[1165] Step 8:

[1166] The server begins training the generative AI model. The AI ​​model is trained using data to acquire the necessary predictive capabilities.

[1167] Step 9:

[1168] The device provides an interface for the user to input questions. It displays input fields for web forms and desktop applications.

[1169] Step 10:

[1170] The user enters a work-related question into the terminal. For example, they might enter, "Who is the best employee for the next project?"

[1171] Step 11:

[1172] When the device receives a user's question, it analyzes the user's emotions using an emotion engine. This is done using facial recognition and text analysis.

[1173] Step 12:

[1174] The device sends questions and sentiment data to the server. RESTful APIs and message queues are used to send user queries and sentiment data to the server.

[1175] Step 13:

[1176] The server inputs the received question and sentiment data into a generative AI model. The AI ​​model is then invoked to generate an answer based on the question and sentiment data.

[1177] Step 14:

[1178] The AI ​​model generates answers based on the input question and its associated emotions. For example, based on the training data, it might recommend "Ichiro Tanaka and Jiro Suzuki are the best employees for the next project."

[1179] Step 15:

[1180] The server formats the generated response, converting it into a user-friendly format and adding necessary information. It also provides additional encouragement and support based on the user's sentiment.

[1181] Step 16:

[1182] The device displays formatted answers to the user. The results are displayed in a visually easy-to-understand interface.

[1183] The above outlines the specific process flow from when the system generates and provides the optimal answer and feedback based on the user's questions and emotions.

[1184] (Example 2)

[1185] Next, we will describe Example 2. 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."

[1186] In today's business environment, there is a need for a system that can comprehensively manage and quickly access employee skills, performance evaluations, business partner information, project information, and product information. However, current systems manage this information in a dispersed manner, making it difficult to provide necessary information quickly and appropriately. Furthermore, they cannot provide feedback that responds to user emotions, limiting their ability to improve user satisfaction. Therefore, a system that combines integrated information management with emotion recognition capabilities is necessary.

[1187] The specific processing performed by the specific 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 skill data of all employees, means for collecting performance evaluation data of all employees, means for collecting business partner information, means for preprocessing the collected data, means for inputting the preprocessed data into a generative AI model, means for recognizing the user's emotions, means for receiving questions from the user, means for the generative AI model to generate answers based on the received questions, means for adjusting feedback based on the recognized emotions, and means for presenting the generated answers and adjusted feedback to the user. This makes it possible not only to generate quick and appropriate answers based on aggregated data, but also to provide feedback that is in line with the user's emotions.

[1188] "Skill data" refers to information about the specialized knowledge and skills that employees possess.

[1189] "Performance evaluation data" refers to information about an employee's past performance and achievements.

[1190] "Business partner information" refers to information about business partners and customers.

[1191] "Project information" refers to information about ongoing or completed projects.

[1192] "Product information" refers to information about products that the company manufactures and sells.

[1193] "Preprocessing" is the process of converting raw data into a format that can be used by the AI ​​model.

[1194] A "generative AI model" is an artificial intelligence model that generates natural language based on input data.

[1195] "Emotion recognition" is a technology that identifies emotions from a user's facial expressions or input text.

[1196] "Feedback" refers to supplementary information and advice provided in addition to the answers to user questions.

[1197] A "closed environment" is a secure operating environment where external access is restricted.

[1198] This invention is a system that integrates all employees' skill data, performance evaluation data, business partner information, project information, and product information to provide information useful for each employee's work. Furthermore, by incorporating an emotion engine to recognize user emotions, it provides more comprehensive feedback and support. This system consists of three main components: a server, a terminal, and a user, each performing a specific function.

[1199] server

[1200] The server's role is to collect information from multiple data sources and preprocess it. Specifically, it retrieves data from HR databases, performance management systems, CRM systems, project management systems, and product databases. This data is normalized into a unified format using libraries such as Pandas. Next, the preprocessed data is input into a generative AI model for training. Natural language generation models such as GPT-3 are used as generative AI models.

[1201] Furthermore, the emotion recognition engine installed on the server analyzes user input and recognizes the user's emotions. A specific emotion recognition API is used for this emotion recognition.

[1202] terminal

[1203] The terminal provides an interface for users to input questions into the system and view the results. It is typically implemented as a web or desktop application. It uses HTML or JavaScript to display user input forms and sends the user's questions to the server along with sentiment data analyzed by an emotion engine. As the user inputs a question, the emotion recognition engine analyzes the user's emotions and determines what kind of feedback is appropriate.

[1204] User

[1205] This system allows users to quickly obtain information about their work and receive emotion-based feedback and support. Specifically, they can input questions to identify the best employee for the next project. For example, they might input a question like, "Who is the best employee for the next project?" The system also automatically recognizes the user's emotions during this process.

[1206] Specific example

[1207] The following are specific examples of how the system generates answers to particular questions and provides appropriate feedback.

[1208] 1. User: When entering the question, "Who is the best employee for the next project?", if the user is feeling anxious, the emotion recognition API will analyze that emotion.

[1209] 2. Terminal: Sends recognized emotion data along with the question to the server.

[1210] 3. Server: Receives questions and sentiment data, inputs them into a generative AI model to generate answers, and adds encouraging feedback to address user anxieties.

[1211] 4. Server: Returns the generated response and adjusted feedback to the terminal.

[1212] 5. Device: Displays the received responses and feedback to the user.

[1213] In this way, users can quickly obtain useful information related to their work and receive appropriate support tailored to their needs.

[1214] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1215] Step 1:

[1216] Data Acquisition and Preprocessing

[1217] The server collects necessary information from various data sources. It retrieves skill data from the HR database and performance evaluation data from the performance management system. It also retrieves business partner information from the CRM system and project and product information from their respective systems.

[1218] Specifically, the server collects data and preprocesses it as follows:

[1219] Inputs: HR database, performance management system, CRM system, project management system, product database

[1220] Data Retrieval: Data is retrieved using SQL queries, RESTful APIs, and SOAP APIs. Examples: SQL query "SELECT FROM skills_table", RESTful API "GET / mbo-data", SOAP API query

[1221] Preprocessing: Normalize the collected data and convert it to a unified format using the Pandas library.

[1222] Output: Preprocessed dataset

[1223] Step 2:

[1224] emotion recognition

[1225] The server activates the emotion recognition engine and analyzes the user's input data. The emotion recognition engine analyzes the text and facial images entered by the user on the device to recognize the user's emotions.

[1226] Specifically, the server recognizes emotions in the following way:

[1227] Input: User text input, face image

[1228] Emotion recognition processing: Perform text analysis using "sentiment = model.predict(user_input_text)" and face recognition using "emotion = model.recognize(face_image)".

[1229] Output: User sentiment data

[1230] Step 3:

[1231] Receiving and sending user input data

[1232] The device collects questions from the user and sends them to the server along with sentiment data. The device uses HTML and JavaScript to display input forms for the user and collects the entered data.

[1233] Specifically, the terminal collects and transmits data in the following manner:

[1234] Input: User questions, sentiment data

[1235] Data transmission: Using JavaScript, user questions and sentiment data are sent to the server via AJAX requests.

[1236] Output: Question and sentiment data sent to the server

[1237] Step 4:

[1238] AI model-based question answer generation

[1239] The server inputs the received question and sentiment data into a generative AI model to generate an answer. The generative AI model generates the optimal answer based on the pre-processed data.

[1240] Specifically, the server generates the response as follows:

[1241] Input: User questions, sentiment data, preprocessed dataset

[1242] Model Input: Input the received data into the generative AI model. Example: "response = gpt3.generate(prompt)"

[1243] Output: Generated answer

[1244] Step 5:

[1245] Emotion-based feedback adjustment

[1246] The server reviews the generated responses and adjusts the feedback based on sentiment data. For example, if the user is feeling anxious, it adds an encouraging message to alleviate that anxiety.

[1247] Specifically, the server adjusts the feedback as follows:

[1248] Input: Generated responses, sentiment data

[1249] Feedback adjustment: "if user_emotion == 'anxiety': response += 'We will provide reassuring information to address your anxiety.'"

[1250] Output: Adjusted feedback

[1251] Step 6:

[1252] Send and view responses and feedback

[1253] The server sends the generated response and adjusted feedback to the device. The device then displays it to the user.

[1254] Specifically, the server and terminal send and display data in the following manner.

[1255] Input: Adjusted feedback

[1256] Data formatting and transmission: Execute "json_response = jsonify(response_data)" and return it as the API response.

[1257] Output: Responses and feedback displayed to the user

[1258] (Application Example 2)

[1259] Next, we will explain application example 2. In the following explanation, 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."

[1260] In today's increasingly diverse work environment, there is a need to efficiently integrate vast amounts of data, such as employee skill data, performance data, client information, project information, and product information, and to provide appropriate feedback. Furthermore, it is necessary to recognize user emotions and provide feedback tailored to those situations in order to improve work efficiency and employee mental support. Since such a system does not exist, the objective of this invention is to provide a means to solve this problem.

[1261] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1262] In this invention, the server includes means for collecting skill data of all employees, means for collecting MBO data of all employees, means for collecting customer information, means for collecting project information, means for collecting product information, means for preprocessing the collected data, means for inputting the preprocessed data into a generative AI model, means for receiving user questions, means for the generative AI model to generate answers based on the received questions, means for presenting the generated answers to the user, means for recognizing the user's emotions, means for providing emotion-based feedback, and means for providing information to the user through various devices (including smart glasses). This makes it possible to efficiently utilize integrated data and provide appropriate answers to user questions and emotion-based feedback in real time.

[1263] "Means of collecting skill data for all employees" refers to a method for systematically acquiring and storing in a database the specialized knowledge, abilities, and work experience of all employees.

[1264] "Means for collecting MBO data from all employees" refers to methods for obtaining and recording the goal achievement status and evaluation results of all employees.

[1265] "Means of collecting customer information" refers to methods for acquiring and managing information about a company's business partners.

[1266] "Means of collecting project information" refers to methods for obtaining and storing detailed information about ongoing or past projects.

[1267] "Means of collecting product information" refers to methods for obtaining and managing detailed product information and performance data.

[1268] "Means for preprocessing collected data" refers to methods for normalizing information obtained from various data sources and converting it into a consistent format.

[1269] "Means for inputting pre-processed data into a generative AI model" refers to a method of inputting normalized data into an AI model and training the model.

[1270] "Means for receiving user inquiries" refers to an interface that accepts user inquiries and questions in an input format.

[1271] "A means by which a generative AI model generates an answer based on a received question" refers to a method for an AI model to generate an appropriate answer based on a question received from a user.

[1272] "Means of presenting generated answers to the user" refers to an interface for displaying answers generated by an AI model to the user.

[1273] "Means of recognizing user emotions" refers to methods for analyzing a user's facial expressions and tone of voice to determine their emotional state.

[1274] "Means of providing emotion-based feedback" refers to methods for providing appropriate feedback and support messages in accordance with the recognized emotions of the user.

[1275] "Means of providing information to users through various devices (including smart glasses)" refers to methods of providing information to users in real time using smart glasses or other wearable devices.

[1276] This invention is a system that integrates employee skill data, MBO data, customer information, project information, and product information, and combines them with an emotion recognition engine to provide comprehensive feedback and support. This system mainly consists of three main components: a server, a terminal, and a user.

[1277] server

[1278] The server plays the role of collecting necessary information from multiple data sources and performing preprocessing. The hardware used includes common cloud servers (e.g., AWS, Azure). It also inputs the collected data into a generative AI model (e.g., OpenAI's GPT-4) for training. Furthermore, an emotion engine (e.g., Affectiva, IBM Watson) that analyzes user input and performs sentiment recognition is also incorporated into the server. This enables the server to generate optimal answers to user work-related questions and provide appropriate, emotion-based feedback.

[1279] For example, the server performs the following data processing:

[1280] 1. Data Collection: Obtain skill data for all employees from the human resources management system, MBO data from the performance management system, customer information from the customer relationship management system, project information from the project management system, and product information from the product database.

[1281] 2. Data preprocessing: Normalize the acquired data and convert it into a consistent format.

[1282] 3. AI Model Input and Training: Preprocessed data is input into the generative AI model for training.

[1283] 4. Emotion Recognition: Analyzes user input and recognizes their emotional state.

[1284] terminal

[1285] The terminal plays the role of providing an interface for users to input questions into the system. While typically implemented as a web or desktop application, it can also be compatible with wearable devices such as smart glasses. The terminal sends the user's questions and their emotional data to the server, and displays the server's responses and feedback to the user.

[1286] As a concrete example, in a factory work support application using smart glasses, workers can wear the smart glasses and receive work instructions and encouraging messages in real time. For example, feedback such as, "The next task is to install part A. The necessary tools are a screwdriver and screws. If you are feeling stressed, please stay calm and proceed with the work," may be provided.

[1287] User

[1288] Users can use the system to quickly obtain work-related information and receive emotion-based feedback and support. When a question is entered, the system recognizes the user's emotions along with the question, resulting in more accurate feedback.

[1289] For example, if a user is feeling anxious when entering the question, "Who are the best employees for the next project?", they will be provided with feedback such as, "You have excellent team members. There's no need to worry."

[1290] Example of a prompt

[1291] Question: "What is the next task?"

[1292] Emotions: Stress

[1293] The generated message is: "The next task is to install part A. The necessary tools are a screwdriver and screws. Please proceed calmly."

[1294] The above describes the embodiments of the present invention. This system enables users to efficiently utilize integrated data and receive appropriate answers to work-related questions and sentiment-based feedback in real time.

[1295] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1296] Step 1:

[1297] The server collects employee skill data, MBO data, customer information, project information, and product information from multiple data sources. Inputs are from each data source, and output is an integrated dataset. Specifically, it retrieves data from human resources management systems, performance management systems, customer relationship management systems, project management systems, and product databases.

[1298] Step 2:

[1299] The server preprocesses the collected data. The input is an integrated dataset, and the output is normalized data. Specific operations include standardizing data formats and imputing missing values. Through this preprocessing, the data is transformed into a format suitable for generative AI models.

[1300] Step 3:

[1301] The server inputs pre-processed data into a generative AI model and trains the AI ​​model. The input is normalized data, and the output is the trained AI model. Specifically, data is fed into a generative AI model (e.g., OpenAI's GPT-4) to train it so that it can generate appropriate feedback and responses.

[1302] Step 4:

[1303] The user inputs a question into the system via a terminal. The input is the user's question, and the output is question data. The terminal uses an emotion engine to recognize the user's emotions in response to the question and generates question data and emotion data.

[1304] Step 5:

[1305] The terminal sends question data and sentiment data to the server. The input is question data and sentiment data, and the output is the server's reception. Specifically, data is sent to the server through the terminal's interface.

[1306] Step 6:

[1307] The server inputs the received question data and sentiment data into a generative AI model. The input consists of question data and sentiment data, and the output is the generated answer and appropriately adjusted feedback. The AI ​​model generates the optimal answer to the question, along with sentiment-based feedback.

[1308] Step 7:

[1309] The server formats the generated responses and feedback and sends them to the terminal. The input is the generated responses and feedback, and the output is the formatted data. Specifically, it reformats it into a user-friendly format.

[1310] Step 8:

[1311] The device displays formatted responses and feedback to the user. The input is formatted data, and the output is information provided to the user. Specifically, the information is displayed using smart glasses or other device displays.

[1312] As a concrete example, the following describes the behavior when a user asks, "Who is the best employee for the next project?" and is feeling anxious:

[1313] In Step 1, information is collected from each data source.

[1314] In step 2, the data is preprocessed.

[1315] In step 3, the generative AI model is trained.

[1316] In step 4, the user enters the question.

[1317] In step 5, the device sends the question and sentiment data to the server.

[1318] In step 6, the AI ​​model generates appropriate answers and emotion-based feedback.

[1319] In step 7, the server formats the data.

[1320] In step 8, the device displays the following message to the user: "Tanaka is the most suitable employee, and you can entrust the matter to him with confidence. Please do not worry."

[1321] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1322] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1323] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1324] [Fourth Embodiment]

[1325] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1326] As shown in Figure 7, the 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.

[1327] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1328] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1329] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1330] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1331] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1332] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1333] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1334] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[1335] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1336] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1337] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1338] This invention is a system that integrates all employees' skill data, MBO data, customer information, project information, and product information to provide information useful for each employee's work. This system consists of three main components: a server, a terminal, and a user, each performing a specific function.

[1339] server

[1340] The server collects necessary information from multiple data sources and performs preprocessing. Then, it inputs the data into a generative AI model (e.g., GPT) to allow it to learn.

[1341] Data Collection: The server retrieves skill data for all employees from the HR database. Next, it retrieves MBO data from the performance management system and customer information from the CRM system. It also retrieves project information from the project management system and product information from the product database.

[1342] Preprocessing: Normalize the acquired data, removing unnecessary line breaks and special characters. Unify the format and convert it to a format suitable for AI models (e.g., JSON format).

[1343] Input to the AI ​​model: Preprocessed data is input into a generative AI model, and the necessary training is performed.

[1344] terminal

[1345] The terminal provides an interface for users to input questions into the system and view the results. It is typically implemented as a web application or desktop application.

[1346] Interface provision: The terminal provides a form where the user can enter a question. For example, it can accept questions such as, "Who is the best employee for the next project?"

[1347] Data transmission: The terminal sends the user's question to the server.

[1348] User

[1349] Users can use this system to quickly obtain information related to their work.

[1350] Question Input: Enter specific work-related questions into the terminal. For example, "Who is the best employee for the next project?"

[1351] Specific example of processing

[1352] The following is a concrete example of how the system generates answers to specific questions.

[1353] 1. User: Enters the question "Who is the best employee for the next project?" into the terminal.

[1354] 2. Terminal: Receives questions and sends their contents to the server.

[1355] 3. Server: Receives questions and inputs them into the generative AI model.

[1356] 4. AI Model: Generates the best answer to a question based on training data (e.g., Employee A, Employee B).

[1357] 5. Server: Receives the generated response and formats it into a format to be returned to the user.

[1358] 6. Terminal: Displays formatted answers to the user.

[1359] As a result, users can instantly obtain information on the best employees for their next project, improving work efficiency and productivity.

[1360] security

[1361] Because the system handles highly confidential company information, it operates in a closed environment. This environment is designed to restrict external access and minimize the risk of information leakage.

[1362] Based on the above, the present invention provides specific means for each employee to quickly acquire information necessary for their work and to improve work efficiency.

[1363] The following describes the processing flow.

[1364] Step 1:

[1365] The server retrieves all employees' skill data from the HR database. Specifically, it executes an SQL query to retrieve the skill information of all employees.

[1366] Step 2:

[1367] The server retrieves MBO data from the performance management system. This uses API requests to retrieve each employee's goals and their achievement status.

[1368] Step 3:

[1369] The server retrieves customer information from the CRM system. A RESTful API is used to extract customer information from the existing CRM system.

[1370] Step 4:

[1371] The server retrieves project information from the project management system. It collects information about the project's objectives, schedule, and resources via an API.

[1372] Step 5:

[1373] The server retrieves product information from the product database. It obtains data such as product specifications, release schedules, and related projects.

[1374] Step 6:

[1375] All data acquired by the server is preprocessed. This includes normalizing text data, converting formats, and supplementing missing data.

[1376] Step 7:

[1377] The server inputs pre-processed data into a generative AI model. The data is converted to JSON format and loaded into the AI ​​model as training data.

[1378] Step 8:

[1379] The server begins training the generative AI model. The AI ​​model is trained using data to acquire the necessary predictive capabilities.

[1380] Step 9:

[1381] The device provides an interface for the user to input questions. It displays input fields for web forms and desktop applications.

[1382] Step 10:

[1383] The user enters a work-related question into the terminal. For example, they might enter, "Who is the best employee for the next project?"

[1384] Step 11:

[1385] The terminal sends the user's question to the server. RESTful APIs or message queues are used to send user queries to the server.

[1386] Step 12:

[1387] The server inputs the received question into a generative AI model. The AI ​​model is then called to analyze the question and generate an appropriate answer.

[1388] Step 13:

[1389] The AI ​​model generates answers based on the input questions. For example, based on the training data, it might recommend "Ichiro Tanaka and Jiro Suzuki are the best employees for the next project."

[1390] Step 14:

[1391] The server formats the generated response, converting it into a user-friendly format and adding necessary information.

[1392] Step 15:

[1393] The device displays formatted answers to the user. The results are displayed in a visually easy-to-understand interface.

[1394] The above outlines the specific process by which the system generates and provides the optimal answer to a user's question.

[1395] (Example 1)

[1396] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1397] Traditional systems made it difficult to integrate and manage skill data, MBO data, customer information, project information, and product information for all employees of a company. Furthermore, there was insufficient means to quickly provide information useful for each employee's work based on this data, hindering operational efficiency. In addition, because this data includes highly confidential information, appropriate security measures are necessary.

[1398] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1399] In this invention, the server includes means for collecting skill data of all employees, means for collecting MBO data of all employees, means for collecting customer information, means for collecting project information, means for collecting product information, means for normalizing the collected data and removing unnecessary line breaks and special characters, means for converting the preprocessed data into a unified format, means for inputting the data converted into a unified format into a generative AI model, means for receiving user questions, means for transmitting the received questions to the server, means for the server to generate answers based on the received questions using the generative AI model, and means for formatting the generated answers and presenting them to the user. This makes it possible to integrate individual data and provide information quickly and accurately using a generative AI model, thereby improving operational efficiency and ensuring security.

[1400] "Skill data" refers to information about the skills and abilities that employees possess.

[1401] "MBO data" refers to data related to the goals and results achieved by employees based on the Management by Objectives (MBO) system.

[1402] "Customer information" refers to information about customers and partners with whom a company conducts business.

[1403] "Project information" refers to data about ongoing projects within a company, including project progress and information about the members involved.

[1404] "Product information" refers to information about the products and services that a company offers.

[1405] "Preprocessing" is the process of normalizing collected data and removing unnecessary line breaks and special characters.

[1406] "Unified formatting" refers to the process of converting information obtained from different data sources into a consistent format.

[1407] A "generative AI model" is an artificial intelligence model that generates text based on a large amount of data, such as GPT.

[1408] "Question reception" refers to the process of receiving inquiries from users.

[1409] "Submitting a question" refers to the act of sending a user's question to the server.

[1410] "Answer generation" refers to the act of generating appropriate answers based on received questions using a generative AI model.

[1411] "Answer formatting" is the process of preparing the generated answers into a format that can be presented to the user.

[1412] This invention integrates all employees' skill data, MBO data, customer information, project information, and product information to provide information useful for each employee's work. This system consists of three main components: a server, a terminal, and a user, each performing a specific function.

[1413] server

[1414] The server collects necessary information from multiple data sources and performs preprocessing. It also analyzes the data using generative AI models to generate optimal answers to user questions.

[1415] Data Collection: The server retrieves skill data for all employees from the HR database. It also retrieves MBO data from the performance management system, customer information from the CRM system, project information from the project management system, and product information from the product database.

[1416] Hardware / software used: AWS EC2, AWS RDS

[1417] Specific examples of operation:

[1418] SQL query: SELECT FROM skills WHERE employee_id IS NOT NULL;

[1419] API call: curl -X GET https: / / api.example.com / mbo-data

[1420] Preprocessing: The acquired data is normalized, and unnecessary line breaks and special characters are removed. Then, the data format is standardized and converted to, for example, JSON format.

[1421] Hardware / software used: Python script

[1422] Specific examples of operation:

[1423] Special character removal: str.replace('\n', ' ').replace('\t', ' ')

[1424] JSON conversion: json.dumps(data)

[1425] AI model training: Preprocessed data is input into a generative AI model (e.g., GPT) to train the model.

[1426] Hardware / software used: OpenAI GPT-3, Python scripts

[1427] Specific examples of operation:

[1428] Execute the script: python train_model.py --data<path_to_preprocessed_data>

[1429] terminal

[1430] The terminal provides an interface for users to input questions into the system and view the results. It is typically implemented as a web application or desktop application.

[1431] Interface provision: The terminal provides a form where the user can enter a question. For example, it can accept questions such as, "Who is the best employee for the next project?"

[1432] Hardware / software used: HTML, JavaScript

[1433] Specific examples of operation:

[1434] Question form: <input type="text" id="userQuestion">

[1435] Send event: document.getElementById('sendButton').onclick = sendQuestion;

[1436] Data transmission: The terminal sends the user's question to the server.

[1437] Hardware / software used: Fetch API, JSON

[1438] Specific examples of operation:

[1439] Converting the question to JSON: let questionData = JSON.stringify({ question: userQuestion});

[1440] HTTP POST request: fetch(' / api / questions', { method: 'POST', body: questionData});

[1441] User

[1442] Users can use this system to quickly obtain information related to their work.

[1443] Question Input: Enter specific work-related questions into the terminal. For example, "Who is the best employee for the next project?"

[1444] Specific example of operation: Enter "Who is the best employee for the next project?" into the inquiry form and click the submit button.

[1445] Example of question and answer processing

[1446] 1. User: Enters the question "Who is the best employee for the next project?" into the terminal.

[1447] 2. Terminal: Receives questions and sends their contents to the server.

[1448] 3. Server: Receives questions and inputs them into the generative AI model.

[1449] 4. AI Model: Generates the best answer to a question based on training data (e.g., Employee A, Employee B).

[1450] 5. Server: Receives the generated response and formats it into a format to be returned to the user.

[1451] 6. Terminal: Displays formatted answers to the user.

[1452] This system will allow users to quickly obtain information useful for their work, and is expected to improve work efficiency.

[1453] security

[1454] Because the system handles highly confidential company information, it operates in a closed environment. This environment restricts external access and is designed to minimize the risk of information leakage. Specifically, this includes firewall configuration and the regular application of security patches.

[1455] Based on the above, the present invention provides specific means for each employee to quickly acquire information necessary for their work and to improve work efficiency.

[1456] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1457] Step 1:

[1458] The server collects skill data for all employees from the HR database. The server issues SQL queries to retrieve the skill data and converts this dataset into a list of skills for each employee. The input to this process is the HR database, and the output is a list of skill data.

[1459] Specific example of operation: SELECT FROM skills WHERE employee_id IS NOT NULL;

[1460] Step 2:

[1461] The server calls the performance management system's API to collect MBO data. The MBO information is retrieved via the API call and organized as performance data for each employee. The input to this process is the performance management system's API endpoint, and the output is a list of MBO data.

[1462] Specific example of operation: curl -X GET https: / / api.example.com / mbo-data

[1463] Step 3:

[1464] The server interacts with the CRM system to collect customer information. The server retrieves customer information via an API and stores that data in a database. The input to this process is the CRM system's API, and the output is a list of customer information.

[1465] Specific example of operation: curl -X GET https: / / api.example.com / clients

[1466] Step 4:

[1467] The server retrieves project information from the project management system's database. It issues SQL queries to obtain the project information and converts it into a list format. The input to this process is the project management system's database, and the output is a list of project information.

[1468] Specific example of operation: SELECT FROM projects WHERE status='active';

[1469] Step 5:

[1470] The server accesses the product database and collects product information. It issues SQL queries to retrieve product information and converts the data into a list format. The input to this process is the product database, and the output is a list of product information.

[1471] Specific example of operation: SELECT FROM products;

[1472] Step 6:

[1473] The server normalizes the collected data and removes unnecessary line breaks and special characters. A Python script is used to perform the data cleaning. The input to this process is the various collected data, and the output is the normalized dataset.

[1474] Specific example of operation: str.replace('\n', ' ').replace('\t', ' ')

[1475] Step 7:

[1476] The server converts the preprocessed data into a unified format (e.g., JSON). A Python script is used to perform this data format conversion. The input to this process is the preprocessed data, and the output is a unified format dataset.

[1477] Specific example of operation: json.dumps(data)

[1478] Step 8:

[1479] The server inputs data converted to a unified format into a generative AI model (e.g., GPT) and trains the model. It runs a training script and provides data to ensure the model performs optimally. The input to this process is a dataset in a unified format, and the output is a trained AI model.

[1480] Specific example of operation: python train_model.py --data<path_to_preprocessed_data>

[1481] Step 9:

[1482] Users enter specific business-related questions through a web form. The entered questions are converted to JSON format and sent from the terminal to the server. The input for this process is the user's questions, and the output is the question data sent to the server.

[1483] Specific example of operation: let questionData = JSON.stringify({ question: userQuestion});

[1484] Step 10:

[1485] The terminal receives the user's question and sends its contents to the server. The question data is sent to the server using an HTTP POST request. The input to this process is the question data in JSON format, and the output is the request sent to the server.

[1486] Specific example of operation: fetch(' / api / questions', { method: 'POST', body: questionData});

[1487] Step 11:

[1488] The server inputs the received question into a generative AI model and generates the optimal answer. The AI ​​model generates the answer based on the training data and returns the result to the server. The input to this process is the user's question data, and the output is the generated answer.

[1489] Specific example of operation: let formattedQuestion = formatForAIModel(questionData);

[1490] Step 12:

[1491] The server receives the generated response and formats it for presentation to the user. The formatted response is returned to the terminal as an HTTP response. The input to this process is the generated response, and the output is the response presented to the user.

[1492] Specific example of operation: let jsonResponse = JSON.stringify({ answer: generatedAnswer});

[1493] Step 13:

[1494] The terminal displays the responses received from the server to the user. The generated responses are visualized through a web interface. The input to this process is the response data from the server, and the output is the information presented to the user.

[1495] Specific example of operation: document.getElementById('answerDisplay').innerText = response.answer;

[1496] Step 14:

[1497] The server manages the system to ensure it operates in a closed environment. It regularly performs firewall configuration and applies security patches. The input to this process is the configuration information of the operating environment, and the output is a secure system state.

[1498] Specific example of operation: iptables -A INPUT -p tcp --dport 80 -j ACCEPT

[1499] (Application Example 1)

[1500] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1501] Modern factories require improved efficiency in each work area and the overall system, while simultaneously enabling rapid responses to anomalies. Monitoring robot status, managing work progress, and identifying necessary actions are particularly crucial for on-site technicians. However, there is a lack of systems that adequately collect and analyze this data and provide the necessary information immediately. Existing systems struggle with centralized data management and anomaly detection, potentially delaying rapid responses. Therefore, a system is needed that supports efficient factory operations and enables rapid responses to anomalies.

[1502] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1503] In this invention, the server includes means for collecting skill data of all employees, means for collecting MBO data of all employees, means for collecting customer information, means for collecting project information, means for collecting product information, means for preprocessing the collected data, means for inputting the preprocessed data into a generative artificial intelligence model, means for receiving user questions, means for the generative artificial intelligence model to generate answers based on the received questions, means for presenting the generated answers to the user, means for on-site workers to check the status of robots and work progress in real time through smart glasses, means for providing optimal actions to each robot and worker, and means for immediately notifying and proposing countermeasures in the event of an anomaly. This makes it possible to centrally manage various data within the factory, grasp the situation on-site in real time, and propose the optimal work to be done next. Furthermore, it is possible to respond quickly in the event of an anomaly and improve the efficiency of the entire factory.

[1504] "All employee skill data" refers to data on the skills, expertise, qualifications, and experience of all employees throughout the company.

[1505] "MBO data for all employees" refers to data related to achievement targets and performance evaluations based on the goal management system for all employees.

[1506] "Customer information" refers to information about customers and partner companies with which a company does business.

[1507] "Project information" refers to information about each project, such as its progress, assigned personnel, schedule, and resources.

[1508] "Product information" refers to information about the products and services that a company handles.

[1509] A "generative artificial intelligence model" is an artificial intelligence model that uses natural language processing technology to generate appropriate answers and suggestions based on input data.

[1510] "Means of receiving user questions" refers to interfaces or devices that allow users to input questions into the system.

[1511] "Means for generating answers" refers to a mechanism that uses a generative artificial intelligence model to generate the optimal answer to a user's question.

[1512] "Means of presenting answers to users" refers to a mechanism that provides the generated answers to users in an easy-to-read format.

[1513] "Smart glasses" are wearable devices that have the function of integrating and displaying digital information in addition to information from the real world.

[1514] "Methods for real-time monitoring" refer to technologies and interfaces that instantly acquire on-site conditions and data, and provide users with the necessary information on the spot.

[1515] "Means for immediate notification and proposal of countermeasures in the event of an anomaly" refers to a mechanism for promptly issuing a warning and proposing necessary countermeasures when an anomaly is detected within the factory.

[1516] This invention is a system that integrates all employees' skill data, MBO data, customer information, project information, and product information to provide information useful for the work of each employee and field worker. This system consists of three main components: a server, terminals, and users.

[1517] server

[1518] The server collects necessary information from multiple data sources and performs preprocessing. Then, it inputs the data into a generative artificial intelligence model (e.g., GPT) to allow it to learn.

[1519] 1. Data Collection

[1520] The server retrieves skill data for all employees from the HR database and MBO data from the performance management system. It also retrieves customer information from the CRM system, project information from the project management system, and product information from the product database.

[1521] 2. Preprocessing

[1522] The acquired data is normalized, removing unnecessary line breaks and special characters. The format is standardized and converted to a format suitable for artificial intelligence models (e.g., JSON). This ensures data consistency and accuracy. Specifically, numerical data is standardized using libraries such as StandardScaler.

[1523] 3. Input to the AI ​​model

[1524] Preprocessed data is input into a generative artificial intelligence model, and the necessary training is performed. Examples of generative AI models used include GPT-2 and GPT-3. Examples of prompts include, "Who is the best employee for the next project?" and "What is the best action for the robot at this point?"

[1525] terminal

[1526] The terminal provides an interface for users to input questions into the system and view the results.

[1527] 1. Interface provision

[1528] The terminal provides a form where users can enter questions. For example, it might accept questions such as, "Who is the best employee for the next project?"

[1529] 2. Data transmission

[1530] The terminal sends the user's question to the server.

[1531] 3. Display results

[1532] The generated responses are displayed in a user-friendly format. When using smart glasses, the status of robots in the factory and the progress of their work can be checked in real time. A user interface (UI) for this purpose is included.

[1533] User

[1534] Users can use this system to quickly obtain information related to their work.

[1535] 1. Enter your question

[1536] Users input specific, work-related questions into the terminal. For example, they might ask questions like, "Who is the best employee for the next project?" or "What is the current status of the robots on site?"

[1537] 2. Check the results

[1538] Review the generated results and decide on the next action. For example, you can determine the optimal employee allocation or the next work instructions for the robots.

[1539] Specific example

[1540] For example, if a user asks, "Who is the best employee for the next project?", the server inputs pre-processed data into a generative artificial intelligence model and generates the optimal answer. This answer is then presented to the user via a terminal. Similarly, if a field worker uses smart glasses to ask, "What is the best action for the robot at this moment?", the server can use the generative artificial intelligence model based on real-time data to provide the optimal work instructions.

[1541] As described above, this invention is a system that enables on-site workers to obtain appropriate information in real time and respond quickly.

[1542] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1543] Step 1:

[1544] The server collects data from various data sources. Specifically, it retrieves skill data for all employees from the HR database and MBO data from the performance management system. It also retrieves customer information from the CRM system and project information from the project management system. Furthermore, it retrieves product information from the product database. The input data consists of data from various systems, and the output is a dictionary-format dataset containing the respective data.

[1545] Step 2:

[1546] The server preprocesses the collected data. Specifically, it normalizes skill data, MBO data, customer information, project information, and product information. During this process, unnecessary line breaks and special characters are removed from text data, and numerical data is standardized using StandardScaler. The input is the raw data collected in step 1, and the output is the preprocessed, clean data.

[1547] Step 3:

[1548] The server inputs preprocessed data into a generative artificial intelligence model. Specifically, this data is converted to JSON format and input into the AI ​​model (e.g., GPT-2 or GPT-3). Here, the input is preprocessed data, and the output is the trained dataset in the generative artificial intelligence model.

[1549] Step 4:

[1550] The terminal accepts user questions. When a user enters a question into the terminal's input form, it accepts questions such as, "Who is the best employee for the next project?" The input is the user's question, and the output is the string data of that question.

[1551] Step 5:

[1552] The terminal sends the user's question to the server. The input is the user's question text, and the output is the question data sent to the server.

[1553] Step 6:

[1554] The server inputs a question into a generative artificial intelligence model and generates an answer. Specifically, the server combines collected preprocessed data with the user's question and inputs it into the AI ​​model to generate the optimal answer. The input consists of the user's question and preprocessed data, while the output is the generated answer text.

[1555] Step 7:

[1556] The server formats the generated response and returns it to the terminal. Specifically, it receives the output from the AI ​​model and formats it into a format that is easy for the user to understand. The input is the output text from the AI ​​model, and the output is the formatted response text.

[1557] Step 8:

[1558] The terminal presents the formatted response to the user. When using smart glasses, this response is displayed so that field workers can view it in real time. The input is the formatted response text, and the output is the display data shown to the user.

[1559] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1560] This invention provides a system that integrates all employees' skill data, MBO data, customer information, project information, and product information to provide information useful for each employee's work, and combines this with an emotion engine to recognize user emotions, thereby providing even more comprehensive feedback and support. This system consists of three main components: a server, a terminal, and a user, each performing a specific function.

[1561] server

[1562] The server collects necessary information from multiple data sources and performs preprocessing. It then inputs this data into a generative AI model for training. Furthermore, it recognizes user emotions and provides appropriate feedback and support information.

[1563] Data Collection and Preprocessing: Skill data for all employees is obtained from the HR database, MBO data from the performance management system, customer information from the CRM system, project information from the project management system, and product information from the product database. After normalizing and standardizing the format of this data, it is input into a generative AI model.

[1564] Inputting and training the AI ​​model: Preprocessed data is input into the generative AI model, and the necessary learning is performed.

[1565] Emotion Engine: Analyzes user input and performs emotion recognition.

[1566] terminal

[1567] The terminal provides an interface for users to input questions into the system and view the results. It is typically implemented as a web application or desktop application.

[1568] Interface provision: The device provides a form where the user can enter a question, and the emotion engine recognizes the user's emotions as they enter the question.

[1569] Data transmission: The terminal sends the user's questions and the results of the sentiment engine's recognition to the server.

[1570] User

[1571] Users can use this system to quickly obtain information about their work and receive emotion-based feedback and support.

[1572] Question Input: Enter specific, work-related questions into the terminal. For example, "Who is the best employee for the next project?" The user's emotions are also recognized during this process.

[1573] Specific example of processing

[1574] The following are specific examples of how the system generates answers to particular questions and provides appropriate feedback.

[1575] 1. User: When entering the question, "Who is the best employee for the next project?", if the user is feeling anxious, the emotion engine will recognize that emotion based on facial recognition and text analysis technology.

[1576] 2. Terminal: Sends sentiment data to the server along with the question.

[1577] 3. Server: Receives questions and sentiment data and inputs them into a generative AI model.

[1578] 4. AI Model: Based on training data, it generates the best possible answers to questions and adjusts the feedback based on recognized emotions. For example, if the answer is "The best candidates for the next project are Ichiro Tanaka and Jiro Suzuki," it will also provide additional encouragement and support information to users who are perceived as feeling anxious.

[1579] 5. Server: Formats the generated responses and adjusted feedback and returns them to the terminal.

[1580] 6. Terminal: Displays formatted answers and feedback to the user.

[1581] As a result, users can quickly obtain information on the best employees for their next project, and also receive appropriate support based on their emotions.

[1582] security

[1583] Because the system handles highly confidential company information, it operates in a closed environment. This environment is designed to restrict external access and minimize the risk of information leakage.

[1584] Based on the above, the present invention provides specific means for each employee to quickly acquire information necessary for their work, and further to provide feedback and support based on user emotions.

[1585] The following describes the processing flow.

[1586] Step 1:

[1587] The server retrieves skill data for all employees from the HR database. Specifically, it executes an SQL query to retrieve skill information for all employees.

[1588] Step 2:

[1589] The server retrieves MBO data from the performance management system. This uses API requests to retrieve each employee's goals and their achievement status.

[1590] Step 3:

[1591] The server retrieves customer information from the CRM system. A RESTful API is used to extract customer information from the existing CRM system.

[1592] Step 4:

[1593] The server retrieves project information from the project management system. It collects information about the project's objectives, schedule, and resources via an API.

[1594] Step 5:

[1595] The server retrieves product information from the product database. It obtains data such as product specifications, release schedules, and related projects.

[1596] Step 6:

[1597] All data acquired by the server is preprocessed. This includes normalizing text data, converting formats, and supplementing missing data.

[1598] Step 7:

[1599] The server inputs pre-processed data into a generative AI model. The data is converted to JSON format and loaded into the AI ​​model as training data.

[1600] Step 8:

[1601] The server begins training the generative AI model. The AI ​​model is trained using data to acquire the necessary predictive capabilities.

[1602] Step 9:

[1603] The device provides an interface for the user to input questions. It displays input fields for web forms and desktop applications.

[1604] Step 10:

[1605] The user enters a work-related question into the terminal. For example, they might enter, "Who is the best employee for the next project?"

[1606] Step 11:

[1607] When the device receives a user's question, it analyzes the user's emotions using an emotion engine. This is done using facial recognition and text analysis.

[1608] Step 12:

[1609] The device sends questions and sentiment data to the server. RESTful APIs and message queues are used to send user queries and sentiment data to the server.

[1610] Step 13:

[1611] The server inputs the received question and sentiment data into a generative AI model. The AI ​​model is then invoked to generate an answer based on the question and sentiment data.

[1612] Step 14:

[1613] The AI ​​model generates answers based on the input question and its associated emotions. For example, based on the training data, it might recommend "Ichiro Tanaka and Jiro Suzuki are the best employees for the next project."

[1614] Step 15:

[1615] The server formats the generated response, converting it into a user-friendly format and adding necessary information. It also provides additional encouragement and support based on the user's sentiment.

[1616] Step 16:

[1617] The device displays formatted answers to the user. The results are displayed in a visually easy-to-understand interface.

[1618] The above outlines the specific process flow from when the system generates and provides the optimal answer and feedback based on the user's questions and emotions.

[1619] (Example 2)

[1620] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1621] In today's business environment, there is a need for a system that can comprehensively manage and quickly access employee skills, performance evaluations, business partner information, project information, and product information. However, current systems manage this information in a dispersed manner, making it difficult to provide necessary information quickly and appropriately. Furthermore, they cannot provide feedback that responds to user emotions, limiting their ability to improve user satisfaction. Therefore, a system that combines integrated information management with emotion recognition capabilities is necessary.

[1622] The specific processing performed by the specific 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 skill data of all employees, means for collecting performance evaluation data of all employees, means for collecting business partner information, means for preprocessing the collected data, means for inputting the preprocessed data into a generative AI model, means for recognizing the user's emotions, means for receiving questions from the user, means for the generative AI model to generate answers based on the received questions, means for adjusting feedback based on the recognized emotions, and means for presenting the generated answers and adjusted feedback to the user. This makes it possible not only to generate quick and appropriate answers based on aggregated data, but also to provide feedback that is in line with the user's emotions.

[1623] "Skill data" refers to information about the specialized knowledge and skills that employees possess.

[1624] "Performance evaluation data" refers to information about an employee's past performance and achievements.

[1625] "Business partner information" refers to information about business partners and customers.

[1626] "Project information" refers to information about ongoing or completed projects.

[1627] "Product information" refers to information about products that the company manufactures and sells.

[1628] "Preprocessing" is the process of converting raw data into a format that can be used by the AI ​​model.

[1629] A "generative AI model" is an artificial intelligence model that generates natural language based on input data.

[1630] "Emotion recognition" is a technology that identifies emotions from a user's facial expressions or input text.

[1631] "Feedback" refers to supplementary information and advice provided in addition to the answers to user questions.

[1632] A "closed environment" is a secure operating environment where external access is restricted.

[1633] This invention is a system that integrates all employees' skill data, performance evaluation data, business partner information, project information, and product information to provide information useful for each employee's work. Furthermore, by incorporating an emotion engine to recognize user emotions, it provides more comprehensive feedback and support. This system consists of three main components: a server, a terminal, and a user, each performing a specific function.

[1634] server

[1635] The server's role is to collect information from multiple data sources and preprocess it. Specifically, it retrieves data from HR databases, performance management systems, CRM systems, project management systems, and product databases. This data is normalized into a unified format using libraries such as Pandas. Next, the preprocessed data is input into a generative AI model for training. Natural language generation models such as GPT-3 are used as generative AI models.

[1636] Furthermore, the emotion recognition engine installed on the server analyzes user input and recognizes the user's emotions. A specific emotion recognition API is used for this emotion recognition.

[1637] terminal

[1638] The terminal provides an interface for users to input questions into the system and view the results. It is typically implemented as a web or desktop application. It uses HTML or JavaScript to display user input forms and sends the user's questions to the server along with sentiment data analyzed by an emotion engine. As the user inputs a question, the emotion recognition engine analyzes the user's emotions and determines what kind of feedback is appropriate.

[1639] User

[1640] This system allows users to quickly obtain information about their work and receive emotion-based feedback and support. Specifically, they can input questions to identify the best employee for the next project. For example, they might input a question like, "Who is the best employee for the next project?" The system also automatically recognizes the user's emotions during this process.

[1641] Specific example

[1642] The following are specific examples of how the system generates answers to particular questions and provides appropriate feedback.

[1643] 1. User: When entering the question, "Who is the best employee for the next project?", if the user is feeling anxious, the emotion recognition API will analyze that emotion.

[1644] 2. Terminal: Sends recognized emotion data along with the question to the server.

[1645] 3. Server: Receives questions and sentiment data, inputs them into a generative AI model to generate answers, and adds encouraging feedback to address user anxieties.

[1646] 4. Server: Returns the generated response and adjusted feedback to the terminal.

[1647] 5. Device: Displays the received responses and feedback to the user.

[1648] In this way, users can quickly obtain useful information related to their work and receive appropriate support tailored to their needs.

[1649] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1650] Step 1:

[1651] Data Acquisition and Preprocessing

[1652] The server collects necessary information from various data sources. It retrieves skill data from the HR database and performance evaluation data from the performance management system. It also retrieves business partner information from the CRM system and project and product information from their respective systems.

[1653] Specifically, the server collects data and preprocesses it as follows:

[1654] Inputs: HR database, performance management system, CRM system, project management system, product database

[1655] Data Retrieval: Data is retrieved using SQL queries, RESTful APIs, and SOAP APIs. Examples: SQL query "SELECT FROM skills_table", RESTful API "GET / mbo-data", SOAP API query

[1656] Preprocessing: Normalize the collected data and convert it to a unified format using the Pandas library.

[1657] Output: Preprocessed dataset

[1658] Step 2:

[1659] emotion recognition

[1660] The server activates the emotion recognition engine and analyzes the user's input data. The emotion recognition engine analyzes the text and facial images entered by the user on the device to recognize the user's emotions.

[1661] Specifically, the server recognizes emotions in the following way:

[1662] Input: User text input, face image

[1663] Emotion recognition processing: Perform text analysis using "sentiment = model.predict(user_input_text)" and face recognition using "emotion = model.recognize(face_image)".

[1664] Output: User sentiment data

[1665] Step 3:

[1666] Receiving and sending user input data

[1667] The device collects questions from the user and sends them to the server along with sentiment data. The device uses HTML and JavaScript to display input forms for the user and collects the entered data.

[1668] Specifically, the terminal collects and transmits data in the following manner:

[1669] Input: User questions, sentiment data

[1670] Data transmission: Using JavaScript, user questions and sentiment data are sent to the server via AJAX requests.

[1671] Output: Question and sentiment data sent to the server

[1672] Step 4:

[1673] AI model-based question answer generation

[1674] The server inputs the received question and sentiment data into a generative AI model to generate an answer. The generative AI model generates the optimal answer based on the pre-processed data.

[1675] Specifically, the server generates the response as follows:

[1676] Input: User questions, sentiment data, preprocessed dataset

[1677] Model Input: Input the received data into the generative AI model. Example: "response = gpt3.generate(prompt)"

[1678] Output: Generated answer

[1679] Step 5:

[1680] Emotion-based feedback adjustment

[1681] The server reviews the generated responses and adjusts the feedback based on sentiment data. For example, if the user is feeling anxious, it adds an encouraging message to alleviate that anxiety.

[1682] Specifically, the server adjusts the feedback as follows:

[1683] Input: Generated responses, sentiment data

[1684] Feedback adjustment: "if user_emotion == 'anxiety': response += 'We will provide reassuring information to address your anxiety.'"

[1685] Output: Adjusted feedback

[1686] Step 6:

[1687] Send and view responses and feedback

[1688] The server sends the generated response and adjusted feedback to the device. The device then displays it to the user.

[1689] Specifically, the server and terminal send and display data in the following manner.

[1690] Input: Adjusted feedback

[1691] Data formatting and transmission: Execute "json_response = jsonify(response_data)" and return it as the API response.

[1692] Output: Responses and feedback displayed to the user

[1693] (Application Example 2)

[1694] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1695] In today's increasingly diverse work environment, there is a need to efficiently integrate vast amounts of data, such as employee skill data, performance data, client information, project information, and product information, and to provide appropriate feedback. Furthermore, it is necessary to recognize user emotions and provide feedback tailored to those situations in order to improve work efficiency and employee mental support. Since such a system does not exist, the objective of this invention is to provide a means to solve this problem.

[1696] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1697] In this invention, the server includes means for collecting skill data of all employees, means for collecting MBO data of all employees, means for collecting customer information, means for collecting project information, means for collecting product information, means for preprocessing the collected data, means for inputting the preprocessed data into a generative AI model, means for receiving user questions, means for the generative AI model to generate answers based on the received questions, means for presenting the generated answers to the user, means for recognizing the user's emotions, means for providing emotion-based feedback, and means for providing information to the user through various devices (including smart glasses). This makes it possible to efficiently utilize integrated data and provide appropriate answers to user questions and emotion-based feedback in real time.

[1698] "Means of collecting skill data for all employees" refers to a method for systematically acquiring and storing in a database the specialized knowledge, abilities, and work experience of all employees.

[1699] "Means for collecting MBO data from all employees" refers to methods for obtaining and recording the goal achievement status and evaluation results of all employees.

[1700] "Means of collecting customer information" refers to methods for acquiring and managing information about a company's business partners.

[1701] "Means of collecting project information" refers to methods for obtaining and storing detailed information about ongoing or past projects.

[1702] "Means of collecting product information" refers to methods for obtaining and managing detailed product information and performance data.

[1703] "Means for preprocessing collected data" refers to methods for normalizing information obtained from various data sources and converting it into a consistent format.

[1704] "Means for inputting pre-processed data into a generative AI model" refers to a method of inputting normalized data into an AI model and training the model.

[1705] "Means for receiving user inquiries" refers to an interface that accepts user inquiries and questions in an input format.

[1706] "A means by which a generative AI model generates an answer based on a received question" refers to a method for an AI model to generate an appropriate answer based on a question received from a user.

[1707] "Means of presenting generated answers to the user" refers to an interface for displaying answers generated by an AI model to the user.

[1708] "Means of recognizing user emotions" refers to methods for analyzing a user's facial expressions and tone of voice to determine their emotional state.

[1709] "Means of providing emotion-based feedback" refers to methods for providing appropriate feedback and support messages in accordance with the recognized emotions of the user.

[1710] "Means of providing information to users through various devices (including smart glasses)" refers to methods of providing information to users in real time using smart glasses or other wearable devices.

[1711] This invention is a system that integrates employee skill data, MBO data, customer information, project information, and product information, and combines them with an emotion recognition engine to provide comprehensive feedback and support. This system mainly consists of three main components: a server, a terminal, and a user.

[1712] server

[1713] The server plays the role of collecting necessary information from multiple data sources and performing preprocessing. The hardware used includes common cloud servers (e.g., AWS, Azure). It also inputs the collected data into a generative AI model (e.g., OpenAI's GPT-4) for training. Furthermore, an emotion engine (e.g., Affectiva, IBM Watson) that analyzes user input and performs sentiment recognition is also incorporated into the server. This enables the server to generate optimal answers to user work-related questions and provide appropriate, emotion-based feedback.

[1714] For example, the server performs the following data processing:

[1715] 1. Data Collection: Obtain skill data for all employees from the human resources management system, MBO data from the performance management system, customer information from the customer relationship management system, project information from the project management system, and product information from the product database.

[1716] 2. Data preprocessing: Normalize the acquired data and convert it into a consistent format.

[1717] 3. AI Model Input and Training: Preprocessed data is input into the generative AI model for training.

[1718] 4. Emotion Recognition: Analyzes user input and recognizes their emotional state.

[1719] terminal

[1720] The terminal plays the role of providing an interface for users to input questions into the system. While typically implemented as a web or desktop application, it can also be compatible with wearable devices such as smart glasses. The terminal sends the user's questions and their emotional data to the server, and displays the server's responses and feedback to the user.

[1721] As a concrete example, in a factory work support application using smart glasses, workers can wear the smart glasses and receive work instructions and encouraging messages in real time. For example, feedback such as, "The next task is to install part A. The necessary tools are a screwdriver and screws. If you are feeling stressed, please stay calm and proceed with the work," may be provided.

[1722] User

[1723] Users can use the system to quickly obtain work-related information and receive emotion-based feedback and support. When a question is entered, the system recognizes the user's emotions along with the question, resulting in more accurate feedback.

[1724] For example, if a user is feeling anxious when entering the question, "Who are the best employees for the next project?", they will be provided with feedback such as, "You have excellent team members. There's no need to worry."

[1725] Example of a prompt

[1726] Question: "What is the next task?"

[1727] Emotions: Stress

[1728] The generated message is: "The next task is to install part A. The necessary tools are a screwdriver and screws. Please proceed calmly."

[1729] The above describes the embodiments of the present invention. This system enables users to efficiently utilize integrated data and receive appropriate answers to work-related questions and sentiment-based feedback in real time.

[1730] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1731] Step 1:

[1732] The server collects employee skill data, MBO data, customer information, project information, and product information from multiple data sources. Inputs are from each data source, and output is an integrated dataset. Specifically, it retrieves data from human resources management systems, performance management systems, customer relationship management systems, project management systems, and product databases.

[1733] Step 2:

[1734] The server preprocesses the collected data. The input is an integrated dataset, and the output is normalized data. Specific operations include standardizing data formats and imputing missing values. Through this preprocessing, the data is transformed into a format suitable for generative AI models.

[1735] Step 3:

[1736] The server inputs pre-processed data into a generative AI model and trains the AI ​​model. The input is normalized data, and the output is the trained AI model. Specifically, data is fed into a generative AI model (e.g., OpenAI's GPT-4) to train it so that it can generate appropriate feedback and responses.

[1737] Step 4:

[1738] The user inputs a question into the system via a terminal. The input is the user's question, and the output is question data. The terminal uses an emotion engine to recognize the user's emotions in response to the question and generates question data and emotion data.

[1739] Step 5:

[1740] The terminal sends question data and sentiment data to the server. The input is question data and sentiment data, and the output is the server's reception. Specifically, data is sent to the server through the terminal's interface.

[1741] Step 6:

[1742] The server inputs the received question data and sentiment data into a generative AI model. The input consists of question data and sentiment data, and the output is the generated answer and appropriately adjusted feedback. The AI ​​model generates the optimal answer to the question, along with sentiment-based feedback.

[1743] Step 7:

[1744] The server formats the generated responses and feedback and sends them to the terminal. The input is the generated responses and feedback, and the output is the formatted data. Specifically, it reformats it into a user-friendly format.

[1745] Step 8:

[1746] The device displays formatted responses and feedback to the user. The input is formatted data, and the output is information provided to the user. Specifically, the information is displayed using smart glasses or other device displays.

[1747] As a concrete example, the following describes the behavior when a user asks, "Who is the best employee for the next project?" and is feeling anxious:

[1748] In Step 1, information is collected from each data source.

[1749] In step 2, the data is preprocessed.

[1750] In step 3, the generative AI model is trained.

[1751] In step 4, the user enters the question.

[1752] In step 5, the device sends the question and sentiment data to the server.

[1753] In step 6, the AI ​​model generates appropriate answers and emotion-based feedback.

[1754] In step 7, the server formats the data.

[1755] In step 8, the device displays the following message to the user: "Tanaka is the most suitable employee, and you can entrust the matter to him with confidence. Please do not worry."

[1756] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1757] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1758] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1759] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1760] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1761] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1762] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1763] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1764] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1765] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1766] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1767] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1768] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1769] 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.

[1770] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1771] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1772] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1773] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1774] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1775] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1776] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[1777] The following is further disclosed regarding the embodiments described above.

[1778] (Claim 1)

[1779] A means of collecting skill data for all employees,

[1780] A means of collecting MBO data for all employees,

[1781] Means of collecting customer information,

[1782] Means of collecting project information,

[1783] Means of collecting product information,

[1784] Means for preprocessing the collected data,

[1785] A means for inputting preprocessed data into a generative AI model,

[1786] A means of receiving user questions,

[1787] A means by which a generative AI model generates an answer based on the received question,

[1788] A system that includes means for presenting the generated answer to the user.

[1789] (Claim 2)

[1790] The system according to claim 1, further comprising means for providing information to identify the best employee for the next project based on user questions.

[1791] (Claim 3)

[1792] The system according to claim 1, further comprising means for inputting confidential company information into a generative AI model in a closed environment and using it as training data for the AI ​​model.

[1793] "Example 1"

[1794] (Claim 1)

[1795] A means of collecting skill data for all employees,

[1796] A means of collecting MBO data for all employees,

[1797] Means of collecting customer information,

[1798] Means of collecting project information,

[1799] Means of collecting product information,

[1800] A method for normalizing collected data and removing unnecessary line breaks and special characters,

[1801] A means of converting preprocessed data into a unified format,

[1802] A means of inputting data converted into a unified format into a generative AI model,

[1803] A means of receiving user questions,

[1804] A means of sending the received question content to the server,

[1805] A means for a server to generate an answer based on a question received using a generative AI model,

[1806] A system that includes means for formatting the generated response and presenting it to the user.

[1807] (Claim 2)

[1808] The system according to claim 1, further comprising means for providing information to identify the best employee for the next project based on user questions.

[1809] (Claim 3)

[1810] The system according to claim 1, further comprising means for managing confidential company information in a closed environment and using it as training data for a generative AI model.

[1811] "Application Example 1"

[1812] (Claim 1)

[1813] A means of collecting skill data for all employees,

[1814] A means of collecting MBO data for all employees,

[1815] Means of collecting customer information,

[1816] Means of collecting project information,

[1817] Means of collecting product information,

[1818] Means for preprocessing the collected data,

[1819] A means for inputting preprocessed data into a generative artificial intelligence model,

[1820] A means of receiving user questions,

[1821] A means by which a generative artificial intelligence model generates an answer based on the received question,

[1822] A means of presenting the generated answer to the user,

[1823] A means for on-site workers to check the status of robots and work progress in real time through smart glasses,

[1824] A means of providing the optimal action for each robot and worker,

[1825] A system that includes means for immediately notifying and proposing countermeasures in the event of an anomaly.

[1826] (Claim 2)

[1827] The system according to claim 1, further comprising means for providing information to identify the best employee for the next project based on user questions.

[1828] (Claim 3)

[1829] The system according to claim 1, further comprising means for inputting confidential company information into a generative artificial intelligence model in a closed environment and using it as training data for the artificial intelligence model.

[1830] "Example 2 of combining an emotion engine"

[1831] (Claim 1)

[1832] A means of collecting skill data for all employees,

[1833] A means of collecting performance evaluation data for all employees,

[1834] Methods for gathering information on business partners,

[1835] Means of collecting project information,

[1836] Means of collecting product information,

[1837] Means for preprocessing the collected data,

[1838] A means for inputting preprocessed data into a generative AI model,

[1839] Means of recognizing user emotions,

[1840] A means of receiving user questions,

[1841] A means by which a generative AI model generates an answer based on the received question,

[1842] Means of adjusting feedback based on recognized emotions,

[1843] A system that includes means for presenting generated responses and adjusted feedback to the user.

[1844] (Claim 2)

[1845] The system according to claim 1, further comprising means for providing information to identify the best employee for the next project based on the user's questions, and in addition, means for providing support information based on the user's emotions.

[1846] (Claim 3)

[1847] The system according to claim 1, further comprising means for inputting confidential company information into a generative AI model in a closed environment and using it as training data for the AI ​​model.

[1848] "Application example 2 of combining emotional engines"

[1849] (Claim 1)

[1850] A means of collecting skill data for all employees,

[1851] A means of collecting MBO data for all employees,

[1852] Means of collecting customer information,

[1853] Means of collecting project information,

[1854] Means of collecting product information,

[1855] Means for preprocessing the collected data,

[1856] A means for inputting preprocessed data into a generative AI model,

[1857] A means of receiving user questions,

[1858] A means by which a generative AI model generates an answer based on the received question,

[1859] A means of presenting the generated answer to the user,

[1860] Means of recognizing user emotions,

[1861] Means of providing emotion-based feedback,

[1862] Means of providing information to users through various devices (including smart glasses)

[1863] A system that includes this.

[1864] (Claim 2)

[1865] The system according to claim 1, further comprising means for providing information to identify the best employee for the next project based on user questions.

[1866] (Claim 3)

[1867] The system according to claim 1, further comprising means for inputting confidential company information into a generative AI model in a closed environment and using it as training data for the AI ​​model. [Explanation of symbols]

[1868] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting skill data for all employees, A means of collecting MBO data for all employees, Means of collecting customer information, Means of collecting project information, Means of collecting product information, Means for preprocessing the collected data, A means for inputting preprocessed data into a generative AI model, A means of receiving user questions, A means by which a generative AI model generates an answer based on the received question, A system that includes means for presenting the generated answer to the user.

2. The system according to claim 1, further comprising means for providing information to identify the most suitable employee for the next project based on a user's question.

3. The system according to claim 1, further comprising means for inputting confidential company information into a generative AI model in a closed environment and using it as training data for the AI ​​model.

Images