system

Abstract

We provide the system. [Solution] A system that includes means for analyzing employee information, chats, emails, and deliverables using a large-scale language model, means for comprehensively covering relationships between employees and individual areas of expertise based on the analysis results, and means for providing information to resolve questions.

Description

[Technical Field]

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

[0002] Patent Literature 1 discloses a persona chatbot control method executed by at least one processor, the method comprising: a step of receiving a user utterance; a step of adding the user utterance to a prompt including an instruction text associated with a description related to a character of a chatbot; a step of encoding the prompt; and a step of inputting the encoded prompt into a language model to generate a chatbot utterance responsive to the user utterance. [Prior Art Literature] [Patent Literature]

[0003] [Patent Literature 1] Japanese Patent Application Laid-Open No. 2022-180282 [Summary of Invention] [Problem to be Solved by the Invention]

[0004] The increase in the number of employees and the spread of remote work have accelerated the dilution of connections between employees and the fragmentation of information. This gives rise to questions such as "Who should I ask?" and "Isn't there anyone suitable for this?", resulting in decreased work efficiency. [Means for Solving the Problem]

[0005] Employee information, chats, emails, and deliverables are analyzed using a large language model, and relationships between employees and individual specialized fields are comprehensively covered based on the analysis results. This allows questions to be resolved immediately and improves work efficiency. [Brief Description of Drawings]

[0006] [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 Embodiment 1 of Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1 of Form Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2 of Embodiment 2. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2 of Form Example 2. [Figure 15] This is a sequence diagram showing the processing flow of the data processing system in Embodiment 3 of Example 3. [Figure 16] This is a sequence diagram showing the processing flow of the data processing system in Application Example 3 of Form Example 3. [Figure 17] FIG. 12 is a sequence diagram illustrating a processing flow of a data processing system according to Embodiment 1 of First Example Embodiment in a case where an emotion engine is combined. [Figure 18] FIG. 13 is a sequence diagram illustrating a processing flow of a data processing system according to Application Example 1 of First Example Embodiment in a case where an emotion engine is combined. [Figure 19] FIG. 14 is a sequence diagram illustrating a processing flow of a data processing system according to Embodiment 2 of Second Example Embodiment in a case where an emotion engine is combined. [Figure 20] FIG. 15 is a sequence diagram illustrating a processing flow of a data processing system according to Application Example 2 of Second Example Embodiment in a case where an emotion engine is combined. [Figure 21] FIG. 16 is a sequence diagram illustrating a processing flow of a data processing system according to Embodiment 3 of Third Example Embodiment in a case where an emotion engine is combined. [Figure 22] FIG. 17 is a sequence diagram illustrating a processing flow of a data processing system according to Application Example 3 of Third Example Embodiment in a case where an emotion engine is combined. [Figure 23] FIG. 18 is a sequence diagram illustrating a processing flow of a data processing system according to another embodiment. DESCRIPTION OF EMBODIMENTS

[0007] Hereinafter, an example embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0008] First, terms used in the following description will be explained.

[0009] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic device or a combination of a plurality of arithmetic devices. Further, the processor may be one type of arithmetic device or a combination of a plurality of types of arithmetic devices. Examples of arithmetic devices include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), or TPU (TENSOR PROCESSING UNIT (Registered Trademark)).

[0010] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as a work memory by a processor.

[0011] In the following embodiments, signed storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), magnetic tape, and the like.

[0012] In the following embodiments, signed communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. Communication I / F governs communication between a plurality of computers. Examples of communication standards applied to communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (Registered Trademark), Bluetooth (Registered Trademark), and the like.

[0013] 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."

[0014] [First Embodiment]

[0015] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0016] 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.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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.

[0022] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0023] 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.

[0024] 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.

[0025] 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.

[0026] Next, the identification process performed by the identification processing unit 290 of the data processing device 12 will be described.

[0027] "Example of form 1"

[0028] This embodiment of the present invention uses a large-scale language model to analyze employee information, chats, emails, and deliverables. Specifically, employee information, including information such as employees' skill sets, past projects, and areas of expertise, as well as chats and emails recording communication between employees, and deliverables such as reports and presentations created by employees, are input into the large-scale language model. The large-scale language model analyzes this information to extract relationships between employees and their individual areas of expertise.

[0029] "Example of form 2"

[0030] Next, based on the analysis results, we address the question, "Who should I ask?" Specifically, we identify employees who are likely to have solutions to a particular problem and provide information about those employees. For example, if an employee has a question about a particular technology, we recommend an employee who has been analyzed as being proficient in that technology.

[0031] "Example of form 3"

[0032] Furthermore, based on the analysis results, it addresses the question, "Is there anyone like this?" Specifically, it provides information to help find employees with specific skills and experience. For example, if a project team is looking for an employee with a particular skill, it will recommend employees who have been analyzed as possessing that skill.

[0033] The following describes the processing flow for each example of the form.

[0034] "Example of form 1"

[0035] Step 1: Analyze employee information using a large-scale language model. Employee information includes employee skill sets, past projects, and areas of expertise.

[0036] Step 2: Similarly, analyze chats and emails that record communication between employees.

[0037] Step 3: Next, analyze deliverables such as reports and presentations created by employees.

[0038] Step 4: Integrate these analysis results and extract the relationships between employees and their individual areas of expertise. (Example 2)

[0039] Step 1: Based on the analysis results, resolve the question, "Who should I ask?"

[0040] Step 2: Identify employees who are most likely to have solutions to the specific problem.

[0041] Step 3: Provide information about the employee. For example, if an employee has a question about a particular technology, recommend an employee who has been analyzed as being proficient in that technology.

[0042] "Example of form 3"

[0043] Step 1: Based on the analysis results, answer the question, "Are there any people like this?" Step 2: Provide information to find employees with specific skills and experience.

[0044] Step 3: For example, if a project team is looking for an employee with a specific skill, recommend an employee who has been analyzed to possess that skill.

[0045] (Example 1)

[0046] Next, we will describe Example 1 of Form 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."

[0047] In modern businesses, accurately understanding employees' skills and areas of expertise and quickly identifying the right people is crucial. However, the sheer volume of employee information, communication history, and deliverables makes it difficult to efficiently analyze this data and extract the necessary information. Furthermore, finding employees with specific areas of expertise or identifying the appropriate contact person is not easy.

[0048] 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.

[0049] In this invention, the server includes means for collecting information, means for preprocessing the information, and means for analyzing the information using a large-scale language model. This makes it possible to efficiently extract employee relationships and areas of expertise and to quickly provide the necessary information.

[0050] An "information processing device" is a computer system used for collecting, processing, and analyzing data.

[0051] "Means of collecting information" refers to the function of obtaining necessary data from databases or other information sources.

[0052] "Preprocessing means" refers to a function that performs processing to convert collected data into a format suitable for analysis.

[0053] A "large-scale language model" is an advanced machine learning model designed for natural language processing, possessing the ability to analyze vast amounts of text data.

[0054] "Means of analysis" refers to the process of extracting specific information or patterns using pre-processed data.

[0055] "Means for extracting relationships and areas of expertise" refers to a function that identifies relationships between employees and their individual areas of expertise from the analysis results.

[0056] A "generative AI model" is a model that uses artificial intelligence to generate new information and content.

[0057] A "prompt statement" is an instruction given to a generative AI model to obtain specific information.

[0058] The invention is described in terms of its implementation. This system uses an information processing device to analyze employee information, communication history, and deliverables. Specifically, the server collects employee skill sets, past projects, areas of expertise, chat and email history, and created reports and presentations from a database. This data is preprocessed by the server and converted into a format suitable for large-scale language models.

[0059] The server inputs pre-processed data into a large-scale language model. Suitable models for this are commonly used natural language processing models such as GPT-4® and BERT. The model analyzes the input data and extracts relationships between employees and their individual areas of expertise.

[0060] The analysis results are stored in a database by the server and can be accessed later. Users can obtain specific information by entering prompts into the generated AI model. For example, by entering prompts such as "Please tell me about employee A's areas of expertise" or "Please tell me about employees who have shared project experience with employee B," the server extracts the relevant information from the stored analysis results and provides it to the user.

[0061] This system allows companies to efficiently understand their employees' skills and relationships, and quickly identify the right talent.

[0062] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0063] Step 1:

[0064] The server collects employee information, chat history, emails, and deliverables from the database. Inputs include employee skill sets, past projects, areas of expertise, communication history, and created reports and presentations. This data is centrally collected and prepared as foundational data for analysis.

[0065] Step 2:

[0066] The server preprocesses the collected data. The input is the raw data collected in step 1. Specifically, it performs text data cleaning, removal of unnecessary information, tokenization, and data normalization. The output is data in a format suitable for large-scale language models.

[0067] Step 3:

[0068] The terminal inputs pre-processed data into a large-scale language model. The input is the processed data obtained in step 2. Specifically, the data is passed to the model and the analysis is performed. The output is analysis results regarding the relationships between employees and their individual areas of expertise.

[0069] Step 4:

[0070] The server saves the analysis results to a database. The input is the analysis results obtained in step 3. Specifically, the server stores the results in the database in an appropriate format for later reference. The output is the saved analysis results.

[0071] Step 5:

[0072] The user obtains information by inputting prompts into the generating AI model. The input consists of prompts requesting specific information. Specifically, the server extracts relevant information from the database based on the prompts and presents it to the user. The output provides the information the user requested.

[0073] (Application Example 1)

[0074] Next, we will describe Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server," and the smart device 14 will be referred to as a "terminal."

[0075] In modern industrial settings, efficient personnel allocation and team formation are key to improving productivity. However, manually determining the optimal placement, taking into account the skills and past experience of individual personnel, is difficult, time-consuming, and laborious. Furthermore, quickly finding the right personnel is not easy. This leads to challenges such as project delays and wasted resources.

[0076] 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.

[0077] In this invention, the server includes means for analyzing personnel information, communication history, and deliverables using a large-scale language model; means for comprehensively identifying relationships between personnel and their individual areas of expertise based on the analysis results; and means for proposing the optimal team composition based on the analysis results. This enables efficient personnel allocation and rapid team formation.

[0078] A "large-scale language model" is an artificial intelligence model used in natural language processing to learn from large amounts of text data and to understand and generate language.

[0079] "Personnel information" refers to information about individual personnel, such as their skill sets, past project experience, and areas of expertise.

[0080] "Communication history" refers to the record of communication, such as chats and emails, between employees.

[0081] "Deliverables" refer to concrete outputs such as reports and presentations created by employees.

[0082] "Analysis results" refer to the results of information analyzed by a large-scale language model, and include relationships between individuals and their areas of expertise.

[0083] "Team formation" refers to creating a group by combining the most suitable personnel for a specific purpose or project.

[0084] To implement this invention, it is necessary to build a system in which a server analyzes personnel information, communication history, and deliverables using a large-scale language model. The server analyzes this data using the Python programming language and OpenAI's GPT-4 API. Specifically, the server collects data including skill sets, past project experience, and areas of expertise as personnel information, and acquires chat and email records as communication history. As deliverables, it collects outputs such as reports and presentations.

[0085] The server inputs this data into a large-scale language model and extracts the relationships between individuals and their areas of expertise as analysis results. Furthermore, it proposes the optimal team composition based on the analysis results. This proposal aims to streamline personnel allocation within the factory and improve productivity.

[0086] As a concrete example, when setting up a new product line in a factory, the server uses this system to determine which personnel should be assigned to which positions. An example of a prompt to the generative AI model is as follows:

[0087] "Analyze employee data and propose the optimal team composition for launching a new product line. Employee data is as follows: {Employee Data JSON}"

[0088] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0089] Step 1:

[0090] The server collects personnel information, communication history, and deliverables from the database. Inputs include employee skill sets, past project experience, areas of expertise, chat and email records, and deliverables such as reports and presentations. This data is then integrated and prepared for analysis.

[0091] Step 2:

[0092] The server inputs the collected data into a large-scale language model. The input data is structured in JSON format and contains information about each employee. The server analyzes the data using a generative AI model to extract relationships between employees and their individual areas of expertise. The analysis results are output.

[0093] Step 3:

[0094] The server proposes the optimal team composition based on the analysis results. Specifically, it selects the most suitable personnel for the project, taking into account each employee's skills and areas of expertise based on the analysis results. A list of the proposed team compositions is generated as output.

[0095] Step 4:

[0096] The server notifies the user of the proposed team composition. The user receives the notification from the server and confirms the proposed team composition. This allows the user to make efficient personnel allocations. The output includes details of the team composition provided to the user.

[0097] (Example 2)

[0098] Next, we will describe Example 2 of Form 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".

[0099] Within organizations, there is a need to quickly and accurately identify components that are likely to hold the solution to a specific problem and to provide the appropriate information. However, traditional methods present challenges, such as the time-consuming nature of information gathering and analysis, making it difficult to identify the right components.

[0100] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0101] In this invention, the server includes means for collecting information on components using an information processing device, means for analyzing the collected information using a generative AI model, and means for identifying components that are likely to have a solution to a particular problem based on the analysis results. This makes it possible to quickly and accurately identify components that are likely to have a solution to a particular problem and to provide appropriate information.

[0102] An "information processing device" is a device used to collect, process, and analyze data, and includes devices such as computers and servers.

[0103] A "generative AI model" is a model that uses artificial intelligence technology to analyze data and derive solutions to specific problems.

[0104] "Components" refer to individual elements or members within an organization, including individuals or departments with specific skills or knowledge.

[0105] "Analysis results" refer to the results of the analysis obtained after data has been processed by a generative AI model.

[0106] "Identifying" refers to finding elements that meet specific conditions or criteria based on the analysis results.

[0107] "Providing information" refers to presenting users with detailed information about identified components.

[0108] This invention is a system that identifies components within an organization that are likely to possess solutions to specific problems and provides them with appropriate information. The server collects information about the components using an information processing device. Specifically, it retrieves data on the skills and expertise of the components from internal databases and project management tools.

[0109] Next, the server uses a generative AI model to analyze the collected information. This analysis involves data processing and computations that utilize natural language processing techniques to identify components that are familiar with specific technologies or problems. A general large-scale language model is used as the generative AI model.

[0110] Based on the analysis results, the server identifies components that are likely to hold the solution to a specific problem and sends that information to the terminal. The terminal displays information to the user such as the name, role, and area of ​​expertise of the identified component. This allows the user to directly ask questions to the appropriate component.

[0111] For example, if a user enters "I have a question about data analysis in Python," the server sends the following prompt to the AI ​​model: "I have a question about data analysis in Python. Please recommend components that are familiar with this problem." This prompt allows the server to identify appropriate components and provide information to the user.

[0112] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0113] Step 1:

[0114] The server uses an information processing device to collect information about its components. As input, it retrieves data on the components' skills and expertise from internal databases and project management tools. This data includes past project history, skill sets, and job titles. As output, the collected data is passed to a generating AI model.

[0115] Step 2:

[0116] The server analyzes the collected information using a generative AI model. The data collected in step 1 is used as input. The generative AI model utilizes natural language processing techniques to perform data processing and calculations to identify components that are proficient in specific technologies or problems. The output is the analysis result, listing components that are likely to have solutions to the specific problem.

[0117] Step 3:

[0118] The server sends information about the components identified based on the analysis results to the terminal. The analysis results obtained in step 2 are used as input. Specifically, the server organizes information such as the names, roles, and areas of expertise of the identified components and sends it to the terminal. As output, the terminal displays this information to the user.

[0119] Step 4:

[0120] The user can directly ask questions about identified components based on the information displayed on the device. The input is the information about the components displayed on the device. Specifically, the user contacts the components through the device and asks questions. As output, the user can obtain a solution to the problem.

[0121] (Application Example 2)

[0122] Next, we will describe application example 2 of form example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0123] In the operation of industrial machinery, a challenge exists in identifying employees with the expertise to quickly and appropriately resolve technical problems when they occur. To address this challenge, a system is needed that can analyze the nature of the problem, quickly identify the appropriate employees, and contact them.

[0124] 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.

[0125] In this invention, the server includes means for analyzing employee information, communication data, and deliverables using a large-scale language model; means for comprehensively covering relationships between employees and their individual areas of expertise based on the analysis results; means for providing information to resolve questions; means for analyzing problems with industrial machinery and identifying employees with appropriate expertise; and means for providing contact information for the identified employees. This makes it possible to respond quickly and appropriately to technical problems with industrial machinery.

[0126] A "large-scale language model" is an advanced machine learning model designed for natural language processing, which learns language patterns based on large amounts of text data.

[0127] "Employee information" refers to data about employees within a company, including information such as name, job title, area of ​​expertise, and contact information.

[0128] "Communication data" refers to digital communication information such as emails and chat messages exchanged between employees.

[0129] "Deliverables" refer to specific outputs such as documents, reports, and design drawings created by employees through their work.

[0130] "Analysis results" refer to information obtained after analyzing employee information, communication data, and deliverables using a large-scale language model, and include insights into employee relationships and areas of expertise.

[0131] "Specialized field" refers to the area of ​​technology or knowledge in which an employee is particularly proficient.

[0132] "Information provision means" refers to methods and devices for presenting information obtained based on analysis results to employees.

[0133] "Industrial machinery" refers to machinery and equipment used in manufacturing and production industries, specifically for processing and assembling products.

[0134] "Contact information" refers to information such as phone numbers and email addresses necessary to contact a specific employee.

[0135] The system for implementing this invention is designed to quickly resolve technical problems that arise in the operation of industrial machinery. The server analyzes employee information, communication data, and deliverables using a large-scale language model. Specifically, the server uses generative AI models such as OpenAI's GPT-3® to analyze this data and identify employee relationships and areas of expertise.

[0136] The server analyzes data acquired from sensors and cameras on industrial machinery to identify the nature of the problem. Based on the analysis results, it identifies employees with expertise in the relevant area and provides their contact information. This allows users to quickly contact the appropriate employees and take action to resolve the problem.

[0137] As a concrete example, if a machine malfunction occurs in a factory, the server analyzes the data related to the malfunction and inputs a prompt message into an AI model: "Identify an employee with expertise in this machine malfunction." The model then refers to a historical database and recommends the appropriate employee. In this way, the user can quickly obtain the information necessary to solve the problem.

[0138] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0139] Step 1:

[0140] The server receives data acquired from sensors and cameras on industrial machinery. This data includes information such as the machine's operating status and error codes. The server preprocesses this data and converts it into an analyzable format.

[0141] Step 2:

[0142] The server inputs pre-processed data into a generating AI model. Specifically, it uses models such as OpenAI's GPT-3 to analyze machine problems and identify the nature of those problems. This analysis outputs the cause of the problem and related technical information.

[0143] Step 3:

[0144] The server identifies employees with expertise in the problem based on the analysis results. It consults the employee information database to search for employees with expertise matching the analysis results. Information on the identified employees is then output.

[0145] Step 4:

[0146] The server provides the user with the contact information of the identified employee. The user can then use the provided contact information to quickly contact the employee and take action to resolve the issue.

[0147] Step 5:

[0148] Based on information provided by the server, users collaborate with employees to resolve problems. This enables quick and appropriate responses to technical issues with industrial machinery.

[0149] (Example 3)

[0150] Next, we will describe Embodiment 3 of Embodiment Example 3. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0151] In modern organizations, it is crucial to quickly identify individuals with specific skills and experience and assign them to appropriate projects and tasks. However, there is a lack of efficient means to comprehensively understand individuals' skills and experience and provide the necessary information. This leads to challenges such as project delays and delays in finding the right talent.

[0152] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 3 is realized by the following means.

[0153] In this invention, the server includes means for analyzing personal information using a large-scale language model, means for comprehensively covering relationships between individuals and their respective areas of expertise based on the analysis results, and means for providing information to identify individuals with specific skills and experience. This makes it possible to quickly identify individuals with specific skills and assign them to appropriate projects and tasks.

[0154] A "large-scale language model" is an advanced algorithm designed for natural language processing, which learns from large amounts of text data to understand and generate language.

[0155] "Personal information" refers to information about a specific individual, including skills, experience, and past project history.

[0156] "Analysis results" refer to data obtained after processing personal information using a large-scale language model, and include evaluations of individuals' skills and areas of expertise.

[0157] A "prompt statement" is an instruction that a user enters into the system, and it includes requests to obtain specific information.

[0158] "Information provision means" refers to methods for presenting necessary information to users based on analysis results, and is used to identify individuals with specific skills.

[0159] An "output device" is a device used to display analysis results to the user, and includes computer screens and mobile device displays.

[0160] To implement this invention, the user must first enter a prompt message into a terminal to search for an individual with specific skills and experience. The terminal then sends this prompt message to a server. Based on the received prompt message, the server retrieves personal information from its database. This information includes the individual's skills, experience, and past project history.

[0161] The server uses a generative AI model to analyze the acquired information. Specifically, it uses a large-scale language model for natural language processing to evaluate individuals' skill sets and identify individuals with the skills specified in the prompt. Once the analysis is complete, the server sends the analysis results to the terminal. The terminal then displays these results to the user.

[0162] For example, if a user enters the prompt "Find individuals with more than 5 years of experience in data science," the server extracts information on relevant individuals from the database and analyzes it using a generative AI model. As a result of the analysis, the names, departments, and contact information of individuals who meet the criteria are displayed on the device. This allows the user to quickly find the appropriate individuals.

[0163] This system leverages large-scale language models like OpenAI to efficiently analyze personal information, enabling the rapid identification of individuals with specific skills and their placement in appropriate projects and tasks. The flow of the identification process in Example 3 is explained using Figure 15.

[0164] Step 1:

[0165] The user enters a prompt into the terminal to search for individuals with specific skills or experience. The entered prompt becomes an instruction for the system to perform analysis. For example, the user might enter, "Please find individuals with more than 5 years of experience in data science."

[0166] Step 2:

[0167] The terminal sends the user's input prompt message to the server. The server receives this prompt message and prepares for analysis. The prompt message acts as a trigger for the server to retrieve the necessary information from the database.

[0168] Step 3:

[0169] The server retrieves personal information from the database based on the prompt. This information includes the individual's skills, experience, and past project history. The retrieved information becomes input data for analysis by the generative AI model.

[0170] Step 4:

[0171] The server inputs the acquired personal information into a generating AI model for analysis. Specifically, it uses a large-scale language model to evaluate individuals' skill sets and identify individuals who meet the conditions specified in the prompt. As a result of the analysis, a list of individuals who meet the conditions is generated.

[0172] Step 5:

[0173] The server sends the analysis results generated by the AI ​​model to the terminal. The analysis results include the names, departments, and contact information of individuals who meet the specified criteria.

[0174] Step 6:

[0175] The terminal displays the analysis results received from the server to the user. Based on this information, the user can quickly find individuals with specific skills and assign them to appropriate projects and tasks.

[0176] (Application Example 3)

[0177] Next, we will describe application example 3 of form example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0178] In modern industrial settings, there is a need to quickly identify workers with specific skills and assign them to appropriate tasks. However, traditional methods present challenges in efficiently managing and immediately accessing worker skill information when needed. Furthermore, a lack of effective means for providing workers with proper work instructions can lead to decreased work efficiency.

[0179] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means.

[0180] In this invention, the server includes means for analyzing employee information, communication data, and deliverables using a large-scale language model; means for comprehensively identifying relationships between employees and their individual areas of expertise based on the analysis results; means for finding workers with specific skills and assigning them tasks; and means for approaching workers using mobile mechanical devices and instructing them to perform tasks. This makes it possible to quickly identify workers with specific skills and efficiently assign them appropriate tasks.

[0181] A "large-scale language model" is an artificial intelligence technology that learns from vast amounts of text data to understand and generate natural language.

[0182] "Employee information" refers to data about individual employees within an organization, including information such as skills, experience, and job title.

[0183] "Communication data" refers to the content of messages sent and received in digital format, such as emails and chats.

[0184] "Deliverables" refer to specific products, documents, or other outputs produced as a result of work or a project.

[0185] "Analysis results" refer to the insights and conclusions obtained after analyzing data.

[0186] "Relationships between employees" refers to the work-related connections and interactions between employees within an organization.

[0187] "Area of ​​expertise" refers to the area in which an individual employee possesses particularly outstanding skills or knowledge.

[0188] "Workers with specific skills" refers to employees who possess the specialized skills necessary to perform specific tasks or duties.

[0189] A "mobile machine" refers to a machine that can be physically moved and is designed to perform a specific task.

[0190] "Means of giving work instructions" refers to methods or devices used to communicate specific work content and procedures to workers.

[0191] A server plays a central role in implementing this invention. The server uses a large-scale language model to analyze employee information, communication data, and deliverables. Specifically, the server uses a programming language such as Python to retrieve employee information from a database and analyzes the data using natural language processing technology. Based on the analysis results, it is possible to comprehensively analyze the relationships between employees and their individual areas of expertise.

[0192] Furthermore, the server executes an algorithm to find workers with specific skills and assign them tasks. This algorithm uses an SQL database to search for skill information and select the most suitable worker. The selected worker receives work instructions using a mobile machine. This machine communicates with the server via Wi-Fi and provides specific instructions to the worker.

[0193] As a concrete example, consider a situation where a factory needs to find workers with specific machine operation skills to set up a new product line. In this case, the server inputs a prompt message to the AI ​​model saying, "Find workers with the machine operation skills required to set up the new product line," and recommends suitable workers. This improves the efficiency of work within the factory and makes it possible to quickly find workers with the appropriate skills.

[0194] The flow of the specific processing in Application Example 3 will be explained using Figure 16.

[0195] Step 1:

[0196] The server retrieves information on all employees from the employee database. Input includes employee IDs and skill information. Output provides data on employees' skill sets and experience. This data is extracted from the database using SQL queries.

[0197] Step 2:

[0198] The server inputs the acquired employee information into a large-scale language model and performs natural language processing. The input includes text data related to employees' skills and experience. The output provides analysis results regarding employee relationships and areas of expertise. This analysis is performed using a natural language processing algorithm implemented in Python.

[0199] Step 3:

[0200] The server searches for workers with specific skills based on the analysis results. The input includes information about the project's required skills. The output is a list of the most suitable workers. In this step, a generative AI model is used to generate prompts and recommend appropriate workers.

[0201] Step 4:

[0202] The server sends commands to a mobile machine to instruct a selected worker to perform a task. Inputs include the worker's ID and the task description. Output is that the machine approaches the worker and provides the work instructions. This communication takes place via Wi-Fi, and the machine operates according to the instructions.

[0203] Step 5:

[0204] The user receives feedback from the machine and monitors the progress of the work. Input includes feedback data from the machine. Output provides information on the work completion status and any problems encountered. Based on this information, the user can provide additional instructions as needed.

[0205] 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.

[0206] "Example of form 1"

[0207] One embodiment of the present invention combines a large-scale language model with an emotion engine. The large-scale language model analyzes employee information, chats, emails, and deliverables to comprehensively cover employee relationships and individual areas of expertise. Meanwhile, the emotion engine recognizes the user's emotions and uses the results to analyze the large-scale language model. For example, if a user is feeling frustrated, the emotion engine captures that information, and the large-scale language model uses that information to recommend an appropriate employee.

[0208] "Example of form 2"

[0209] In another embodiment of the present invention, the emotion engine recommends the most suitable employee based on the user's emotions. Specifically, if the user is feeling happy, the emotion engine captures that information, and the large-scale language model uses that information to recommend an employee who is likely to feel similar happiness. This facilitates smoother communication between the user and the employee.

[0210] "Example of form 3"

[0211] In a further embodiment of the present invention, the emotion engine analyzes the user's emotions and uses the results to analyze a large-scale language model. Specifically, if the user is feeling angry, the emotion engine captures that information, and the large-scale language model uses that information to recommend employees who are judged to have high problem-solving abilities. This helps the user solve their problems.

[0212] The following describes the processing flow for each example of the form.

[0213] "Example of form 1"

[0214] Step 1: A large-scale language model analyzes employee information, chat messages, emails, and deliverables.

[0215] Step 2: The emotion engine recognizes the user's emotions.

[0216] Step 3: The analysis results from the emotion engine are fed back into the large-scale language model.

[0217] Step 4: A large-scale language model recommends appropriate employees based on the analysis results of the emotion engine. (Example 2)

[0218] Step 1: The emotion engine recognizes the user's emotions.

[0219] Step 2: A large-scale language model analyzes employee information, chat messages, emails, and deliverables.

[0220] Step 3: A large-scale language model uses the results of the emotion engine's analysis to recommend employees who are likely to experience similar feelings of joy.

[0221] "Example of form 3"

[0222] Step 1: The emotion engine recognizes the user's emotions.

[0223] Step 2: A large-scale language model analyzes employee information, chat messages, emails, and deliverables.

[0224] Step 3: A large-scale language model recommends employees who are judged to have high problem-solving abilities based on the analysis results of the emotion engine.

[0225] (Example 1)

[0226] Next, we will describe Example 1 of Form 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."

[0227] In modern businesses, accurately understanding employees' skills and areas of expertise and making appropriate personnel placements is crucial. However, efficiently analyzing vast amounts of data such as employee information, communication history, and deliverables to clearly identify individual strengths and interpersonal relationships is difficult. Furthermore, there is a need for personnel recommendations and problem-solving information that takes employees' emotional states into account. An effective system is needed to address these challenges.

[0228] 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.

[0229] In this invention, the server includes means for analyzing personal information, communication history, and created materials using a natural language processing model; means for identifying interpersonal relationships and individual areas of expertise based on the analysis results; and means for an emotion analysis device to recognize the user's emotional state and utilize the results for the analysis of the natural language processing model. This enables accurate understanding of employees' skills and areas of expertise, and allows for appropriate personnel placement and the provision of information for problem solving.

[0230] An "information processing device" is a computer system used to collect, analyze, and process data.

[0231] A "natural language processing model" is an artificial intelligence technology used to understand and analyze human language.

[0232] "Personal information" refers to information about a specific individual, such as their skill set or project history.

[0233] "Communication history" refers to records of communication between individuals, such as emails and chats.

[0234] "Created works" refer to deliverables such as reports and presentations created by individuals.

[0235] "Relationships" refer to information that indicates interactions and connections between individuals.

[0236] "Specialized area" refers to the field or skill in which an individual excels.

[0237] An "emotion analysis device" is a device used to recognize and analyze the emotional state of a user.

[0238] "User" refers to an individual or organization that uses the system.

[0239] "Information provision" refers to the act of presenting useful information to users based on analysis results.

[0240] This invention is a system that uses an information processing device to analyze personal information, communication history, and created materials to identify relationships between individuals and their areas of expertise. Specifically, the server uses a natural language processing model, such as OpenAI's GPT-4, to analyze this data. The server collects employee skill sets, project history, email exchanges, and created reports and presentations from a company's database.

[0241] The server preprocesses the collected data and inputs it into a natural language processing model. Preprocessing includes tokenizing text data and filtering out irrelevant information. Based on the analysis, the server extracts relationships between employees and their individual areas of expertise.

[0242] Furthermore, the server uses an emotion analyzer to recognize the user's emotional state. For example, if a user inputs "the project isn't progressing," the emotion analyzer detects frustration and uses that information to analyze the natural language processing model.

[0243] The terminal displays the analysis results received from the server to the user. The user can review the recommended employees and suggestions on the screen and decide on their next action.

[0244] As a concrete example, if a user enters the prompt message, "Please recommend the best data analysis expert for Project Y," the server will recommend a suitable employee based on the analysis results. This system takes into account the employee's skills and feelings to support optimal personnel placement and improved communication.

[0245] The flow of the specific processing in Example 1 will be explained using Figure 17.

[0246] Step 1:

[0247] The server collects the data. The server accesses the company's database to retrieve employee skill sets, project history, email correspondence, and created reports and presentations. The input is the company's database, and the output is data formatted for analysis. Specifically, the server extracts information from the database via an API.

[0248] Step 2:

[0249] The server preprocesses the data. The server converts the collected data into a format suitable for the natural language processing model. The input is the data obtained in step 1, and the output is tokenized data with unnecessary information filtered out. Specifically, the server tokenizes the text data and removes noisy information.

[0250] Step 3:

[0251] The server analyzes the data using a natural language processing model. The server inputs the pre-processed data into the natural language processing model to extract relationships between employees and their individual areas of expertise. The input is the data pre-processed in step 2, and the output is the relationship and area of ​​expertise information as a result of the analysis. Specifically, the server inputs data into the model and obtains the analysis results.

[0252] Step 4:

[0253] The server performs sentiment analysis. Based on the user's input prompts and past communication history, the server uses a sentiment analysis device to recognize the user's emotional state. The input is the user's prompts and history data, and the output is information about the emotional state. Specifically, the server applies a sentiment analysis algorithm to identify the emotion.

[0254] Step 5:

[0255] The server integrates the analysis results and sends them to the terminal. The server integrates the information obtained from the natural language processing model and sentiment analysis to generate information useful to the user. The input is the output of steps 3 and 4, and the output is the integrated analysis result. Specifically, the server integrates the data and prepares it for transmission to the terminal.

[0256] Step 6:

[0257] The terminal displays the results. The terminal displays the analysis results received from the server to the user. The input is the analysis results sent from the server, and the output is the information that the user can see on the screen. Specifically, the terminal visually displays the results, allowing the user to decide on the next action.

[0258] (Application Example 1)

[0259] Next, we will describe Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server," and the smart device 14 will be referred to as a "terminal."

[0260] In modern industrial settings, efficient task assignment that takes into account workers' skills and emotional states is essential. However, conventional systems struggle to consider workers' emotional states, resulting in decreased work efficiency and increased worker stress. To address these challenges, a system is needed that analyzes workers' skills and emotional states in real time and assigns them the most suitable tasks.

[0261] 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.

[0262] In this invention, the server includes means for analyzing personnel information, communication history, and deliverables using a large-scale language model; means for comprehensively identifying relationships between personnel and their individual areas of expertise based on the analysis results; and means for analyzing individual emotional states using an emotion recognition engine. This enables efficient task assignment that takes into account the skills and emotional states of the workers.

[0263] A "large-scale language model" is an artificial intelligence technology that learns from vast amounts of text data to understand and generate natural language.

[0264] "Personnel information" refers to information such as the skill set, past work history, and area of ​​expertise of individual workers.

[0265] "Communication history" refers to records of communication between workers, such as chats and emails.

[0266] "Deliverables" refer to specific work results such as reports and presentations created by workers.

[0267] An "emotion recognition engine" is a technology that analyzes the emotional state of workers and acquires that information in real time.

[0268] "Task assignment" is the process of selecting the most suitable tasks for workers and distributing them in order to carry out the work efficiently.

[0269] The system for implementing this invention consists of a server equipped with a large-scale language model and an emotion recognition engine. The server first collects personnel information, communication history, and deliverables, and then analyzes this data using the large-scale language model. As a result of the analysis, the relationships between workers and their individual areas of expertise become clear.

[0270] Next, the server uses an emotion recognition engine to analyze the worker's current emotional state in real time. This emotional information is important for understanding the worker's stress level and motivation.

[0271] Based on the analysis results and emotion information, the server assigns the optimal task to each worker. This can be expected to improve work efficiency and reduce workers' stress. As a specific example, when worker A is feeling frustrated, the server can reduce worker A's stress by assigning a low-burden task to worker A.

[0272] An example of a prompt sentence to be input to a generative AI model is: "Analyze employee information, chat logs, and deliverables, and assign optimal tasks in consideration of each employee's specialized fields and current emotional state."

[0273] In this way, the server achieves efficient task assignment that considers workers' skills and emotional states.

[0274] The flow of the specific process in Application Example 1 will be described with reference to FIG. 18.

[0275] Step 1:

[0276] The server collects personnel information, communication history, and deliverables from the database. These pieces of data include each worker's skill set, past work history, specialized fields, records of chats and emails, and created reports, presentations, and the like. The input data is transferred to the server in text format.

[0277] Step 2:

[0278] The server analyzes the collected data using a large language model. Specifically, it receives text data as input, and extracts relationships between workers and individual specialized fields using natural language processing techniques. As output, a skill map and a relationship map of the workers are generated.

[0279] Step 3:

[0280] The server analyzes the worker's current emotional state using an emotion recognition engine. It receives the worker's facial image and audio data as input, and identifies the worker's emotional state (e.g., stress, motivation) by applying an emotion recognition algorithm. As an output, emotional state data for each worker is generated.

[0281] Step 4:

[0282] The server integrates the analysis results and emotion information, and assigns an optimal task to each worker. Specifically, it receives a skill map and emotional state data as input, and selects a task suitable for the worker by applying a task assignment algorithm. As an output, a task assignment list for each worker is generated.

[0283] Step 5:

[0284] The server notifies workers of the task assignment results using a generative AI model. It generates a prompt sentence and transmits the notification to the worker's terminal. As an example of a specific prompt sentence, "Analyze employee information, chat logs, and deliverables, and assign the optimal task in consideration of each employee's specialty and current emotional state." is used. As an output, the notification is displayed on the worker's terminal.

[0285] (Example 2)

[0286] Next, Example 2 of the second embodiment will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart device 14 is referred to as a "terminal".

[0287] There is a problem that it is difficult to quickly and accurately identify other employees with appropriate knowledge and experience for problems or questions faced by an employee. In addition, optimal emotion-based employee recommendation is required to facilitate smooth communication between employees.

[0288] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is implemented by the following respective means.

[0289] In this invention, the server includes means for analyzing employee information, communication data, and deliverables using a large-scale language model; means for comprehensively covering relationships between employees and their individual areas of expertise based on the analysis results; and means for analyzing the user's emotions using an emotion analysis engine and recommending the most suitable employee. This enables the rapid identification of other employees with the appropriate knowledge to address problems faced by employees, and facilitates smooth, emotion-based communication.

[0290] A "large-scale language model" is an artificial intelligence model designed for natural language processing, trained on a vast dataset.

[0291] "Employee information" refers to data about employees, such as their skill sets, work history, and areas of expertise.

[0292] "Communication data" refers to information such as emails and chat messages exchanged between employees.

[0293] "Deliverables" refer to documents, reports, and project outputs created by employees through their work.

[0294] "Analysis results" refers to the results of analyzing data obtained using large-scale language models and sentiment analysis engines.

[0295] An "emotion analysis engine" is a technology that analyzes a user's emotions and suggests appropriate actions based on those emotions.

[0296] "Users" refers to employees or individuals who use the system to obtain information.

[0297] "Specialized field" refers to the area of ​​technology or knowledge in which an employee is particularly proficient.

[0298] "Recommendation" refers to the act of presenting the most suitable employees or information based on analysis results.

[0299] The present invention is a system that rapidly identifies other employees with appropriate knowledge for problems faced by an employee, and enables smooth emotion-based communication. Specific embodiments of the system are described below.

[0300] The server receives input data from a user and performs analysis using a generative AI model. Natural language processing technology is utilized for this analysis, specifically, large language models such as OpenAI's GPT are used. The server understands the user's questions and problems, and searches an internal database to identify employees with relevant knowledge. This database includes the skill sets and work histories of employees.

[0301] Furthermore, the server analyzes the user's emotion using a sentiment analysis engine. For example, if the user feels joy when inputting a question, the server recommends employees who are highly likely to have a similar emotion based on this information. This process smoothes communication between the user and the recommended employee.

[0302] As a specific example, consider a case where a user asks the question "I want to learn detailed information about a new technology". The server analyzes this question and recommends an employee determined to be proficient in the relevant technology. Furthermore, if the user feels joy when asking the question, the sentiment engine recommends an employee who similarly has passion for the technology based on this information.

[0303] An example of a prompt input to the generative AI model is "Please recommend the most suitable employee for an employee who has a question about technology". By using this prompt, the server identifies an appropriate employee and provides the information to the user.

[0304] The flow of identification processing in Embodiment 2 will be described with reference to FIG. 19.

[0305] Step 1:

[0306] The user enters questions or problems through the terminal. For example, they might enter something like, "I want to learn more about this new technology." The terminal then sends this input data to the server. The input data is text information that includes the user's questions and feelings.

[0307] Step 2:

[0308] The server analyzes the received input data. This analysis uses a generative AI model. Specifically, it uses a large-scale language model such as OpenAI's GPT to understand the user's question. The server analyzes the input data using natural language processing techniques to identify the user's intent. The output is the analyzed user intent and related keywords.

[0309] Step 3:

[0310] The server searches the company's internal database based on the analysis results. This database contains employee skill sets and work histories. The server queries the database to identify employees with knowledge relevant to the user's question. The input is the analyzed keywords, and the output is a list of relevant employees.

[0311] Step 4:

[0312] The server uses an emotion analysis engine to analyze the user's emotions. It identifies the emotions the user is feeling when entering a question and recommends employees who are likely to have similar emotions. The input is data about the user's emotions, and the output is a list of the most suitable employees based on those emotions.

[0313] Step 5:

[0314] The server provides the user with information about the identified employee. The terminal displays this information to the user. For example, the information might be presented as, "An employee with technical expertise can answer your questions." The input is a list of the most suitable employees, and the output is the information provided to the user.

[0315] (Application Example 2)

[0316] Next, we will describe application example 2 of form example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0317] It is essential to identify engineers who can respond quickly and appropriately to technical problems that arise within the factory, and to resolve these problems efficiently. Furthermore, facilitating smooth communication among employees is also crucial to improving the speed of problem-solving.

[0318] 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.

[0319] In this invention, the server includes means for analyzing employee information, communication data, and deliverables using a large-scale language model; means for comprehensively covering relationships between employees and their individual areas of expertise based on the analysis results; means for providing information to resolve questions; means for automated machinery in the factory to detect anomalies and transmit the information to the cloud; means for a generated AI model on the cloud to perform analysis and identify appropriate technicians; and means for sending notifications to the identified technicians. This enables rapid response to technical problems within the factory and smooth communication among employees.

[0320] A "large-scale language model" is an advanced machine learning model designed for natural language processing, which understands and generates language based on large amounts of text data.

[0321] "Employee information" refers to data about employees within a company, including individual skills, experience, job title, and job responsibilities.

[0322] "Communication data" refers to records of digital communications such as emails and chat messages exchanged between employees.

[0323] "Deliverables" refer to specific outputs such as documents, reports, and design drawings created by employees through their work.

[0324] "Analysis results" refer to information obtained after analyzing employee information, communication data, and deliverables using a large-scale language model, and include insights into employee relationships and areas of expertise.

[0325] "Automated machinery" refers to mechanical devices used in factories that operate automatically using sensors and control systems.

[0326] "Cloud" refers to a service of computer resources and data storage provided via the internet, and is a platform for storing and processing data.

[0327] A "generative AI model" is a model that uses artificial intelligence technology to analyze data and generate new information and insights.

[0328] A "technician" is a person who possesses specialized knowledge and skills in a particular technical field and is responsible for tasks such as problem-solving and machine maintenance.

[0329] A "notification" is a message or alert sent via email or smart device to inform a recipient of specific information.

[0330] The system for implementing this invention is designed to quickly resolve technical problems within a factory. The server uses a large-scale language model to analyze employee information, communication data, and deliverables. This allows for comprehensive analysis of employee relationships and individual areas of expertise.

[0331] Automated machinery within the factory uses sensors to detect anomalies and transmits this information to the cloud. On the cloud, a generative AI model analyzes the data and identifies the appropriate technician. This identified technician receives a notification via their device, such as a smartphone or smart glasses.

[0332] For example, if an automated machine in a factory detects abnormal vibrations, that data is sent to the cloud. A generative AI model on the cloud identifies a technician with expertise in vibrations and sends a notification to his smartphone saying, "Abnormal vibrations have been detected in machine X. Please take action."

[0333] An example of a prompt message is, "Abnormal vibration has been detected in the machine. Please identify a technician with expertise in vibration." This prompt message allows the generating AI model to quickly identify the appropriate technician.

[0334] This system enables rapid response to technical issues within the factory and facilitates smooth communication among employees.

[0335] The flow of a specific process in Application Example 2 will be explained using Figure 20.

[0336] Step 1:

[0337] The server receives sensor data transmitted from automated machinery within the factory. This data includes information on the machine's operating status and signs of malfunctions. The server analyzes the received data to determine whether an anomaly has been detected.

[0338] Step 2:

[0339] If an anomaly is detected, the server sends the information to the cloud. In the cloud, a generative AI model receives this data as input and analyzes the type of anomaly and its scope of impact. Based on the analysis results, it identifies which technical fields of expertise are needed.

[0340] Step 3:

[0341] The cloud-based AI model identifies the appropriate engineers based on the analysis results. This process involves referencing an employee database to select engineers with the necessary expertise. Information on the selected engineers is then output.

[0342] Step 4:

[0343] The server generates a notification for the identified technician. This notification includes detailed information about the anomaly and the need for action. The notification is sent to the technician's device (smartphone or smart glasses).

[0344] Step 5:

[0345] Technicians receive notifications on their terminals and begin responding to an anomaly. Based on the notification, technicians head to the site and work to resolve the problem. This enables rapid problem resolution.

[0346] (Example 3)

[0347] Next, we will describe Embodiment 3 of Embodiment Example 3. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0348] In today's workplace environment, it is difficult to quickly identify individuals with specific skills and experience. Furthermore, recommending the right person while considering the user's feelings is also challenging. This can lead to delays in project progress and stalls in problem-solving.

[0349] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 3 is realized by the following means.

[0350] In this invention, the server includes means for analyzing job information using a generative AI model, means for recommending personnel with specific skills based on the analysis results, and means for analyzing the user's emotions using an emotion analysis engine and recommending personnel judged to have high problem-solving abilities based on the results. This makes it possible to quickly find personnel with specific skills and recommend appropriate personnel that take into account the user's emotions.

[0351] A "generative AI model" is a model that uses artificial intelligence technology to perform natural language processing and analyze or generate data for specific tasks.

[0352] "Job information" refers to data about employees and personnel, such as skills, experience, resumes, and project history.

[0353] "Analysis results" refers to the results of analyzing data obtained by generative AI models and emotion analysis engines.

[0354] "Specific skills" refer to the specialized knowledge and techniques required for a particular task or project.

[0355] An "emotion analysis engine" refers to software or a system that analyzes a user's emotions and identifies their emotional state.

[0356] A "prompt sentence" is an instruction sentence input to a generative AI model, and refers to a sentence that includes a question or request to obtain specific information.

[0357] "Problem-solving ability" refers to the ability to effectively address specific challenges or problems and find solutions.

[0358] A description of embodiments for carrying out this invention will be given.

[0359] The server first analyzes job information using a generative AI model. This analysis utilizes natural language processing technology and targets data such as skills, experience, resumes, and project history related to employees and personnel. Specifically, a database management system (DBMS) is used to collect and analyze this data.

[0360] Next, the server recommends individuals with specific skills based on the analysis results. The generative AI model searches the database for individuals with the relevant skills based on the prompt text and creates a recommendation list. For example, if a user enters the prompt text "Please recommend employees who are strong in data analysis," the server will respond to this request by listing suitable individuals.

[0361] Furthermore, the device uses an emotion analysis engine to analyze the user's emotions. If the user is feeling anger or stress, it sends that information to the server. Based on this emotional information, the server recommends individuals who are judged to have high problem-solving abilities. This makes it possible to select the most suitable personnel while taking the user's emotions into consideration.

[0362] As a concrete example, suppose a project is behind schedule and the user enters a prompt message saying, "Please recommend an employee with strong problem-solving skills to help the project progress." In this case, the server considers the results of the sentiment analysis engine and recommends an appropriate person, thereby facilitating the smooth progress of the project. The specific processing flow in Example 3 will be explained using Figure 21.

[0363] Step 1:

[0364] The server uses a database management system (DBMS) to collect job information related to employees and personnel, such as skills, experience, resumes, and project history. The input consists of various job information within the database. The server retrieves this data and builds a basic dataset for analysis. The output is a dataset of job information necessary for analysis.

[0365] Step 2:

[0366] The server uses a generative AI model to analyze the collected job information. The input is the dataset of job information obtained in Step 1. The server utilizes natural language processing technology to analyze the data in order to identify individuals with specific skills and experience. The output is the analysis results regarding each employee's skills and experience.

[0367] Step 3:

[0368] The user enters a prompt to search for personnel with specific skills. The input is a prompt message entered by the user. For example, the user might enter a prompt message such as, "Please recommend an employee with strong data analysis skills." The output is that the server receives this prompt message and uses it as an instruction for analysis.

[0369] Step 4:

[0370] The server searches for suitable personnel from the analysis results based on the prompt message and creates a recommendation list. The input consists of the analysis results obtained in step 2 and the prompt message entered in step 3. The server compares these and lists the most suitable personnel. The output is a list of recommended personnel.

[0371] Step 5:

[0372] The device analyzes the user's emotions using an emotion analysis engine. The input is data related to the user's emotions. The device analyzes this data to identify the user's emotional state. The output is the analysis result regarding the user's emotional state.

[0373] Step 6:

[0374] The server recommends individuals deemed to have high problem-solving abilities based on the results of the emotion analysis engine. The inputs are the emotion analysis results obtained in step 5 and the recommendation list obtained in step 4. The server considers these factors to select the most suitable individuals. The output is a final list of recommended individuals, taking emotions into account.

[0375] (Application Example 3)

[0376] Next, we will describe application example 3 of form example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0377] In modern industrial settings, there is a need to quickly identify personnel with specific skills and provide appropriate problem-solving. However, traditional methods are time-consuming in finding the necessary personnel and have difficulty addressing issues that take emotional factors into consideration.

[0378] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means.

[0379] In this invention, the server includes means for analyzing personnel information, communication data, and deliverables using a large-scale language model; means for comprehensively covering the relationships between personnel and their individual areas of expertise based on the analysis results; and means for analyzing the user's emotions using an emotion analysis engine and utilizing the results in the large-scale language model. This enables the rapid identification of personnel with specific skills and appropriate problem-solving that takes emotional factors into consideration.

[0380] A "large-scale language model" is an artificial intelligence technology that has the ability to understand and generate natural language based on vast amounts of data.

[0381] "Personnel information" refers to data on individual personnel, such as their skills, experience, and performance.

[0382] "Communication data" refers to information generated through digital communication such as email and chat.

[0383] "Deliverables" refer to specific products or documents produced as a result of a project or task.

[0384] An "emotion analysis engine" is a technology that analyzes a user's emotions and identifies their emotional state.

[0385] A "specialized field" refers to an area that focuses on specific knowledge or skills.

[0386] "Problem-solving ability" refers to the ability to find effective solutions to challenges and problems.

[0387] "Recommendation" is the act of presenting the best option based on specific conditions.

[0388] The system for implementing this invention operates in a network environment including a server and terminals. The server runs a program that analyzes personnel information, communication data, and deliverables using a large-scale language model. This analysis uses the Hugging Face Transformers library and performs natural language processing. Based on the analysis results, the server comprehensively covers the relationships between personnel and their individual areas of expertise and stores them in a database.

[0389] Furthermore, the server uses an emotion analysis engine to analyze users' emotions and utilizes the results in a large-scale language model. The emotion analysis uses software capable of real-time data processing. This allows for the rapid identification of individuals with specific skills and the recommendation of those deemed to have high problem-solving abilities.

[0390] The terminal sends a query to the server when the user is looking for someone with specific skills. The server searches its database based on the received query and lists the relevant personnel. When the user is troubleshooting a machine, the terminal performs sentiment analysis and recommends the most suitable technician.

[0391] As a concrete example, when a machine malfunctions, the terminal prompts the AI ​​model with the message, "We are looking for a technician who can troubleshoot machine A." The model then consults a skills database and lists suitable technicians. It also analyzes the emotions of the surrounding workers and prioritizes recommending technicians who are deemed calm and possess strong problem-solving abilities.

[0392] Example of a prompt:

[0393] "We are looking for a technician who can troubleshoot machine A. Please perform an emotional analysis and recommend the most suitable technician."

[0394] The flow of the specific processing in Application Example 3 will be explained using Figure 22.

[0395] Step 1:

[0396] The user uses a terminal to enter a prompt message to search for personnel with specific skills. The entered prompt message is sent from the terminal to the server.

[0397] Step 2:

[0398] The server parses the received prompt message and queries the skills database. The database contains information about the skills and experience of the personnel. The server generates a list of the relevant personnel as a result of the query.

[0399] Step 3:

[0400] The server uses an emotion analysis engine to analyze the user's emotions. It uses the user's voice and text data as input to identify their emotional state. The analysis results are fed back into a large-scale language model.

[0401] Step 4:

[0402] Based on the results of the sentiment analysis, the server prioritizes selecting individuals from a list who are judged to have high problem-solving abilities. The information of the selected individuals is sent to the terminal.

[0403] Step 5:

[0404] The terminal displays personnel information received from the server to the user. Based on the displayed information, the user can select the appropriate personnel and contact them.

[0405] Step 6:

[0406] Users can contact the personnel they have selected from their device. Email and chat are used as communication methods. This allows users to quickly begin taking action to resolve their problems.

[0407] (Other examples)

[0408] Next, other embodiments will be described. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0409] In today's information society, it is difficult to quickly and accurately obtain the necessary information from a vast amount of data. Furthermore, when users retrieve specific information, they need to consider the relevance and specialization of the information, but conventional systems have the challenge of not being able to do this efficiently.

[0410] The identification process performed by the identification processing unit 290 of the data processing device 12 in other embodiments is realized by the following means.

[0411] In this invention, the server includes means for collecting and preprocessing information, means for analyzing the information using a large-scale language model to identify relationships and areas of expertise, and means for generating and inputting prompts to instruct a generative AI model to acquire specific information. This makes it possible to quickly and accurately obtain the information that the user needs.

[0412] An "information processing device" is a computer system used for collecting, processing, and analyzing data, and is a device that receives input from a user and provides the necessary information.

[0413] "Preprocessing" refers to the data cleaning and normalization processes performed to prepare collected data into a format that is easy to analyze.

[0414] A "large-scale language model" is an advanced machine learning model designed for natural language processing, possessing the ability to understand the meaning and context of language based on vast amounts of text data.

[0415] "Relationship" refers to the connections and interactions that exist between different data points within the analyzed information.

[0416] A "specialized field" is an area where specific knowledge or skills are studied intensively, and it indicates which field the analyzed information belongs to.

[0417] A "generative AI model" is an artificial intelligence model trained to produce appropriate output for a specific task, and is a model that has the ability to generate information based on prompts.

[0418] A "prompt" is a text input used to give instructions to a generative AI model to obtain specific information.

[0419] The following describes "modes for carrying out the invention."

[0420] ---

[0421] This invention is a system that efficiently collects and analyzes information and quickly provides users with the information they need. The system uses a server as an information processing device, a terminal for users to input information, and a generative AI model.

[0422] The server receives information entered by the user from their terminal. The user enters information via a web browser and sends it to the server as an HTTP request. The server uses a Python script to clean and normalize the received information, ensuring data consistency.

[0423] Next, the server prepares the pre-processed information for input into OpenAI's GPT-4, a large-scale language model. For analysis, the natural language processing library spaCy is used. Using spaCy, the information is tokenized and tagged with parts of speech to extract the semantic relationships of the information. Based on the analysis results, the server identifies the relationships and specialized fields of the information and stores them in a MySQL® database.

[0424] When a user wants to obtain specific information, they send a request to the server. Based on the user's request, the server generates a prompt for the AI ​​model. An example of a prompt is, "Please provide information on the latest trends in AI technology." This prompt is input into GPT-4, and the server retrieves the generated information.

[0425] The acquired information is sent from the server to the user's terminal. The user can view the information on a web browser. The user interface is built using HTML and JavaScript (registered trademark) and is designed to allow users to easily search for and view information.

[0426] This system allows users to quickly and accurately obtain the information they need, and enables searches that take into account the relevance and specialization of the information.

[0427] The flow of specific processing in other embodiments will be explained using Figure 23.

[0428] Step 1:

[0429] The user enters information into a form on a web browser using their device. The entered information is sent to the server as an HTTP request. The input data contains an overview of the information the user wants to obtain. The server receives this information and performs data cleaning and normalization. Specifically, it uses a Python script to remove unnecessary whitespace and special characters and standardize the data format. This ensures the consistency of the information.

[0430] Step 2:

[0431] The server prepares to use OpenAI's GPT-4, a large-scale language model, to analyze preprocessed information. For analysis, it uses spaCy, a natural language processing library. Using spaCy, the information is tokenized and tagged with parts of speech to extract semantic relationships. The input data is preprocessed information, and the output is the analysis result showing the relationships and specialized fields of the information. The server saves this analysis result to a MySQL database.

[0432] Step 3:

[0433] When a user wants to obtain specific information, they send a request from their device to the server. The request includes details of the information the user wants to know. Based on this request, the server generates a prompt for the AI ​​model. An example of a prompt is, "Please provide information on the latest trends in AI technology." This prompt is input to GPT-4. The input data is the prompt, and the output is the generated information.

[0434] Step 4:

[0435] The server retrieves information generated from GPT-4 and sends it to the user's terminal. The user can view this information in a web browser. The user interface is built using HTML and JavaScript and is designed to allow users to easily search and view information. The input data is the generated information, and the output is the information provided to the user. The user can then make decisions based on this information.

[0436] 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.

[0437] Data generation model 58 is a form of 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> 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.

[0438] Other examples of generative AI include Gemini® (registered trademark) (Internet search). <url: https: gemini.google.com ?hl="ja">) are examples.

[0439] 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.

[0440] [Second Embodiment]

[0441] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0442] 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.

[0443] 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).

[0444] 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.

[0445] 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.

[0446] 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).

[0447] 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.

[0448] 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.

[0449] 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.

[0450] 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.

[0451] 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.

[0452] Next, the identification process performed by the identification processing unit 290 of the data processing device 12 will be described.

[0453] "Example of form 1"

[0454] This embodiment of the present invention uses a large-scale language model to analyze employee information, chats, emails, and deliverables. Specifically, employee information, including information such as employees' skill sets, past projects, and areas of expertise, as well as chats and emails recording communication between employees, and deliverables such as reports and presentations created by employees, are input into the large-scale language model. The large-scale language model analyzes this information to extract relationships between employees and their individual areas of expertise.

[0455] "Example of form 2"

[0456] Next, based on the analysis results, we address the question, "Who should I ask?" Specifically, we identify employees who are likely to have solutions to a particular problem and provide information about those employees. For example, if an employee has a question about a particular technology, we recommend an employee who has been analyzed as being proficient in that technology.

[0457] "Example of form 3"

[0458] Furthermore, based on the analysis results, it addresses the question, "Is there anyone like this?" Specifically, it provides information to help find employees with specific skills and experience. For example, if a project team is looking for an employee with a particular skill, it will recommend employees who have been analyzed as possessing that skill.

[0459] The following describes the processing flow for each example of the form.

[0460] "Example of form 1"

[0461] Step 1: Analyze employee information using a large-scale language model. Employee information includes employee skill sets, past projects, and areas of expertise.

[0462] Step 2: Similarly, analyze chats and emails that record communication between employees.

[0463] Step 3: Next, analyze deliverables such as reports and presentations created by employees.

[0464] Step 4: Integrate these analysis results and extract the relationships between employees and their individual areas of expertise. (Example 2)

[0465] Step 1: Based on the analysis results, resolve the question, "Who should I ask?"

[0466] Step 2: Identify employees who are most likely to have solutions to the specific problem.

[0467] Step 3: Provide information about the employee. For example, if an employee has a question about a particular technology, recommend an employee who has been analyzed as being proficient in that technology.

[0468] "Example of form 3"

[0469] Step 1: Based on the analysis results, answer the question, "Are there any people like this?" Step 2: Provide information to find employees with specific skills and experience.

[0470] Step 3: For example, if a project team is looking for an employee with a specific skill, recommend an employee who has been analyzed to possess that skill.

[0471] (Example 1)

[0472] Next, we will describe Embodiment 1 of Embodiment 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".

[0473] In modern businesses, accurately understanding employees' skills and areas of expertise and quickly identifying the right people is crucial. However, the sheer volume of employee information, communication history, and deliverables makes it difficult to efficiently analyze this data and extract the necessary information. Furthermore, finding employees with specific areas of expertise or identifying the appropriate contact person is not easy.

[0474] 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.

[0475] In this invention, the server includes means for collecting information, means for preprocessing the information, and means for analyzing the information using a large-scale language model. This makes it possible to efficiently extract employee relationships and areas of expertise and to quickly provide the necessary information.

[0476] An "information processing device" is a computer system used for collecting, processing, and analyzing data.

[0477] "Means of collecting information" refers to the function of obtaining necessary data from databases or other information sources.

[0478] "Preprocessing means" refers to a function that performs processing to convert collected data into a format suitable for analysis.

[0479] A "large-scale language model" is an advanced machine learning model designed for natural language processing, possessing the ability to analyze vast amounts of text data.

[0480] "Means of analysis" refers to the process of extracting specific information or patterns using pre-processed data.

[0481] "Means for extracting relationships and areas of expertise" refers to a function that identifies relationships between employees and their individual areas of expertise from the analysis results.

[0482] A "generative AI model" is a model that uses artificial intelligence to generate new information and content.

[0483] A "prompt statement" is an instruction given to a generative AI model to obtain specific information.

[0484] The invention is described in terms of its implementation. This system uses an information processing device to analyze employee information, communication history, and deliverables. Specifically, the server collects employee skill sets, past projects, areas of expertise, chat and email history, and created reports and presentations from a database. This data is preprocessed by the server and converted into a format suitable for large-scale language models.

[0485] The server inputs pre-processed data into a large-scale language model. Suitable models for this are commonly used natural language processing models such as GPT-4 and BERT. The model analyzes the input data and extracts relationships between employees and their individual areas of expertise.

[0486] The analysis results are stored in a database by the server and can be accessed later. Users can obtain specific information by entering prompts into the generated AI model. For example, by entering prompts such as "Please tell me about employee A's areas of expertise" or "Please tell me about employees who have shared project experience with employee B," the server extracts the relevant information from the stored analysis results and provides it to the user.

[0487] This system allows companies to efficiently understand their employees' skills and relationships, and quickly identify the right talent.

[0488] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0489] Step 1:

[0490] The server collects employee information, chat history, emails, and deliverables from the database. Inputs include employee skill sets, past projects, areas of expertise, communication history, and created reports and presentations. This data is centrally collected and prepared as foundational data for analysis.

[0491] Step 2:

[0492] The server preprocesses the collected data. The input is the raw data collected in step 1. Specifically, it performs text data cleaning, removal of unnecessary information, tokenization, and data normalization. The output is data in a format suitable for large-scale language models.

[0493] Step 3:

[0494] The terminal inputs pre-processed data into a large-scale language model. The input is the processed data obtained in step 2. Specifically, the data is passed to the model and the analysis is performed. The output is analysis results regarding the relationships between employees and their individual areas of expertise.

[0495] Step 4:

[0496] The server saves the analysis results to a database. The input is the analysis results obtained in step 3. Specifically, the server stores the results in the database in an appropriate format for later reference. The output is the saved analysis results.

[0497] Step 5:

[0498] The user obtains information by inputting prompts into the generating AI model. The input consists of prompts requesting specific information. Specifically, the server extracts relevant information from the database based on the prompts and presents it to the user. The output provides the information the user requested.

[0499] (Application Example 1)

[0500] Next, we will describe Application Example 1 of Form 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."

[0501] In modern industrial settings, efficient personnel allocation and team formation are key to improving productivity. However, manually determining the optimal placement, taking into account the skills and past experience of individual personnel, is difficult, time-consuming, and laborious. Furthermore, quickly finding the right personnel is not easy. This leads to challenges such as project delays and wasted resources.

[0502] 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.

[0503] In this invention, the server includes means for analyzing personnel information, communication history, and deliverables using a large-scale language model; means for comprehensively identifying relationships between personnel and their individual areas of expertise based on the analysis results; and means for proposing the optimal team composition based on the analysis results. This enables efficient personnel allocation and rapid team formation.

[0504] A "large-scale language model" is an artificial intelligence model used in natural language processing to learn from large amounts of text data and to understand and generate language.

[0505] "Personnel information" refers to information about individual personnel, such as their skill sets, past project experience, and areas of expertise.

[0506] "Communication history" refers to the record of communication, such as chats and emails, between employees.

[0507] "Deliverables" refer to concrete outputs such as reports and presentations created by employees.

[0508] "Analysis results" refer to the results of information analyzed by a large-scale language model, and include relationships between individuals and their areas of expertise.

[0509] "Team formation" refers to creating a group by combining the most suitable personnel for a specific purpose or project.

[0510] To implement this invention, it is necessary to build a system in which a server analyzes personnel information, communication history, and deliverables using a large-scale language model. The server analyzes this data using the Python programming language and OpenAI's GPT-4 API. Specifically, the server collects data including skill sets, past project experience, and areas of expertise as personnel information, and acquires chat and email records as communication history. As deliverables, it collects outputs such as reports and presentations.

[0511] The server inputs this data into a large-scale language model and extracts the relationships between individuals and their areas of expertise as analysis results. Furthermore, it proposes the optimal team composition based on the analysis results. This proposal aims to streamline personnel allocation within the factory and improve productivity.

[0512] As a concrete example, when setting up a new product line in a factory, the server uses this system to determine which personnel should be assigned to which positions. An example of a prompt to the generative AI model is as follows:

[0513] "Analyze employee data and propose the optimal team composition for launching a new product line. Employee data is as follows: {Employee Data JSON}"

[0514] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0515] Step 1:

[0516] The server collects personnel information, communication history, and deliverables from the database. Inputs include employee skill sets, past project experience, areas of expertise, chat and email records, and deliverables such as reports and presentations. This data is then integrated and prepared for analysis.

[0517] Step 2:

[0518] The server inputs the collected data into a large-scale language model. The input data is structured in JSON format and contains information about each employee. The server analyzes the data using a generative AI model to extract relationships between employees and their individual areas of expertise. The analysis results are output.

[0519] Step 3:

[0520] The server proposes the optimal team composition based on the analysis results. Specifically, it selects the most suitable personnel for the project, taking into account each employee's skills and areas of expertise based on the analysis results. A list of the proposed team compositions is generated as output.

[0521] Step 4:

[0522] The server notifies the user of the proposed team composition. The user receives the notification from the server and confirms the proposed team composition. This allows the user to make efficient personnel allocations. The output includes details of the team composition provided to the user.

[0523] (Example 2)

[0524] Next, we will describe Example 2 of Form 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".

[0525] Within organizations, there is a need to quickly and accurately identify components that are likely to hold the solution to a specific problem and to provide the appropriate information. However, traditional methods present challenges, such as the time-consuming nature of information gathering and analysis, making it difficult to identify the right components.

[0526] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0527] In this invention, the server includes means for collecting information on components using an information processing device, means for analyzing the collected information using a generative AI model, and means for identifying components that are likely to have a solution to a particular problem based on the analysis results. This makes it possible to quickly and accurately identify components that are likely to have a solution to a particular problem and to provide appropriate information.

[0528] An "information processing device" is a device used to collect, process, and analyze data, and includes devices such as computers and servers.

[0529] A "generative AI model" is a model that uses artificial intelligence technology to analyze data and derive solutions to specific problems.

[0530] "Components" refer to individual elements or members within an organization, including individuals or departments with specific skills or knowledge.

[0531] "Analysis results" refer to the results of the analysis obtained after data has been processed by a generative AI model.

[0532] "Identifying" refers to finding elements that meet specific conditions or criteria based on the analysis results.

[0533] "Providing information" refers to presenting users with detailed information about identified components.

[0534] This invention is a system that identifies components within an organization that are likely to possess solutions to specific problems and provides them with appropriate information. The server collects information about the components using an information processing device. Specifically, it retrieves data on the skills and expertise of the components from internal databases and project management tools.

[0535] Next, the server uses a generative AI model to analyze the collected information. This analysis involves data processing and computations that utilize natural language processing techniques to identify components that are familiar with specific technologies or problems. A general large-scale language model is used as the generative AI model.

[0536] Based on the analysis results, the server identifies components that are likely to hold the solution to a specific problem and sends that information to the terminal. The terminal displays information to the user such as the name, role, and area of ​​expertise of the identified component. This allows the user to directly ask questions to the appropriate component.

[0537] For example, if a user enters "I have a question about data analysis in Python," the server sends the following prompt to the AI ​​model: "I have a question about data analysis in Python. Please recommend components that are familiar with this problem." This prompt allows the server to identify appropriate components and provide information to the user.

[0538] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0539] Step 1:

[0540] The server uses an information processing device to collect information about its components. As input, it retrieves data on the components' skills and expertise from internal databases and project management tools. This data includes past project history, skill sets, and job titles. As output, the collected data is passed to a generating AI model.

[0541] Step 2:

[0542] The server analyzes the collected information using a generative AI model. The data collected in step 1 is used as input. The generative AI model utilizes natural language processing techniques to perform data processing and calculations to identify components that are proficient in specific technologies or problems. The output is the analysis result, listing components that are likely to have solutions to the specific problem.

[0543] Step 3:

[0544] The server sends information about the components identified based on the analysis results to the terminal. The analysis results obtained in step 2 are used as input. Specifically, the server organizes information such as the names, roles, and areas of expertise of the identified components and sends it to the terminal. As output, the terminal displays this information to the user.

[0545] Step 4:

[0546] The user can directly ask questions about identified components based on the information displayed on the device. The input is the information about the components displayed on the device. Specifically, the user contacts the components through the device and asks questions. As output, the user can obtain a solution to the problem.

[0547] (Application Example 2)

[0548] Next, we will describe application example 2 of form example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0549] In the operation of industrial machinery, a challenge exists in identifying employees with the expertise to quickly and appropriately resolve technical problems when they occur. To address this challenge, a system is needed that can analyze the nature of the problem, quickly identify the appropriate employees, and contact them.

[0550] 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.

[0551] In this invention, the server includes means for analyzing employee information, communication data, and deliverables using a large-scale language model; means for comprehensively covering relationships between employees and their individual areas of expertise based on the analysis results; means for providing information to resolve questions; means for analyzing problems with industrial machinery and identifying employees with appropriate expertise; and means for providing contact information for the identified employees. This makes it possible to respond quickly and appropriately to technical problems with industrial machinery.

[0552] A "large-scale language model" is an advanced machine learning model designed for natural language processing, which learns language patterns based on large amounts of text data.

[0553] "Employee information" refers to data about employees within a company, including information such as name, job title, area of ​​expertise, and contact information.

[0554] "Communication data" refers to digital communication information such as emails and chat messages exchanged between employees.

[0555] "Deliverables" refer to specific outputs such as documents, reports, and design drawings created by employees through their work.

[0556] "Analysis results" refer to information obtained after analyzing employee information, communication data, and deliverables using a large-scale language model, and include insights into employee relationships and areas of expertise.

[0557] "Specialized field" refers to the area of ​​technology or knowledge in which an employee is particularly proficient.

[0558] "Information provision means" refers to methods and devices for presenting information obtained based on analysis results to employees.

[0559] "Industrial machinery" refers to machinery and equipment used in manufacturing and production industries, specifically for processing and assembling products.

[0560] "Contact information" refers to information such as phone numbers and email addresses necessary to contact a specific employee.

[0561] The system for implementing this invention is designed to quickly resolve technical problems that arise in the operation of industrial machinery. The server analyzes employee information, communication data, and deliverables using a large-scale language model. Specifically, the server uses generative AI models such as OpenAI's GPT-3 to analyze this data and identify employee relationships and areas of expertise.

[0562] The server analyzes data acquired from sensors and cameras on industrial machinery to identify the nature of the problem. Based on the analysis results, it identifies employees with expertise in the relevant area and provides their contact information. This allows users to quickly contact the appropriate employees and take action to resolve the problem.

[0563] As a concrete example, if a machine malfunction occurs in a factory, the server analyzes the data related to the malfunction and inputs a prompt message into an AI model: "Identify an employee with expertise in this machine malfunction." The model then refers to a historical database and recommends the appropriate employee. In this way, the user can quickly obtain the information necessary to solve the problem.

[0564] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0565] Step 1:

[0566] The server receives data acquired from sensors and cameras on industrial machinery. This data includes information such as the machine's operating status and error codes. The server preprocesses this data and converts it into an analyzable format.

[0567] Step 2:

[0568] The server inputs pre-processed data into a generating AI model. Specifically, it uses models such as OpenAI's GPT-3 to analyze machine problems and identify the nature of those problems. This analysis outputs the cause of the problem and related technical information.

[0569] Step 3:

[0570] The server identifies employees with expertise in the problem based on the analysis results. It consults the employee information database to search for employees with expertise matching the analysis results. Information on the identified employees is then output.

[0571] Step 4:

[0572] The server provides the user with the contact information of the identified employee. The user can then use the provided contact information to quickly contact the employee and take action to resolve the issue.

[0573] Step 5:

[0574] Based on information provided by the server, users collaborate with employees to resolve problems. This enables quick and appropriate responses to technical issues with industrial machinery.

[0575] (Example 3)

[0576] Next, we will describe Embodiment 3 of Embodiment Example 3. 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".

[0577] In modern organizations, it is crucial to quickly identify individuals with specific skills and experience and assign them to appropriate projects and tasks. However, there is a lack of efficient means to comprehensively understand individuals' skills and experience and provide the necessary information. This leads to challenges such as project delays and delays in finding the right talent.

[0578] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 3 is realized by the following means.

[0579] In this invention, the server includes means for analyzing personal information using a large-scale language model, means for comprehensively covering relationships between individuals and their respective areas of expertise based on the analysis results, and means for providing information to identify individuals with specific skills and experience. This makes it possible to quickly identify individuals with specific skills and assign them to appropriate projects and tasks.

[0580] A "large-scale language model" is an advanced algorithm designed for natural language processing, which learns from large amounts of text data to understand and generate language.

[0581] "Personal information" refers to information about a specific individual, including skills, experience, and past project history.

[0582] "Analysis results" refer to data obtained after processing personal information using a large-scale language model, and include evaluations of individuals' skills and areas of expertise.

[0583] A "prompt statement" is an instruction that a user enters into the system, and it includes requests to obtain specific information.

[0584] "Information provision means" refers to methods for presenting necessary information to users based on analysis results, and is used to identify individuals with specific skills.

[0585] An "output device" is a device used to display analysis results to the user, and includes computer screens and mobile device displays.

[0586] To implement this invention, the user must first enter a prompt message into a terminal to search for an individual with specific skills and experience. The terminal then sends this prompt message to a server. Based on the received prompt message, the server retrieves personal information from its database. This information includes the individual's skills, experience, and past project history.

[0587] The server uses a generative AI model to analyze the acquired information. Specifically, it uses a large-scale language model for natural language processing to evaluate individuals' skill sets and identify individuals with the skills specified in the prompt. Once the analysis is complete, the server sends the analysis results to the terminal. The terminal then displays these results to the user.

[0588] For example, if a user enters the prompt "Find individuals with more than 5 years of experience in data science," the server extracts information on relevant individuals from the database and analyzes it using a generative AI model. As a result of the analysis, the names, departments, and contact information of individuals who meet the criteria are displayed on the device. This allows the user to quickly find the appropriate individuals.

[0589] This system leverages large-scale language models like OpenAI to efficiently analyze personal information, enabling the rapid identification of individuals with specific skills and their placement in appropriate projects and tasks. The flow of the identification process in Example 3 is explained using Figure 15.

[0590] Step 1:

[0591] The user enters a prompt into the terminal to search for individuals with specific skills or experience. The entered prompt becomes an instruction for the system to perform analysis. For example, the user might enter, "Please find individuals with more than 5 years of experience in data science."

[0592] Step 2:

[0593] The terminal sends the user's input prompt message to the server. The server receives this prompt message and prepares for analysis. The prompt message acts as a trigger for the server to retrieve the necessary information from the database.

[0594] Step 3:

[0595] The server retrieves personal information from the database based on the prompt. This information includes the individual's skills, experience, and past project history. The retrieved information becomes input data for analysis by the generative AI model.

[0596] Step 4:

[0597] The server inputs the acquired personal information into a generating AI model for analysis. Specifically, it uses a large-scale language model to evaluate individuals' skill sets and identify individuals who meet the conditions specified in the prompt. As a result of the analysis, a list of individuals who meet the conditions is generated.

[0598] Step 5:

[0599] The server sends the analysis results generated by the AI ​​model to the terminal. The analysis results include the names, departments, and contact information of individuals who meet the specified criteria.

[0600] Step 6:

[0601] The terminal displays the analysis results received from the server to the user. Based on this information, the user can quickly find individuals with specific skills and assign them to appropriate projects and tasks.

[0602] (Application Example 3)

[0603] Next, we will describe application example 3 of form example 3. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0604] In modern industrial settings, there is a need to quickly identify workers with specific skills and assign them to appropriate tasks. However, traditional methods present challenges in efficiently managing and immediately accessing worker skill information when needed. Furthermore, a lack of effective means for providing workers with proper work instructions can lead to decreased work efficiency.

[0605] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means.

[0606] In this invention, the server includes means for analyzing employee information, communication data, and deliverables using a large-scale language model; means for comprehensively identifying relationships between employees and their individual areas of expertise based on the analysis results; means for finding workers with specific skills and assigning them tasks; and means for approaching workers using mobile mechanical devices and instructing them to perform tasks. This makes it possible to quickly identify workers with specific skills and efficiently assign them appropriate tasks.

[0607] A "large-scale language model" is an artificial intelligence technology that learns from vast amounts of text data to understand and generate natural language.

[0608] "Employee information" refers to data about individual employees within an organization, including information such as skills, experience, and job title.

[0609] "Communication data" refers to the content of messages sent and received in digital format, such as emails and chats.

[0610] "Deliverables" refer to specific products, documents, or other outputs produced as a result of work or a project.

[0611] "Analysis results" refer to the insights and conclusions obtained after analyzing data.

[0612] "Relationships between employees" refers to the work-related connections and interactions between employees within an organization.

[0613] "Area of ​​expertise" refers to the area in which an individual employee possesses particularly outstanding skills or knowledge.

[0614] "Workers with specific skills" refers to employees who possess the specialized skills necessary to perform specific tasks or duties.

[0615] A "mobile machine" refers to a machine that can be physically moved and is designed to perform a specific task.

[0616] "Means of giving work instructions" refers to methods or devices used to communicate specific work content and procedures to workers.

[0617] A server plays a central role in implementing this invention. The server uses a large-scale language model to analyze employee information, communication data, and deliverables. Specifically, the server uses a programming language such as Python to retrieve employee information from a database and analyzes the data using natural language processing technology. Based on the analysis results, it is possible to comprehensively analyze the relationships between employees and their individual areas of expertise.

[0618] Furthermore, the server executes an algorithm to find workers with specific skills and assign them tasks. This algorithm uses an SQL database to search for skill information and select the most suitable worker. The selected worker receives work instructions using a mobile machine. This machine communicates with the server via Wi-Fi and provides specific instructions to the worker.

[0619] As a concrete example, consider a situation where a factory needs to find workers with specific machine operation skills to set up a new product line. In this case, the server inputs a prompt message to the AI ​​model saying, "Find workers with the machine operation skills required to set up the new product line," and recommends suitable workers. This improves the efficiency of work within the factory and makes it possible to quickly find workers with the appropriate skills.

[0620] The flow of the specific processing in Application Example 3 will be explained using Figure 16.

[0621] Step 1:

[0622] The server retrieves information on all employees from the employee database. Input includes employee IDs and skill information. Output provides data on employees' skill sets and experience. This data is extracted from the database using SQL queries.

[0623] Step 2:

[0624] The server inputs the acquired employee information into a large-scale language model and performs natural language processing. The input includes text data related to employees' skills and experience. The output provides analysis results regarding employee relationships and areas of expertise. This analysis is performed using a natural language processing algorithm implemented in Python.

[0625] Step 3:

[0626] The server searches for workers with specific skills based on the analysis results. The input includes information about the project's required skills. The output is a list of the most suitable workers. In this step, a generative AI model is used to generate prompts and recommend appropriate workers.

[0627] Step 4:

[0628] The server sends commands to a mobile machine to instruct a selected worker to perform a task. Inputs include the worker's ID and the task description. Output is that the machine approaches the worker and provides the work instructions. This communication takes place via Wi-Fi, and the machine operates according to the instructions.

[0629] Step 5:

[0630] The user receives feedback from the machine and monitors the progress of the work. Input includes feedback data from the machine. Output provides information on the work completion status and any problems encountered. Based on this information, the user can provide additional instructions as needed.

[0631] 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.

[0632] "Example of form 1"

[0633] One embodiment of the present invention combines a large-scale language model with an emotion engine. The large-scale language model analyzes employee information, chats, emails, and deliverables to comprehensively cover employee relationships and individual areas of expertise. Meanwhile, the emotion engine recognizes the user's emotions and uses the results to analyze the large-scale language model. For example, if a user is feeling frustrated, the emotion engine captures that information, and the large-scale language model uses that information to recommend an appropriate employee.

[0634] "Example of form 2"

[0635] In another embodiment of the present invention, the emotion engine recommends the most suitable employee based on the user's emotions. Specifically, if the user is feeling happy, the emotion engine captures that information, and the large-scale language model uses that information to recommend an employee who is likely to feel similar happiness. This facilitates smoother communication between the user and the employee.

[0636] "Example of form 3"

[0637] In a further embodiment of the present invention, the emotion engine analyzes the user's emotions and uses the results to analyze a large-scale language model. Specifically, if the user is feeling angry, the emotion engine captures that information, and the large-scale language model uses that information to recommend employees who are judged to have high problem-solving abilities. This helps the user solve their problems.

[0638] The following describes the processing flow for each example of the form.

[0639] "Example of form 1"

[0640] Step 1: A large-scale language model analyzes employee information, chat messages, emails, and deliverables.

[0641] Step 2: The emotion engine recognizes the user's emotions.

[0642] Step 3: The analysis results from the emotion engine are fed back into the large-scale language model.

[0643] Step 4: A large-scale language model recommends appropriate employees based on the analysis results of the emotion engine. (Example 2)

[0644] Step 1: The emotion engine recognizes the user's emotions.

[0645] Step 2: A large-scale language model analyzes employee information, chat messages, emails, and deliverables.

[0646] Step 3: A large-scale language model uses the results of the emotion engine's analysis to recommend employees who are likely to experience similar feelings of joy.

[0647] "Example of form 3"

[0648] Step 1: The emotion engine recognizes the user's emotions.

[0649] Step 2: A large-scale language model analyzes employee information, chat messages, emails, and deliverables.

[0650] Step 3: A large-scale language model recommends employees who are judged to have high problem-solving abilities based on the analysis results of the emotion engine.

[0651] (Example 1)

[0652] Next, we will describe Embodiment 1 of Embodiment 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".

[0653] In modern businesses, accurately understanding employees' skills and areas of expertise and making appropriate personnel placements is crucial. However, efficiently analyzing vast amounts of data such as employee information, communication history, and deliverables to clearly identify individual strengths and interpersonal relationships is difficult. Furthermore, there is a need for personnel recommendations and problem-solving information that takes employees' emotional states into account. An effective system is needed to address these challenges.

[0654] 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.

[0655] In this invention, the server includes means for analyzing personal information, communication history, and created materials using a natural language processing model; means for identifying interpersonal relationships and individual areas of expertise based on the analysis results; and means for an emotion analysis device to recognize the user's emotional state and utilize the results for the analysis of the natural language processing model. This enables accurate understanding of employees' skills and areas of expertise, and allows for appropriate personnel placement and the provision of information for problem solving.

[0656] An "information processing device" is a computer system used to collect, analyze, and process data.

[0657] A "natural language processing model" is an artificial intelligence technology used to understand and analyze human language.

[0658] "Personal information" refers to information about a specific individual, such as their skill set or project history.

[0659] "Communication history" refers to records of communication between individuals, such as emails and chats.

[0660] "Created works" refer to deliverables such as reports and presentations created by individuals.

[0661] "Relationships" refer to information that indicates interactions and connections between individuals.

[0662] "Specialized area" refers to the field or skill in which an individual excels.

[0663] An "emotion analysis device" is a device used to recognize and analyze the emotional state of a user.

[0664] "User" refers to an individual or organization that uses the system.

[0665] "Information provision" refers to the act of presenting useful information to users based on analysis results.

[0666] This invention is a system that uses an information processing device to analyze personal information, communication history, and created materials to identify relationships between individuals and their areas of expertise. Specifically, the server uses a natural language processing model, such as OpenAI's GPT-4, to analyze this data. The server collects employee skill sets, project history, email exchanges, and created reports and presentations from a company's database.

[0667] The server preprocesses the collected data and inputs it into a natural language processing model. Preprocessing includes tokenizing text data and filtering out irrelevant information. Based on the analysis, the server extracts relationships between employees and their individual areas of expertise.

[0668] Furthermore, the server uses an emotion analyzer to recognize the user's emotional state. For example, if a user inputs "the project isn't progressing," the emotion analyzer detects frustration and uses that information to analyze the natural language processing model.

[0669] The terminal displays the analysis results received from the server to the user. The user can review the recommended employees and suggestions on the screen and decide on their next action.

[0670] As a concrete example, if a user enters the prompt message, "Please recommend the best data analysis expert for Project Y," the server will recommend a suitable employee based on the analysis results. This system takes into account the employee's skills and feelings to support optimal personnel placement and improved communication.

[0671] The flow of the specific processing in Example 1 will be explained using Figure 17.

[0672] Step 1:

[0673] The server collects the data. The server accesses the company's database to retrieve employee skill sets, project history, email correspondence, and created reports and presentations. The input is the company's database, and the output is data formatted for analysis. Specifically, the server extracts information from the database via an API.

[0674] Step 2:

[0675] The server preprocesses the data. The server converts the collected data into a format suitable for the natural language processing model. The input is the data obtained in step 1, and the output is tokenized data with unnecessary information filtered out. Specifically, the server tokenizes the text data and removes noisy information.

[0676] Step 3:

[0677] The server analyzes the data using a natural language processing model. The server inputs the pre-processed data into the natural language processing model to extract relationships between employees and their individual areas of expertise. The input is the data pre-processed in step 2, and the output is the relationship and area of ​​expertise information as a result of the analysis. Specifically, the server inputs data into the model and obtains the analysis results.

[0678] Step 4:

[0679] The server performs sentiment analysis. Based on the user's input prompts and past communication history, the server uses a sentiment analysis device to recognize the user's emotional state. The input is the user's prompts and history data, and the output is information about the emotional state. Specifically, the server applies a sentiment analysis algorithm to identify the emotion.

[0680] Step 5:

[0681] The server integrates the analysis results and sends them to the terminal. The server integrates the information obtained from the natural language processing model and sentiment analysis to generate information useful to the user. The input is the output of steps 3 and 4, and the output is the integrated analysis result. Specifically, the server integrates the data and prepares it for transmission to the terminal.

[0682] Step 6:

[0683] The terminal displays the results. The terminal displays the analysis results received from the server to the user. The input is the analysis results sent from the server, and the output is the information that the user can see on the screen. Specifically, the terminal visually displays the results, allowing the user to decide on the next action.

[0684] (Application Example 1)

[0685] Next, we will describe Application Example 1 of Form 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."

[0686] In modern industrial settings, efficient task assignment that takes into account workers' skills and emotional states is essential. However, conventional systems struggle to consider workers' emotional states, resulting in decreased work efficiency and increased worker stress. To address these challenges, a system is needed that analyzes workers' skills and emotional states in real time and assigns them the most suitable tasks.

[0687] 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.

[0688] In this invention, the server includes means for analyzing personnel information, communication history, and deliverables using a large-scale language model; means for comprehensively identifying relationships between personnel and their individual areas of expertise based on the analysis results; and means for analyzing individual emotional states using an emotion recognition engine. This enables efficient task assignment that takes into account the skills and emotional states of the workers.

[0689] A "large-scale language model" is an artificial intelligence technology that learns from vast amounts of text data to understand and generate natural language.

[0690] "Personnel information" refers to information such as the skill set, past work history, and area of ​​expertise of individual workers.

[0691] "Communication history" refers to records of communication between workers, such as chats and emails.

[0692] "Deliverables" refer to specific work results such as reports and presentations created by workers.

[0693] An "emotion recognition engine" is a technology that analyzes the emotional state of workers and acquires that information in real time.

[0694] "Task assignment" is the process of selecting the most suitable tasks for workers and distributing them in order to carry out the work efficiently.

[0695] The system for implementing this invention consists of a server equipped with a large-scale language model and an emotion recognition engine. The server first collects personnel information, communication history, and deliverables, and then analyzes this data using the large-scale language model. As a result of the analysis, the relationships between workers and their individual areas of expertise become clear.

[0696] Next, the server uses an emotion recognition engine to analyze the worker's current emotional state in real time. This emotional information is important for understanding the worker's stress level and motivation.

[0697] Based on analysis results and emotional information, the server assigns the most suitable task to each worker. This is expected to improve work efficiency and reduce worker stress. For example, if worker A is feeling frustrated, the server can reduce worker A's stress by assigning them a less demanding task.

[0698] An example of a prompt to input into the generating AI model is: "Analyze employee information, chat logs, and deliverables, and assign the most suitable task to each employee, taking into account their areas of expertise and current emotional state."

[0699] In this way, the server enables efficient task assignment that takes into account the skills and emotional state of the workers.

[0700] The flow of a specific process in Application Example 1 will be explained using Figure 18.

[0701] Step 1:

[0702] The server collects personnel information, communication history, and deliverables from a database. This data includes each worker's skill set, past work history, area of ​​expertise, chat and email records, and reports and presentations they have created. Input data is passed to the server in text format.

[0703] Step 2:

[0704] The server analyzes the collected data using a large-scale language model. Specifically, it receives text data as input and uses natural language processing techniques to extract relationships between workers and their individual areas of expertise. As output, it generates skill maps and relationship maps of the workers.

[0705] Step 3:

[0706] The server uses an emotion recognition engine to analyze the current emotional state of the workers. It receives facial images and voice data of the workers as input and applies an emotion recognition algorithm to identify the workers' emotional state (e.g., stress, motivation). Emotional state data for each worker is generated as output.

[0707] Step 4:

[0708] The server integrates analysis results and emotional information to assign the most suitable tasks to each worker. Specifically, it receives skill maps and emotional state data as input and applies a task assignment algorithm to select tasks appropriate for each worker. The output is a list of task assignments for each worker.

[0709] Step 5:

[0710] The server uses a generative AI model to notify workers of the task assignment results. It generates a prompt message and sends a notification to the worker's terminal. A specific example of a prompt message is: "Analyze employee information, chat logs, and deliverables, and assign the most suitable task considering each employee's strengths and current emotional state." The output is a notification displayed on the worker's terminal.

[0711] (Example 2)

[0712] Next, we will describe Example 2 of Form 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".

[0713] There is a challenge in quickly and accurately identifying other employees with the appropriate knowledge and experience to address problems and questions faced by employees. Furthermore, there is a need for emotionally-based recommendations of the most suitable employees to facilitate smooth communication among employees.

[0714] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0715] In this invention, the server includes means for analyzing employee information, communication data, and deliverables using a large-scale language model; means for comprehensively covering relationships between employees and their individual areas of expertise based on the analysis results; and means for analyzing the user's emotions using an emotion analysis engine and recommending the most suitable employee. This enables the rapid identification of other employees with the appropriate knowledge to address problems faced by employees, and facilitates smooth, emotion-based communication.

[0716] A "large-scale language model" is an artificial intelligence model designed for natural language processing, trained on a vast dataset.

[0717] "Employee information" refers to data about employees, such as their skill sets, work history, and areas of expertise.

[0718] "Communication data" refers to information such as emails and chat messages exchanged between employees.

[0719] "Deliverables" refer to documents, reports, and project outputs created by employees through their work.

[0720] "Analysis results" refers to the results of analyzing data obtained using large-scale language models and sentiment analysis engines.

[0721] An "emotion analysis engine" is a technology that analyzes a user's emotions and suggests appropriate actions based on those emotions.

[0722] "Users" refers to employees or individuals who use the system to obtain information.

[0723] "Specialized field" refers to the area of ​​technology or knowledge in which an employee is particularly proficient.

[0724] "Recommendation" refers to the act of presenting the most suitable employees or information based on analysis results.

[0725] This invention is a system that enables employees to quickly identify other employees with the appropriate knowledge to address problems they face, and facilitates smooth, emotion-based communication. Specific embodiments of this system are described below.

[0726] The server receives input data from the user and performs analysis using a generative AI model. This analysis utilizes natural language processing techniques, specifically large-scale language models such as OpenAI's GPT. The server searches the company's internal database to understand the user's questions and problems and identify employees with relevant knowledge. This database contains employees' skill sets and work histories.

[0727] Furthermore, the server uses an emotion analysis engine to analyze the user's emotions. For example, if a user feels joy when entering a question, the server uses that information to recommend employees who are likely to have similar emotions. This process facilitates smoother communication between users and employees.

[0728] As a concrete example, consider a case where a user asks, "I want to learn more about this new technology." The server analyzes this question and recommends an employee who is deemed to be proficient in the relevant technology. Furthermore, if the user expresses joy when asking the question, the emotion engine uses that information to recommend an employee who shares the same passion for technology.

[0729] An example of a prompt to input into the generating AI model might be, "Recommend the best employee for an employee who has a technical question." Using this prompt, the server will identify the appropriate employee and provide the information to the user.

[0730] The flow of the specific processing in Example 2 will be explained using Figure 19.

[0731] Step 1:

[0732] The user enters questions or problems through the terminal. For example, they might enter something like, "I want to learn more about this new technology." The terminal then sends this input data to the server. The input data is text information that includes the user's questions and feelings.

[0733] Step 2:

[0734] The server analyzes the received input data. This analysis uses a generative AI model. Specifically, it uses a large-scale language model such as OpenAI's GPT to understand the user's question. The server analyzes the input data using natural language processing techniques to identify the user's intent. The output is the analyzed user intent and related keywords.

[0735] Step 3:

[0736] The server searches the company's internal database based on the analysis results. This database contains employee skill sets and work histories. The server queries the database to identify employees with knowledge relevant to the user's question. The input is the analyzed keywords, and the output is a list of relevant employees.

[0737] Step 4:

[0738] The server uses an emotion analysis engine to analyze the user's emotions. It identifies the emotions the user is feeling when entering a question and recommends employees who are likely to have similar emotions. The input is data about the user's emotions, and the output is a list of the most suitable employees based on those emotions.

[0739] Step 5:

[0740] The server provides the user with information about the identified employee. The terminal displays this information to the user. For example, the information might be presented as, "An employee with technical expertise can answer your questions." The input is a list of the most suitable employees, and the output is the information provided to the user.

[0741] (Application Example 2)

[0742] Next, we will describe application example 2 of form example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0743] It is essential to identify engineers who can respond quickly and appropriately to technical problems that arise within the factory, and to resolve these problems efficiently. Furthermore, facilitating smooth communication among employees is also crucial to improving the speed of problem-solving.

[0744] 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.

[0745] In this invention, the server includes means for analyzing employee information, communication data, and deliverables using a large-scale language model; means for comprehensively covering relationships between employees and their individual areas of expertise based on the analysis results; means for providing information to resolve questions; means for automated machinery in the factory to detect anomalies and transmit the information to the cloud; means for a generated AI model on the cloud to perform analysis and identify appropriate technicians; and means for sending notifications to the identified technicians. This enables rapid response to technical problems within the factory and smooth communication among employees.

[0746] A "large-scale language model" is an advanced machine learning model designed for natural language processing, which understands and generates language based on large amounts of text data.

[0747] "Employee information" refers to data about employees within a company, including individual skills, experience, job title, and job responsibilities.

[0748] "Communication data" refers to records of digital communications such as emails and chat messages exchanged between employees.

[0749] "Deliverables" refer to specific outputs such as documents, reports, and design drawings created by employees through their work.

[0750] "Analysis results" refer to information obtained after analyzing employee information, communication data, and deliverables using a large-scale language model, and include insights into employee relationships and areas of expertise.

[0751] "Automated machinery" refers to mechanical devices used in factories that operate automatically using sensors and control systems.

[0752] "Cloud" refers to a service of computer resources and data storage provided via the internet, and is a platform for storing and processing data.

[0753] A "generative AI model" is a model that uses artificial intelligence technology to analyze data and generate new information and insights.

[0754] A "technician" is a person who possesses specialized knowledge and skills in a particular technical field and is responsible for tasks such as problem-solving and machine maintenance.

[0755] A "notification" is a message or alert sent via email or smart device to inform a recipient of specific information.

[0756] The system for implementing this invention is designed to quickly resolve technical problems within a factory. The server uses a large-scale language model to analyze employee information, communication data, and deliverables. This allows for comprehensive analysis of employee relationships and individual areas of expertise.

[0757] Automated machinery within the factory uses sensors to detect anomalies and transmits this information to the cloud. On the cloud, a generative AI model analyzes the data and identifies the appropriate technician. This identified technician receives a notification via their device, such as a smartphone or smart glasses.

[0758] For example, if an automated machine in a factory detects abnormal vibrations, that data is sent to the cloud. A generative AI model on the cloud identifies a technician with expertise in vibrations and sends a notification to his smartphone saying, "Abnormal vibrations have been detected in machine X. Please take action."

[0759] An example of a prompt message is, "Abnormal vibration has been detected in the machine. Please identify a technician with expertise in vibration." This prompt message allows the generating AI model to quickly identify the appropriate technician.

[0760] This system enables rapid response to technical issues within the factory and facilitates smooth communication among employees.

[0761] The flow of a specific process in Application Example 2 will be explained using Figure 20.

[0762] Step 1:

[0763] The server receives sensor data transmitted from automated machinery within the factory. This data includes information on the machine's operating status and signs of malfunctions. The server analyzes the received data to determine whether an anomaly has been detected.

[0764] Step 2:

[0765] If an anomaly is detected, the server sends the information to the cloud. In the cloud, a generative AI model receives this data as input and analyzes the type of anomaly and its scope of impact. Based on the analysis results, it identifies which technical fields of expertise are needed.

[0766] Step 3:

[0767] The cloud-based AI model identifies the appropriate engineers based on the analysis results. This process involves referencing an employee database to select engineers with the necessary expertise. Information on the selected engineers is then output.

[0768] Step 4:

[0769] The server generates a notification for the identified technician. This notification includes detailed information about the anomaly and the need for action. The notification is sent to the technician's device (smartphone or smart glasses).

[0770] Step 5:

[0771] Technicians receive notifications on their terminals and begin responding to an anomaly. Based on the notification, technicians head to the site and work to resolve the problem. This enables rapid problem resolution.

[0772] (Example 3)

[0773] Next, we will describe Embodiment 3 of Embodiment Example 3. 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".

[0774] In today's workplace environment, it is difficult to quickly identify individuals with specific skills and experience. Furthermore, recommending the right person while considering the user's feelings is also challenging. This can lead to delays in project progress and stalls in problem-solving.

[0775] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 3 is realized by the following means.

[0776] In this invention, the server includes means for analyzing job information using a generative AI model, means for recommending personnel with specific skills based on the analysis results, and means for analyzing the user's emotions using an emotion analysis engine and recommending personnel judged to have high problem-solving abilities based on the results. This makes it possible to quickly find personnel with specific skills and recommend appropriate personnel that take into account the user's emotions.

[0777] A "generative AI model" is a model that uses artificial intelligence technology to perform natural language processing and analyze or generate data for specific tasks.

[0778] "Job information" refers to data about employees and personnel, such as skills, experience, resumes, and project history.

[0779] "Analysis results" refers to the results of analyzing data obtained by generative AI models and emotion analysis engines.

[0780] "Specific skills" refer to the specialized knowledge and techniques required for a particular task or project.

[0781] An "emotion analysis engine" refers to software or a system that analyzes a user's emotions and identifies their emotional state.

[0782] A "prompt sentence" is an instruction sentence input to a generative AI model, and refers to a sentence that includes a question or request to obtain specific information.

[0783] "Problem-solving ability" refers to the ability to effectively address specific challenges or problems and find solutions.

[0784] A description of embodiments for carrying out this invention will be given.

[0785] The server first analyzes job information using a generative AI model. This analysis utilizes natural language processing technology and targets data such as skills, experience, resumes, and project history related to employees and personnel. Specifically, a database management system (DBMS) is used to collect and analyze this data.

[0786] Next, the server recommends individuals with specific skills based on the analysis results. The generative AI model searches the database for individuals with the relevant skills based on the prompt text and creates a recommendation list. For example, if a user enters the prompt text "Please recommend employees who are strong in data analysis," the server will respond to this request by listing suitable individuals.

[0787] Furthermore, the device uses an emotion analysis engine to analyze the user's emotions. If the user is feeling anger or stress, it sends that information to the server. Based on this emotional information, the server recommends individuals who are judged to have high problem-solving abilities. This makes it possible to select the most suitable personnel while taking the user's emotions into consideration.

[0788] As a concrete example, suppose a project is behind schedule and the user enters a prompt message saying, "Please recommend an employee with strong problem-solving skills to help the project progress." In this case, the server considers the results of the sentiment analysis engine and recommends an appropriate person, thereby facilitating the smooth progress of the project. The specific processing flow in Example 3 will be explained using Figure 21.

[0789] Step 1:

[0790] The server uses a database management system (DBMS) to collect job information related to employees and personnel, such as skills, experience, resumes, and project history. The input consists of various job information within the database. The server retrieves this data and builds a basic dataset for analysis. The output is a dataset of job information necessary for analysis.

[0791] Step 2:

[0792] The server uses a generative AI model to analyze the collected job information. The input is the dataset of job information obtained in Step 1. The server utilizes natural language processing technology to analyze the data in order to identify individuals with specific skills and experience. The output is the analysis results regarding each employee's skills and experience.

[0793] Step 3:

[0794] The user enters a prompt to search for personnel with specific skills. The input is a prompt message entered by the user. For example, the user might enter a prompt message such as, "Please recommend an employee with strong data analysis skills." The output is that the server receives this prompt message and uses it as an instruction for analysis.

[0795] Step 4:

[0796] The server searches for suitable personnel from the analysis results based on the prompt message and creates a recommendation list. The input consists of the analysis results obtained in step 2 and the prompt message entered in step 3. The server compares these and lists the most suitable personnel. The output is a list of recommended personnel.

[0797] Step 5:

[0798] The device analyzes the user's emotions using an emotion analysis engine. The input is data related to the user's emotions. The device analyzes this data to identify the user's emotional state. The output is the analysis result regarding the user's emotional state.

[0799] Step 6:

[0800] The server recommends individuals deemed to have high problem-solving abilities based on the results of the emotion analysis engine. The inputs are the emotion analysis results obtained in step 5 and the recommendation list obtained in step 4. The server considers these factors to select the most suitable individuals. The output is a final list of recommended individuals, taking emotions into account.

[0801] (Application Example 3)

[0802] Next, we will describe application example 3 of form example 3. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0803] In modern industrial settings, there is a need to quickly identify personnel with specific skills and provide appropriate problem-solving. However, traditional methods are time-consuming in finding the necessary personnel and have difficulty addressing issues that take emotional factors into consideration.

[0804] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means.

[0805] In this invention, the server includes means for analyzing personnel information, communication data, and deliverables using a large-scale language model; means for comprehensively covering the relationships between personnel and their individual areas of expertise based on the analysis results; and means for analyzing the user's emotions using an emotion analysis engine and utilizing the results in the large-scale language model. This enables the rapid identification of personnel with specific skills and appropriate problem-solving that takes emotional factors into consideration.

[0806] A "large-scale language model" is an artificial intelligence technology that has the ability to understand and generate natural language based on vast amounts of data.

[0807] "Personnel information" refers to data on individual personnel, such as their skills, experience, and performance.

[0808] "Communication data" refers to information generated through digital communication such as email and chat.

[0809] "Deliverables" refer to specific products or documents produced as a result of a project or task.

[0810] An "emotion analysis engine" is a technology that analyzes a user's emotions and identifies their emotional state.

[0811] A "specialized field" refers to an area that focuses on specific knowledge or skills.

[0812] "Problem-solving ability" refers to the ability to find effective solutions to challenges and problems.

[0813] "Recommendation" is the act of presenting the best option based on specific conditions.

[0814] The system for implementing this invention operates in a network environment including a server and terminals. The server runs a program that analyzes personnel information, communication data, and deliverables using a large-scale language model. This analysis uses the Hugging Face Transformers library and performs natural language processing. Based on the analysis results, the server comprehensively covers the relationships between personnel and their individual areas of expertise and stores them in a database.

[0815] Furthermore, the server uses an emotion analysis engine to analyze users' emotions and utilizes the results in a large-scale language model. The emotion analysis uses software capable of real-time data processing. This allows for the rapid identification of individuals with specific skills and the recommendation of those deemed to have high problem-solving abilities.

[0816] The terminal sends a query to the server when the user is looking for someone with specific skills. The server searches its database based on the received query and lists the relevant personnel. When the user is troubleshooting a machine, the terminal performs sentiment analysis and recommends the most suitable technician.

[0817] As a concrete example, when a machine malfunctions, the terminal prompts the AI ​​model with the message, "We are looking for a technician who can troubleshoot machine A." The model then consults a skills database and lists suitable technicians. It also analyzes the emotions of the surrounding workers and prioritizes recommending technicians who are deemed calm and possess strong problem-solving abilities.

[0818] Example of a prompt:

[0819] "We are looking for a technician who can troubleshoot machine A. Please perform an emotional analysis and recommend the most suitable technician."

[0820] The flow of the specific processing in Application Example 3 will be explained using Figure 22.

[0821] Step 1:

[0822] The user uses a terminal to enter a prompt message to search for personnel with specific skills. The entered prompt message is sent from the terminal to the server.

[0823] Step 2:

[0824] The server parses the received prompt message and queries the skills database. The database contains information about the skills and experience of the personnel. The server generates a list of the relevant personnel as a result of the query.

[0825] Step 3:

[0826] The server uses an emotion analysis engine to analyze the user's emotions. It uses the user's voice and text data as input to identify their emotional state. The analysis results are fed back into a large-scale language model.

[0827] Step 4:

[0828] Based on the results of the sentiment analysis, the server prioritizes selecting individuals from a list who are judged to have high problem-solving abilities. The information of the selected individuals is sent to the terminal.

[0829] Step 5:

[0830] The terminal displays personnel information received from the server to the user. Based on the displayed information, the user can select the appropriate personnel and contact them.

[0831] Step 6:

[0832] Users can contact the personnel they have selected from their device. Email and chat are used as communication methods. This allows users to quickly begin taking action to resolve their problems.

[0833] (Other examples)

[0834] Since this is the same as the specific processing described in the other embodiments of the first embodiment above, the explanation will be omitted.

[0835] 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.

[0836] The data generation model 58 is a form of so-called generative AI (Artificial Intelligence). One example of the data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> 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.

[0837] Other examples of generative AI include Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) are examples.

[0838] 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.

[0839] [Third Embodiment]

[0840] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0841] 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.

[0842] 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).

[0843] 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.

[0844] 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.

[0845] 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).

[0846] 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.

[0847] 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.

[0848] 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.

[0849] 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.

[0850] 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.

[0851] Next, the identification process performed by the identification processing unit 290 of the data processing device 12 will be described.

[0852] "Example of form 1"

[0853] This embodiment of the present invention uses a large-scale language model to analyze employee information, chats, emails, and deliverables. Specifically, employee information, including information such as employees' skill sets, past projects, and areas of expertise, as well as chats and emails recording communication between employees, and deliverables such as reports and presentations created by employees, are input into the large-scale language model. The large-scale language model analyzes this information to extract relationships between employees and their individual areas of expertise.

[0854] "Example of form 2"

[0855] Next, based on the analysis results, we address the question, "Who should I ask?" Specifically, we identify employees who are likely to have solutions to a particular problem and provide information about those employees. For example, if an employee has a question about a particular technology, we recommend an employee who has been analyzed as being proficient in that technology.

[0856] "Example of form 3"

[0857] Furthermore, based on the analysis results, it addresses the question, "Is there anyone like this?" Specifically, it provides information to help find employees with specific skills and experience. For example, if a project team is looking for an employee with a particular skill, it will recommend employees who have been analyzed as possessing that skill.

[0858] The following describes the processing flow for each example of the form.

[0859] "Example of form 1"

[0860] Step 1: Analyze employee information using a large-scale language model. Employee information includes employee skill sets, past projects, and areas of expertise.

[0861] Step 2: Similarly, analyze chats and emails that record communication between employees.

[0862] Step 3: Next, analyze deliverables such as reports and presentations created by employees.

[0863] Step 4: Integrate these analysis results and extract the relationships between employees and their individual areas of expertise. (Example 2)

[0864] Step 1: Based on the analysis results, resolve the question, "Who should I ask?"

[0865] Step 2: Identify employees who are most likely to have solutions to the specific problem.

[0866] Step 3: Provide information about the employee. For example, if an employee has a question about a particular technology, recommend an employee who has been analyzed as being proficient in that technology.

[0867] "Example of form 3"

[0868] Step 1: Based on the analysis results, answer the question, "Are there any people like this?" Step 2: Provide information to find employees with specific skills and experience.

[0869] Step 3: For example, if a project team is looking for an employee with a specific skill, recommend an employee who has been analyzed to possess that skill.

[0870] (Example 1)

[0871] Next, we will describe Embodiment 1 of 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."

[0872] In modern businesses, accurately understanding employees' skills and areas of expertise and quickly identifying the right people is crucial. However, the sheer volume of employee information, communication history, and deliverables makes it difficult to efficiently analyze this data and extract the necessary information. Furthermore, finding employees with specific areas of expertise or identifying the appropriate contact person is not easy.

[0873] 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.

[0874] In this invention, the server includes means for collecting information, means for preprocessing the information, and means for analyzing the information using a large-scale language model. This makes it possible to efficiently extract employee relationships and areas of expertise and to quickly provide the necessary information.

[0875] An "information processing device" is a computer system used for collecting, processing, and analyzing data.

[0876] "Means of collecting information" refers to the function of obtaining necessary data from databases or other information sources.

[0877] "Preprocessing means" refers to a function that performs processing to convert collected data into a format suitable for analysis.

[0878] A "large-scale language model" is an advanced machine learning model designed for natural language processing, possessing the ability to analyze vast amounts of text data.

[0879] "Means of analysis" refers to the process of extracting specific information or patterns using pre-processed data.

[0880] "Means for extracting relationships and areas of expertise" refers to a function that identifies relationships between employees and their individual areas of expertise from the analysis results.

[0881] A "generative AI model" is a model that uses artificial intelligence to generate new information and content.

[0882] A "prompt statement" is an instruction given to a generative AI model to obtain specific information.

[0883] The invention is described in terms of its implementation. This system uses an information processing device to analyze employee information, communication history, and deliverables. Specifically, the server collects employee skill sets, past projects, areas of expertise, chat and email history, and created reports and presentations from a database. This data is preprocessed by the server and converted into a format suitable for large-scale language models.

[0884] The server inputs pre-processed data into a large-scale language model. Suitable models for this are commonly used natural language processing models such as GPT-4 and BERT. The model analyzes the input data and extracts relationships between employees and their individual areas of expertise.

[0885] The analysis results are stored in a database by the server and can be accessed later. Users can obtain specific information by entering prompts into the generated AI model. For example, by entering prompts such as "Please tell me about employee A's areas of expertise" or "Please tell me about employees who have shared project experience with employee B," the server extracts the relevant information from the stored analysis results and provides it to the user.

[0886] This system allows companies to efficiently understand their employees' skills and relationships, and quickly identify the right talent.

[0887] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0888] Step 1:

[0889] The server collects employee information, chat history, emails, and deliverables from the database. Inputs include employee skill sets, past projects, areas of expertise, communication history, and created reports and presentations. This data is centrally collected and prepared as foundational data for analysis.

[0890] Step 2:

[0891] The server preprocesses the collected data. The input is the raw data collected in step 1. Specifically, it performs text data cleaning, removal of unnecessary information, tokenization, and data normalization. The output is data in a format suitable for large-scale language models.

[0892] Step 3:

[0893] The terminal inputs pre-processed data into a large-scale language model. The input is the processed data obtained in step 2. Specifically, the data is passed to the model and the analysis is performed. The output is analysis results regarding the relationships between employees and their individual areas of expertise.

[0894] Step 4:

[0895] The server saves the analysis results to a database. The input is the analysis results obtained in step 3. Specifically, the server stores the results in the database in an appropriate format for later reference. The output is the saved analysis results.

[0896] Step 5:

[0897] The user obtains information by inputting prompts into the generating AI model. The input consists of prompts requesting specific information. Specifically, the server extracts relevant information from the database based on the prompts and presents it to the user. The output provides the information the user requested.

[0898] (Application Example 1)

[0899] Next, we will describe Application Example 1 of Form 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."

[0900] In modern industrial settings, efficient personnel allocation and team formation are key to improving productivity. However, manually determining the optimal placement, taking into account the skills and past experience of individual personnel, is difficult, time-consuming, and laborious. Furthermore, quickly finding the right personnel is not easy. This leads to challenges such as project delays and wasted resources.

[0901] 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.

[0902] In this invention, the server includes means for analyzing personnel information, communication history, and deliverables using a large-scale language model; means for comprehensively identifying relationships between personnel and their individual areas of expertise based on the analysis results; and means for proposing the optimal team composition based on the analysis results. This enables efficient personnel allocation and rapid team formation.

[0903] A "large-scale language model" is an artificial intelligence model used in natural language processing to learn from large amounts of text data and to understand and generate language.

[0904] "Personnel information" refers to information about individual personnel, such as their skill sets, past project experience, and areas of expertise.

[0905] "Communication history" refers to the record of communication, such as chats and emails, between employees.

[0906] "Deliverables" refer to concrete outputs such as reports and presentations created by employees.

[0907] "Analysis results" refer to the results of information analyzed by a large-scale language model, and include relationships between individuals and their areas of expertise.

[0908] "Team formation" refers to creating a group by combining the most suitable personnel for a specific purpose or project.

[0909] To implement this invention, it is necessary to build a system in which a server analyzes personnel information, communication history, and deliverables using a large-scale language model. The server analyzes this data using the Python programming language and OpenAI's GPT-4 API. Specifically, the server collects data including skill sets, past project experience, and areas of expertise as personnel information, and acquires chat and email records as communication history. As deliverables, it collects outputs such as reports and presentations.

[0910] The server inputs this data into a large-scale language model and extracts the relationships between individuals and their areas of expertise as analysis results. Furthermore, it proposes the optimal team composition based on the analysis results. This proposal aims to streamline personnel allocation within the factory and improve productivity.

[0911] As a concrete example, when setting up a new product line in a factory, the server uses this system to determine which personnel should be assigned to which positions. An example of a prompt to the generative AI model is as follows:

[0912] "Analyze employee data and propose the optimal team composition for launching a new product line. Employee data is as follows: {Employee Data JSON}"

[0913] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0914] Step 1:

[0915] The server collects personnel information, communication history, and deliverables from the database. Inputs include employee skill sets, past project experience, areas of expertise, chat and email records, and deliverables such as reports and presentations. This data is then integrated and prepared for analysis.

[0916] Step 2:

[0917] The server inputs the collected data into a large-scale language model. The input data is structured in JSON format and contains information about each employee. The server analyzes the data using a generative AI model to extract relationships between employees and their individual areas of expertise. The analysis results are output.

[0918] Step 3:

[0919] The server proposes the optimal team composition based on the analysis results. Specifically, it selects the most suitable personnel for the project, taking into account each employee's skills and areas of expertise based on the analysis results. A list of the proposed team compositions is generated as output.

[0920] Step 4:

[0921] The server notifies the user of the proposed team composition. The user receives the notification from the server and confirms the proposed team composition. This allows the user to make efficient personnel allocations. The output includes details of the team composition provided to the user.

[0922] (Example 2)

[0923] Next, we will describe Example 2 of the morphological example. 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."

[0924] Within organizations, there is a need to quickly and accurately identify components that are likely to hold the solution to a specific problem and to provide the appropriate information. However, traditional methods present challenges, such as the time-consuming nature of information gathering and analysis, making it difficult to identify the right components.

[0925] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0926] In this invention, the server includes means for collecting information on components using an information processing device, means for analyzing the collected information using a generative AI model, and means for identifying components that are likely to have a solution to a particular problem based on the analysis results. This makes it possible to quickly and accurately identify components that are likely to have a solution to a particular problem and to provide appropriate information.

[0927] An "information processing device" is a device used to collect, process, and analyze data, and includes devices such as computers and servers.

[0928] A "generative AI model" is a model that uses artificial intelligence technology to analyze data and derive solutions to specific problems.

[0929] "Components" refer to individual elements or members within an organization, including individuals or departments with specific skills or knowledge.

[0930] "Analysis results" refer to the results of the analysis obtained after data has been processed by a generative AI model.

[0931] "Identifying" refers to finding elements that meet specific conditions or criteria based on the analysis results.

[0932] "Providing information" refers to presenting users with detailed information about identified components.

[0933] This invention is a system that identifies components within an organization that are likely to possess solutions to specific problems and provides them with appropriate information. The server collects information about the components using an information processing device. Specifically, it retrieves data on the skills and expertise of the components from internal databases and project management tools.

[0934] Next, the server uses a generative AI model to analyze the collected information. This analysis involves data processing and computations that utilize natural language processing techniques to identify components that are familiar with specific technologies or problems. A general large-scale language model is used as the generative AI model.

[0935] Based on the analysis results, the server identifies components that are likely to hold the solution to a specific problem and sends that information to the terminal. The terminal displays information to the user such as the name, role, and area of ​​expertise of the identified component. This allows the user to directly ask questions to the appropriate component.

[0936] For example, if a user enters "I have a question about data analysis in Python," the server sends the following prompt to the AI ​​model: "I have a question about data analysis in Python. Please recommend components that are familiar with this problem." This prompt allows the server to identify appropriate components and provide information to the user.

[0937] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0938] Step 1:

[0939] The server uses an information processing device to collect information about its components. As input, it retrieves data on the components' skills and expertise from internal databases and project management tools. This data includes past project history, skill sets, and job titles. As output, the collected data is passed to a generating AI model.

[0940] Step 2:

[0941] The server analyzes the collected information using a generative AI model. The data collected in step 1 is used as input. The generative AI model utilizes natural language processing techniques to perform data processing and calculations to identify components that are proficient in specific technologies or problems. The output is the analysis result, listing components that are likely to have solutions to the specific problem.

[0942] Step 3:

[0943] The server sends information about the components identified based on the analysis results to the terminal. The analysis results obtained in step 2 are used as input. Specifically, the server organizes information such as the names, roles, and areas of expertise of the identified components and sends it to the terminal. As output, the terminal displays this information to the user.

[0944] Step 4:

[0945] The user can directly ask questions about identified components based on the information displayed on the device. The input is the information about the components displayed on the device. Specifically, the user contacts the components through the device and asks questions. As output, the user can obtain a solution to the problem.

[0946] (Application Example 2)

[0947] Next, we will describe application example 2 of form 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."

[0948] In the operation of industrial machinery, a challenge exists in identifying employees with the expertise to quickly and appropriately resolve technical problems when they occur. To address this challenge, a system is needed that can analyze the nature of the problem, quickly identify the appropriate employees, and contact them.

[0949] 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.

[0950] In this invention, the server includes means for analyzing employee information, communication data, and deliverables using a large-scale language model; means for comprehensively covering relationships between employees and their individual areas of expertise based on the analysis results; means for providing information to resolve questions; means for analyzing problems with industrial machinery and identifying employees with appropriate expertise; and means for providing contact information for the identified employees. This makes it possible to respond quickly and appropriately to technical problems with industrial machinery.

[0951] A "large-scale language model" is an advanced machine learning model designed for natural language processing, which learns language patterns based on large amounts of text data.

[0952] "Employee information" refers to data about employees within a company, including information such as name, job title, area of ​​expertise, and contact information.

[0953] "Communication data" refers to digital communication information such as emails and chat messages exchanged between employees.

[0954] "Deliverables" refer to specific outputs such as documents, reports, and design drawings created by employees through their work.

[0955] "Analysis results" refer to information obtained after analyzing employee information, communication data, and deliverables using a large-scale language model, and include insights into employee relationships and areas of expertise.

[0956] "Specialized field" refers to the area of ​​technology or knowledge in which an employee is particularly proficient.

[0957] "Information provision means" refers to methods and devices for presenting information obtained based on analysis results to employees.

[0958] "Industrial machinery" refers to machinery and equipment used in manufacturing and production industries, specifically for processing and assembling products.

[0959] "Contact information" refers to information such as phone numbers and email addresses necessary to contact a specific employee.

[0960] The system for implementing this invention is designed to quickly resolve technical problems that arise in the operation of industrial machinery. The server analyzes employee information, communication data, and deliverables using a large-scale language model. Specifically, the server uses generative AI models such as OpenAI's GPT-3 to analyze this data and identify employee relationships and areas of expertise.

[0961] The server analyzes data acquired from sensors and cameras on industrial machinery to identify the nature of the problem. Based on the analysis results, it identifies employees with expertise in the relevant area and provides their contact information. This allows users to quickly contact the appropriate employees and take action to resolve the problem.

[0962] As a concrete example, if a machine malfunction occurs in a factory, the server analyzes the data related to the malfunction and inputs a prompt message into an AI model: "Identify an employee with expertise in this machine malfunction." The model then refers to a historical database and recommends the appropriate employee. In this way, the user can quickly obtain the information necessary to solve the problem.

[0963] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0964] Step 1:

[0965] The server receives data acquired from sensors and cameras on industrial machinery. This data includes information such as the machine's operating status and error codes. The server preprocesses this data and converts it into an analyzable format.

[0966] Step 2:

[0967] The server inputs pre-processed data into a generating AI model. Specifically, it uses models such as OpenAI's GPT-3 to analyze machine problems and identify the nature of those problems. This analysis outputs the cause of the problem and related technical information.

[0968] Step 3:

[0969] The server identifies employees with expertise in the problem based on the analysis results. It consults the employee information database to search for employees with expertise matching the analysis results. Information on the identified employees is then output.

[0970] Step 4:

[0971] The server provides the user with the contact information of the identified employee. The user can then use the provided contact information to quickly contact the employee and take action to resolve the issue.

[0972] Step 5:

[0973] Based on information provided by the server, users collaborate with employees to resolve problems. This enables quick and appropriate responses to technical issues with industrial machinery.

[0974] (Example 3)

[0975] Next, we will describe Embodiment 3 of Embodiment Example 3. 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."

[0976] In modern organizations, it is crucial to quickly identify individuals with specific skills and experience and assign them to appropriate projects and tasks. However, there is a lack of efficient means to comprehensively understand individuals' skills and experience and provide the necessary information. This leads to challenges such as project delays and delays in finding the right talent.

[0977] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 3 is realized by the following means.

[0978] In this invention, the server includes means for analyzing personal information using a large-scale language model, means for comprehensively covering relationships between individuals and their respective areas of expertise based on the analysis results, and means for providing information to identify individuals with specific skills and experience. This makes it possible to quickly identify individuals with specific skills and assign them to appropriate projects and tasks.

[0979] A "large-scale language model" is an advanced algorithm designed for natural language processing, which learns from large amounts of text data to understand and generate language.

[0980] "Personal information" refers to information about a specific individual, including skills, experience, and past project history.

[0981] "Analysis results" refer to data obtained after processing personal information using a large-scale language model, and include evaluations of individuals' skills and areas of expertise.

[0982] A "prompt statement" is an instruction that a user enters into the system, and it includes requests to obtain specific information.

[0983] "Information provision means" refers to methods for presenting necessary information to users based on analysis results, and is used to identify individuals with specific skills.

[0984] An "output device" is a device used to display analysis results to the user, and includes computer screens and mobile device displays.

[0985] To implement this invention, the user must first enter a prompt message into a terminal to search for an individual with specific skills and experience. The terminal then sends this prompt message to a server. Based on the received prompt message, the server retrieves personal information from its database. This information includes the individual's skills, experience, and past project history.

[0986] The server uses a generative AI model to analyze the acquired information. Specifically, it uses a large-scale language model for natural language processing to evaluate individuals' skill sets and identify individuals with the skills specified in the prompt. Once the analysis is complete, the server sends the analysis results to the terminal. The terminal then displays these results to the user.

[0987] For example, if a user enters the prompt "Find individuals with more than 5 years of experience in data science," the server extracts information on relevant individuals from the database and analyzes it using a generative AI model. As a result of the analysis, the names, departments, and contact information of individuals who meet the criteria are displayed on the device. This allows the user to quickly find the appropriate individuals.

[0988] This system leverages large-scale language models like OpenAI to efficiently analyze personal information, enabling the rapid identification of individuals with specific skills and their placement in appropriate projects and tasks. The flow of the identification process in Example 3 is explained using Figure 15.

[0989] Step 1:

[0990] The user enters a prompt into the terminal to search for individuals with specific skills or experience. The entered prompt becomes an instruction for the system to perform analysis. For example, the user might enter, "Please find individuals with more than 5 years of experience in data science."

[0991] Step 2:

[0992] The terminal sends the user's input prompt message to the server. The server receives this prompt message and prepares for analysis. The prompt message acts as a trigger for the server to retrieve the necessary information from the database.

[0993] Step 3:

[0994] The server retrieves personal information from the database based on the prompt. This information includes the individual's skills, experience, and past project history. The retrieved information becomes input data for analysis by the generative AI model.

[0995] Step 4:

[0996] The server inputs the acquired personal information into a generating AI model for analysis. Specifically, it uses a large-scale language model to evaluate individuals' skill sets and identify individuals who meet the conditions specified in the prompt. As a result of the analysis, a list of individuals who meet the conditions is generated.

[0997] Step 5:

[0998] The server sends the analysis results generated by the AI ​​model to the terminal. The analysis results include the names, departments, and contact information of individuals who meet the specified criteria.

[0999] Step 6:

[1000] The terminal displays the analysis results received from the server to the user. Based on this information, the user can quickly find individuals with specific skills and assign them to appropriate projects and tasks.

[1001] (Application Example 3)

[1002] Next, we will describe application example 3 of form example 3. 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."

[1003] In modern industrial settings, there is a need to quickly identify workers with specific skills and assign them to appropriate tasks. However, traditional methods present challenges in efficiently managing and immediately accessing worker skill information when needed. Furthermore, a lack of effective means for providing workers with proper work instructions can lead to decreased work efficiency.

[1004] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means.

[1005] In this invention, the server includes means for analyzing employee information, communication data, and deliverables using a large-scale language model; means for comprehensively identifying relationships between employees and their individual areas of expertise based on the analysis results; means for finding workers with specific skills and assigning them tasks; and means for approaching workers using mobile mechanical devices and instructing them to perform tasks. This makes it possible to quickly identify workers with specific skills and efficiently assign them appropriate tasks.

[1006] A "large-scale language model" is an artificial intelligence technology that learns from vast amounts of text data to understand and generate natural language.

[1007] "Employee information" refers to data about individual employees within an organization, including information such as skills, experience, and job title.

[1008] "Communication data" refers to the content of messages sent and received in digital format, such as emails and chats.

[1009] "Deliverables" refer to specific products, documents, or other outputs produced as a result of work or a project.

[1010] "Analysis results" refer to the insights and conclusions obtained after analyzing data.

[1011] "Relationships between employees" refers to the work-related connections and interactions between employees within an organization.

[1012] "Area of ​​expertise" refers to the area in which an individual employee possesses particularly outstanding skills or knowledge.

[1013] "Workers with specific skills" refers to employees who possess the specialized skills necessary to perform specific tasks or duties.

[1014] A "mobile machine" refers to a machine that can be physically moved and is designed to perform a specific task.

[1015] "Means of giving work instructions" refers to methods or devices used to communicate specific work content and procedures to workers.

[1016] A server plays a central role in implementing this invention. The server uses a large-scale language model to analyze employee information, communication data, and deliverables. Specifically, the server uses a programming language such as Python to retrieve employee information from a database and analyzes the data using natural language processing technology. Based on the analysis results, it is possible to comprehensively analyze the relationships between employees and their individual areas of expertise.

[1017] Furthermore, the server executes an algorithm to find workers with specific skills and assign them tasks. This algorithm uses an SQL database to search for skill information and select the most suitable worker. The selected worker receives work instructions using a mobile machine. This machine communicates with the server via Wi-Fi and provides specific instructions to the worker.

[1018] As a concrete example, consider a situation where a factory needs to find workers with specific machine operation skills to set up a new product line. In this case, the server inputs a prompt message to the AI ​​model saying, "Find workers with the machine operation skills required to set up the new product line," and recommends suitable workers. This improves the efficiency of work within the factory and makes it possible to quickly find workers with the appropriate skills.

[1019] The flow of the specific processing in Application Example 3 will be explained using Figure 16.

[1020] Step 1:

[1021] The server retrieves information on all employees from the employee database. Input includes employee IDs and skill information. Output provides data on employees' skill sets and experience. This data is extracted from the database using SQL queries.

[1022] Step 2:

[1023] The server inputs the acquired employee information into a large-scale language model and performs natural language processing. The input includes text data related to employees' skills and experience. The output provides analysis results regarding employee relationships and areas of expertise. This analysis is performed using a natural language processing algorithm implemented in Python.

[1024] Step 3:

[1025] The server searches for workers with specific skills based on the analysis results. The input includes information about the project's required skills. The output is a list of the most suitable workers. In this step, a generative AI model is used to generate prompts and recommend appropriate workers.

[1026] Step 4:

[1027] The server sends commands to a mobile machine to instruct a selected worker to perform a task. Inputs include the worker's ID and the task description. Output is that the machine approaches the worker and provides the work instructions. This communication takes place via Wi-Fi, and the machine operates according to the instructions.

[1028] Step 5:

[1029] The user receives feedback from the machine and monitors the progress of the work. Input includes feedback data from the machine. Output provides information on the work completion status and any problems encountered. Based on this information, the user can provide additional instructions as needed.

[1030] 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.

[1031] "Example of form 1"

[1032] One embodiment of the present invention combines a large-scale language model with an emotion engine. The large-scale language model analyzes employee information, chats, emails, and deliverables to comprehensively cover employee relationships and individual areas of expertise. Meanwhile, the emotion engine recognizes the user's emotions and uses the results to analyze the large-scale language model. For example, if a user is feeling frustrated, the emotion engine captures that information, and the large-scale language model uses that information to recommend an appropriate employee.

[1033] "Example of form 2"

[1034] In another embodiment of the present invention, the emotion engine recommends the most suitable employee based on the user's emotions. Specifically, if the user is feeling happy, the emotion engine captures that information, and the large-scale language model uses that information to recommend an employee who is likely to feel similar happiness. This facilitates smoother communication between the user and the employee.

[1035] "Example of form 3"

[1036] In a further embodiment of the present invention, the emotion engine analyzes the user's emotions and uses the results to analyze a large-scale language model. Specifically, if the user is feeling angry, the emotion engine captures that information, and the large-scale language model uses that information to recommend employees who are judged to have high problem-solving abilities. This helps the user solve their problems.

[1037] The following describes the processing flow for each example of the form.

[1038] "Example of form 1"

[1039] Step 1: A large-scale language model analyzes employee information, chat messages, emails, and deliverables.

[1040] Step 2: The emotion engine recognizes the user's emotions.

[1041] Step 3: The analysis results from the emotion engine are fed back into the large-scale language model.

[1042] Step 4: A large-scale language model recommends appropriate employees based on the analysis results of the emotion engine. (Example 2)

[1043] Step 1: The emotion engine recognizes the user's emotions.

[1044] Step 2: A large-scale language model analyzes employee information, chat messages, emails, and deliverables.

[1045] Step 3: A large-scale language model uses the results of the emotion engine's analysis to recommend employees who are likely to experience similar feelings of joy.

[1046] "Example of form 3"

[1047] Step 1: The emotion engine recognizes the user's emotions.

[1048] Step 2: A large-scale language model analyzes employee information, chat messages, emails, and deliverables.

[1049] Step 3: A large-scale language model recommends employees who are judged to have high problem-solving abilities based on the analysis results of the emotion engine.

[1050] (Example 1)

[1051] Next, we will describe Embodiment 1 of 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."

[1052] In modern businesses, accurately understanding employees' skills and areas of expertise and making appropriate personnel placements is crucial. However, efficiently analyzing vast amounts of data such as employee information, communication history, and deliverables to clearly identify individual strengths and interpersonal relationships is difficult. Furthermore, there is a need for personnel recommendations and problem-solving information that takes employees' emotional states into account. An effective system is needed to address these challenges.

[1053] 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.

[1054] In this invention, the server includes means for analyzing personal information, communication history, and created materials using a natural language processing model; means for identifying interpersonal relationships and individual areas of expertise based on the analysis results; and means for an emotion analysis device to recognize the user's emotional state and utilize the results for the analysis of the natural language processing model. This enables accurate understanding of employees' skills and areas of expertise, and allows for appropriate personnel placement and the provision of information for problem solving.

[1055] An "information processing device" is a computer system used to collect, analyze, and process data.

[1056] A "natural language processing model" is an artificial intelligence technology used to understand and analyze human language.

[1057] "Personal information" refers to information about a specific individual, such as their skill set or project history.

[1058] "Communication history" refers to records of communication between individuals, such as emails and chats.

[1059] "Created works" refer to deliverables such as reports and presentations created by individuals.

[1060] "Relationships" refer to information that indicates interactions and connections between individuals.

[1061] "Specialized area" refers to the field or skill in which an individual excels.

[1062] An "emotion analysis device" is a device used to recognize and analyze the emotional state of a user.

[1063] "User" refers to an individual or organization that uses the system.

[1064] "Information provision" refers to the act of presenting useful information to users based on analysis results.

[1065] This invention is a system that uses an information processing device to analyze personal information, communication history, and created materials to identify relationships between individuals and their areas of expertise. Specifically, the server uses a natural language processing model, such as OpenAI's GPT-4, to analyze this data. The server collects employee skill sets, project history, email exchanges, and created reports and presentations from a company's database.

[1066] The server preprocesses the collected data and inputs it into a natural language processing model. Preprocessing includes tokenizing text data and filtering out irrelevant information. Based on the analysis, the server extracts relationships between employees and their individual areas of expertise.

[1067] Furthermore, the server uses an emotion analyzer to recognize the user's emotional state. For example, if a user inputs "the project isn't progressing," the emotion analyzer detects frustration and uses that information to analyze the natural language processing model.

[1068] The terminal displays the analysis results received from the server to the user. The user can review the recommended employees and suggestions on the screen and decide on their next action.

[1069] As a concrete example, if a user enters the prompt message, "Please recommend the best data analysis expert for Project Y," the server will recommend a suitable employee based on the analysis results. This system takes into account the employee's skills and feelings to support optimal personnel placement and improved communication.

[1070] The flow of the specific processing in Example 1 will be explained using Figure 17.

[1071] Step 1:

[1072] The server collects the data. The server accesses the company's database to retrieve employee skill sets, project history, email correspondence, and created reports and presentations. The input is the company's database, and the output is data formatted for analysis. Specifically, the server extracts information from the database via an API.

[1073] Step 2:

[1074] The server preprocesses the data. The server converts the collected data into a format suitable for the natural language processing model. The input is the data obtained in step 1, and the output is tokenized data with unnecessary information filtered out. Specifically, the server tokenizes the text data and removes noisy information.

[1075] Step 3:

[1076] The server analyzes the data using a natural language processing model. The server inputs the pre-processed data into the natural language processing model to extract relationships between employees and their individual areas of expertise. The input is the data pre-processed in step 2, and the output is the relationship and area of ​​expertise information as a result of the analysis. Specifically, the server inputs data into the model and obtains the analysis results.

[1077] Step 4:

[1078] The server performs sentiment analysis. Based on the user's input prompts and past communication history, the server uses a sentiment analysis device to recognize the user's emotional state. The input is the user's prompts and history data, and the output is information about the emotional state. Specifically, the server applies a sentiment analysis algorithm to identify the emotion.

[1079] Step 5:

[1080] The server integrates the analysis results and sends them to the terminal. The server integrates the information obtained from the natural language processing model and sentiment analysis to generate information useful to the user. The input is the output of steps 3 and 4, and the output is the integrated analysis result. Specifically, the server integrates the data and prepares it for transmission to the terminal.

[1081] Step 6:

[1082] The terminal displays the results. The terminal displays the analysis results received from the server to the user. The input is the analysis results sent from the server, and the output is the information that the user can see on the screen. Specifically, the terminal visually displays the results, allowing the user to decide on the next action.

[1083] (Application Example 1)

[1084] Next, we will describe Application Example 1 of Form 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."

[1085] In modern industrial settings, efficient task assignment that takes into account workers' skills and emotional states is essential. However, conventional systems struggle to consider workers' emotional states, resulting in decreased work efficiency and increased worker stress. To address these challenges, a system is needed that analyzes workers' skills and emotional states in real time and assigns them the most suitable tasks.

[1086] 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.

[1087] In this invention, the server includes means for analyzing personnel information, communication history, and deliverables using a large-scale language model; means for comprehensively identifying relationships between personnel and their individual areas of expertise based on the analysis results; and means for analyzing individual emotional states using an emotion recognition engine. This enables efficient task assignment that takes into account the skills and emotional states of the workers.

[1088] A "large-scale language model" is an artificial intelligence technology that learns from vast amounts of text data to understand and generate natural language.

[1089] "Personnel information" refers to information such as the skill set, past work history, and area of ​​expertise of individual workers.

[1090] "Communication history" refers to records of communication between workers, such as chats and emails.

[1091] "Deliverables" refer to specific work results such as reports and presentations created by workers.

[1092] An "emotion recognition engine" is a technology that analyzes the emotional state of workers and acquires that information in real time.

[1093] "Task assignment" is the process of selecting the most suitable tasks for workers and distributing them in order to carry out the work efficiently.

[1094] The system for implementing this invention consists of a server equipped with a large-scale language model and an emotion recognition engine. The server first collects personnel information, communication history, and deliverables, and then analyzes this data using the large-scale language model. As a result of the analysis, the relationships between workers and their individual areas of expertise become clear.

[1095] Next, the server uses an emotion recognition engine to analyze the worker's current emotional state in real time. This emotional information is important for understanding the worker's stress level and motivation.

[1096] Based on analysis results and emotional information, the server assigns the most suitable task to each worker. This is expected to improve work efficiency and reduce worker stress. For example, if worker A is feeling frustrated, the server can reduce worker A's stress by assigning them a less demanding task.

[1097] An example of a prompt to input into the generating AI model is: "Analyze employee information, chat logs, and deliverables, and assign the most suitable task to each employee, taking into account their areas of expertise and current emotional state."

[1098] In this way, the server enables efficient task assignment that takes into account the skills and emotional state of the workers.

[1099] The flow of a specific process in Application Example 1 will be explained using Figure 18.

[1100] Step 1:

[1101] The server collects personnel information, communication history, and deliverables from a database. This data includes each worker's skill set, past work history, area of ​​expertise, chat and email records, and reports and presentations they have created. Input data is passed to the server in text format.

[1102] Step 2:

[1103] The server analyzes the collected data using a large-scale language model. Specifically, it receives text data as input and uses natural language processing techniques to extract relationships between workers and their individual areas of expertise. As output, it generates skill maps and relationship maps of the workers.

[1104] Step 3:

[1105] The server uses an emotion recognition engine to analyze the current emotional state of the workers. It receives facial images and voice data of the workers as input and applies an emotion recognition algorithm to identify the workers' emotional state (e.g., stress, motivation). Emotional state data for each worker is generated as output.

[1106] Step 4:

[1107] The server integrates analysis results and emotional information to assign the most suitable tasks to each worker. Specifically, it receives skill maps and emotional state data as input and applies a task assignment algorithm to select tasks appropriate for each worker. The output is a list of task assignments for each worker.

[1108] Step 5:

[1109] The server uses a generative AI model to notify workers of the task assignment results. It generates a prompt message and sends a notification to the worker's terminal. A specific example of a prompt message is: "Analyze employee information, chat logs, and deliverables, and assign the most suitable task considering each employee's strengths and current emotional state." The output is a notification displayed on the worker's terminal.

[1110] (Example 2)

[1111] Next, we will describe Example 2 of the morphological example. 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."

[1112] There is a challenge in quickly and accurately identifying other employees with the appropriate knowledge and experience to address problems and questions faced by employees. Furthermore, there is a need for emotionally-based recommendations of the most suitable employees to facilitate smooth communication among employees.

[1113] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1114] In this invention, the server includes means for analyzing employee information, communication data, and deliverables using a large-scale language model; means for comprehensively covering relationships between employees and their individual areas of expertise based on the analysis results; and means for analyzing the user's emotions using an emotion analysis engine and recommending the most suitable employee. This enables the rapid identification of other employees with the appropriate knowledge to address problems faced by employees, and facilitates smooth, emotion-based communication.

[1115] A "large-scale language model" is an artificial intelligence model designed for natural language processing, trained on a vast dataset.

[1116] "Employee information" refers to data about employees, such as their skill sets, work history, and areas of expertise.

[1117] "Communication data" refers to information such as emails and chat messages exchanged between employees.

[1118] "Deliverables" refer to documents, reports, and project outputs created by employees through their work.

[1119] "Analysis results" refers to the results of analyzing data obtained using large-scale language models and sentiment analysis engines.

[1120] An "emotion analysis engine" is a technology that analyzes a user's emotions and suggests appropriate actions based on those emotions.

[1121] "Users" refers to employees or individuals who use the system to obtain information.

[1122] "Specialized field" refers to the area of ​​technology or knowledge in which an employee is particularly proficient.

[1123] "Recommendation" refers to the act of presenting the most suitable employees or information based on analysis results.

[1124] This invention is a system that enables employees to quickly identify other employees with the appropriate knowledge to address problems they face, and facilitates smooth, emotion-based communication. Specific embodiments of this system are described below.

[1125] The server receives input data from the user and performs analysis using a generative AI model. This analysis utilizes natural language processing techniques, specifically large-scale language models such as OpenAI's GPT. The server searches the company's internal database to understand the user's questions and problems and identify employees with relevant knowledge. This database contains employees' skill sets and work histories.

[1126] Furthermore, the server uses an emotion analysis engine to analyze the user's emotions. For example, if a user feels joy when entering a question, the server uses that information to recommend employees who are likely to have similar emotions. This process facilitates smoother communication between users and employees.

[1127] As a concrete example, consider a case where a user asks, "I want to learn more about this new technology." The server analyzes this question and recommends an employee who is deemed to be proficient in the relevant technology. Furthermore, if the user expresses joy when asking the question, the emotion engine uses that information to recommend an employee who shares the same passion for technology.

[1128] An example of a prompt to input into the generating AI model might be, "Recommend the best employee for an employee who has a technical question." Using this prompt, the server will identify the appropriate employee and provide the information to the user.

[1129] The flow of the specific processing in Example 2 will be explained using Figure 19.

[1130] Step 1:

[1131] The user enters questions or problems through the terminal. For example, they might enter something like, "I want to learn more about this new technology." The terminal then sends this input data to the server. The input data is text information that includes the user's questions and feelings.

[1132] Step 2:

[1133] The server analyzes the received input data. This analysis uses a generative AI model. Specifically, it uses a large-scale language model such as OpenAI's GPT to understand the user's question. The server analyzes the input data using natural language processing techniques to identify the user's intent. The output is the analyzed user intent and related keywords.

[1134] Step 3:

[1135] The server searches the company's internal database based on the analysis results. This database contains employee skill sets and work histories. The server queries the database to identify employees with knowledge relevant to the user's question. The input is the analyzed keywords, and the output is a list of relevant employees.

[1136] Step 4:

[1137] The server uses an emotion analysis engine to analyze the user's emotions. It identifies the emotions the user is feeling when entering a question and recommends employees who are likely to have similar emotions. The input is data about the user's emotions, and the output is a list of the most suitable employees based on those emotions.

[1138] Step 5:

[1139] The server provides the user with information about the identified employee. The terminal displays this information to the user. For example, the information might be presented as, "An employee with technical expertise can answer your questions." The input is a list of the most suitable employees, and the output is the information provided to the user.

[1140] (Application Example 2)

[1141] Next, we will describe application example 2 of form 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."

[1142] It is essential to identify engineers who can respond quickly and appropriately to technical problems that arise within the factory, and to resolve these problems efficiently. Furthermore, facilitating smooth communication among employees is also crucial to improving the speed of problem-solving.

[1143] 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.

[1144] In this invention, the server includes means for analyzing employee information, communication data, and deliverables using a large-scale language model; means for comprehensively covering relationships between employees and their individual areas of expertise based on the analysis results; means for providing information to resolve questions; means for automated machinery in the factory to detect anomalies and transmit the information to the cloud; means for a generated AI model on the cloud to perform analysis and identify appropriate technicians; and means for sending notifications to the identified technicians. This enables rapid response to technical problems within the factory and smooth communication among employees.

[1145] A "large-scale language model" is an advanced machine learning model designed for natural language processing, which understands and generates language based on large amounts of text data.

[1146] "Employee information" refers to data about employees within a company, including individual skills, experience, job title, and job responsibilities.

[1147] "Communication data" refers to records of digital communications such as emails and chat messages exchanged between employees.

[1148] "Deliverables" refer to specific outputs such as documents, reports, and design drawings created by employees through their work.

[1149] "Analysis results" refer to information obtained after analyzing employee information, communication data, and deliverables using a large-scale language model, and include insights into employee relationships and areas of expertise.

[1150] "Automated machinery" refers to mechanical devices used in factories that operate automatically using sensors and control systems.

[1151] "Cloud" refers to a service of computer resources and data storage provided via the internet, and is a platform for storing and processing data.

[1152] A "generative AI model" is a model that uses artificial intelligence technology to analyze data and generate new information and insights.

[1153] A "technician" is a person who possesses specialized knowledge and skills in a particular technical field and is responsible for tasks such as problem-solving and machine maintenance.

[1154] A "notification" is a message or alert sent via email or smart device to inform a recipient of specific information.

[1155] The system for implementing this invention is designed to quickly resolve technical problems within a factory. The server uses a large-scale language model to analyze employee information, communication data, and deliverables. This allows for comprehensive analysis of employee relationships and individual areas of expertise.

[1156] Automated machinery within the factory uses sensors to detect anomalies and transmits this information to the cloud. On the cloud, a generative AI model analyzes the data and identifies the appropriate technician. This identified technician receives a notification via their device, such as a smartphone or smart glasses.

[1157] For example, if an automated machine in a factory detects abnormal vibrations, that data is sent to the cloud. A generative AI model on the cloud identifies a technician with expertise in vibrations and sends a notification to his smartphone saying, "Abnormal vibrations have been detected in machine X. Please take action."

[1158] An example of a prompt message is, "Abnormal vibration has been detected in the machine. Please identify a technician with expertise in vibration." This prompt message allows the generating AI model to quickly identify the appropriate technician.

[1159] This system enables rapid response to technical issues within the factory and facilitates smooth communication among employees.

[1160] The flow of a specific process in Application Example 2 will be explained using Figure 20.

[1161] Step 1:

[1162] The server receives sensor data transmitted from automated machinery within the factory. This data includes information on the machine's operating status and signs of malfunctions. The server analyzes the received data to determine whether an anomaly has been detected.

[1163] Step 2:

[1164] If an anomaly is detected, the server sends the information to the cloud. In the cloud, a generative AI model receives this data as input and analyzes the type of anomaly and its scope of impact. Based on the analysis results, it identifies which technical fields of expertise are needed.

[1165] Step 3:

[1166] The cloud-based AI model identifies the appropriate engineers based on the analysis results. This process involves referencing an employee database to select engineers with the necessary expertise. Information on the selected engineers is then output.

[1167] Step 4:

[1168] The server generates a notification for the identified technician. This notification includes detailed information about the anomaly and the need for action. The notification is sent to the technician's device (smartphone or smart glasses).

[1169] Step 5:

[1170] Technicians receive notifications on their terminals and begin responding to an anomaly. Based on the notification, technicians head to the site and work to resolve the problem. This enables rapid problem resolution.

[1171] (Example 3)

[1172] Next, we will describe Embodiment 3 of Embodiment Example 3. 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."

[1173] In today's workplace environment, it is difficult to quickly identify individuals with specific skills and experience. Furthermore, recommending the right person while considering the user's feelings is also challenging. This can lead to delays in project progress and stalls in problem-solving.

[1174] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 3 is realized by the following means.

[1175] In this invention, the server includes means for analyzing job information using a generative AI model, means for recommending personnel with specific skills based on the analysis results, and means for analyzing the user's emotions using an emotion analysis engine and recommending personnel judged to have high problem-solving abilities based on the results. This makes it possible to quickly find personnel with specific skills and recommend appropriate personnel that take into account the user's emotions.

[1176] A "generative AI model" is a model that uses artificial intelligence technology to perform natural language processing and analyze or generate data for specific tasks.

[1177] "Job information" refers to data about employees and personnel, such as skills, experience, resumes, and project history.

[1178] "Analysis results" refers to the results of analyzing data obtained by generative AI models and emotion analysis engines.

[1179] "Specific skills" refer to the specialized knowledge and techniques required for a particular task or project.

[1180] An "emotion analysis engine" refers to software or a system that analyzes a user's emotions and identifies their emotional state.

[1181] A "prompt sentence" is an instruction sentence input to a generative AI model, and refers to a sentence that includes a question or request to obtain specific information.

[1182] "Problem-solving ability" refers to the ability to effectively address specific challenges or problems and find solutions.

[1183] A description of embodiments for carrying out this invention will be given.

[1184] The server first analyzes job information using a generative AI model. This analysis utilizes natural language processing technology and targets data such as skills, experience, resumes, and project history related to employees and personnel. Specifically, a database management system (DBMS) is used to collect and analyze this data.

[1185] Next, the server recommends individuals with specific skills based on the analysis results. The generative AI model searches the database for individuals with the relevant skills based on the prompt text and creates a recommendation list. For example, if a user enters the prompt text "Please recommend employees who are strong in data analysis," the server will respond to this request by listing suitable individuals.

[1186] Furthermore, the device uses an emotion analysis engine to analyze the user's emotions. If the user is feeling anger or stress, it sends that information to the server. Based on this emotional information, the server recommends individuals who are judged to have high problem-solving abilities. This makes it possible to select the most suitable personnel while taking the user's emotions into consideration.

[1187] As a concrete example, suppose a project is behind schedule and the user enters a prompt message saying, "Please recommend an employee with strong problem-solving skills to help the project progress." In this case, the server considers the results of the sentiment analysis engine and recommends an appropriate person, thereby facilitating the smooth progress of the project. The specific processing flow in Example 3 will be explained using Figure 21.

[1188] Step 1:

[1189] The server uses a database management system (DBMS) to collect job information related to employees and personnel, such as skills, experience, resumes, and project history. The input consists of various job information within the database. The server retrieves this data and builds a basic dataset for analysis. The output is a dataset of job information necessary for analysis.

[1190] Step 2:

[1191] The server uses a generative AI model to analyze the collected job information. The input is the dataset of job information obtained in Step 1. The server utilizes natural language processing technology to analyze the data in order to identify individuals with specific skills and experience. The output is the analysis results regarding each employee's skills and experience.

[1192] Step 3:

[1193] The user enters a prompt to search for personnel with specific skills. The input is a prompt message entered by the user. For example, the user might enter a prompt message such as, "Please recommend an employee with strong data analysis skills." The output is that the server receives this prompt message and uses it as an instruction for analysis.

[1194] Step 4:

[1195] The server searches for suitable personnel from the analysis results based on the prompt message and creates a recommendation list. The input consists of the analysis results obtained in step 2 and the prompt message entered in step 3. The server compares these and lists the most suitable personnel. The output is a list of recommended personnel.

[1196] Step 5:

[1197] The device analyzes the user's emotions using an emotion analysis engine. The input is data related to the user's emotions. The device analyzes this data to identify the user's emotional state. The output is the analysis result regarding the user's emotional state.

[1198] Step 6:

[1199] The server recommends individuals deemed to have high problem-solving abilities based on the results of the emotion analysis engine. The inputs are the emotion analysis results obtained in step 5 and the recommendation list obtained in step 4. The server considers these factors to select the most suitable individuals. The output is a final list of recommended individuals, taking emotions into account.

[1200] (Application Example 3)

[1201] Next, we will describe application example 3 of form example 3. 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."

[1202] In modern industrial settings, there is a need to quickly identify personnel with specific skills and provide appropriate problem-solving. However, traditional methods are time-consuming in finding the necessary personnel and have difficulty addressing issues that take emotional factors into consideration.

[1203] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means.

[1204] In this invention, the server includes means for analyzing personnel information, communication data, and deliverables using a large-scale language model; means for comprehensively covering the relationships between personnel and their individual areas of expertise based on the analysis results; and means for analyzing the user's emotions using an emotion analysis engine and utilizing the results in the large-scale language model. This enables the rapid identification of personnel with specific skills and appropriate problem-solving that takes emotional factors into consideration.

[1205] A "large-scale language model" is an artificial intelligence technology that has the ability to understand and generate natural language based on vast amounts of data.

[1206] "Personnel information" refers to data on individual personnel, such as their skills, experience, and performance.

[1207] "Communication data" refers to information generated through digital communication such as email and chat.

[1208] "Deliverables" refer to specific products or documents produced as a result of a project or task.

[1209] An "emotion analysis engine" is a technology that analyzes a user's emotions and identifies their emotional state.

[1210] A "specialized field" refers to an area that focuses on specific knowledge or skills.

[1211] "Problem-solving ability" refers to the ability to find effective solutions to challenges and problems.

[1212] "Recommendation" is the act of presenting the best option based on specific conditions.

[1213] The system for implementing this invention operates in a network environment including a server and terminals. The server runs a program that analyzes personnel information, communication data, and deliverables using a large-scale language model. This analysis uses the Hugging Face Transformers library and performs natural language processing. Based on the analysis results, the server comprehensively covers the relationships between personnel and their individual areas of expertise and stores them in a database.

[1214] Furthermore, the server uses an emotion analysis engine to analyze users' emotions and utilizes the results in a large-scale language model. The emotion analysis uses software capable of real-time data processing. This allows for the rapid identification of individuals with specific skills and the recommendation of those deemed to have high problem-solving abilities.

[1215] The terminal sends a query to the server when the user is looking for someone with specific skills. The server searches its database based on the received query and lists the relevant personnel. When the user is troubleshooting a machine, the terminal performs sentiment analysis and recommends the most suitable technician.

[1216] As a concrete example, when a machine malfunctions, the terminal prompts the AI ​​model with the message, "We are looking for a technician who can troubleshoot machine A." The model then consults a skills database and lists suitable technicians. It also analyzes the emotions of the surrounding workers and prioritizes recommending technicians who are deemed calm and possess strong problem-solving abilities.

[1217] Example of a prompt:

[1218] "We are looking for a technician who can troubleshoot machine A. Please perform an emotional analysis and recommend the most suitable technician."

[1219] The flow of the specific processing in Application Example 3 will be explained using Figure 22.

[1220] Step 1:

[1221] The user uses a terminal to enter a prompt message to search for personnel with specific skills. The entered prompt message is sent from the terminal to the server.

[1222] Step 2:

[1223] The server parses the received prompt message and queries the skills database. The database contains information about the skills and experience of the personnel. The server generates a list of the relevant personnel as a result of the query.

[1224] Step 3:

[1225] The server uses an emotion analysis engine to analyze the user's emotions. It uses the user's voice and text data as input to identify their emotional state. The analysis results are fed back into a large-scale language model.

[1226] Step 4:

[1227] Based on the results of the sentiment analysis, the server prioritizes selecting individuals from a list who are judged to have high problem-solving abilities. The information of the selected individuals is sent to the terminal.

[1228] Step 5:

[1229] The terminal displays personnel information received from the server to the user. Based on the displayed information, the user can select the appropriate personnel and contact them.

[1230] Step 6:

[1231] Users can contact the personnel they have selected from their device. Email and chat are used as communication methods. This allows users to quickly begin taking action to resolve their problems.

[1232] (Other examples)

[1233] Since this is the same as the specific processing described in the other embodiments of the first embodiment above, the explanation will be omitted.

[1234] 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.

[1235] The data generation model 58 is a form of so-called generative AI (Artificial Intelligence). One example of the data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> 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.

[1236] Other examples of generative AI include Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) are examples.

[1237] 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.

[1238] [Fourth Embodiment]

[1239] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1240] 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.

[1241] 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).

[1242] 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.

[1243] 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.

[1244] 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).

[1245] 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.

[1246] 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.

[1247] 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.

[1248] 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.

[1249] 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.

[1250] 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.

[1251] Next, the identification process performed by the identification processing unit 290 of the data processing device 12 will be described.

[1252] "Example of form 1"

[1253] This embodiment of the present invention uses a large-scale language model to analyze employee information, chats, emails, and deliverables. Specifically, employee information, including information such as employees' skill sets, past projects, and areas of expertise, as well as chats and emails recording communication between employees, and deliverables such as reports and presentations created by employees, are input into the large-scale language model. The large-scale language model analyzes this information to extract relationships between employees and their individual areas of expertise.

[1254] "Example of form 2"

[1255] Next, based on the analysis results, we address the question, "Who should I ask?" Specifically, we identify employees who are likely to have solutions to a particular problem and provide information about those employees. For example, if an employee has a question about a particular technology, we recommend an employee who has been analyzed as being proficient in that technology.

[1256] "Example of form 3"

[1257] Furthermore, based on the analysis results, it addresses the question, "Is there anyone like this?" Specifically, it provides information to help find employees with specific skills and experience. For example, if a project team is looking for an employee with a particular skill, it will recommend employees who have been analyzed as possessing that skill.

[1258] The following describes the processing flow for each example of the form.

[1259] "Example of form 1"

[1260] Step 1: Analyze employee information using a large-scale language model. Employee information includes employee skill sets, past projects, and areas of expertise.

[1261] Step 2: Similarly, analyze chats and emails that record communication between employees.

[1262] Step 3: Next, analyze deliverables such as reports and presentations created by employees.

[1263] Step 4: Integrate these analysis results and extract the relationships between employees and their individual areas of expertise. (Example 2)

[1264] Step 1: Based on the analysis results, resolve the question, "Who should I ask?"

[1265] Step 2: Identify employees who are most likely to have solutions to the specific problem.

[1266] Step 3: Provide information about the employee. For example, if an employee has a question about a particular technology, recommend an employee who has been analyzed as being proficient in that technology.

[1267] "Example of form 3"

[1268] Step 1: Based on the analysis results, answer the question, "Are there any people like this?" Step 2: Provide information to find employees with specific skills and experience.

[1269] Step 3: For example, if a project team is looking for an employee with a specific skill, recommend an employee who has been analyzed to possess that skill.

[1270] (Example 1)

[1271] Next, we will describe Embodiment 1 of Example Form 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1272] In modern businesses, accurately understanding employees' skills and areas of expertise and quickly identifying the right people is crucial. However, the sheer volume of employee information, communication history, and deliverables makes it difficult to efficiently analyze this data and extract the necessary information. Furthermore, finding employees with specific areas of expertise or identifying the appropriate contact person is not easy.

[1273] 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.

[1274] In this invention, the server includes means for collecting information, means for preprocessing the information, and means for analyzing the information using a large-scale language model. This makes it possible to efficiently extract employee relationships and areas of expertise and to quickly provide the necessary information.

[1275] An "information processing device" is a computer system used for collecting, processing, and analyzing data.

[1276] "Means of collecting information" refers to the function of obtaining necessary data from databases or other information sources.

[1277] "Preprocessing means" refers to a function that performs processing to convert collected data into a format suitable for analysis.

[1278] A "large-scale language model" is an advanced machine learning model designed for natural language processing, possessing the ability to analyze vast amounts of text data.

[1279] "Means of analysis" refers to the process of extracting specific information or patterns using pre-processed data.

[1280] "Means for extracting relationships and areas of expertise" refers to a function that identifies relationships between employees and their individual areas of expertise from the analysis results.

[1281] A "generative AI model" is a model that uses artificial intelligence to generate new information and content.

[1282] A "prompt statement" is an instruction given to a generative AI model to obtain specific information.

[1283] The invention is described in terms of its implementation. This system uses an information processing device to analyze employee information, communication history, and deliverables. Specifically, the server collects employee skill sets, past projects, areas of expertise, chat and email history, and created reports and presentations from a database. This data is preprocessed by the server and converted into a format suitable for large-scale language models.

[1284] The server inputs pre-processed data into a large-scale language model. Suitable models for this are commonly used natural language processing models such as GPT-4 and BERT. The model analyzes the input data and extracts relationships between employees and their individual areas of expertise.

[1285] The analysis results are stored in a database by the server and can be accessed later. Users can obtain specific information by entering prompts into the generated AI model. For example, by entering prompts such as "Please tell me about employee A's areas of expertise" or "Please tell me about employees who have shared project experience with employee B," the server extracts the relevant information from the stored analysis results and provides it to the user.

[1286] This system allows companies to efficiently understand their employees' skills and relationships, and quickly identify the right talent.

[1287] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1288] Step 1:

[1289] The server collects employee information, chat history, emails, and deliverables from the database. Inputs include employee skill sets, past projects, areas of expertise, communication history, and created reports and presentations. This data is centrally collected and prepared as foundational data for analysis.

[1290] Step 2:

[1291] The server preprocesses the collected data. The input is the raw data collected in step 1. Specifically, it performs text data cleaning, removal of unnecessary information, tokenization, and data normalization. The output is data in a format suitable for large-scale language models.

[1292] Step 3:

[1293] The terminal inputs pre-processed data into a large-scale language model. The input is the processed data obtained in step 2. Specifically, the data is passed to the model and the analysis is performed. The output is analysis results regarding the relationships between employees and their individual areas of expertise.

[1294] Step 4:

[1295] The server saves the analysis results to a database. The input is the analysis results obtained in step 3. Specifically, the server stores the results in the database in an appropriate format for later reference. The output is the saved analysis results.

[1296] Step 5:

[1297] The user obtains information by inputting prompts into the generating AI model. The input consists of prompts requesting specific information. Specifically, the server extracts relevant information from the database based on the prompts and presents it to the user. The output provides the information the user requested.

[1298] (Application Example 1)

[1299] Next, we will describe Application Example 1 of Form 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".

[1300] In modern industrial settings, efficient personnel allocation and team formation are key to improving productivity. However, manually determining the optimal placement, taking into account the skills and past experience of individual personnel, is difficult, time-consuming, and laborious. Furthermore, quickly finding the right personnel is not easy. This leads to challenges such as project delays and wasted resources.

[1301] 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.

[1302] In this invention, the server includes means for analyzing personnel information, communication history, and deliverables using a large-scale language model; means for comprehensively identifying relationships between personnel and their individual areas of expertise based on the analysis results; and means for proposing the optimal team composition based on the analysis results. This enables efficient personnel allocation and rapid team formation.

[1303] A "large-scale language model" is an artificial intelligence model used in natural language processing to learn from large amounts of text data and to understand and generate language.

[1304] "Personnel information" refers to information about individual personnel, such as their skill sets, past project experience, and areas of expertise.

[1305] "Communication history" refers to the record of communication, such as chats and emails, between employees.

[1306] "Deliverables" refer to concrete outputs such as reports and presentations created by employees.

[1307] "Analysis results" refer to the results of information analyzed by a large-scale language model, and include relationships between individuals and their areas of expertise.

[1308] "Team formation" refers to creating a group by combining the most suitable personnel for a specific purpose or project.

[1309] To implement this invention, it is necessary to build a system in which a server analyzes personnel information, communication history, and deliverables using a large-scale language model. The server analyzes this data using the Python programming language and OpenAI's GPT-4 API. Specifically, the server collects data including skill sets, past project experience, and areas of expertise as personnel information, and acquires chat and email records as communication history. As deliverables, it collects outputs such as reports and presentations.

[1310] The server inputs this data into a large-scale language model and extracts the relationships between individuals and their areas of expertise as analysis results. Furthermore, it proposes the optimal team composition based on the analysis results. This proposal aims to streamline personnel allocation within the factory and improve productivity.

[1311] As a concrete example, when setting up a new product line in a factory, the server uses this system to determine which personnel should be assigned to which positions. An example of a prompt to the generative AI model is as follows:

[1312] "Analyze employee data and propose the optimal team composition for launching a new product line. Employee data is as follows: {Employee Data JSON}"

[1313] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1314] Step 1:

[1315] The server collects personnel information, communication history, and deliverables from the database. Inputs include employee skill sets, past project experience, areas of expertise, chat and email records, and deliverables such as reports and presentations. This data is then integrated and prepared for analysis.

[1316] Step 2:

[1317] The server inputs the collected data into a large-scale language model. The input data is structured in JSON format and contains information about each employee. The server analyzes the data using a generative AI model to extract relationships between employees and their individual areas of expertise. The analysis results are output.

[1318] Step 3:

[1319] The server proposes the optimal team composition based on the analysis results. Specifically, it selects the most suitable personnel for the project, taking into account each employee's skills and areas of expertise based on the analysis results. A list of the proposed team compositions is generated as output.

[1320] Step 4:

[1321] The server notifies the user of the proposed team composition. The user receives the notification from the server and confirms the proposed team composition. This allows the user to make efficient personnel allocations. The output includes details of the team composition provided to the user.

[1322] (Example 2)

[1323] Next, we will describe Example 2 of the Form 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".

[1324] Within organizations, there is a need to quickly and accurately identify components that are likely to hold the solution to a specific problem and to provide the appropriate information. However, traditional methods present challenges, such as the time-consuming nature of information gathering and analysis, making it difficult to identify the right components.

[1325] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1326] In this invention, the server includes means for collecting information on components using an information processing device, means for analyzing the collected information using a generative AI model, and means for identifying components that are likely to have a solution to a particular problem based on the analysis results. This makes it possible to quickly and accurately identify components that are likely to have a solution to a particular problem and to provide appropriate information.

[1327] An "information processing device" is a device used to collect, process, and analyze data, and includes devices such as computers and servers.

[1328] A "generative AI model" is a model that uses artificial intelligence technology to analyze data and derive solutions to specific problems.

[1329] "Components" refer to individual elements or members within an organization, including individuals or departments with specific skills or knowledge.

[1330] "Analysis results" refer to the results of the analysis obtained after data has been processed by a generative AI model.

[1331] "Identifying" refers to finding elements that meet specific conditions or criteria based on the analysis results.

[1332] "Providing information" refers to presenting users with detailed information about identified components.

[1333] This invention is a system that identifies components within an organization that are likely to possess solutions to specific problems and provides them with appropriate information. The server collects information about the components using an information processing device. Specifically, it retrieves data on the skills and expertise of the components from internal databases and project management tools.

[1334] Next, the server uses a generative AI model to analyze the collected information. This analysis involves data processing and computations that utilize natural language processing techniques to identify components that are familiar with specific technologies or problems. A general large-scale language model is used as the generative AI model.

[1335] Based on the analysis results, the server identifies components that are likely to hold the solution to a specific problem and sends that information to the terminal. The terminal displays information to the user such as the name, role, and area of ​​expertise of the identified component. This allows the user to directly ask questions to the appropriate component.

[1336] For example, if a user enters "I have a question about data analysis in Python," the server sends the following prompt to the AI ​​model: "I have a question about data analysis in Python. Please recommend components that are familiar with this problem." This prompt allows the server to identify appropriate components and provide information to the user.

[1337] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1338] Step 1:

[1339] The server uses an information processing device to collect information about its components. As input, it retrieves data on the components' skills and expertise from internal databases and project management tools. This data includes past project history, skill sets, and job titles. As output, the collected data is passed to a generating AI model.

[1340] Step 2:

[1341] The server analyzes the collected information using a generative AI model. The data collected in step 1 is used as input. The generative AI model utilizes natural language processing techniques to perform data processing and calculations to identify components that are proficient in specific technologies or problems. The output is the analysis result, listing components that are likely to have solutions to the specific problem.

[1342] Step 3:

[1343] The server sends information about the components identified based on the analysis results to the terminal. The analysis results obtained in step 2 are used as input. Specifically, the server organizes information such as the names, roles, and areas of expertise of the identified components and sends it to the terminal. As output, the terminal displays this information to the user.

[1344] Step 4:

[1345] The user can directly ask questions about identified components based on the information displayed on the device. The input is the information about the components displayed on the device. Specifically, the user contacts the components through the device and asks questions. As output, the user can obtain a solution to the problem.

[1346] (Application Example 2)

[1347] Next, we will describe application example 2 of form 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".

[1348] In the operation of industrial machinery, a challenge exists in identifying employees with the expertise to quickly and appropriately resolve technical problems when they occur. To address this challenge, a system is needed that can analyze the nature of the problem, quickly identify the appropriate employees, and contact them.

[1349] 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.

[1350] In this invention, the server includes means for analyzing employee information, communication data, and deliverables using a large-scale language model; means for comprehensively covering relationships between employees and their individual areas of expertise based on the analysis results; means for providing information to resolve questions; means for analyzing problems with industrial machinery and identifying employees with appropriate expertise; and means for providing contact information for the identified employees. This makes it possible to respond quickly and appropriately to technical problems with industrial machinery.

[1351] A "large-scale language model" is an advanced machine learning model designed for natural language processing, which learns language patterns based on large amounts of text data.

[1352] "Employee information" refers to data about employees within a company, including information such as name, job title, area of ​​expertise, and contact information.

[1353] "Communication data" refers to digital communication information such as emails and chat messages exchanged between employees.

[1354] "Deliverables" refer to specific outputs such as documents, reports, and design drawings created by employees through their work.

[1355] "Analysis results" refer to information obtained after analyzing employee information, communication data, and deliverables using a large-scale language model, and include insights into employee relationships and areas of expertise.

[1356] "Specialized field" refers to the area of ​​technology or knowledge in which an employee is particularly proficient.

[1357] "Information provision means" refers to methods and devices for presenting information obtained based on analysis results to employees.

[1358] "Industrial machinery" refers to machinery and equipment used in manufacturing and production industries, specifically for processing and assembling products.

[1359] "Contact information" refers to information such as phone numbers and email addresses necessary to contact a specific employee.

[1360] The system for implementing this invention is designed to quickly resolve technical problems that arise in the operation of industrial machinery. The server analyzes employee information, communication data, and deliverables using a large-scale language model. Specifically, the server uses generative AI models such as OpenAI's GPT-3 to analyze this data and identify employee relationships and areas of expertise.

[1361] The server analyzes data acquired from sensors and cameras on industrial machinery to identify the nature of the problem. Based on the analysis results, it identifies employees with expertise in the relevant area and provides their contact information. This allows users to quickly contact the appropriate employees and take action to resolve the problem.

[1362] As a concrete example, if a machine malfunction occurs in a factory, the server analyzes the data related to the malfunction and inputs a prompt message into an AI model: "Identify an employee with expertise in this machine malfunction." The model then refers to a historical database and recommends the appropriate employee. In this way, the user can quickly obtain the information necessary to solve the problem.

[1363] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1364] Step 1:

[1365] The server receives data acquired from sensors and cameras on industrial machinery. This data includes information such as the machine's operating status and error codes. The server preprocesses this data and converts it into an analyzable format.

[1366] Step 2:

[1367] The server inputs pre-processed data into a generating AI model. Specifically, it uses models such as OpenAI's GPT-3 to analyze machine problems and identify the nature of those problems. This analysis outputs the cause of the problem and related technical information.

[1368] Step 3:

[1369] The server identifies employees with expertise in the problem based on the analysis results. It consults the employee information database to search for employees with expertise matching the analysis results. Information on the identified employees is then output.

[1370] Step 4:

[1371] The server provides the user with the contact information of the identified employee. The user can then use the provided contact information to quickly contact the employee and take action to resolve the issue.

[1372] Step 5:

[1373] Based on information provided by the server, users collaborate with employees to resolve problems. This enables quick and appropriate responses to technical issues with industrial machinery.

[1374] (Example 3)

[1375] Next, we will describe Embodiment 3 of Example 3. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1376] In modern organizations, it is crucial to quickly identify individuals with specific skills and experience and assign them to appropriate projects and tasks. However, there is a lack of efficient means to comprehensively understand individuals' skills and experience and provide the necessary information. This leads to challenges such as project delays and delays in finding the right talent.

[1377] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 3 is realized by the following means.

[1378] In this invention, the server includes means for analyzing personal information using a large-scale language model, means for comprehensively covering relationships between individuals and their respective areas of expertise based on the analysis results, and means for providing information to identify individuals with specific skills and experience. This makes it possible to quickly identify individuals with specific skills and assign them to appropriate projects and tasks.

[1379] A "large-scale language model" is an advanced algorithm designed for natural language processing, which learns from large amounts of text data to understand and generate language.

[1380] "Personal information" refers to information about a specific individual, including skills, experience, and past project history.

[1381] "Analysis results" refer to data obtained after processing personal information using a large-scale language model, and include evaluations of individuals' skills and areas of expertise.

[1382] A "prompt statement" is an instruction that a user enters into the system, and it includes requests to obtain specific information.

[1383] "Information provision means" refers to methods for presenting necessary information to users based on analysis results, and is used to identify individuals with specific skills.

[1384] An "output device" is a device used to display analysis results to the user, and includes computer screens and mobile device displays.

[1385] To implement this invention, the user must first enter a prompt message into a terminal to search for an individual with specific skills and experience. The terminal then sends this prompt message to a server. Based on the received prompt message, the server retrieves personal information from its database. This information includes the individual's skills, experience, and past project history.

[1386] The server uses a generative AI model to analyze the acquired information. Specifically, it uses a large-scale language model for natural language processing to evaluate individuals' skill sets and identify individuals with the skills specified in the prompt. Once the analysis is complete, the server sends the analysis results to the terminal. The terminal then displays these results to the user.

[1387] For example, if a user enters the prompt "Find individuals with more than 5 years of experience in data science," the server extracts information on relevant individuals from the database and analyzes it using a generative AI model. As a result of the analysis, the names, departments, and contact information of individuals who meet the criteria are displayed on the device. This allows the user to quickly find the appropriate individuals.

[1388] This system leverages large-scale language models like OpenAI to efficiently analyze personal information, enabling the rapid identification of individuals with specific skills and their placement in appropriate projects and tasks. The flow of the identification process in Example 3 is explained using Figure 15.

[1389] Step 1:

[1390] The user enters a prompt into the terminal to search for individuals with specific skills or experience. The entered prompt becomes an instruction for the system to perform analysis. For example, the user might enter, "Please find individuals with more than 5 years of experience in data science."

[1391] Step 2:

[1392] The terminal sends the user's input prompt message to the server. The server receives this prompt message and prepares for analysis. The prompt message acts as a trigger for the server to retrieve the necessary information from the database.

[1393] Step 3:

[1394] The server retrieves personal information from the database based on the prompt. This information includes the individual's skills, experience, and past project history. The retrieved information becomes input data for analysis by the generative AI model.

[1395] Step 4:

[1396] The server inputs the acquired personal information into a generating AI model for analysis. Specifically, it uses a large-scale language model to evaluate individuals' skill sets and identify individuals who meet the conditions specified in the prompt. As a result of the analysis, a list of individuals who meet the conditions is generated.

[1397] Step 5:

[1398] The server sends the analysis results generated by the AI ​​model to the terminal. The analysis results include the names, departments, and contact information of individuals who meet the specified criteria.

[1399] Step 6:

[1400] The terminal displays the analysis results received from the server to the user. Based on this information, the user can quickly find individuals with specific skills and assign them to appropriate projects and tasks.

[1401] (Application Example 3)

[1402] Next, we will describe application example 3 of form example 3. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1403] In modern industrial settings, there is a need to quickly identify workers with specific skills and assign them to appropriate tasks. However, traditional methods present challenges in efficiently managing and immediately accessing worker skill information when needed. Furthermore, a lack of effective means for providing workers with proper work instructions can lead to decreased work efficiency.

[1404] The specific processing performed by the specific processing unit 290 of the data process...

Claims

[Claim 1] A system comprising a server and a user terminal, The processor of the aforementioned server is Employee information, including employee skill sets, communication history, including chat or email records between employees, and data on deliverables created by employees are collected from the database and preprocessed. By inputting the pre-processed data into a large-scale language model and analyzing it, the relationships between employees and their individual areas of expertise are extracted. The system acquires user inquiries entered from the user terminal and recognizes the user's emotional state using an emotion engine. If the aforementioned emotional state is anger, a prompt message is generated instructing the system to recommend an employee who is judged to have high problem-solving ability based on the extracted relationships between the employees and their areas of expertise. If the aforementioned emotional state is joy, a prompt message is generated instructing the system to recommend an employee who is likely to have that joyful emotion, based on the extracted relationships between the employees and their areas of expertise. A system that inputs the generated prompt sentence into a generating AI model to obtain a response to the query and sends it to the user terminal.

Images