System

Abstract

To provide a system.SOLUTION: A system includes: means for acquiring personnel information; means for acquiring information containing an experience-based measure, a project, an expertise, qualification, and a field of interest; means for storing the acquired information in a database; means for generating a best mix team proposal across organizations by entering the stored information into a generative AI model; and means for presenting the generated team draft to a user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] With conventional HR information systems, it was difficult to create the best mix of teams across organizations, or to simulate projects in specific fields with specific members. There was also a need for effective support for HR strategies such as team formation, human resource development, skill improvement, and recruitment. [Means for solving the problem]

[0005] This invention inputs information such as personnel information, experience, projects, specialties, qualifications, and areas of interest, and then uses AI to propose the best mix of teams across organizations based on this information. It also has the functionality to suggest teams suitable for specific projects and to simulate projects in specific fields with specific members. This provides effective support for personnel strategies such as team formation, human resource development, skill improvement, and recruitment. [Brief explanation of the drawings]

[0006] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 2 is a sequence diagram showing a flow of processing in the data processing system according to the first embodiment of the first form example. [Figure 12]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Embodiment 1. [Figure 13] FIG. 10 is a sequence diagram showing a processing flow of a data processing system in a second embodiment of the second form example. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Embodiment Example 2. [Figure 15] FIG. 10 is a sequence diagram showing the flow of processing in a data processing system according to a third embodiment of the third embodiment. [Figure 16] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Embodiment 3. [Figure 17] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the first embodiment of the first form example when an emotion engine is combined. [Figure 18] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Embodiment 1 when an emotion engine is combined. [Figure 19] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the second embodiment of the second form example when an emotion engine is combined. [Figure 20] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Form Example 2 when an emotion engine is combined. [Figure 21] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the third embodiment of the third form example when an emotion engine is combined. [Figure 22] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Form Example 3 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

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

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

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

[0010] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

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

[0012] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0013] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0014] [First embodiment]

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

[0016] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0017] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0018] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0019] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

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

[0021] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0023] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0024] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0025] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

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

[0027] "Example 1"

[0028] The system of the present invention has a means for inputting information such as personnel information, experience, projects, specialties, qualifications, and areas of interest. Specifically, this information is stored in a database and analyzed by AI. Based on this information, the AI ​​proposes a best-mix team proposal across organizations. For example, for a specific project, it selects members with the optimal skills and experience and proposes their combination.

[0029] "Example 2"

[0030] The system of the present invention also has the ability to propose teams suitable for specific projects. Specifically, the AI ​​compares project requirements with personnel information and proposes the optimal team composition. For example, for a new software development project, it selects members with the appropriate programming skills and experience and proposes their combination.

[0031] "Example 3"

[0032] Furthermore, the system of the present invention has a function that enables simulation of a project in a specific field with specific members. Specifically, the AI ​​compares the members' skills with the project requirements and performs a simulation based on the results. For example, if a specific member is to carry out a new marketing project, the AI ​​compares the member's marketing skills with the project requirements and simulates the project's success probability and required resources based on the results.

[0033] The processing flow of each embodiment will be described below.

[0034] "Example 1"

[0035] Step 1: Enter personnel information and experience, projects, specialties, qualifications, areas of interest, etc. into the database.

[0036] Step 2: AI analyzes this information and proposes the best mix of teams across the organization.

[0037] Step 3: Utilize the proposed team plan for team formation, human resource development, skill development, and recruitment. "Format Example 2"

[0038] Step 1: Define the requirements for your specific project.

[0039] Step 2: AI compares the project requirements with personnel information and suggests the optimal team composition.

[0040] Step 3: Apply the proposed team structure to the project.

[0041] "Example 3"

[0042] Step 1: Define a project with specific members and in a specific field.

[0043] Step 2: The AI ​​compares the skills of members with the project requirements and performs a simulation based on the results.

[0044] Step 3: Based on the simulation results, evaluate the probability of project success and the resources required.

[0045] Example 1

[0046] Next, a description will be given of 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."

[0047] With conventional personnel management systems, it was difficult to effectively utilize the skills and experience of individual employees to form optimal teams. Furthermore, there was a lack of objective criteria for selecting the best members for specific projects, making it difficult to improve the efficiency of the entire organization. Furthermore, there was a lack of concrete methods for utilizing the proposed team plans in actual team formation, human resource development, skill improvement, and recruitment.

[0048] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0049] In this invention, the server includes: a means for inputting personnel information; a means for inputting information such as experience, projects, specialties, qualifications, and areas of interest; a means for storing the input information in a database; a means for using a generative AI model to analyze the stored information; a means for inputting a prompt to the generative AI model to generate a cross-organizational best-mix team proposal; a means for presenting the generated team proposal to the user; and a means for utilizing the proposed team proposal in team formation, human resource development, skill improvement, and recruitment. This makes it possible to maximize the skills and experience of individual employees and select the optimal members for a specific project. Furthermore, the proposed team proposal can be utilized in specific personnel policies, improving the efficiency of the entire organization.

[0050] "Human resources information" refers to data such as an employee's basic information, work history, skills, evaluations, and qualifications.

[0051] "Experience measures" refer to the experience and achievements of employees in projects and work they have participated in in the past.

[0052] A "project" refers to a set of activities or tasks carried out within an organization to achieve a specific purpose.

[0053] "Specialty" refers to the specialized knowledge and skills an employee has in a particular field or technology.

[0054] "Qualification" refers to any official certification or certificate obtained by an employee.

[0055] "Areas of interest" refers to areas or topics in which employees have personal interests.

[0056] A "database" refers to a system that systematically organizes and stores information so that it can be searched and used as needed.

[0057] A "generative AI model" is a model that uses artificial intelligence to analyze data and perform specific tasks.

[0058] A "prompt" refers to an instruction or question input to a generative AI model.

[0059] A "best mix team proposal" refers to a proposal that proposes a combination of members with the optimal skills and experience for a specific project.

[0060] "User" refers to a person who uses the system to input information and receive results.

[0061] "Team formation" refers to the process of selecting the best members to form a team to achieve a specific purpose.

[0062] "Human resource development" refers to education and training to improve employees' skills and abilities.

[0063] "Skill improvement" refers to activities aimed at further enhancing employees' skills and knowledge.

[0064] "Recruitment" refers to the process of selecting and adding new employees to an organization.

[0065] The present invention is a system in which a server, a terminal, and a user work in cooperation with each other. A specific embodiment of this system will be described below.

[0066] Server Operation

[0067] The server receives information provided by users, such as personnel information, experience, projects, specialties, qualifications, and areas of interest. This information is sent in JSON format via an HTTP request. The server stores the received information in a relational database such as MySQL (registered trademark) or PostgreSQL.

[0068] The server then uses a generative AI model to analyze the stored information. Specifically, it uses a Python API to call OpenAI's GPT-4 model to generate a prompt. By inputting the prompt into the generative AI model, it generates a best-mix team proposal across organizations.

[0069] The generated team proposals are sent from the server to the device as an HTTP response in JSON format, allowing the user to check the optimal team member combinations.

[0070] Device behavior

[0071] The terminal receives information entered by the user through an input form, such as personnel information, experience, projects, specialties, qualifications, and areas of interest. This information is collected using a form on the web browser with JavaScript (registered trademark).

[0072] The collected information is sent to the server in JSON format using an AJAX request. The best mix team proposal received from the server is analyzed using JavaScript and dynamically reflected in HTML, allowing users to view the team proposal on their device screen.

[0073] User Actions

[0074] Users use their terminals to enter information such as personnel information, experience, projects, specialties, qualifications, and areas of interest. Specifically, they enter the required information into a form on a web browser. Once the information is complete, the terminal sends it to the server.

[0075] After receiving the best mix team proposal from the server, the user can check the team proposal displayed on the device screen, select the optimal team members, and take specific actions to ensure the success of the project.

[0076] Specific examples

[0077] For example, suppose a user wants to select the best team members to start a new project. The user uses a terminal to enter the following information:

[0078] Project name: New product development project

[0079] Required skills: Machine learning, data analysis, project management

[0080] Project duration: 6 months

[0081] The server receives this information, stores it in a database, and then uses a generative AI model to select the best team members and propose a team plan like this:

[0082] Member 1: Machine learning expert with 5 years of experience

[0083] Member 2: Data analysis expert with 3 years of experience

[0084] Member 3: Project management expert with 10 years of experience

[0085] Prompt Sentence Examples

[0086] "Please suggest the best team members with machine learning, data analysis, and project management skills for a new product development project. The project will last six months."

[0087] In this way, users can easily select the most suitable team members.

[0088] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0089] Step 1:

[0090] Users use their devices to enter information such as personnel information, experience, projects, specialties, qualifications, and areas of interest. Specifically, they enter the required information into a form on a web browser. The entered information is converted into JSON format using JavaScript.

[0091] Input: Information entered by the user, such as personnel information, experience, projects, specialties, qualifications, and areas of interest

[0092] Output: JSON format data

[0093] Step 2:

[0094] The terminal sends the input information to the server. Specifically, it uses an AJAX request to send JSON format data to the server as an HTTP request.

[0095] Input: JSON format data

[0096] Output: HTTP request to the server

[0097] Step 3:

[0098] The server receives the information sent from the device. Specifically, it analyzes the JSON format data received through the HTTP request and extracts the necessary information.

[0099] Input: JSON format data received as an HTTP request

[0100] Output: Extracted information

[0101] Step 4:

[0102] The server stores the received information in a database. Specifically, it uses a relational database such as MySQL or PostgreSQL and stores the data using an INSERT statement.

[0103] Input: Extracted information

[0104] Output: Information stored in the database

[0105] Step 5:

[0106] The server then invokes a generative AI model to analyze the stored information. Specifically, it uses a Python API to invoke OpenAI's GPT-4 model and generate a prompt.

[0107] Input: Information stored in a database

[0108] Output: Generated prompt statement

[0109] Step 6:

[0110] The server inputs prompt statements into the generative AI model to generate a best-mix team proposal across organizations. Specifically, it analyzes the results returned by the generative AI model and creates a list of appropriate members.

[0111] Input: Generated prompt text

[0112] Output: Best Mix Team Proposal

[0113] Step 7:

[0114] The server sends the generated team proposals to the device, specifically returning the results in JSON format as an HTTP response.

[0115] Input: Best Mix Team Proposal

[0116] Output: JSON formatted data as an HTTP response to the terminal

[0117] Step 8:

[0118] The device displays the best mix team proposal received from the server to the user. Specifically, it parses the received JSON data using JavaScript and dynamically reflects it in HTML.

[0119] Input: JSON format data as an HTTP response from the server

[0120] Output: Team proposals displayed to the user

[0121] Step 9:

[0122] Users can review the team proposals displayed on their device screen, select the most suitable team members, and take concrete actions to ensure the project's success.

[0123] Input: Team proposal displayed on the terminal

[0124] Output: User confirmation and action

[0125] (Application example 1)

[0126] Next, a description will be given of Application Example 1 of Embodiment 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."

[0127] In conventional factories, it was difficult to form optimal teams that took into account the skills and experience of workers, making it difficult to carry out work efficiently. Furthermore, there was no system for selecting the best workers for a specific project, which sometimes led to reduced work efficiency and project delays. This resulted in a decline in productivity throughout the factory and a loss of competitiveness.

[0128] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0129] In this invention, the server includes means for inputting personnel information, means for inputting information such as experience, projects, specialties, qualifications, and areas of interest, AI means for proposing a best mix team plan across organizations based on the input information, means for utilizing the proposed team plan in team formation, human resource development, skill improvement, and recruitment, and means for storing information such as the skills, experience, qualifications, and areas of interest of workers in the factory in a database and proposing the optimal work team for a specific task or project. This makes it possible to form the optimal work team in the factory, improving work efficiency and smooth project execution.

[0130] "Personnel information" refers to information about individuals, such as an employee's name, age, work history, skills, qualifications, and evaluations.

[0131] "Experience measures" refers to information that indicates the specific experience and achievements of an employee in projects or work that the employee has participated in in the past.

[0132] A "project" is a set of tasks or activities planned and carried out to achieve a specific purpose.

[0133] "Specialty" refers to the field, skill, or knowledge in which an employee is particularly skilled.

[0134] "Qualifications" refers to any official certifications, certificates, licenses, etc. that an employee has obtained.

[0135] "Areas of interest" refers to areas or topics that employees have a personal interest in.

[0136] "AI means" refers to systems and algorithms that use artificial intelligence technology to analyze data and make optimal team composition and proposals.

[0137] A "database" is a collection of information that is systematically organized and made available for efficient search and use.

[0138] A "work team" is a group of workers organized to accomplish a specific task or project.

[0139] "Team formation" is the process of selecting the best members to form a team for a specific purpose or project.

[0140] "Human resource development" refers to the activities of providing education and training to improve employees' skills and knowledge.

[0141] "Skill Up" refers to improving employees' skills and abilities.

[0142] "Recruitment" is the process of selecting and hiring new employees.

[0143] A system for carrying out this invention is configured as follows: The server includes means for inputting personnel information, means for inputting information such as experience measures, projects, specialties, qualifications, and areas of interest, AI means for proposing a best mix team plan across organizations based on the input information, means for utilizing the proposed team plan in team formation, human resource development, skill improvement, and recruitment, and means for storing information such as the skills, experience, qualifications, and areas of interest of factory workers in a database and proposing the optimal work team for a specific task or project.

[0144] The server runs the program using Python and uses SQLite as the database. The scikit-learn library is used for AI analysis. Specifically, worker information is stored in the database and the profiles are vectorized using a TF-IDF vectorizer. The cosine similarity between the project requirements and the worker profiles is calculated to suggest the optimal work team.

[0145] Users access the system using a smartphone or tablet and input the project requirements. The server then proposes the optimal work team based on the input requirements. For example, if the project requirements are "robotics, automation, and maintenance," the AI ​​will select the workers most suited to this.

[0146] An example prompt might be, "Enter 'Robotics, automation, maintenance' as your project requirements. Let the AI ​​suggest the best work team."

[0147] This system enables the optimal organization of work teams within the factory, improving work efficiency and ensuring smooth project execution.

[0148] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0149] Step 1:

[0150] Users access the system using a smartphone or tablet and enter project requirements.

[0151] Input: Project requirements (e.g., "Robotics, Automation, Maintenance")

[0152] Output: The input project requirements

[0153] Step 2:

[0154] The server receives the input project requirements and retrieves the worker information from the database.

[0155] Input: Project Requirements

[0156] Output: Worker information (e.g., skills, experience, qualifications, areas of interest)

[0157] Step 3:

[0158] The server vectorizes the worker information using a TF-IDF vectorizer.

[0159] Input: Worker information

[0160] Output: Vectorized worker profiles

[0161] Step 4:

[0162] The server vectorizes the project requirements and calculates the cosine similarity with the worker profiles.

[0163] Inputs: Vectorized project requirements, Vectorized worker profiles

[0164] Output: Cosine similarity score

[0165] Step 5:

[0166] The server selects the best working team based on the cosine similarity score.

[0167] Input: Cosine similarity score

[0168] Output: A list of optimal work team members

[0169] Step 6:

[0170] The server displays the optimal work team suggestions to the user.

[0171] Input: List of suitable work team members

[0172] Output: Optimal work team proposals displayed to the user

[0173] Step 7:

[0174] The user reviews the proposed work team and makes adjustments as needed.

[0175] Input: Optimal work team proposal

[0176] Output: Coordinated work team member list

[0177] In this way, the system proposes the optimal work team based on the project requirements entered by the user, and the user can confirm and adjust the proposal, resulting in efficient work team formation within the factory.

[0178] Example 2

[0179] Next, a description will be given of 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 will be referred to as a "terminal."

[0180] Conventional team formation systems have difficulty efficiently comparing project requirements with personnel information and proposing optimal team compositions. Furthermore, they have problems in that they are unable to perform simulations based on the proposed team compositions or perform advanced analysis using generative AI models.

[0181] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for inputting personnel information, means for inputting information such as experience, projects, specialties, qualifications, and areas of interest, artificial intelligence means for proposing a best-mix team plan across organizations based on the input information, means for utilizing the proposed team plan in team formation, human resource development, skill improvement, and recruitment, means for generating prompt statements based on project requirements and personnel information, means for inputting the generated prompt statements into a generative AI model to propose an optimal team composition, and means for displaying the proposed team composition. This makes it possible to efficiently propose a team composition optimal for project requirements and further perform simulations and advanced analyses based on the proposal.

[0182] "Human Resources Information" refers to information such as an employee's skill set, years of experience, qualifications, and past project history.

[0183] "Experience measures" refer to the content and results of the experience an employee has had in projects or work they have participated in in the past.

[0184] A "project" is a set of tasks or activities planned to achieve a specific purpose.

[0185] "Specialty" refers to a field or skill in which an employee is particularly skilled.

[0186] "Qualification" refers to any official certification or certificate obtained by an employee.

[0187] "Areas of interest" refers to areas or topics that employees are interested in.

[0188] "Artificial intelligence means" refers to algorithms and models that suggest optimal team compositions based on collected data.

[0189] A "prompt" refers to an instruction or question that is input into a generative AI model.

[0190] A "generative AI model" refers to an artificial intelligence model that suggests optimal team composition based on input prompt text.

[0191] "Team formation" refers to selecting the best members for a specific project and forming a team.

[0192] "Human resource development" refers to education and training to improve employees' skills and abilities.

[0193] "Skill improvement" refers to improving employees' skills and knowledge.

[0194] "Recruitment" refers to the process of selecting and hiring new employees.

[0195] The present invention is a system for proposing a team suitable for a specific project. A specific embodiment of this system will be described below.

[0196] First, a user accesses the system's web interface using a terminal and enters the project requirements, including the required programming language, years of experience, and other skills. For example, the user might enter requirements such as "Python, JavaScript, 5+ years of experience, database management, and cloud services experience."

[0197] Next, the server retrieves relevant personnel information from a database based on the project requirements entered by the user. The database stores each member's skill set, years of experience, past project history, and other information. The server connects to the MySQL database and retrieves the personnel information using an SQL query. For example, it executes a query such as "SELECT FROM HR INFORMATION WHERE SKILLS LIKE '%Python%' AND YEARS OF EXPERIENCE >= 5."

[0198] The server generates a prompt to be input to the generative AI model based on the acquired personnel information. This prompt contains detailed descriptions of the project requirements and the skills and experience of each member. For example, the following prompts can be generated:

[0199] Project requirements:

[0200] Programming languages: Python, JavaScript

[0201] Years of experience: 5 years or more

[0202] Other skills: Database management, cloud services experience

[0203] Personnel information:

[0204] Member A: Python (5 years), JavaScript (3 years), Database Management (2 years)

[0205] Member B: Python (6 years), JavaScript (5 years), Cloud Services (4 years)

[0206] Member C: Python (4 years), JavaScript (6 years), Database Management (5 years)

[0207] Please suggest the best team composition.

[0208] The server inputs the generated prompt to a generative AI model (e.g., OpenAI's GPT-4) via an API request. The generative AI model then proposes the optimal team composition based on the input prompt. For example, it returns a suggestion such as, "Member B and Member C are optimal."

[0209] Finally, the server displays the proposal received from the generative AI model on a web interface. The user can review the proposed team composition and modify or approve it as needed. For example, a message such as "Members B and C have been selected" may be displayed.

[0210] This system efficiently proposes the team composition that best suits the project requirements, and also enables simulations and advanced analysis based on those proposals.

[0211] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0212] Step 1:

[0213] A user accesses the system's web interface using a terminal and enters project requirements, including the required programming language, years of experience, and other skills. For example, a requirement might be "Python, JavaScript, 5+ years of experience, database management, and cloud service experience." The input data is then sent to the server.

[0214] Step 2:

[0215] The server receives project requirements submitted by users and retrieves the relevant personnel information from the database. The server connects to the MySQL database and retrieves the personnel information using an SQL query. For example, it executes a query such as "SELECT FROM HR INFORMATION WHERE SKILLS LIKE '%Python%' AND YEARS OF EXPERIENCE >= 5". The input is the project requirements and the output is the retrieved personnel information.

[0216] Step 3:

[0217] The server generates a prompt sentence to be input to the generative AI model based on the acquired personnel information. The server generates the prompt sentence using a Python script. For example, it generates the following prompt sentence:

[0218] Project requirements:

[0219] Programming languages: Python, JavaScript

[0220] Years of experience: 5 years or more

[0221] Other skills: Database management, cloud services experience

[0222] Personnel information:

[0223] Member A: Python (5 years), JavaScript (3 years), Database Management (2 years)

[0224] Member B: Python (6 years), JavaScript (5 years), Cloud Services (4 years)

[0225] Member C: Python (4 years), JavaScript (6 years), Database Management (5 years)

[0226] Please suggest the best team composition.

[0227] The input is the personnel information obtained and the output is the generated prompt sentence.

[0228] Step 4:

[0229] The server inputs the generated prompt to a generative AI model (for example, OpenAI's GPT-4) via an API request. The generative AI model then proposes the optimal team composition based on the input prompt. For example, it returns a suggestion such as "Member B and Member C are optimal." The input is the generated prompt, and the output is the suggestion from the generative AI model.

[0230] Step 5:

[0231] The server displays the proposal received from the generative AI model on a web interface. The user can review the proposed team composition and make any necessary modifications or approvals. For example, a message such as "Members B and C have been selected" is displayed. The input is the proposal from the generative AI model, and the output is the team composition displayed to the user.

[0232] (Application example 2)

[0233] Next, a description will be given of 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 will be referred to as a "terminal."

[0234] Conventional systems only considered human resources when proposing teams suitable for specific projects, making it difficult to form optimal teams that took into account the skill sets and operating status of the machines and robots in the factory. Furthermore, the system lacked the functionality to automatically generate operating schedules for the proposed teams, making efficient project management difficult.

[0235] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for inputting personnel information; means for inputting information such as experience, projects, specialties, qualifications, and areas of interest; AI means for proposing a best-mix team plan across organizations based on the input information; means for utilizing the proposed team plan in team formation, human resource development, skill improvement, and recruitment; means for managing the skill sets and operating status of each machine in the factory; means for inputting requirements for a new manufacturing project; means for AI to propose an optimal machine team; and means for automatically generating an operating schedule for the proposed team. This enables optimal team formation and efficient project management that takes into account both human and machine resources.

[0236] "Human Resources Information" refers to information such as an employee's skills, experience, qualifications, areas of expertise, and areas of interest.

[0237] "Experience measures" refer to the experience of projects and work that employees have previously participated in.

[0238] A "project" is a set of activities planned and carried out to achieve a specific purpose.

[0239] "Specialty" refers to advanced knowledge and skills in a particular field.

[0240] "Qualification" refers to the certification or attestation required to perform a particular job or function.

[0241] "Areas of interest" refers to areas or topics that an employee is personally interested in.

[0242] "Best Mix Team Proposal" refers to a plan that proposes the combination of members that best suits the project requirements.

[0243] "AI means" refers to a function that uses artificial intelligence to analyze data and propose optimal team composition and schedules.

[0244] "Team formation" refers to the process of selecting the best members for a particular project and building a team.

[0245] "Human resource development" refers to education and training to improve employees' skills and abilities.

[0246] "Skill Up" refers to improving employees' skills and knowledge.

[0247] "Recruitment" refers to the process of selecting and hiring new employees.

[0248] The "skill set of each machine in the factory" refers to the specific functions and capabilities of each machine or robot used in the factory.

[0249] "Operational status" refers to the current state in which a machine or robot is operating or is available for operation.

[0250] "New Manufacturing Project Requirements" refers to the conditions and specifications required for a new manufacturing project.

[0251] The "optimal machine team" refers to the combination of machines and robots that best meets the project requirements.

[0252] "Work schedule" refers to a plan showing when each member of the proposed team will be available.

[0253] A system for carrying out this invention has the following configuration: A server includes means for inputting personnel information, means for inputting information such as experience measures, projects, specialties, qualifications, and areas of interest, AI means for proposing a best mix team plan across organizations based on the input information, means for utilizing the proposed team plan in team formation, human resource development, skill improvement, and recruitment, means for managing the skill set and operating status of each machine in a factory, means for inputting requirements for a new manufacturing project, means for AI to propose an optimal machine team, and means for automatically generating an operating schedule for the proposed team.

[0254] Hardware and software used

[0255] Hardware: Servers, smartphones

[0256] Software: Python, scikit-learn, NumPy

[0257] Data processing and calculation

[0258] The server first inputs information such as personnel information, experience, projects, specialties, qualifications, and areas of interest into a database. Next, it collects data to manage the skill sets and operating status of each machine in the factory and inputs the requirements for a new manufacturing project. Based on this data, the AI ​​means proposes the optimal machine team. The AI ​​means uses scikit-learn's cosine_similarity to calculate the similarity between the project requirements and the machine skill sets and selects the optimal team. Furthermore, it processes the data using NumPy to automatically generate the operating schedule for the proposed team.

[0259] Specific examples

[0260] For example, if the requirements for a new manufacturing project are Skill A, Skill B, and Skill C, then Robot 1 in the factory has the skill set [1, 0, 1] and the available date is "2023-10-01", Robot 2 has the skill set [0, 1, 1] and the available date is "2023-10-05", and Robot 3 has the skill set [1, 1, 0] and the available date is "2023-10-03". In this case, the AI ​​tool will propose the optimal team based on this information and automatically generate an operating schedule.

[0261] Prompt Sentence Examples

[0262] A new manufacturing project requires skills A, B, and C. Please propose the optimal team taking into account the skill sets and operational status of the robots in the factory.

[0263] This enables optimal team formation and efficient project management that takes into account both human and machine resources.

[0264] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0265] Step 1:

[0266] The server inputs information such as personnel information and experience policies, projects, specialties, qualifications, areas of interest, etc. into the database, including employee skill sets, past project experience, etc. The input data is stored in the database for later processing.

[0267] Step 2:

[0268] The server collects data to manage the skill sets and operational status of each machine in the factory. Specifically, it inputs information such as the functions, capabilities, and available days of each machine or robot into a database. This data is used to optimally organize the machines into teams.

[0269] Step 3:

[0270] Users enter requirements for new manufacturing projects into the server, including the skills and capabilities needed, project start and finish dates, etc. The project requirements are then stored in a database.

[0271] Step 4:

[0272] The server processes the data to propose the optimal team based on the input project requirements and the personnel and machine information in the database. Specifically, it uses scikit-learn's cosine_similarity to calculate the similarity between the project requirements and the skill sets of each machine. Based on the calculation results, it selects the optimal machine team.

[0273] Step 5:

[0274] The server automatically generates a work schedule for the proposed team. Specifically, it uses NumPy to create a schedule based on the available days for the selected machines and robots. The generated schedule provides an optimal work plan between the start and end dates of the project.

[0275] Step 6:

[0276] The server presents the proposed team and work schedule to the user. The user reviews the proposed team composition and schedule, and makes any necessary modifications or approvals. The final team composition and schedule are finalized as the project execution plan.

[0277] In this way, the server achieves optimal team formation and efficient project management that takes into account both human and machine resources.

[0278] Example 3

[0279] Next, a description will be given of a third embodiment of the third embodiment. 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."

[0280] With conventional project management systems, it was difficult to properly match member skills with project requirements, making it impossible to accurately predict the probability of project success. Furthermore, the lack of functionality to simulate projects in specific fields with specific members made it difficult to allocate resources and evaluate the probability of success during the project planning stage. This hindered the efficient progress of projects and improved success rates.

[0281] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0282] In this invention, the server includes: a means for inputting personnel information; a means for inputting information such as experience, projects, specialties, qualifications, and areas of interest; an artificial intelligence means for proposing a best-mix team plan across organizations based on the input information; a means for utilizing the proposed team plan in team formation, human resource development, skill improvement, and recruitment; a means for acquiring skill data of specific members and project requirement data; a means for comparing the acquired skill data with the requirement data; a means for inputting prompts into the generative AI model to perform a simulation; and a means for displaying the simulation results to the user. This enables appropriate matching of member skills with project requirements and accurate prediction of the project's success probability. Furthermore, it is possible to simulate a project in a specific field with specific members, making it easier to allocate resources and evaluate the success probability during the project planning stage.

[0283] "Human Resources Information" is information about an employee, such as their skills, experience, qualifications, and areas of interest.

[0284] "Experienced measures" refers to information that refers to specific efforts and results in projects or tasks that have been implemented in the past.

[0285] A "project" is a set of activities or tasks planned and carried out to achieve a specific purpose.

[0286] "Specialization" refers to having advanced knowledge and skills in a particular field or area.

[0287] A "certification" is an official recognition or certification required to perform a particular job or function.

[0288] An "area of ​​interest" is a field or area in which an individual is particularly interested and wants to actively engage.

[0289] "Artificial intelligence means" are systems or algorithms that use machine learning and data analysis to automatically perform specific tasks.

[0290] The "best mix team proposal" is a plan that proposes the optimal combination of members for the success of the project.

[0291] "Team building" is the process of selecting and organizing the right people for a project.

[0292] "Human resource development" refers to the activity of providing education and training to improve the skills and abilities of employees.

[0293] "Skill improvement" refers to further enhancing an individual's skills and knowledge.

[0294] "Recruitment" is the process by which an organization selects and hires new employees.

[0295] "Skill data" is information about the specific skills and knowledge that an individual possesses.

[0296] "Requirements data" is information about the conditions and specifications necessary for the project to be successful.

[0297] A "generative AI model" is an artificial intelligence model that uses natural language processing and machine learning to generate appropriate output from input data.

[0298] A "prompt sentence" is a sentence of instructions or questions that is input to a generative AI model.

[0299] "Simulation" is the process of virtually recreating a real-world project or situation and predicting its outcome.

[0300] "Users" are individuals or organizations that use this system to simulate projects and check the results.

[0301] This invention is a system that enables simulation of a project in a specific field with specific members. This system operates in cooperation with three entities: a server, a terminal, and a user.

[0302] The server first has a means for inputting personnel information. This means stores personal information such as employee skills, experience, qualifications, and areas of interest in a database and has the function of retrieving it as needed. The database uses a relational database management system (RDBMS) such as MySQL or PostgreSQL.

[0303] Next, the server has a means for inputting information such as experience, projects, specialties, qualifications, areas of interest, etc. This allows specific efforts and results from past projects and tasks to be stored in a database and retrieved as needed.

[0304] The server has an artificial intelligence means that proposes the best mix of teams across organizations based on the input information. This artificial intelligence means is a system or algorithm that uses machine learning and data analysis to automatically perform specific tasks. Specifically, it uses programming languages ​​such as Python and R and utilizes data processing libraries such as Pandas and NumPy.

[0305] Furthermore, the server has the means to utilize the proposed team proposals for team formation, human resource development, skill upgrading, and recruitment, which can assist in the process of selecting and organizing the right members for the project.

[0306] The server has a means for acquiring the skill data of a specific member and the requirement data of a project, and by this means, the skill data of the member and the requirement data of the project can be acquired from the database and compared.

[0307] The server also includes a means to compare the acquired skill data with the requirements data, using programming languages ​​such as Python and R and leveraging data processing libraries such as Pandas and NumPy.

[0308] The server has a means to input a prompt sentence into the generative AI model and perform a simulation. For example, OpenAI's GPT-4 is used as the generative AI model. An example of a prompt sentence is as follows:

[0309] Member A's marketing skills include: marketing strategy, data analysis, and advertising operations. The requirements for a new marketing project include: market research, targeting, and advertising campaign design. Simulate the probability of success and the resources required for this project.

[0310] Finally, the server has a means to display the simulation results to the user. The user can check the simulation results by accessing the web application using a terminal. The web application framework used is Django or Flask.

[0311] As a specific example, when a user requests a simulation of a new marketing project, the server retrieves member A's skill data and the project's requirements data from the database and compares them using Python. Then, it inputs a prompt statement into the generative AI model, obtains the simulation results, and displays them to the user. In this way, the user can specifically check the project's success probability and required resources. The flow of the identification process in Example 3 will be explained using Figure 15.

[0312] Step 1:

[0313] A user requests a simulation of a project.

[0314] A user accesses a web application using a terminal and requests a simulation of a specific project. As input, they provide details of the project (e.g., a new marketing project). As output, the request is sent to the server.

[0315] Step 2:

[0316] The server retrieves the member's skill data.

[0317] The server retrieves the skill data of the members participating in the project from the database. As input, it uses the member's ID and project details. As output, it retrieves the member's skill data (e.g., marketing strategy, data analysis, advertising operations).

[0318] Step 3:

[0319] The server retrieves the project requirements data.

[0320] The server also retrieves the project requirements data from the database. As input, it uses the project ID and details. As output, it gets the project requirements data (e.g. market research, targeting, advertising campaign design).

[0321] Step 4:

[0322] The server compares the skills data with the requirements data.

[0323] The server uses Python to compare the member's skill data with the project's requirement data. This comparison uses data processing libraries such as Pandas and NumPy. The acquired skill data and requirement data are used as input. The output is the match between the skills and requirements.

[0324] Step 5:

[0325] The server inputs a prompt sentence into the generative AI model.

[0326] The server inputs an appropriate prompt to the generative AI model (e.g., OpenAI's GPT-4). It uses skill data, requirement data, and fitness data as input. An example prompt is as follows:

[0327] Member A's marketing skills include: marketing strategy, data analysis, and advertising operations. The requirements for a new marketing project include: market research, targeting, and advertising campaign design. Simulate the probability of success and the resources required for this project.

[0328] As an output, the generative AI model provides simulation results.

[0329] Step 6:

[0330] The server retrieves the simulation results.

[0331] The server obtains the simulation results obtained from the generative AI model. As input, it uses the prompt sentence entered into the generative AI model. As output, it obtains the simulation results (e.g., the probability of project success, required resources).

[0332] Step 7:

[0333] The server displays the simulation results to the user.

[0334] The server displays the simulation results to the user through a web application. The simulation results obtained from the generative AI model are used as input. The simulation results are displayed on the user's device as output. The user can check the project's success probability and required resources on the device screen.

[0335] (Application example 3)

[0336] Next, a description will be given of 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 will be referred to as a "terminal."

[0337] Conventional project management systems lack the functionality to compare the skills of specific members with project requirements and, based on the results, simulate the probability of project success and the resources required. Furthermore, in factory project management, it is difficult to properly evaluate the skills of specific members or robots and form optimal teams. Therefore, there is a need for a system that can increase the probability of project success and achieve efficient resource allocation.

[0338] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0339] In this invention, the server includes a means for inputting personnel information, a means for inputting information such as experience, projects, specialties, qualifications, and areas of interest, an AI means for proposing a best mix team plan across organizations based on the input information, a means for utilizing the proposed team plan in team formation, human resource development, skill improvement, and recruitment, and a means for comparing the skills of specific members with the requirements of a project and simulating the probability of project success and the required resources based on the results. This makes it possible to properly evaluate the skills of specific members and robots and form optimal teams.

[0340] "Human resources information" refers to data about human resources within an organization, such as employee personal information, work history, skills, evaluations, and qualifications.

[0341] "Experienced measures" refer to specific initiatives and methodologies used in projects and work carried out in the past.

[0342] A "project" is a set of activities or tasks planned and executed to achieve a specific goal.

[0343] "Specialization" refers to having advanced knowledge and skills in a particular field or area.

[0344] "Qualification" refers to the official recognition or certification required to perform a particular job or function.

[0345] An "area of ​​interest" refers to a field or area in which an individual is particularly interested and wants to actively engage.

[0346] A "best mix team proposal" is a proposal for team composition that optimally combines the skills and experience of members from both inside and outside the organization.

[0347] "AI means" refers to a means of analyzing data using artificial intelligence technology to create optimal team formations and simulate projects.

[0348] "Team formation" refers to the selection and organization of the members needed to carry out a specific project or task.

[0349] "Human resource development" refers to education and training to improve employees' skills and abilities.

[0350] "Skill Up" refers to improving an individual's skills and abilities.

[0351] "Recruitment" refers to the process by which an organization selects and hires new talent.

[0352] "Project success probability" refers to the likelihood that a particular project will be completed as planned and achieve its goals.

[0353] "Resources" refers to the human resources, funds, equipment, time, and other resources required to carry out a project or task.

[0354] "Simulation" is a method for virtually recreating real-world projects and tasks and predicting their outcomes.

[0355] "In-factory project management" refers to the process of planning, executing, monitoring and evaluating projects carried out within a factory.

[0356] As an embodiment of the present invention, a system for supporting project management within a factory is constructed. A specific embodiment of the system is shown below.

[0357] System configuration

[0358] The system consists of the following main components:

[0359] 1. Server:

[0360] Database: Stores data such as personnel information, experience measures, project information, specialties, qualifications, and areas of interest.

[0361] AI module: Compares personnel information with project requirements and simulates optimal team composition and the probability of project success.

[0362] Simulation engine: Evaluates the skills of specific members and robots, and calculates the probability of project success and required resources.

[0363] 2. Terminal:

[0364] Smartphones: Used by factory managers and workers to access the system and check project progress and simulation results.

[0365] Tablet: Used to view and interact with detailed data on a larger screen.

[0366] Program processing

[0367] The server processes the data in the following steps:

[0368] 1. Data Collection and Storage:

[0369] Data such as personnel information, experience measures, project information, specialties, qualifications, areas of interest, etc. are stored in the database.

[0370] 2. Data Analysis:

[0371] Based on the collected data, the AI ​​module selects the most suitable members and robots for a specific project.

[0372] The simulation engine compares the skills of the selected members and robots with the project requirements and calculates the probability of success and the resources required.

[0373] 3. Displaying the results:

[0374] Simulation results are displayed to managers and workers via smartphones or tablets.

[0375] Hardware and software used

[0376] Hardware: Servers, smartphones, tablets

[0377] Software: Python, pandas, numpy, scikit-learn

[0378] Specific examples

[0379] For example, to simulate a project to launch a new product line, you might use a prompt like this:

[0380] Example prompt sentence:

[0381] Compare the skills of each robot against the project requirements to simulate the probability of success and the resources needed for a new product line launch project.

[0382] By inputting this prompt into a generative AI model, detailed simulation results can be obtained regarding the project's success probability and required resources.

[0383] As described above, this invention is a system that can increase the probability of project success by streamlining project management within a factory and appropriately evaluating the skills of specific members and robots.

[0384] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0385] Step 1:

[0386] The server collects data such as personnel information, experience measures, project information, specialties, qualifications, and areas of interest, and stores it in a database. Inputs include skill information for each employee and robot, past project data, and qualification information. Organizing this data and storing it in a database provides the basic data required for subsequent processing.

[0387] Step 2:

[0388] The server uses an AI module to analyze the collected data. Specifically, it compares the skills of each member or robot with the project requirements to select the most suitable members or robots for a particular project. The input includes the project requirements and the skill data of each member or robot. The AI ​​module compares this data and selects the most suitable members or robots. The output is a list of selected members or robots.

[0389] Step 3:

[0390] The server uses a simulation engine to calculate the probability of project success and the required resources based on the skills of the selected members and robots and the project requirements. The input includes a list of selected members and robots and the project requirements. The simulation engine calculates the success probability and required resources based on this data. The output is a detailed simulation result of the success probability and required resources.

[0391] Step 4:

[0392] The server sends the simulation results to smartphones or tablets and displays them to managers and workers. The input includes the simulation results. The device receives these results and displays them in a visually easy-to-understand format for the user. The output allows managers and workers to check the simulation results and use them to progress the project.

[0393] Step 5:

[0394] Using a smartphone or tablet, users monitor project progress based on simulation results and make adjustments as needed. Inputs include simulation results and actual project progress. Users can compare these data and make necessary adjustments to increase the project's chances of success. Outputs include the adjusted project plan and progress.

[0395] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0396] "Example 1"

[0397] As one embodiment of the present invention, a system incorporating an emotion engine is provided. This system recognizes a user's emotions and optimizes team composition based on the emotions. Specifically, the system includes an emotion recognition module for recognizing the user's emotions and a team optimization module for optimizing the team composition based on the recognized emotions. The emotion recognition module recognizes emotions from the user's facial expressions, tone of voice, choice of words, etc. The team optimization module optimizes the team composition taking the recognized emotions into consideration. For example, if it recognizes that a certain member is feeling stressed, it suggests measures such as adding another member to the team to reduce the burden on that member.

[0398] "Example 2"

[0399] Another embodiment of the present invention provides a system incorporating an emotion engine. This system recognizes a user's emotion and predicts the probability of project success based on the emotion. Specifically, the system includes an emotion recognition module for recognizing the user's emotion and a success probability prediction module for predicting the probability of project success based on the recognized emotion. The success probability prediction module predicts the probability of project success based on the recognized emotion and data from past projects. For example, if it is recognized that all team members are highly motivated, the system predicts that the probability of project success is high.

[0400] "Example 3"

[0401] As one embodiment of the present invention, a system incorporating an emotion engine is provided. This system recognizes a user's emotions and optimizes team composition based on the emotions. Specifically, the system includes an emotion recognition module for recognizing the user's emotions and a team optimization module for optimizing the team composition based on the recognized emotions. The emotion recognition module recognizes emotions from the user's facial expressions, tone of voice, choice of words, etc. The team optimization module optimizes the team composition taking the recognized emotions into consideration. For example, if it recognizes that a certain member is feeling stressed, it suggests measures such as adding another member to the team to reduce the burden on that member.

[0402] The processing flow of each embodiment will be described below.

[0403] "Example 1"

[0404] Step 1: The emotion recognition module is activated to recognize emotions from the user's facial expressions, tone of voice, choice of words, etc.

[0405] Step 2: The emotion information recognized by the emotion recognition module is sent to the team optimization module.

[0406] Step 3: The team optimization module optimizes the team composition taking into account the transmitted emotional information.

[0407] Step 4: For example, if you recognize that a member is feeling stressed, suggest measures to alleviate that member's burden, such as adding another member to the team.

[0408] "Example 2"

[0409] Step 1: The emotion recognition module is activated to recognize emotions from the user's facial expressions, tone of voice, choice of words, etc.

[0410] Step 2: The emotion information recognized by the emotion recognition module is sent to the success probability prediction module.

[0411] Step 3: The success probability prediction module predicts the success probability of the project based on the transmitted emotional information and data from past projects.

[0412] Step 4: For example, if you perceive that all team members are highly motivated, you predict that the project has a high probability of success.

[0413] Example 1

[0414] Next, a description will be given of 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."

[0415] Conventional team formation systems have difficulty forming optimal teams based on the skills and experience of their members, and do not take into account the emotional state of the members. This leads to problems such as reduced project efficiency and lower member satisfaction. Furthermore, they lack simulation functionality for selecting the optimal team members for a specific project.

[0416] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0417] In this invention, the server includes: a means for inputting personnel information; a means for inputting information such as experience, projects, specialties, qualifications, and areas of interest; an artificial intelligence means for proposing a best-mix team plan across organizations based on the input information; a means for utilizing the proposed team plan in team formation, human resource development, skill improvement, and recruitment; an emotion recognition means for recognizing the user's emotions; and a means for optimizing team composition based on the recognized emotions. This enables optimal team formation based on the skills and experience of members, and further allows optimization taking into account the members' emotional states, thereby improving project efficiency and member satisfaction. A simulation function is also provided for selecting the optimal members for a specific project.

[0418] "Personnel information" refers to information about individuals, such as an employee's name, position, work history, evaluation, skills, and qualifications.

[0419] The "experience measure" is information indicating the experience and achievements of an employee in projects or work that the employee has participated in in the past.

[0420] A "project" is a set of activities or tasks planned and carried out within an organization to achieve a specific goal.

[0421] "Specialty" refers to the advanced knowledge and skills an employee has in a particular field or technology.

[0422] "Qualification" refers to the official recognition or certification required for an employee to perform a particular job or function.

[0423] "Areas of interest" refers to areas or topics that employees are personally interested in and would like to learn or work on.

[0424] "Artificial intelligence means" refers to algorithms or models that analyze input data and derive optimal results based on a specific purpose.

[0425] "Emotion recognition means" refers to technologies and modules that analyze and identify emotions from a user's facial expressions, tone of voice, choice of words, etc.

[0426] "Team composition optimization" refers to algorithms or processes for optimizing the selection and placement of team members based on perceived sentiment and other data.

[0427] This invention is a system that organizes optimal teams based on information provided by users, such as personnel information, experience, projects, specialties, qualifications, and areas of interest. The system operates in cooperation with three parties: a server, a terminal, and a user.

[0428] The server provides a web interface for inputting user-provided information. Through a web browser, the user inputs information such as the project name, required skills, member experience, specialty, qualifications, and areas of interest. For example, the user inputs members with the skills of "data analysis," "project management," and "software development" for "Project B."

[0429] The server stores the input information in a database (e.g., MySQL or PostgreSQL). The database stores detailed information about each member, such as their skills, experience, and qualifications. The server then analyzes the information stored in the database using a generative AI model (e.g., OpenAI's GPT-4). The AI ​​model runs an algorithm based on the input information to select the best members for the project.

[0430] Based on the analysis results of the AI ​​model, the server generates the optimal team member combination for a specific project. For example, for Project B, it proposes a combination of a data scientist, a project manager, and a software engineer.

[0431] Furthermore, the server uses an emotion recognition module (for example, Microsoft® Azure® Emotion API) to recognize the user's emotions. It analyzes data such as facial expressions, tone of voice, and word choice provided by the user via the webcam or microphone. The server optimizes team composition based on the recognized emotions. For example, if it recognizes that a certain member is feeling stressed, it will suggest measures such as adding another member to reduce that member's burden.

[0432] The server presents the optimized team proposal to the user, who can review the proposed team proposal through a web interface and make any necessary modifications or approvals.

[0433] For example, if a user is assembling a team for Project B, they enter the following information:

[0434] Project Name: Project B

[0435] Required skills: Data analysis, project management, software development

[0436] Member experience: 5+ years of data analysis experience, 3+ years of project management experience, 2+ years of software development experience

[0437] The server stores this information in a database, and the AI ​​analyzes it. The AI ​​selects the most suitable members and proposes the following team proposals:

[0438] Data Scientist: Taro Tanaka (10 years of data analysis experience)

[0439] Project Manager: Hanako Suzuki (5 years of project management experience)

[0440] Software Engineer: Jiro Sato (3 years of software development experience)

[0441] Examples of prompts include:

[0442] "For Project B, select the best team members with skills in data analysis, project management, and software development. Also consider the number of years of experience each team member has."

[0443] In this way, the server, terminals, and users work together to operate the system.

[0444] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0445] Step 1:

[0446] The user enters information

[0447] The user opens a web browser and accesses the system's login page. After logging in, they enter the required information into the project information input form and click the "Submit" button. The information entered includes the project name, required skills, member experience, specialization, qualifications, and areas of interest. The input data is sent to the server.

[0448] Step 2:

[0449] The server stores the information in a database

[0450] The server receives the information sent by the user and stores it in the database. Specifically, it executes SQL queries to insert project information and member information into the database. The input data is saved in the database.

[0451] Step 3:

[0452] The server analyzes the data using an AI model

[0453] The server retrieves the necessary information from the database and inputs it into the generative AI model. The AI ​​model performs analysis to select the best members for the project. Specifically, it calculates the optimal combination of members based on the input skills and experience. The input data is sent to the AI ​​model, and a list of the best members is obtained as output data.

[0454] Step 4:

[0455] The server generates team proposals

[0456] The server generates the optimal team member combination for a specific project based on the analysis results of the AI ​​model. For example, it proposes a combination of data scientists, project managers, and software engineers for Project B. The input data is the output data of the AI ​​model, and the proposed team is generated as output data.

[0457] Step 5:

[0458] The server recognizes emotions using an emotion engine

[0459] The server inputs data acquired from the user's webcam and microphone into the emotion recognition module. The module analyzes the user's facial expressions and tone of voice to identify emotions. Specifically, it uses image analysis and voice analysis algorithms to determine the user's emotional state. The input data is from the webcam and microphone, and the output data is the recognized emotion.

[0460] Step 6:

[0461] Server optimizes teams based on emotions

[0462] The server optimizes the team composition based on the recognized emotions. For example, it suggests additional members to reduce the burden on members who are feeling stressed. Specifically, it rearranges or adds team members by taking the emotional data into consideration. The input data is the recognized emotional data, and the output data is an optimized team proposal.

[0463] Step 7:

[0464] The server presents the optimized team proposal to the user.

[0465] The server presents the optimized team proposal to the user, who can then review the proposed team proposal through a web interface and make any necessary modifications or approvals. The input data is the optimized team proposal, and the output data is user feedback.

[0466] (Application example 1)

[0467] Next, a description will be given of Application Example 1 of Embodiment 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."

[0468] Conventional team formation systems can propose optimal teams based on personnel and skill information, but they do not consider the robot's operating status, maintenance history, or stress recognition using an emotion engine when forming teams. This makes it difficult to form optimal robot teams to maximize work efficiency within a factory. Furthermore, because the robot's stress level is not taken into account, there is a risk of reduced operational efficiency.

[0469] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0470] In this invention, the server includes means for inputting personnel information, means for inputting information such as experience, projects, specialties, qualifications, and areas of interest, means for proposing a best mix team plan across organizations based on the input information, means for inputting information such as robot skills, experience, operation status, and maintenance history, means for recognizing stress from the robot's operation status and error frequency using an emotion engine, and means for optimizing team formation based on the recognized stress information. This maximizes work efficiency in the factory and enables optimal team formation taking into account the robot's stress level.

[0471] "Personnel information" refers to basic information about employees, such as their names, ages, job titles, work histories, and evaluation results.

[0472] "Experience measures" are information about an employee's experience, such as projects and tasks they have participated in in the past, skills and qualifications they have acquired, and training they have received.

[0473] A "project" is a set of activities or tasks planned and carried out within an organization to achieve a specific purpose.

[0474] "Specialty" refers to the specialized knowledge or skills an employee has in a particular field or technology.

[0475] "Qualification" refers to the certification or certificate required for an employee to perform a particular job or function.

[0476] "Areas of interest" refers to areas or topics that employees have a personal interest in.

[0477] "AI means" refers to a means of analyzing data using artificial intelligence technology and making optimal team formations and proposals.

[0478] An "emotion engine" is a technology that recognizes the emotions of users and robots and responds appropriately based on those emotions.

[0479] "Operation status" refers to information such as the actual operating state of a robot or machine, its operating time, and its operating rate.

[0480] "Maintenance history" is a record of the maintenance, inspections, and repairs that a robot or machine has undergone in the past.

[0481] "Stress" refers to the burden or pressure that robots or machines experience due to excessive load or the frequency of errors.

[0482] "Team formation" refers to selecting the best members to form a team for a specific purpose or project.

[0483] The system for implementing this invention operates in cooperation with a server, a terminal, and a user. The server has AI means for analyzing information stored in a database, such as personnel information, experience measures, projects, specialties, qualifications, and areas of interest, and proposing optimal team composition. The server also stores information on robots' skills, experience, operating status, and maintenance history in the database, and is equipped with means for recognizing stress levels based on the robots' operating status and error frequency using an emotion engine. This allows for optimal team composition based on the recognized stress information.

[0484] The server implements AI methods using programming languages ​​such as Python and R, and uses libraries such as Pandas and Scikit-learn for data analysis. The emotion engine uses emotion recognition software such as EmotionEngine. This allows the server to retrieve information from the database, perform clustering and emotion recognition, and propose optimal team formations.

[0485] The terminals can be smartphones, tablets, factory management systems, etc., and display the team formations proposed by the server, allowing users to confirm and operate them. The terminals communicate with the server via a web browser or dedicated application, obtaining and updating information in real time.

[0486] Users, such as factory managers and project managers, use their terminals to check the team composition proposed by the server, and make any necessary corrections or approvals. Based on the proposed team composition, users instruct the actual work and monitor the robots' operating status and stress levels.

[0487] For example, the following prompts can be fed to a generative AI model:

[0488] "Please propose the optimal robot team based on the skill level, experience, maintenance history, error rate, and downtime data of the robots in the factory. In particular, please consider the stress level of robots with high error rates and downtime, and propose measures to reduce the burden."

[0489] Using this prompt, the generative AI model can generate specific suggestions for optimizing the robot team in the factory.

[0490] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0491] Step 1:

[0492] The server retrieves information from the database, such as personnel information, experience measures, projects, specialties, qualifications, areas of interest, robot skills, experience, operating status, and maintenance history. The input is various information stored in the database, and the output is the dataset required for analysis. Specifically, it extracts the required information from the database using SQL queries.

[0493] Step 2:

[0494] The server uses AI techniques to perform clustering based on the acquired data. The input is the dataset acquired in step 1, and the output is the cluster information for each robot. Specifically, the server preprocesses the data using the Pandas library and applies the KMeans clustering algorithm from Scikit-learn.

[0495] Step 3:

[0496] The server uses an emotion engine to recognize stress from the robot's operating status and error frequency. The input is the operating status and error frequency data obtained in step 1, and the output is the stress level of each robot. The specific operation is to calculate the stress level using the Emotion Engine.

[0497] Step 4:

[0498] The server proposes optimal team composition based on the cluster information and stress levels. The input is the cluster information obtained in step 2 and the stress levels obtained in step 3, and the output is the optimal team composition proposal. Specifically, the server uses an AI algorithm to optimize the team composition.

[0499] Step 5:

[0500] The server sends the optimal team formation plan to the terminal. The input is the team formation plan obtained in step 4, and the output is the team formation plan displayed on the terminal. Specifically, the server sends data to the terminal using an HTTP request.

[0501] Step 6:

[0502] The terminal displays the team composition proposal received from the server to the user. The input is the team composition proposal sent from the server in step 5, and the output is a screen display that the user can check. Specifically, the data is displayed using a web browser or a dedicated application.

[0503] Step 7:

[0504] The user checks the proposed team composition through the terminal and modifies or approves it as necessary. The input is the proposed team composition displayed in step 6, and the output is the modified or approved proposed team composition. Specific operations are performed through the user interface.

[0505] Step 8:

[0506] The server receives corrections and approvals from the user and finalizes the team composition. The input is the correction or approval information sent by the user in step 7, and the output is the finalized team composition proposal. Specifically, the server saves the final team composition proposal in the database.

[0507] Example 2

[0508] Next, a description will be given of 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 will be referred to as a "terminal."

[0509] Conventional team formation systems have the problem that it is difficult to select the most suitable team members for the project requirements, and they are unable to predict the probability of project success taking into account the emotions and motivation of team members. Therefore, in order to improve the success rate of projects, a system that combines more advanced team formation and emotion recognition is needed.

[0510] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0511] In this invention, the server includes means for inputting personnel information, means for inputting information such as experience, projects, specialties, qualifications, and areas of interest, artificial intelligence means for proposing a best mix team plan across organizations based on the input information, means for utilizing the proposed team plan in team formation, human resource development, skill improvement, and recruitment, emotion recognition means for recognizing user emotions, and success probability prediction means for predicting the probability of project success based on the recognized emotions. This makes it possible to form a team optimal for project requirements and further predict the probability of project success taking into account the emotions of team members.

[0512] "Human Resources Information" refers to detailed information about employees, such as their skill sets, years of experience, qualifications, and past project history.

[0513] "Experience measures" are measures aimed at improving the experience and skills that employees have gained through projects and work they have previously participated in.

[0514] A "project" is a set of tasks or activities organized to achieve a specific goal.

[0515] "Specialty" refers to having advanced knowledge and skills in a particular field or technology.

[0516] A "qualification" is a formal recognition or certification required to perform a particular job or function.

[0517] "Areas of interest" are areas or topics that employees are personally interested in and would like to learn more about.

[0518] "Artificial intelligence means" are techniques or algorithms that use machine learning or data analysis to automatically perform specific tasks.

[0519] "Emotion recognition means" refers to technology or modules for analyzing and recognizing emotions from a user's facial expressions, voice, etc.

[0520] A "success probability prediction method" is a technology or algorithm for predicting the success probability of a specific project based on past data and current circumstances.

[0521] This invention is a system that proposes the optimal team for a project and predicts the probability of success of the project using an emotion engine. This system operates in cooperation with three parties: a server, a terminal, and a user.

[0522] System configuration

[0523] The server uses the following hardware and software:

[0524] Hardware: High-performance processor, memory, and storage

[0525] Software: Python, TENSORFLOW (registered trademark), database management system

[0526] The terminal uses the following hardware and software:

[0527] Hardware: Camera, microphone, display

[0528] Software: OpenCV, speech recognition software, user interface

[0529] The user is responsible for inputting project requirements and sentiment data.

[0530] Program processing

[0531] The server first receives the project requirements input by the user, including the required skill set, years of experience, project duration, etc. The server then collects employee skill sets and past project experience from the company's database, which is obtained from employee resumes and past project reports.

[0532] Based on the collected data, the server uses TensorFlow to select the optimal team. This AI model compares the project requirements with the employee skill sets and calculates the optimal team combination. The calculation results are sent to the device and displayed to the user.

[0533] Examples:

[0534] Suppose a new software development project is being started. This project requires programming skills in Java and Python with at least five years of experience. The server searches the employee database for members who meet these criteria and suggests the best team. The terminal screen displays "Recommended team members: Taro Tanaka (Java, 7 years), Hanako Suzuki (Python, 6 years)."

[0535] Example prompt sentence:

[0536] "For a new software development project, select someone with Java and Python skills and at least 5 years of experience."

[0537] The device then collects the user's emotional data. It uses a camera and microphone to capture the user's facial expressions and voice in real time. The collected data is analyzed using OpenCV and speech recognition software. The analysis results are then sent to the server.

[0538] The server uses the received emotion data to predict the success probability of the project using a success probability prediction module. This module compares past project data with the current emotion data to calculate the success probability. The calculation result is sent to the terminal and displayed to the user.

[0539] Examples:

[0540] If all team members are perceived to be highly motivated, the server predicts a high probability of success for the project. Conversely, if many team members are feeling stressed, it predicts a low probability of success. The device screen displays "Current project's success probability: 80%."

[0541] Example prompt sentence:

[0542] "Predict the probability of project success based on current team member sentiment data."

[0543] In this way, the system can assemble a team that best suits the project requirements and also predict the probability of project success by taking into account the emotions of team members.

[0544] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0545] Step 1:

[0546] Entering project requirements

[0547] The user inputs the project requirements into the terminal.

[0548] Inputs: Required skill set, years of experience, project duration, etc.

[0549] Specific operation: The user enters "Java and Python skills required, member with 5+ years of experience" into the terminal form.

[0550] Output: The entered project requirements data.

[0551] Step 2:

[0552] Collecting personnel information

[0553] The server collects employee skill sets and past project experience from the company's database.

[0554] Input: Project requirements data.

[0555] What happens: The server queries the database to get a list of employees who have the skills "Java" and "Python" and who have "5+ years of experience."

[0556] Output: Collected employee skill sets and experience data.

[0557] Step 3:

[0558] Selecting the best team using AI models

[0559] The server inputs the collected personnel information and project requirements into an AI model to select the optimal team.

[0560] Inputs: Employee skill sets and experience data, project requirement data.

[0561] Specific operation: The server inputs data into the TensorFlow model and calculates the optimal team member combination.

[0562] Output: A list of optimal team members.

[0563] Step 4:

[0564] View team suggestions

[0565] The terminal displays the optimum team proposal sent from the server to the user.

[0566] Input: A list of suitable team members.

[0567] Specific operation: The device screen will display "Recommended team members: Tanaka Taro (Java, 7th year), Suzuki Hanako (Python, 6th year)."

[0568] Output: The team proposals displayed to the user.

[0569] Step 5:

[0570] Collecting Emotional Data

[0571] The device collects the user's facial expressions and voice through a camera and microphone.

[0572] Input: User's facial expression data, voice data.

[0573] Specific operation: The device's camera captures the user's face and the microphone records the user's voice.

[0574] Output: Collected emotion data.

[0575] Step 6:

[0576] Emotional Data Analysis

[0577] The terminal inputs the collected emotion data into an emotion recognition module and analyzes the user's emotions.

[0578] Input: Collected emotion data.

[0579] Specific operation: The device analyzes the facial image captured by the device using OpenCV and recognizes it as "high motivation."

[0580] Output: Parsed emotion data.

[0581] Step 7:

[0582] Predicting the probability of success

[0583] The server predicts the success probability of the project based on the analyzed emotion data using a success probability prediction module.

[0584] Input: Parsed sentiment data, past project data.

[0585] Specific operation: The server inputs emotional data and past project data and predicts an "80% chance of success."

[0586] Output: Predicted probability of success.

[0587] Step 8:

[0588] Displaying success probability

[0589] The terminal displays the success probability sent from the server to the user.

[0590] Input: Predicted probability of success.

[0591] Specific operation: The device screen will display "Current project success probability: 80%."

[0592] Output: Probability of success displayed to the user.

[0593] (Application example 2)

[0594] Next, a description will be given of 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 will be referred to as a "terminal."

[0595] With conventional project management systems, it was difficult to form appropriate teams and predict the probability of project success. Furthermore, there was a lack of real-time project management within the factory and a means to grasp the emotional state of team members, which led to problems with project efficiency and success rates. This often resulted in project progress being delayed and results not being achieved as expected.

[0596] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0597] In this invention, the server includes a means for inputting personnel information, a means for inputting information such as experience, projects, specialties, qualifications, and areas of interest, an AI means for proposing a best-mix team plan across organizations based on the input information, a means for utilizing the proposed team plan for team formation, human resource development, skill improvement, and recruitment, an emotion recognition module for recognizing a user's emotion, a success probability prediction module for predicting the probability of project success based on the recognized emotion, and a smart glasses application for supporting project management within a factory. This enables appropriate team formation and prediction of the probability of project success, enabling real-time project management within a factory and understanding the emotional states of team members.

[0598] "Human resources information" refers to information such as employee skills, experience, qualifications, position, and evaluations.

[0599] "Experienced measures" refers to information on measures and initiatives implemented in past projects and business operations.

[0600] A "project" is a set of activities or tasks planned and carried out to achieve a specific purpose.

[0601] "Specialty" refers to advanced knowledge and skills in a particular field or technology.

[0602] "Qualification" refers to the certification or certificate required to perform a particular job or function.

[0603] "Areas of interest" refers to areas or themes that employees are interested in and want to actively work on.

[0604] "AI means" refers to a system that uses artificial intelligence technology to analyze data and predict optimal team composition and the probability of project success.

[0605] An "emotion recognition module" refers to software or hardware for recognizing emotions from a user's facial expressions, voice, etc.

[0606] "Success Probability Prediction Module" refers to software or hardware for predicting the probability of project success based on perceived sentiment and past data.

[0607] "Smart glasses application" refers to software that is installed on smart glasses and is used to manage projects within factories and display the emotional state of team members in real time.

[0608] To implement this invention, the following hardware and software are required: Smart glasses equipped with a camera and a display are required for the hardware, and OpenCV, EmotionRecognizer, TeamOptimizer, and SuccessPredictor are required for the software.

[0609] The server first acquires video from the camera. The acquired video is processed in real time using OpenCV. Next, the EmotionRecognizer is used to recognize the user's emotions. This emotion recognition module extracts emotions from the user's facial expressions and voice, and sends them as data to the server.

[0610] Based on the received emotion data, the server uses TeamOptimizer to propose the optimal team. TeamOptimizer analyzes information such as employee personnel information, experience, projects, specialties, qualifications, and areas of interest to form the optimal team for the project.

[0611] Furthermore, the server uses SuccessPredictor to predict the success probability of the project based on the recognized emotions and past project data. The success probability prediction module receives emotion data and team composition data as input and calculates the success probability of the project.

[0612] These results are displayed in real time on the smart glasses display, allowing users to check the optimal team composition and the probability of project success through the smart glasses.

[0613] As a concrete example, consider a project to launch a new product line in a factory. For this project, members with the appropriate skills are selected, and their emotional states are monitored in real time to predict the probability of success. This information is provided to factory managers through smart glasses, enabling them to efficiently manage the progress of the project.

[0614] An example of a prompt to input to a generative AI model is as follows:

[0615] For a new product line launch project, select members with the appropriate skills, and develop an application that monitors their emotional state in real time to predict the probability of success. The hardware used is smart glasses, and the software used is OpenCV, EmotionRecognizer, TeamOptimizer, and SuccessPredictor.

[0616] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0617] Step 1:

[0618] The server acquires video from the camera of the smart glasses. The input is the camera image, and the output is real-time video data. Specifically, it uses OpenCV to capture video from the camera and processes each frame.

[0619] Step 2:

[0620] The server inputs the acquired video data into EmotionRecognizer to recognize the user's emotions. The input is video data and the output is emotional data. Specifically, EmotionRecognizer analyzes the user's facial expressions and voice from the video data to identify their emotions.

[0621] Step 3:

[0622] The server uses TeamOptimizer to propose the optimal team based on the recognized emotion data. The input is emotion data and information such as personnel information, experience, projects, specialties, qualifications, and areas of interest, and the output is optimal team composition data. Specifically, TeamOptimizer analyzes this data and selects the best members for the project.

[0623] Step 4:

[0624] The server inputs the proposed team composition data and emotion data into SuccessPredictor to predict the success probability of the project. The input is team composition data and emotion data, and the output is success probability data. Specifically, SuccessPredictor calculates the success probability based on past project data and current emotion data.

[0625] Step 5:

[0626] The server displays the success probability data and team composition data on the smart glasses display. The input is the success probability data and team composition data, and the output is the information displayed on the display. Specifically, the optimal team composition and project success probability are displayed in real time on the smart glasses display so that the user can check them.

[0627] Example 3

[0628] Next, a description will be given of a third embodiment of the third embodiment. 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."

[0629] Conventional team formation systems have the problem of being difficult to form optimal teams that take into account not only the skills of the members and the requirements of the project, but also the emotions of the users. Furthermore, it is not possible to fully simulate a project in a specific field with specific members, making it difficult to predict the probability of project success and the resources required. This has led to issues such as delays in project progress and increased burdens on members.

[0630] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0631] In this invention, the server includes means for inputting personnel information, means for inputting information such as experience, projects, specialties, qualifications, and areas of interest, artificial intelligence means for proposing a best mix team plan across organizations based on the input information, means for utilizing the proposed team plan in team formation, human resource development, skill improvement, and recruitment, means for enabling a simulation of a project in a specific field with specific members, and means for recognizing user emotions and optimizing team composition based on the emotions. This makes it possible to predict the success rate of a project and the required resources, and further realizes optimal team formation taking user emotions into consideration.

[0632] "Human resources information" refers to information such as employee skills, experience, qualifications, position, and evaluations.

[0633] "Experienced measures" refer to specific measures and initiatives in projects or work in which an employee has been involved in the past.

[0634] A "project" is a set of activities planned and carried out within an organization to achieve a specific goal.

[0635] "Specialty" refers to a field or skill in which an employee is particularly skilled.

[0636] "Qualification" refers to any official certification or certificate obtained by an employee.

[0637] "Areas of interest" refers to areas or topics that an employee is personally interested in.

[0638] "Artificial intelligence means" refers to technology that uses machine learning and data analysis to create optimal team formation and project simulations based on input information.

[0639] "Team formation" refers to selecting and organizing the best members to carry out a specific project or task.

[0640] "Human resource development" refers to education and training to improve employees' skills and abilities.

[0641] "Skill improvement" refers to efforts to improve employees' expertise and skills.

[0642] "Recruitment" refers to the process of selecting and bringing new employees into an organization.

[0643] "Simulation" refers to a virtual experiment to predict the progress and results of a project under specific conditions.

[0644] "Emotion recognition" refers to technology that analyzes and recognizes emotions from a user's facial expressions, tone of voice, choice of words, etc.

[0645] "Optimizing team composition" refers to determining the most effective team composition by taking into account the user's emotions and skills.

[0646] The present invention is a system that enables simulation of a project in a specific field with specific members, and further has the function of recognizing the user's emotions and optimizing the team composition based on those emotions.

[0647] System configuration

[0648] Hardware

[0649] This system consists of three main components: a server, a terminal, and a user. The server is a computer with high-performance computing capabilities, and the terminal is a device operated by the user (e.g., a PC or smartphone).

[0650] software

[0651] The system includes the following main software modules:

[0652] Artificial intelligence tools (AI models): Built using TensorFlow and PyTorch.

[0653] Emotion Recognition Module: Built using OpenCV and Google® Cloud Speech-to-Text.

[0654] Team Optimization Module: Built using Scikit-learn and Keras.

[0655] Program processing

[0656] Project Simulation Function

[0657] 1. A user enters the requirements for a new project into a terminal, for example, details of a marketing campaign.

[0658] 2. The server retrieves the member's skill data from the database, such as marketing experience, design skills, and data analysis ability.

[0659] 3. The server uses TensorFlow to compare the skills of members with the project requirements, running a skill matching algorithm to calculate the suitability of each member.

[0660] 4. The server simulates the project's success probability and required resources. For example, it calculates that the project has an 80% success rate and that an additional designer is required.

[0661] 5. The server sends the simulation results to the terminal.

[0662] 6. The device displays the simulation results to the user, for example, "The probability of project success is 80%. Additional designers are required."

[0663] Example prompt sentence:

[0664] "To launch a new marketing project, compare team members' skills with the project requirements and simulate the probability of success and resources required."

[0665] Emotion engine function

[0666] 1. The user talks to the device about the progress of the project and the stress they are feeling.

[0667] 2. The device uses OpenCV and Google Cloud Speech-to-Text to analyze the user's facial expressions, tone of voice, and word choice. For example, it detects if the user's face looks tired or if their voice tone is low.

[0668] 3. The device sends the analysis results to the server, such as "The user is feeling stressed."

[0669] 4. The server uses Scikit-learn to run a team optimization module based on the emotional data. Specifically, it performs optimization such as adding other members to reduce the burden on members who are feeling stressed.

[0670] 5. The server sends the optimized team configuration to the device.

[0671] 6. The device displays the optimized team configuration to the user, for example, "The new team configuration will include additional members for support."

[0672] Example prompt sentence:

[0673] "Recognize user emotions and optimize team composition to reduce the burden on stressed members."

[0674] summary

[0675] The present invention utilizes AI models and emotion recognition technology to simulate projects and optimize teams. Through specific processing steps, simulation results and optimized team composition are provided based on data entered by the user. This makes it possible to predict the success rate of a project and the resources required, and also realizes optimal team composition that takes user emotions into account. The flow of the specific processing in Example 3 is explained using Figure 21.

[0676] Project Simulation Function

[0677] Step 1:

[0678] A user enters the requirements for a new project into a terminal.

[0679] Input: Project details (e.g., marketing campaign goals, duration, budget, etc.)

[0680] Output: Project requirements data entered into the terminal

[0681] Specific operation: The user enters project details into the input form on the terminal and presses the submit button.

[0682] Step 2:

[0683] The server retrieves the member's skill data from the database.

[0684] Input: Project requirements data

[0685] Output: Member skill data (e.g., marketing experience, design skills, data analysis ability, etc.)

[0686] Specific operation: The server queries and retrieves relevant member skill data from the database based on the project requirements.

[0687] Step 3:

[0688] The server uses TensorFlow to compare members' skills with the project requirements.

[0689] Input: Member skill data, project requirement data

[0690] Output: Fitness data for each member

[0691] What happens: The server runs a skill matching algorithm to calculate how well each member's skills match the project requirements.

[0692] Step 4:

[0693] The server simulates the project's success rate and required resources.

[0694] Input: Fitness data for each member

[0695] Output: Probability of project success, required resource data

[0696] Specific operation: The server runs a simulation algorithm to calculate the probability of success of the project and the additional resources required.

[0697] Step 5:

[0698] The server transmits the simulation results to the terminal.

[0699] Input: Project success probability, required resource data

[0700] Output: Simulation results sent to the terminal

[0701] Specific operation: The server sends data using a communication protocol for sending the calculation results to the terminal.

[0702] Step 6:

[0703] The terminal displays the simulation results to the user.

[0704] Input: Simulation result data

[0705] Output: Simulation results displayed to the user

[0706] Specific operation: The device displays the simulation results received on the user interface, for example, "The probability of project success is 80%. Additional designers are required."

[0707] Emotion engine function

[0708] Step 1:

[0709] The user talks to the device about the progress of the project and the stress they are feeling.

[0710] Input: User's voice data, facial expression data

[0711] Output: Voice data and facial expression data input to the device

[0712] Specific operation: The user speaks into the device's microphone and camera, and the device captures the audio and video.

[0713] Step 2:

[0714] The device uses OpenCV and Google Cloud Speech-to-Text to analyze the user's facial expressions, tone of voice, and word choice.

[0715] Input: Voice data, facial expression data

[0716] Output: Parsed emotion data (e.g., stress, fatigue, joy, etc.)

[0717] Specific operation: The device converts voice data into text and analyzes facial expression data to recognize emotions.

[0718] Step 3:

[0719] The device sends the analysis results to the server.

[0720] Input: Parsed emotion data

[0721] Output: Emotion data sent to the server

[0722] Specific operation: The terminal transmits data using a communication protocol for transmitting analysis results to the server.

[0723] Step 4:

[0724] The server uses Scikit-learn to run the team optimization module based on the emotion data.

[0725] Input: Emotion data

[0726] Output: Optimized team composition data

[0727] Specific operation: Based on the emotional data, the server calculates the optimal team composition to reduce the burden on members who are feeling stressed.

[0728] Step 5:

[0729] The server sends the optimized team composition to the device.

[0730] Input: Optimized team composition data

[0731] Output: Optimized team composition data sent to the device

[0732] Specific operation: The server sends data using a communication protocol for sending the calculation results to the terminal.

[0733] Step 6:

[0734] The device displays the optimized team configuration to the user.

[0735] Input: Optimized team composition data

[0736] Output: The optimized team composition displayed to the user

[0737] Specific operation: The device displays the optimized team configuration received on the user interface, for example, "The new team configuration will include additional members for support."

[0738] (Application example 3)

[0739] Next, a description will be given of 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 will be referred to as a "terminal."

[0740] While traditional project management systems can organize teams based on the skills and experience of each member, they cannot take into account the emotions of each member or real-time situations, which can lead to reduced work efficiency and the probability of project success. Furthermore, it is difficult to properly distribute the workload among workers within the factory, which can lead to the accumulation of stress and fatigue. This can lead to delays in project progress and a decline in quality.

[0741] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0742] In this invention, the server includes: means for inputting personnel information; means for inputting information such as experience, projects, specialties, qualifications, and areas of interest; artificial intelligence means for proposing a best-mix team plan across organizations based on the input information; means for utilizing the proposed team plan in team formation, human resource development, skill improvement, and recruitment; an emotion recognition module for recognizing emotions; a team optimization module for optimizing team composition based on the recognized emotions; means for enabling a simulation of a project in a specific field with specific members; means for recognizing the skills and emotions of workers in a factory in real time and simulating the project success probability and required resources; and means for optimizing team composition based on the emotions of the workers to improve work efficiency. This enables optimal team formation taking into account the emotions of the members and real-time situations, thereby improving work efficiency and the project success probability.

[0743] "Human resources information" refers to information necessary for human resources management within an organization, such as an employee's personal information, work history, skills, qualifications, and evaluations.

[0744] "Experience measures" refer to the experience and achievements that employees have gained in projects and work they have participated in in the past.

[0745] A "project" is a set of activities or tasks planned and carried out to achieve a specific purpose.

[0746] "Specialty" refers to having advanced knowledge and skills in a particular field or technology.

[0747] "Qualification" refers to the certification or certificate required to perform a particular job or function.

[0748] "Areas of interest" refers to areas or topics that an employee is personally interested in.

[0749] "Artificial intelligence means" refers to a system that uses machine learning and data analysis to optimally organize teams and manage projects based on input information.

[0750] The "emotion recognition module" refers to a system that recognizes emotions from employees' facial expressions, tone of voice, choice of words, etc.

[0751] The "team optimization module" refers to a system for forming optimal teams based on recognized emotions and skill information.

[0752] "Means enabling simulation" refers to a system for predicting the probability of success and the resources required when a project in a specific field is carried out by specific members.

[0753] "Factory workers" refers to employees who work in factories, including those who perform tasks such as manufacturing and assembly.

[0754] "Real-time recognition" refers to instantly grasping and analyzing the current situation and condition.

[0755] "Project success probability" is a measure of the likelihood that a particular project will be completed as planned.

[0756] "Necessary resources" refers to the human resources, equipment, time, funds, etc. required to make the project successful.

[0757] "Work efficiency" is an index that indicates how much work can be done effectively within a certain amount of time.

[0758] A system for carrying out the present invention has the following configuration: a server includes means for inputting personnel information, means for inputting information such as experience measures, projects, specialties, qualifications, and areas of interest, artificial intelligence means for proposing a best-mix team plan across organizations based on the input information, means for utilizing the proposed team plan in team formation, human resource development, skill improvement, and recruitment, an emotion recognition module for recognizing emotions, a team optimization module for optimizing team composition based on the recognized emotions, means for enabling a simulation of a project in a specific field with specific members, means for recognizing the skills and emotions of workers in a factory in real time and simulating the probability of project success and the required resources, and means for optimizing team composition based on the emotions of the workers to improve work efficiency.

[0759] Hardware and software used

[0760] The server uses the following hardware and software:

[0761] Hardware: Factory robots, cameras, microphones

[0762] Software: Python, scikit-learn, TfidfVectorizer

[0763] Data processing and calculation

[0764] The server processes the data and performs calculations as follows:

[0765] 1. Emotion Recognition Module: Using a camera and microphone, the system captures a worker's facial expressions, tone of voice, and choice of words in real time to recognize their emotions. This is achieved through image processing and voice analysis technologies.

[0766] 2. Comparing skills and project requirements: Using TfidfVectorizer, we vectorize the skills of members and project requirements, and calculate the similarity using cosine_similarity. This allows us to evaluate how well the skills of members match the project requirements.

[0767] 3. Team optimization module: Forms optimal teams based on the perceived similarity of emotions and skills, and suggests measures such as adding additional members to relieve the burden on stressed workers.

[0768] Specific examples

[0769] For example, consider a project to set up a new assembly line in a factory. This project requires the skills of "welding" and "assembly." The server recognizes the skills and emotions of workers in real time and organizes the optimal team. For workers who are feeling stressed, the server suggests measures such as adding other members to reduce the burden.

[0770] Prompt Sentence Examples

[0771] Project requirements: "Welding, assembly"

[0772] Member information: [

[0773] {"name": "Worker A", "skills": "welding, assembly", "face_expression": "neutral", "voice_tone": "calm", "word_choice": "positive"},

[0774] {"name": "Worker B", "skills": "Painting, Quality Control", "face_expression": "stressed", "voice_tone": "tense", "word_choice": "negative"},

[0775] {"name": "Worker C", "skills": "Assembly, Inspection", "face_expression": "happy", "voice_tone": "cheerful", "word_choice": "positive"}

[0776] ]

[0777] By inputting this prompt into the generative AI model, we can obtain simulation results for optimal team composition.

[0778] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0779] Step 1:

[0780] The server uses a camera and microphone to capture the facial expressions, tone of voice, and word choice of factory workers in real time. The inputs are camera footage and audio data, and the output is sent to an emotion recognition module. Specifically, the camera captures the worker's face, and the microphone records the worker's voice.

[0781] Step 2:

[0782] The server uses an emotion recognition module to recognize the worker's emotions from the captured facial expressions, tone of voice, and choice of words. The input is the video and audio data acquired in step 1, and the output is the generated recognized emotion data. Specifically, it uses image processing and audio analysis technologies to classify the worker's emotions into categories such as "happy," "stressed," and "neutral."

[0783] Step 3:

[0784] The server acquires worker skill information and project requirement information. The inputs are the worker skill database and project requirement data, and the output is sent to the skill comparison module. Specifically, the server reads worker skill information from the database and acquires project requirement information.

[0785] Step 4:

[0786] The server uses TfidfVectorizer to vectorize the worker skills and project requirements, and calculates the similarity using cosine_similarity. The inputs are the skill information and project requirement information obtained in step 3, and the output is skill similarity data. Specifically, the skill information and project requirement information are vectorized as text data, and the similarity is calculated.

[0787] Step 5:

[0788] The server organizes an optimal team based on the recognized emotion data and skill similarity data. The inputs are the emotion data obtained in step 2 and the skill similarity data obtained in step 4, and the output is an optimized team organization proposal. Specifically, the server takes the emotion data into consideration and proposes measures such as adding other members to reduce the burden on workers who are feeling stressed.

[0789] Step 6:

[0790] The server sends the optimized team composition plan to the project management system and reflects it in the actual team composition. The input is the team composition plan generated in step 5, and the output is the team composition reflected in the project management system. Specifically, the generated team composition plan is sent to the project management system and reflected in the actual team composition.

[0791] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0792] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ) and other generative AIs. Data generation models 58

[0793] , obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in the data format of voice data, text data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0794] Another example of generative AI is Gemini (registered trademark) (Internet search engine). <url: https: gemini.google.com ?hl="ja">) are listed.

[0795] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0796] [Second embodiment]

[0797] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0798] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0799] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0800] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0801] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0802] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0803] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0804] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0805] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0806] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0807] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0808] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0809] "Example 1"

[0810] The system of the present invention has a means for inputting information such as personnel information, experience, projects, specialties, qualifications, and areas of interest. Specifically, this information is stored in a database and analyzed by AI. Based on this information, the AI ​​proposes a best-mix team proposal across organizations. For example, for a specific project, it selects members with the optimal skills and experience and proposes their combination.

[0811] "Example 2"

[0812] The system of the present invention also has the ability to propose teams suitable for specific projects. Specifically, the AI ​​compares project requirements with personnel information and proposes the optimal team composition. For example, for a new software development project, it selects members with the appropriate programming skills and experience and proposes their combination.

[0813] "Example 3"

[0814] Furthermore, the system of the present invention has a function that enables simulation of a project in a specific field with specific members. Specifically, the AI ​​compares the members' skills with the project requirements and performs a simulation based on the results. For example, if a specific member is to carry out a new marketing project, the AI ​​compares the member's marketing skills with the project requirements and simulates the project's success probability and required resources based on the results.

[0815] The processing flow of each embodiment will be described below.

[0816] "Example 1"

[0817] Step 1: Enter personnel information and experience, projects, specialties, qualifications, areas of interest, etc. into the database.

[0818] Step 2: AI analyzes this information and proposes the best mix of teams across the organization.

[0819] Step 3: Utilize the proposed team plan for team formation, human resource development, skill development, and recruitment. "Format Example 2"

[0820] Step 1: Define the requirements for your specific project.

[0821] Step 2: AI compares the project requirements with personnel information and suggests the optimal team composition.

[0822] Step 3: Apply the proposed team structure to the project.

[0823] "Example 3"

[0824] Step 1: Define a project with specific members and in a specific field.

[0825] Step 2: The AI ​​compares the skills of members with the project requirements and performs a simulation based on the results.

[0826] Step 3: Based on the simulation results, evaluate the probability of project success and the resources required.

[0827] Example 1

[0828] Next, a description will be given of 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 glasses 214 will be referred to as a "terminal."

[0829] With conventional personnel management systems, it was difficult to effectively utilize the skills and experience of individual employees to form optimal teams. Furthermore, there was a lack of objective criteria for selecting the best members for specific projects, making it difficult to improve the efficiency of the entire organization. Furthermore, there was a lack of concrete methods for utilizing the proposed team plans in actual team formation, human resource development, skill improvement, and recruitment.

[0830] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0831] In this invention, the server includes: a means for inputting personnel information; a means for inputting information such as experience, projects, specialties, qualifications, and areas of interest; a means for storing the input information in a database; a means for using a generative AI model to analyze the stored information; a means for inputting a prompt to the generative AI model to generate a cross-organizational best-mix team proposal; a means for presenting the generated team proposal to the user; and a means for utilizing the proposed team proposal in team formation, human resource development, skill improvement, and recruitment. This makes it possible to maximize the skills and experience of individual employees and select the optimal members for a specific project. Furthermore, the proposed team proposal can be utilized in specific personnel policies, improving the efficiency of the entire organization.

[0832] "Human resources information" refers to data such as an employee's basic information, work history, skills, evaluations, and qualifications.

[0833] "Experience measures" refer to the experience and achievements of employees in projects and work they have participated in in the past.

[0834] A "project" refers to a set of activities or tasks carried out within an organization to achieve a specific purpose.

[0835] "Specialty" refers to the specialized knowledge and skills an employee has in a particular field or technology.

[0836] "Qualification" refers to any official certification or certificate obtained by an employee.

[0837] "Areas of interest" refers to areas or topics in which employees have personal interests.

[0838] A "database" refers to a system that systematically organizes and stores information so that it can be searched and used as needed.

[0839] A "generative AI model" is a model that uses artificial intelligence to analyze data and perform specific tasks.

[0840] A "prompt" refers to an instruction or question input to a generative AI model.

[0841] A "best mix team proposal" refers to a proposal that proposes a combination of members with the optimal skills and experience for a specific project.

[0842] "User" refers to a person who uses the system to input information and receive results.

[0843] "Team formation" refers to the process of selecting the best members to form a team to achieve a specific purpose.

[0844] "Human resource development" refers to education and training to improve employees' skills and abilities.

[0845] "Skill improvement" refers to activities aimed at further enhancing employees' skills and knowledge.

[0846] "Recruitment" refers to the process of selecting and adding new employees to an organization.

[0847] The present invention is a system in which a server, a terminal, and a user work in cooperation with each other. A specific embodiment of this system will be described below.

[0848] Server Operation

[0849] The server receives information provided by users, such as personnel information, experience, projects, specialties, qualifications, and areas of interest. This information is sent in JSON format via HTTP requests. The server stores the received information in a relational database such as MySQL or PostgreSQL.

[0850] The server then uses a generative AI model to analyze the stored information. Specifically, it uses a Python API to call OpenAI's GPT-4 model and generate a prompt. By inputting the prompt into the generative AI model, it generates a best-mix team proposal across organizations.

[0851] The generated team proposals are sent from the server to the device as an HTTP response in JSON format, allowing the user to check the optimal team member combinations.

[0852] Device behavior

[0853] The terminal receives information entered by the user through an input form, such as personnel information, experience, projects, specialties, qualifications, and areas of interest. This information is collected using a form on the web browser and JavaScript.

[0854] The collected information is sent to the server in JSON format using an AJAX request. The best mix team proposal received from the server is analyzed using JavaScript and dynamically reflected in HTML, allowing users to view the team proposal on their device screen.

[0855] User Actions

[0856] Users use their terminals to enter information such as personnel information, experience, projects, specialties, qualifications, and areas of interest. Specifically, they enter the required information into a form on a web browser. Once the information is complete, the terminal sends it to the server.

[0857] After receiving the best mix team proposal from the server, the user can check the team proposal displayed on the device screen, select the optimal team members, and take specific actions to ensure the success of the project.

[0858] Specific examples

[0859] For example, suppose a user wants to select the best team members to start a new project. The user uses a terminal to enter the following information:

[0860] Project name: New product development project

[0861] Required skills: Machine learning, data analysis, project management

[0862] Project duration: 6 months

[0863] The server receives this information, stores it in a database, and then uses a generative AI model to select the best team members and propose a team plan like this:

[0864] Member 1: Machine learning expert with 5 years of experience

[0865] Member 2: Data analysis expert with 3 years of experience

[0866] Member 3: Project management expert with 10 years of experience

[0867] Prompt Sentence Examples

[0868] "Please suggest the best team members with machine learning, data analysis, and project management skills for a new product development project. The project will last six months."

[0869] In this way, users can easily select the most suitable team members.

[0870] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0871] Step 1:

[0872] Users use their devices to enter information such as personnel information, experience, projects, specialties, qualifications, and areas of interest. Specifically, they enter the required information into a form on a web browser. The entered information is converted into JSON format using JavaScript.

[0873] Input: Information entered by the user, such as personnel information, experience, projects, specialties, qualifications, and areas of interest

[0874] Output: JSON format data

[0875] Step 2:

[0876] The terminal sends the input information to the server. Specifically, it uses an AJAX request to send JSON format data to the server as an HTTP request.

[0877] Input: JSON format data

[0878] Output: HTTP request to the server

[0879] Step 3:

[0880] The server receives the information sent from the device. Specifically, it analyzes the JSON format data received through the HTTP request and extracts the necessary information.

[0881] Input: JSON format data received as an HTTP request

[0882] Output: Extracted information

[0883] Step 4:

[0884] The server stores the received information in a database. Specifically, it uses a relational database such as MySQL or PostgreSQL and stores the data using an INSERT statement.

[0885] Input: Extracted information

[0886] Output: Information stored in the database

[0887] Step 5:

[0888] The server then invokes a generative AI model to analyze the stored information. Specifically, it uses a Python API to invoke OpenAI's GPT-4 model and generate a prompt.

[0889] Input: Information stored in a database

[0890] Output: Generated prompt statement

[0891] Step 6:

[0892] The server inputs prompt statements into the generative AI model to generate a best-mix team proposal across organizations. Specifically, it analyzes the results returned by the generative AI model and creates a list of appropriate members.

[0893] Input: Generated prompt text

[0894] Output: Best Mix Team Proposal

[0895] Step 7:

[0896] The server sends the generated team proposals to the device, specifically returning the results in JSON format as an HTTP response.

[0897] Input: Best Mix Team Proposal

[0898] Output: JSON formatted data as an HTTP response to the terminal

[0899] Step 8:

[0900] The device displays the best mix team proposal received from the server to the user. Specifically, it parses the received JSON data using JavaScript and dynamically reflects it in HTML.

[0901] Input: JSON format data as an HTTP response from the server

[0902] Output: Team proposals displayed to the user

[0903] Step 9:

[0904] Users can review the team proposals displayed on their device screen, select the most suitable team members, and take concrete actions to ensure the project's success.

[0905] Input: Team proposal displayed on the terminal

[0906] Output: User confirmation and action

[0907] (Application example 1)

[0908] Next, a description will be given of 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 glasses 214 will be referred to as a "terminal."

[0909] In conventional factories, it was difficult to form optimal teams that took into account the skills and experience of workers, making it difficult to carry out work efficiently. Furthermore, there was no system for selecting the best workers for a specific project, which sometimes led to reduced work efficiency and project delays. This resulted in a decline in productivity throughout the factory and a loss of competitiveness.

[0910] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0911] In this invention, the server includes means for inputting personnel information, means for inputting information such as experience, projects, specialties, qualifications, and areas of interest, AI means for proposing a best mix team plan across organizations based on the input information, means for utilizing the proposed team plan in team formation, human resource development, skill improvement, and recruitment, and means for storing information such as the skills, experience, qualifications, and areas of interest of workers in the factory in a database and proposing the optimal work team for a specific task or project. This makes it possible to form the optimal work team in the factory, improving work efficiency and smooth project execution.

[0912] "Personnel information" refers to information about individuals, such as an employee's name, age, work history, skills, qualifications, and evaluations.

[0913] "Experience measures" refers to information that indicates the specific experience and achievements of an employee in projects or work that the employee has participated in in the past.

[0914] A "project" is a set of tasks or activities planned and carried out to achieve a specific purpose.

[0915] "Specialty" refers to the field, skill, or knowledge in which an employee is particularly skilled.

[0916] "Qualifications" refers to any official certifications, certificates, licenses, etc. that an employee has obtained.

[0917] "Areas of interest" refers to areas or topics that employees have a personal interest in.

[0918] "AI means" refers to systems and algorithms that use artificial intelligence technology to analyze data and make optimal team composition and proposals.

[0919] A "database" is a collection of information that is systematically organized and made available for efficient search and use.

[0920] A "work team" is a group of workers organized to accomplish a specific task or project.

[0921] "Team formation" is the process of selecting the best members to form a team for a specific purpose or project.

[0922] "Human resource development" refers to the activities of providing education and training to improve employees' skills and knowledge.

[0923] "Skill Up" refers to improving employees' skills and abilities.

[0924] "Recruitment" is the process of selecting and hiring new employees.

[0925] A system for carrying out this invention is configured as follows: The server includes means for inputting personnel information, means for inputting information such as experience measures, projects, specialties, qualifications, and areas of interest, AI means for proposing a best mix team plan across organizations based on the input information, means for utilizing the proposed team plan in team formation, human resource development, skill improvement, and recruitment, and means for storing information such as the skills, experience, qualifications, and areas of interest of factory workers in a database and proposing the optimal work team for a specific task or project.

[0926] The server runs the program using Python and uses SQLite as the database. The scikit-learn library is used for AI analysis. Specifically, worker information is stored in the database and the profiles are vectorized using a TF-IDF vectorizer. The cosine similarity between the project requirements and the worker profiles is calculated to suggest the optimal work team.

[0927] Users access the system using a smartphone or tablet and input the project requirements. The server then proposes the optimal work team based on the input requirements. For example, if the project requirements are "robotics, automation, and maintenance," the AI ​​will select the workers most suited to this.

[0928] An example prompt might be, "Enter 'Robotics, automation, maintenance' as your project requirements. Let the AI ​​suggest the best work team."

[0929] This system enables the optimal organization of work teams within the factory, improving work efficiency and ensuring smooth project execution.

[0930] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0931] Step 1:

[0932] Users access the system using a smartphone or tablet and enter project requirements.

[0933] Input: Project requirements (e.g., "Robotics, Automation, Maintenance")

[0934] Output: The input project requirements

[0935] Step 2:

[0936] The server receives the input project requirements and retrieves the worker information from the database.

[0937] Input: Project Requirements

[0938] Output: Worker information (e.g., skills, experience, qualifications, areas of interest)

[0939] Step 3:

[0940] The server vectorizes the worker information using a TF-IDF vectorizer.

[0941] Input: Worker information

[0942] Output: Vectorized worker profiles

[0943] Step 4:

[0944] The server vectorizes the project requirements and calculates the cosine similarity with the worker profiles.

[0945] Inputs: Vectorized project requirements, Vectorized worker profiles

[0946] Output: Cosine similarity score

[0947] Step 5:

[0948] The server selects the best working team based on the cosine similarity score.

[0949] Input: Cosine similarity score

[0950] Output: A list of optimal work team members

[0951] Step 6:

[0952] The server displays the optimal work team suggestions to the user.

[0953] Input: List of suitable work team members

[0954] Output: Optimal work team proposals displayed to the user

[0955] Step 7:

[0956] The user reviews the proposed work team and makes adjustments as needed.

[0957] Input: Optimal work team proposal

[0958] Output: Coordinated work team member list

[0959] In this way, the system proposes the optimal work team based on the project requirements entered by the user, and the user can confirm and adjust the proposal, resulting in efficient work team formation within the factory.

[0960] Example 2

[0961] Next, a description will be given of 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 glasses 214 will be referred to as a "terminal."

[0962] Conventional team formation systems have difficulty efficiently comparing project requirements with personnel information and proposing optimal team compositions. Furthermore, they have problems in that they are unable to perform simulations based on the proposed team compositions or perform advanced analysis using generative AI models.

[0963] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for inputting personnel information, means for inputting information such as experience, projects, specialties, qualifications, and areas of interest, artificial intelligence means for proposing a best-mix team plan across organizations based on the input information, means for utilizing the proposed team plan in team formation, human resource development, skill improvement, and recruitment, means for generating prompt statements based on project requirements and personnel information, means for inputting the generated prompt statements into a generative AI model to propose an optimal team composition, and means for displaying the proposed team composition. This makes it possible to efficiently propose a team composition optimal for project requirements and further perform simulations and advanced analyses based on the proposal.

[0964] "Human Resources Information" refers to information such as an employee's skill set, years of experience, qualifications, and past project history.

[0965] "Experience measures" refer to the content and results of the experience an employee has had in projects or work they have participated in in the past.

[0966] A "project" is a set of tasks or activities planned to achieve a specific purpose.

[0967] "Specialty" refers to a field or skill in which an employee is particularly skilled.

[0968] "Qualification" refers to any official certification or certificate obtained by an employee.

[0969] "Areas of interest" refers to areas or topics that employees are interested in.

[0970] "Artificial intelligence means" refers to algorithms and models that suggest optimal team compositions based on collected data.

[0971] A "prompt" refers to an instruction or question that is input into a generative AI model.

[0972] A "generative AI model" refers to an artificial intelligence model that suggests optimal team composition based on input prompt text.

[0973] "Team formation" refers to selecting the best members for a specific project and forming a team.

[0974] "Human resource development" refers to education and training to improve employees' skills and abilities.

[0975] "Skill improvement" refers to improving employees' skills and knowledge.

[0976] "Recruitment" refers to the process of selecting and hiring new employees.

[0977] The present invention is a system for proposing a team suitable for a specific project. A specific embodiment of this system will be described below.

[0978] First, a user accesses the system's web interface using a terminal and enters the project requirements, including the required programming language, years of experience, and other skills. For example, the user might enter requirements such as "Python, JavaScript, 5+ years of experience, database management, and cloud services experience."

[0979] Next, the server retrieves relevant personnel information from a database based on the project requirements entered by the user. The database stores each member's skill set, years of experience, past project history, and other information. The server connects to the MySQL database and retrieves the personnel information using an SQL query. For example, it executes a query such as "SELECT FROM HR INFORMATION WHERE SKILLS LIKE '%Python%' AND YEARS OF EXPERIENCE >= 5."

[0980] The server generates a prompt to be input to the generative AI model based on the acquired personnel information. This prompt contains detailed descriptions of the project requirements and the skills and experience of each member. For example, the following prompts can be generated:

[0981] Project requirements:

[0982] Programming languages: Python, JavaScript

[0983] Years of experience: 5 years or more

[0984] Other skills: Database management, cloud services experience

[0985] Personnel information:

[0986] Member A: Python (5 years), JavaScript (3 years), Database Management (2 years)

[0987] Member B: Python (6 years), JavaScript (5 years), Cloud Services (4 years)

[0988] Member C: Python (4 years), JavaScript (6 years), Database Management (5 years)

[0989] Please suggest the best team composition.

[0990] The server inputs the generated prompt to a generative AI model (e.g., OpenAI's GPT-4) via an API request. The generative AI model then proposes the optimal team composition based on the input prompt. For example, it returns a suggestion such as, "Member B and Member C are optimal."

[0991] Finally, the server displays the proposal received from the generative AI model on a web interface. The user can review the proposed team composition and modify or approve it as needed. For example, a message such as "Members B and C have been selected" may be displayed.

[0992] This system efficiently proposes the team composition that best suits the project requirements, and also enables simulations and advanced analysis based on those proposals.

[0993] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0994] Step 1:

[0995] A user accesses the system's web interface using a terminal and enters project requirements, including the required programming language, years of experience, and other skills. For example, a requirement might be "Python, JavaScript, 5+ years of experience, database management, and cloud service experience." The input data is then sent to the server.

[0996] Step 2:

[0997] The server receives project requirements submitted by users and retrieves the relevant personnel information from the database. The server connects to the MySQL database and retrieves the personnel information using an SQL query. For example, it executes a query such as "SELECT FROM HR INFORMATION WHERE SKILLS LIKE '%Python%' AND YEARS OF EXPERIENCE >= 5". The input is the project requirements and the output is the retrieved personnel information.

[0998] Step 3:

[0999] The server generates a prompt sentence to be input to the generative AI model based on the acquired personnel information. The server generates the prompt sentence using a Python script. For example, it generates the following prompt sentence:

[1000] Project requirements:

[1001] Programming languages: Python, JavaScript

[1002] Years of experience: 5 years or more

[1003] Other skills: Database management, cloud services experience

[1004] Personnel information:

[1005] Member A: Python (5 years), JavaScript (3 years), Database Management (2 years)

[1006] Member B: Python (6 years), JavaScript (5 years), Cloud Services (4 years)

[1007] Member C: Python (4 years), JavaScript (6 years), Database Management (5 years)

[1008] Please suggest the best team composition.

[1009] The input is the personnel information obtained and the output is the generated prompt sentence.

[1010] Step 4:

[1011] The server inputs the generated prompt to a generative AI model (for example, OpenAI's GPT-4) via an API request. The generative AI model then proposes the optimal team composition based on the input prompt. For example, it returns a suggestion such as "Member B and Member C are optimal." The input is the generated prompt, and the output is the suggestion from the generative AI model.

[1012] Step 5:

[1013] The server displays the proposal received from the generative AI model on a web interface. The user can review the proposed team composition and make any necessary modifications or approvals. For example, a message such as "Members B and C have been selected" is displayed. The input is the proposal from the generative AI model, and the output is the team composition displayed to the user.

[1014] (Application example 2)

[1015] Next, a description will be given of 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 glasses 214 will be referred to as a "terminal."

[1016] Previous systems only considered human resources when proposing a team suitable for a specific project, making it difficult to form an optimal team that took into account the skill sets and operating status of the machines and robots in the factory. Furthermore, the system lacked the functionality to automatically generate operating schedules for the proposed team, making efficient project management difficult.

[1017] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for inputting personnel information; means for inputting information such as experience, projects, specialties, qualifications, and areas of interest; AI means for proposing a best-mix team plan across organizations based on the input information; means for utilizing the proposed team plan in team formation, human resource development, skill improvement, and recruitment; means for managing the skill sets and operating status of each machine in the factory; means for inputting requirements for a new manufacturing project; means for AI to propose an optimal machine team; and means for automatically generating an operating schedule for the proposed team. This enables optimal team formation and efficient project management that takes into account both human and machine resources.

[1018] "Human Resources Information" refers to information such as an employee's skills, experience, qualifications, areas of expertise, and areas of interest.

[1019] "Experience measures" refer to the experience of projects and work that employees have previously participated in.

[1020] A "project" is a set of activities planned and carried out to achieve a specific purpose.

[1021] "Specialty" refers to advanced knowledge and skills in a particular field.

[1022] "Qualification" refers to the certification or attestation required to perform a particular job or function.

[1023] "Areas of interest" refers to areas or topics that an employee is personally interested in.

[1024] "Best Mix Team Proposal" refers to a plan that proposes the combination of members that best suits the project requirements.

[1025] "AI means" refers to a function that uses artificial intelligence to analyze data and propose optimal team composition and schedules.

[1026] "Team formation" refers to the process of selecting the best members for a particular project and building a team.

[1027] "Human resource development" refers to education and training to improve employees' skills and abilities.

[1028] "Skill Up" refers to improving employees' skills and knowledge.

[1029] "Recruitment" refers to the process of selecting and hiring new employees.

[1030] The "skill set of each machine in the factory" refers to the specific functions and capabilities of each machine or robot used in the factory.

[1031] "Operational status" refers to the current state in which a machine or robot is operating or is available for operation.

[1032] "New Manufacturing Project Requirements" refers to the conditions and specifications required for a new manufacturing project.

[1033] The "optimal machine team" refers to the combination of machines and robots that best meets the project requirements.

[1034] "Work schedule" refers to a plan showing when each member of the proposed team will be available.

[1035] A system for carrying out this invention has the following configuration: A server includes means for inputting personnel information, means for inputting information such as experience measures, projects, specialties, qualifications, and areas of interest, AI means for proposing a best mix team plan across organizations based on the input information, means for utilizing the proposed team plan in team formation, human resource development, skill improvement, and recruitment, means for managing the skill set and operating status of each machine in a factory, means for inputting requirements for a new manufacturing project, means for AI to propose an optimal machine team, and means for automatically generating an operating schedule for the proposed team.

[1036] Hardware and software used

[1037] Hardware: Servers, smartphones

[1038] Software: Python, scikit-learn, NumPy

[1039] Data processing and calculation

[1040] The server first inputs information such as personnel information, experience, projects, specialties, qualifications, and areas of interest into a database. Next, it collects data to manage the skill sets and operating status of each machine in the factory and inputs the requirements for a new manufacturing project. Based on this data, the AI ​​means proposes the optimal machine team. The AI ​​means uses scikit-learn's cosine_similarity to calculate the similarity between the project requirements and the machine skill sets and selects the optimal team. Furthermore, it processes the data using NumPy to automatically generate the operating schedule for the proposed team.

[1041] Specific examples

[1042] For example, if the requirements for a new manufacturing project are Skill A, Skill B, and Skill C, then Robot 1 in the factory has the skill set [1, 0, 1] and the available date is "2023-10-01", Robot 2 has the skill set [0, 1, 1] and the available date is "2023-10-05", and Robot 3 has the skill set [1, 1, 0] and the available date is "2023-10-03". In this case, the AI ​​tool will propose the optimal team based on this information and automatically generate an operating schedule.

[1043] Prompt Sentence Examples

[1044] A new manufacturing project requires skills A, B, and C. Please propose the optimal team taking into account the skill sets and operational status of the robots in the factory.

[1045] This enables optimal team formation and efficient project management that takes into account both human and machine resources.

[1046] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1047] Step 1:

[1048] The server inputs information such as personnel information and experience policies, projects, specialties, qualifications, areas of interest, etc. into the database, including employee skill sets, past project experience, etc. The input data is stored in the database for later processing.

[1049] Step 2:

[1050] The server collects data to manage the skill sets and operational status of each machine in the factory. Specifically, it inputs information such as the functions, capabilities, and available days of each machine or robot into a database. This data is used to optimally organize the machines into teams.

[1051] Step 3:

[1052] Users enter requirements for new manufacturing projects into the server, including the skills and capabilities needed, project start and finish dates, etc. The project requirements are then stored in a database.

[1053] Step 4:

[1054] The server processes the data to propose the optimal team based on the input project requirements and the personnel and machine information in the database. Specifically, it uses scikit-learn's cosine_similarity to calculate the similarity between the project requirements and the skill sets of each machine. Based on the calculation results, it selects the optimal machine team.

[1055] Step 5:

[1056] The server automatically generates a work schedule for the proposed team. Specifically, it uses NumPy to create a schedule based on the available days for the selected machines and robots. The generated schedule provides an optimal work plan between the start and end dates of the project.

[1057] Step 6:

[1058] The server presents the proposed team and work schedule to the user. The user reviews the proposed team composition and schedule, and makes any necessary modifications or approvals. The final team composition and schedule are finalized as the project execution plan.

[1059] In this way, the server achieves optimal team formation and efficient project management that takes into account both human and machine resources.

[1060] Example 3

[1061] Next, a description will be given of 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 glasses 214 will be referred to as a "terminal."

[1062] With conventional project management systems, it was difficult to properly match member skills with project requirements, making it impossible to accurately predict the probability of project success. Furthermore, the lack of functionality to simulate projects in specific fields with specific members made it difficult to allocate resources and evaluate the probability of success during the project planning stage. This hindered the efficient progress of projects and improved success rates.

[1063] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1064] In this invention, the server includes: a means for inputting personnel information; a means for inputting information such as experience, projects, specialties, qualifications, and areas of interest; an artificial intelligence means for proposing a best-mix team plan across organizations based on the input information; a means for utilizing the proposed team plan in team formation, human resource development, skill improvement, and recruitment; a means for acquiring skill data of specific members and project requirement data; a means for comparing the acquired skill data with the requirement data; a means for inputting prompts into the generative AI model to perform a simulation; and a means for displaying the simulation results to the user. This enables appropriate matching of member skills with project requirements and accurate prediction of the project's success probability. Furthermore, it is possible to simulate a project in a specific field with specific members, making it easier to allocate resources and evaluate the success probability during the project planning stage.

[1065] "Human Resources Information" is information about an employee, such as their skills, experience, qualifications, and areas of interest.

[1066] "Experienced measures" refers to information that refers to specific efforts and results in projects or tasks that have been implemented in the past.

[1067] A "project" is a set of activities or tasks planned and carried out to achieve a specific purpose.

[1068] "Specialization" refers to having advanced knowledge and skills in a particular field or area.

[1069] A "certification" is an official recognition or certification required to perform a particular job or function.

[1070] An "area of ​​interest" is a field or area in which an individual is particularly interested and wants to actively engage.

[1071] "Artificial intelligence means" are systems or algorithms that use machine learning and data analysis to automatically perform specific tasks.

[1072] The "best mix team proposal" is a plan that proposes the optimal combination of members for the success of the project.

[1073] "Team building" is the process of selecting and organizing the right people for a project.

[1074] "Human resource development" refers to the activity of providing education and training to improve the skills and abilities of employees.

[1075] "Skill improvement" refers to further enhancing an individual's skills and knowledge.

[1076] "Recruitment" is the process by which an organization selects and hires new employees.

[1077] "Skill data" is information about the specific skills and knowledge that an individual possesses.

[1078] "Requirements data" is information about the conditions and specifications necessary for the project to be successful.

[1079] A "generative AI model" is an artificial intelligence model that uses natural language processing and machine learning to generate appropriate output from input data.

[1080] A "prompt sentence" is a sentence of instructions or questions that is input to a generative AI model.

[1081] "Simulation" is the process of virtually recreating a real-world project or situation and predicting its outcome.

[1082] "Users" are individuals or organizations that use this system to simulate projects and check the results.

[1083] This invention is a system that enables simulation of a project in a specific field with specific members. This system operates in cooperation with three entities: a server, a terminal, and a user.

[1084] The server first has a means for inputting personnel information. This means stores personal information such as employee skills, experience, qualifications, and areas of interest in a database and has the function of retrieving it as needed. The database uses a relational database management system (RDBMS) such as MySQL or PostgreSQL.

[1085] Next, the server has a means for inputting information such as experience, projects, specialties, qualifications, areas of interest, etc. This allows specific efforts and results from past projects and tasks to be stored in a database and retrieved as needed.

[1086] The server has an artificial intelligence means that proposes the best mix of teams across organizations based on the input information. This artificial intelligence means is a system or algorithm that uses machine learning and data analysis to automatically perform specific tasks. Specifically, it uses programming languages ​​such as Python and R and utilizes data processing libraries such as Pandas and NumPy.

[1087] Furthermore, the server has the means to utilize the proposed team proposals for team formation, human resource development, skill upgrading, and recruitment, which can assist in the process of selecting and organizing the right members for the project.

[1088] The server has a means for acquiring the skill data of a specific member and the requirement data of a project, and by this means, the skill data of the member and the requirement data of the project can be acquired from the database and compared.

[1089] The server also includes a means to compare the acquired skill data with the requirements data, using programming languages ​​such as Python and R and leveraging data processing libraries such as Pandas and NumPy.

[1090] The server has a means to input a prompt sentence into the generative AI model and perform a simulation. For example, OpenAI's GPT-4 is used as the generative AI model. An example of a prompt sentence is as follows:

[1091] Member A's marketing skills include: marketing strategy, data analysis, and advertising operations. The requirements for a new marketing project include: market research, targeting, and advertising campaign design. Simulate the probability of success and the resources required for this project.

[1092] Finally, the server has a means to display the simulation results to the user. The user can check the simulation results by accessing the web application using a terminal. The web application framework used is Django or Flask.

[1093] As a specific example, when a user requests a simulation of a new marketing project, the server retrieves member A's skill data and the project's requirements data from the database and compares them using Python. Then, it inputs a prompt statement into the generative AI model, obtains the simulation results, and displays them to the user. In this way, the user can specifically check the project's success probability and required resources. The flow of the identification process in Example 3 will be explained using Figure 15.

[1094] Step 1:

[1095] A user requests a simulation of a project.

[1096] A user accesses a web application using a terminal and requests a simulation of a specific project. As input, they provide details of the project (e.g., a new marketing project). As output, the request is sent to the server.

[1097] Step 2:

[1098] The server retrieves the member's skill data.

[1099] The server retrieves the skill data of the members participating in the project from the database. As input, it uses the member's ID and project details. As output, it retrieves the member's skill data (e.g., marketing strategy, data analysis, advertising operations).

[1100] Step 3:

[1101] The server retrieves the project requirements data.

[1102] The server also retrieves the project requirements data from the database. As input, it uses the project ID and details. As output, it gets the project requirements data (e.g. market research, targeting, advertising campaign design).

[1103] Step 4:

[1104] The server compares the skills data with the requirements data.

[1105] The server uses Python to compare the member's skill data with the project's requirement data. This comparison uses data processing libraries such as Pandas and NumPy. The acquired skill data and requirement data are used as input. The output is the match between the skills and requirements.

[1106] Step 5:

[1107] The server inputs a prompt sentence into the generative AI model.

[1108] The server inputs an appropriate prompt to the generative AI model (e.g., OpenAI's GPT-4). It uses skill data, requirement data, and fitness data as input. An example prompt is as follows:

[1109] Member A's marketing skills include: marketing strategy, data analysis, and advertising operations. The requirements for a new marketing project include: market research, targeting, and advertising campaign design. Simulate the probability of success and the resources required for this project.

[1110] As an output, the generative AI model provides simulation results.

[1111] Step 6:

[1112] The server retrieves the simulation results.

[1113] The server obtains the simulation results obtained from the generative AI model. As input, it uses the prompt sentence entered into the generative AI model. As output, it obtains the simulation results (e.g., the probability of project success, required resources).

[1114] Step 7:

[1115] The server displays the simulation results to the user.

[1116] The server displays the simulation results to the user through a web application. The simulation results obtained from the generative AI model are used as input. The simulation results are displayed on the user's device as output. The user can check the project's success probability and required resources on the device screen.

[1117] (Application example 3)

[1118] Next, a description will be given of 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 glasses 214 will be referred to as a "terminal."

[1119] Conventional project management systems lack the functionality to compare the skills of specific members with project requirements and, based on the results, simulate the probability of project success and the resources required. Furthermore, in factory project management, it is difficult to properly evaluate the skills of specific members or robots and form optimal teams. Therefore, there is a need for a system that can increase the probability of project success and achieve efficient resource allocation.

[1120] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1121] In this invention, the server includes a means for inputting personnel information, a means for inputting information such as experience, projects, specialties, qualifications, and areas of interest, an AI means for proposing a best mix team plan across organizations based on the input information, a means for utilizing the proposed team plan in team formation, human resource development, skill improvement, and recruitment, and a means for comparing the skills of specific members with the requirements of a project and simulating the probability of project success and the required resources based on the results. This makes it possible to properly evaluate the skills of specific members and robots and form optimal teams.

[1122] "Human resources information" refers to data about human resources within an organization, such as employee personal information, work history, skills, evaluations, and qualifications.

[1123] "Experienced measures" refer to specific initiatives and methodologies used in projects and work carried out in the past.

[1124] A "project" is a set of activities or tasks planned and executed to achieve a specific goal.

[1125] "Specialization" refers to having advanced knowledge and skills in a particular field or area.

[1126] "Qualification" refers to the official recognition or certification required to perform a particular job or function.

[1127] An "area of ​​interest" refers to a field or area in which an individual is particularly interested and wants to actively engage.

[1128] A "best mix team proposal" is a proposal for team composition that optimally combines the skills and experience of members from both inside and outside the organization.

[1129] "AI means" refers to a means of analyzing data using artificial intelligence technology to create optimal team formations and simulate projects.

[1130] "Team formation" refers to the selection and organization of the members needed to carry out a specific project or task.

[1131] "Human resource development" refers to education and training to improve employees' skills and abilities.

[1132] "Skill Up" refers to improving an individual's skills and abilities.

[1133] "Recruitment" refers to the process by which an organization selects and hires new talent.

[1134] "Project success probability" refers to the likelihood that a particular project will be completed as planned and achieve its goals.

[1135] "Resources" refers to the human resources, funds, equipment, time, and other resources required to carry out a project or task.

[1136] "Simulation" is a method for virtually recreating real-world projects and tasks and predicting their outcomes.

[1137] "In-factory project management" refers to the process of planning, executing, monitoring and evaluating projects carried out within a factory.

[1138] As an embodiment of the present invention, a system for supporting project management within a factory is constructed. A specific embodiment of the system is shown below.

[1139] System configuration

[1140] The system consists of the following main components:

[1141] 1. Server:

[1142] Database: Stores data such as personnel information, experience measures, project information, specialties, qualifications, and areas of interest.

[1143] AI module: Compares personnel information with project requirements and simulates optimal team composition and the probability of project success.

[1144] Simulation engine: Evaluates the skills of specific members and robots, and calculates the probability of project success and required resources.

[1145] 2. Terminal:

[1146] Smartphones: Used by factory managers and workers to access the system and check project progress and simulation results.

[1147] Tablet: Used to view and interact with detailed data on a larger screen.

[1148] Program processing

[1149] The server processes the data in the following steps:

[1150] 1. Data Collection and Storage:

[1151] Data such as personnel information, experience measures, project information, specialties, qualifications, areas of interest, etc. are stored in the database.

[1152] 2. Data Analysis:

[1153] Based on the collected data, the AI ​​module selects the most suitable members and robots for a specific project.

[1154] The simulation engine compares the skills of the selected members and robots with the project requirements and calculates the probability of success and the resources required.

[1155] 3. Displaying the results:

[1156] Simulation results are displayed to managers and workers via smartphones or tablets.

[1157] Hardware and software used

[1158] Hardware: Servers, smartphones, tablets

[1159] Software: Python, pandas, numpy, scikit-learn

[1160] Specific examples

[1161] For example, to simulate a project to launch a new product line, you might use a prompt like this:

[1162] Example prompt sentence:

[1163] Compare the skills of each robot against the project requirements to simulate the probability of success and the resources needed for a new product line launch project.

[1164] By inputting this prompt into a generative AI model, detailed simulation results can be obtained regarding the project's success probability and required resources.

[1165] As described above, this invention is a system that can increase the probability of project success by streamlining project management within a factory and appropriately evaluating the skills of specific members and robots.

[1166] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1167] Step 1:

[1168] The server collects data such as personnel information, experience measures, project information, specialties, qualifications, and areas of interest, and stores it in a database. Inputs include skill information for each employee and robot, past project data, and qualification information. Organizing this data and storing it in a database provides the basic data required for subsequent processing.

[1169] Step 2:

[1170] The server uses an AI module to analyze the collected data. Specifically, it compares the skills of each member or robot with the project requirements to select the most suitable members or robots for a particular project. The input includes the project requirements and the skill data of each member or robot. The AI ​​module compares this data and selects the most suitable members or robots. The output is a list of selected members or robots.

[1171] Step 3:

[1172] The server uses a simulation engine to calculate the probability of project success and the required resources based on the skills of the selected members and robots and the project requirements. The input includes a list of selected members and robots and the project requirements. The simulation engine calculates the success probability and required resources based on this data. The output is a detailed simulation result of the success probability and required resources.

[1173] Step 4:

[1174] The server sends the simulation results to smartphones or tablets and displays them to managers and workers. The input includes the simulation results. The device receives these results and displays them in a visually easy-to-understand format for the user. The output allows managers and workers to check the simulation results and use them to progress the project.

[1175] Step 5:

[1176] Using a smartphone or tablet, users monitor project progress based on simulation results and make adjustments as needed. Inputs include simulation results and actual project progress. Users can compare these data and make necessary adjustments to increase the project's chances of success. Outputs include the adjusted project plan and progress.

[1177] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1178] "Example 1"

[1179] As one embodiment of the present invention, a system incorporating an emotion engine is provided. This system recognizes a user's emotions and optimizes team composition based on the emotions. Specifically, the system includes an emotion recognition module for recognizing the user's emotions and a team optimization module for optimizing the team composition based on the recognized emotions. The emotion recognition module recognizes emotions from the user's facial expressions, tone of voice, choice of words, etc. The team optimization module optimizes the team composition taking the recognized emotions into consideration. For example, if it recognizes that a certain member is feeling stressed, it suggests measures such as adding another member to the team to reduce the burden on that member.

[1180] "Example 2"

[1181] Another embodiment of the present invention provides a system incorporating an emotion engine. This system recognizes a user's emotion and predicts the probability of project success based on the emotion. Specifically, the system includes an emotion recognition module for recognizing the user's emotion and a success probability prediction module for predicting the probability of project success based on the recognized emotion. The success probability prediction module predicts the probability of project success based on the recognized emotion and data from past projects. For example, if it is recognized that all team members are highly motivated, the system predicts that the probability of project success is high.

[1182] "Example 3"

[1183] As one embodiment of the present invention, a system incorporating an emotion engine is provided. This system recognizes a user's emotions and optimizes team composition based on the emotions. Specifically, the system includes an emotion recognition module for recognizing the user's emotions and a team optimization module for optimizing the team composition based on the recognized emotions. The emotion recognition module recognizes emotions from the user's facial expressions, tone of voice, choice of words, etc. The team optimization module optimizes the team composition taking the recognized emotions into consideration. For example, if it recognizes that a certain member is feeling stressed, it suggests measures such as adding another member to the team to reduce the burden on that member.

[1184] The processing flow of each embodiment will be described below.

[1185] "Example 1"

[1186] Step 1: The emotion recognition module is activated to recognize emotions from the user's facial expressions, tone of voice, choice of words, etc.

[1187] Step 2: The emotion information recognized by the emotion recognition module is sent to the team optimization module.

[1188] Step 3: The team optimization module optimizes the team composition taking into account the transmitted emotional information.

[1189] Step 4: For example, if you recognize that a member is feeling stressed, suggest measures to alleviate that member's burden, such as adding another member to the team.

[1190] "Example 2"

[1191] Step 1: The emotion recognition module is activated to recognize emotions from the user's facial expressions, tone of voice, choice of words, etc.

[1192] Step 2: The emotion information recognized by the emotion recognition module is sent to the success probability prediction module.

[1193] Step 3: The success probability prediction module predicts the success probability of the project based on the transmitted emotional information and data from past projects.

[1194] Step 4: For example, if you perceive that all team members are highly motivated, you predict that the project has a high probability of success.

[1195] Example 1

[1196] Next, a description will be given of 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 glasses 214 will be referred to as a "terminal."

[1197] Conventional team formation systems have difficulty forming optimal teams based on the skills and experience of their members, and do not take into account the emotional state of the members. This leads to problems such as reduced project efficiency and lower member satisfaction. Furthermore, they lack simulation functionality for selecting the optimal team members for a specific project.

[1198] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1199] In this invention, the server includes: a means for inputting personnel information; a means for inputting information such as experience, projects, specialties, qualifications, and areas of interest; an artificial intelligence means for proposing a best-mix team plan across organizations based on the input information; a means for utilizing the proposed team plan in team formation, human resource development, skill improvement, and recruitment; an emotion recognition means for recognizing the user's emotions; and a means for optimizing team composition based on the recognized emotions. This enables optimal team formation based on the skills and experience of members, and further allows optimization taking into account the members' emotional states, thereby improving project efficiency and member satisfaction. A simulation function is also provided for selecting the optimal members for a specific project.

[1200] "Personnel information" refers to information about individuals, such as an employee's name, position, work history, evaluation, skills, and qualifications.

[1201] The "experience measure" is information indicating the experience and achievements of an employee in projects or work that the employee has participated in in the past.

[1202] A "project" is a set of activities or tasks planned and carried out within an organization to achieve a specific goal.

[1203] "Specialty" refers to the advanced knowledge and skills an employee has in a particular field or technology.

[1204] "Qualification" refers to the official recognition or certification required for an employee to perform a particular job or function.

[1205] "Areas of interest" refers to areas or topics that employees are personally interested in and would like to learn or work on.

[1206] "Artificial intelligence means" refers to algorithms or models that analyze input data and derive optimal results based on a specific purpose.

[1207] "Emotion recognition means" refers to technologies and modules that analyze and identify emotions from a user's facial expressions, tone of voice, choice of words, etc.

[1208] "Team composition optimization" refers to algorithms or processes for optimizing the selection and placement of team members based on perceived sentiment and other data.

[1209] This invention is a system that organizes optimal teams based on information provided by users, such as personnel information, experience, projects, specialties, qualifications, and areas of interest. The system operates in cooperation with three parties: a server, a terminal, and a user.

[1210] The server provides a web interface for inputting user-provided information. Through a web browser, the user inputs information such as the project name, required skills, member experience, specialty, qualifications, and areas of interest. For example, the user inputs members with the skills of "data analysis," "project management," and "software development" for "Project B."

[1211] The server stores the input information in a database (e.g., MySQL or PostgreSQL). The database stores detailed information about each member, such as their skills, experience, and qualifications. The server then analyzes the information stored in the database using a generative AI model (e.g., OpenAI's GPT-4). The AI ​​model runs an algorithm based on the input information to select the best members for the project.

[1212] Based on the analysis results of the AI ​​model, the server generates the optimal team member combination for a specific project. For example, for Project B, it proposes a combination of a data scientist, a project manager, and a software engineer.

[1213] Furthermore, the server uses an emotion recognition module (for example, Microsoft Azure's Emotion API) to recognize the user's emotions. It analyzes data such as facial expressions, tone of voice, and word choice provided by the user via the webcam or microphone. The server optimizes team composition based on the recognized emotions. For example, if it recognizes that a certain member is feeling stressed, it will suggest measures such as adding other members to reduce the burden on that member.

[1214] The server presents the optimized team proposal to the user, who can review the proposed team proposal through a web interface and make any necessary modifications or approvals.

[1215] For example, if a user is assembling a team for Project B, they enter the following information:

[1216] Project Name: Project B

[1217] Required skills: Data analysis, project management, software development

[1218] Member experience: 5+ years of data analysis experience, 3+ years of project management experience, 2+ years of software development experience

[1219] The server stores this information in a database, and the AI ​​analyzes it. The AI ​​selects the most suitable members and proposes the following team proposals:

[1220] Data Scientist: Taro Tanaka (10 years of data analysis experience)

[1221] Project Manager: Hanako Suzuki (5 years of project management experience)

[1222] Software Engineer: Jiro Sato (3 years of software development experience)

[1223] Examples of prompts include:

[1224] "For Project B, select the best team members with skills in data analysis, project management, and software development. Also consider the number of years of experience each team member has."

[1225] In this way, the server, terminals, and users work together to operate the system.

[1226] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1227] Step 1:

[1228] The user enters information

[1229] The user opens a web browser and accesses the system's login page. After logging in, they enter the required information into the project information input form and click the "Submit" button. The information entered includes the project name, required skills, member experience, specialization, qualifications, and areas of interest. The input data is sent to the server.

[1230] Step 2:

[1231] The server stores the information in a database

[1232] The server receives the information sent by the user and stores it in the database. Specifically, it executes SQL queries to insert project information and member information into the database. The input data is saved in the database.

[1233] Step 3:

[1234] The server analyzes the data using an AI model

[1235] The server retrieves the necessary information from the database and inputs it into the generative AI model. The AI ​​model performs analysis to select the best members for the project. Specifically, it calculates the optimal combination of members based on the input skills and experience. The input data is sent to the AI ​​model, and a list of the best members is obtained as output data.

[1236] Step 4:

[1237] The server generates team proposals

[1238] The server generates the optimal team member combination for a specific project based on the analysis results of the AI ​​model. For example, it proposes a combination of data scientists, project managers, and software engineers for Project B. The input data is the output data of the AI ​​model, and the proposed team is generated as output data.

[1239] Step 5:

[1240] The server recognizes emotions using an emotion engine

[1241] The server inputs data acquired from the user's webcam and microphone into the emotion recognition module. The module analyzes the user's facial expressions and tone of voice to identify emotions. Specifically, it uses image analysis and voice analysis algorithms to determine the user's emotional state. The input data is from the webcam and microphone, and the output data is the recognized emotion.

[1242] Step 6:

[1243] Server optimizes teams based on emotions

[1244] The server optimizes the team composition based on the recognized emotions. For example, it suggests additional members to reduce the burden on members who are feeling stressed. Specifically, it rearranges or adds team members by taking the emotional data into consideration. The input data is the recognized emotional data, and the output data is an optimized team proposal.

[1245] Step 7:

[1246] The server presents the optimized team proposal to the user.

[1247] The server presents the optimized team proposal to the user, who can then review the proposed team proposal through a web interface and make any necessary modifications or approvals. The input data is the optimized team proposal, and the output data is user feedback.

[1248] (Application example 1)

[1249] Next, a description will be given of 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 glasses 214 will be referred to as a "terminal."

[1250] Conventional team formation systems can propose optimal teams based on personnel and skill information, but they do not consider the robot's operating status, maintenance history, or stress recognition using an emotion engine when forming teams. This makes it difficult to form optimal robot teams to maximize work efficiency within a factory. Furthermore, because the robot's stress level is not taken into account, there is a risk of reduced operational efficiency.

[1251] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1252] In this invention, the server includes means for inputting personnel information, means for inputting information such as experience, projects, specialties, qualifications, and areas of interest, means for proposing a best mix team plan across organizations based on the input information, means for inputting information such as robot skills, experience, operation status, and maintenance history, means for recognizing stress from the robot's operation status and error frequency using an emotion engine, and means for optimizing team formation based on the recognized stress information. This maximizes work efficiency in the factory and enables optimal team formation taking into account the robot's stress level.

[1253] "Personnel information" refers to basic information about employees, such as their names, ages, job titles, work histories, and evaluation results.

[1254] "Experience measures" are information about an employee's experience, such as projects and tasks they have participated in in the past, skills and qualifications they have acquired, and training they have received.

[1255] A "project" is a set of activities or tasks planned and carried out within an organization to achieve a specific purpose.

[1256] "Specialty" refers to the specialized knowledge or skills an employee has in a particular field or technology.

[1257] "Qualification" refers to the certification or certificate required for an employee to perform a particular job or function.

[1258] "Areas of interest" refers to areas or topics that employees have a personal interest in.

[1259] "AI means" refers to a means of analyzing data using artificial intelligence technology and making optimal team formations and proposals.

[1260] An "emotion engine" is a technology that recognizes the emotions of users and robots and responds appropriately based on those emotions.

[1261] "Operation status" refers to information such as the actual operating state of a robot or machine, its operating time, and its operating rate.

[1262] "Maintenance history" is a record of the maintenance, inspections, and repairs that a robot or machine has undergone in the past.

[1263] "Stress" refers to the burden or pressure that robots or machines experience due to excessive load or the frequency of errors.

[1264] "Team formation" refers to selecting the best members to form a team for a specific purpose or project.

[1265] The system for implementing this invention operates in cooperation with a server, a terminal, and a user. The server has AI means for analyzing information stored in a database, such as personnel information, experience measures, projects, specialties, qualifications, and areas of interest, and proposing optimal team composition. The server also stores information on robots' skills, experience, operating status, and maintenance history in the database, and is equipped with means for recognizing stress levels based on the robots' operating status and error frequency using an emotion engine. This allows for optimal team composition based on the recognized stress information.

[1266] The server implements AI methods using programming languages ​​such as Python and R, and uses libraries such as Pandas and Scikit-learn for data analysis. The emotion engine uses emotion recognition software such as EmotionEngine. This allows the server to retrieve information from the database, perform clustering and emotion recognition, and propose optimal team formations.

[1267] The terminals can be smartphones, tablets, factory management systems, etc., and display the team formations proposed by the server, allowing users to confirm and operate them. The terminals communicate with the server via a web browser or dedicated application, obtaining and updating information in real time.

[1268] Users, such as factory managers and project managers, use their terminals to check the team composition proposed by the server, and make any necessary corrections or approvals. Based on the proposed team composition, users instruct the actual work and monitor the robots' operating status and stress levels.

[1269] For example, the following prompts can be fed to a generative AI model:

[1270] "Please propose the optimal robot team based on the skill level, experience, maintenance history, error rate, and downtime data of the robots in the factory. In particular, please consider the stress level of robots with high error rates and downtime, and propose measures to reduce the burden."

[1271] Using this prompt, the generative AI model can generate specific suggestions for optimizing the robot team in the factory.

[1272] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1273] Step 1:

[1274] The server retrieves information from the database, such as personnel information, experience measures, projects, specialties, qualifications, areas of interest, robot skills, experience, operating status, and maintenance history. The input is various information stored in the database, and the output is the dataset required for analysis. Specifically, it extracts the required information from the database using SQL queries.

[1275] Step 2:

[1276] The server uses AI techniques to perform clustering based on the acquired data. The input is the dataset acquired in step 1, and the output is the cluster information for each robot. Specifically, the server preprocesses the data using the Pandas library and applies the KMeans clustering algorithm from Scikit-learn.

[1277] Step 3:

[1278] The server uses an emotion engine to recognize stress from the robot's operating status and error frequency. The input is the operating status and error frequency data obtained in step 1, and the output is the stress level of each robot. The specific operation is to calculate the stress level using the Emotion Engine.

[1279] Step 4:

[1280] The server proposes optimal team composition based on the cluster information and stress levels. The input is the cluster information obtained in step 2 and the stress levels obtained in step 3, and the output is the optimal team composition proposal. Specifically, the server uses an AI algorithm to optimize the team composition.

[1281] Step 5:

[1282] The server sends the optimal team formation plan to the terminal. The input is the team formation plan obtained in step 4, and the output is the team formation plan displayed on the terminal. Specifically, the server sends data to the terminal using an HTTP request.

[1283] Step 6:

[1284] The terminal displays the team composition proposal received from the server to the user. The input is the team composition proposal sent from the server in step 5, and the output is a screen display that the user can check. Specifically, the data is displayed using a web browser or a dedicated application.

[1285] Step 7:

[1286] The user checks the proposed team composition through the terminal and modifies or approves it as necessary. The input is the proposed team composition displayed in step 6, and the output is the modified or approved proposed team composition. Specific operations are performed through the user interface.

[1287] Step 8:

[1288] The server receives corrections and approvals from the user and finalizes the team composition. The input is the correction or approval information sent by the user in step 7, and the output is the finalized team composition proposal. Specifically, the server saves the final team composition proposal in the database.

[1289] Example 2

[1290] Next, a description will be given of 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 glasses 214 will be referred to as a "terminal."

[1291] Conventional team formation systems have the problem that it is difficult to select the most suitable team members for the project requirements, and they are unable to predict the probability of project success taking into account the emotions and motivation of team members. Therefore, in order to improve the success rate of projects, a system that combines more advanced team formation and emotion recognition is needed.

[1292] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1293] In this invention, the server includes means for inputting personnel information, means for inputting information such as experience, projects, specialties, qualifications, and areas of interest, artificial intelligence means for proposing a best mix team plan across organizations based on the input information, means for utilizing the proposed team plan in team formation, human resource development, skill improvement, and recruitment, emotion recognition means for recognizing user emotions, and success probability prediction means for predicting the probability of project success based on the recognized emotions. This makes it possible to form a team optimal for project requirements and further predict the probability of project success taking into account the emotions of team members.

[1294] "Human Resources Information" refers to detailed information about employees, such as their skill sets, years of experience, qualifications, and past project history.

[1295] "Experience measures" are measures aimed at improving the experience and skills that employees have gained through projects and work they have previously participated in.

[1296] A "project" is a set of tasks or activities organized to achieve a specific goal.

[1297] "Specialty" refers to having advanced knowledge and skills in a particular field or technology.

[1298] A "qualification" is a formal recognition or certification required to perform a particular job or function.

[1299] "Areas of interest" are areas or topics that employees are personally interested in and would like to learn more about.

[1300] "Artificial intelligence means" are techniques or algorithms that use machine learning or data analysis to automatically perform specific tasks.

[1301] "Emotion recognition means" refers to technology or modules for analyzing and recognizing emotions from a user's facial expressions, voice, etc.

[1302] A "success probability prediction method" is a technology or algorithm for predicting the success probability of a specific project based on past data and current circumstances.

[1303] This invention is a system that proposes the optimal team for a project and predicts the probability of success of the project using an emotion engine. This system operates in cooperation with three parties: a server, a terminal, and a user.

[1304] System configuration

[1305] The server uses the following hardware and software:

[1306] Hardware: High-performance processor, memory, and storage

[1307] Software: Python, TensorFlow, Database Management System

[1308] The terminal uses the following hardware and software:

[1309] Hardware: Camera, microphone, display

[1310] Software: OpenCV, speech recognition software, user interface

[1311] The user is responsible for inputting project requirements and sentiment data.

[1312] Program processing

[1313] The server first receives the project requirements input by the user, including the required skill set, years of experience, project duration, etc. The server then collects employee skill sets and past project experience from the company's database, which is obtained from employee resumes and past project reports.

[1314] Based on the collected data, the server uses TensorFlow to select the optimal team. This AI model compares the project requirements with the employee skill sets and calculates the optimal team combination. The calculation results are sent to the device and displayed to the user.

[1315] Examples:

[1316] Suppose a new software development project is being started. This project requires programming skills in Java and Python with at least five years of experience. The server searches the employee database for members who meet these criteria and suggests the best team. The terminal screen displays "Recommended team members: Taro Tanaka (Java, 7 years), Hanako Suzuki (Python, 6 years)."

[1317] Example prompt sentence:

[1318] "For a new software development project, select someone with Java and Python skills and at least 5 years of experience."

[1319] The device then collects the user's emotional data. It uses a camera and microphone to capture the user's facial expressions and voice in real time. The collected data is analyzed using OpenCV and speech recognition software. The analysis results are then sent to the server.

[1320] The server uses the received emotion data to predict the success probability of the project using a success probability prediction module. This module compares past project data with the current emotion data to calculate the success probability. The calculation result is sent to the terminal and displayed to the user.

[1321] Examples:

[1322] If all team members are perceived to be highly motivated, the server predicts a high probability of success for the project. Conversely, if many team members are feeling stressed, it predicts a low probability of success. The device screen displays "Current project's success probability: 80%."

[1323] Example prompt sentence:

[1324] "Predict the probability of project success based on current team member sentiment data."

[1325] In this way, the system can assemble a team that best suits the project requirements and also predict the probability of project success by taking into account the emotions of team members.

[1326] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1327] Step 1:

[1328] Entering project requirements

[1329] The user inputs the project requirements into the terminal.

[1330] Inputs: Required skill set, years of experience, project duration, etc.

[1331] Specific operation: The user enters "Java and Python skills required, member with 5+ years of experience" into the terminal form.

[1332] Output: The entered project requirements data.

[1333] Step 2:

[1334] Collecting personnel information

[1335] The server collects employee skill sets and past project experience from the company's database.

[1336] Input: Project requirements data.

[1337] What happens: The server queries the database to get a list of employees who have the skills "Java" and "Python" and who have "5+ years of experience."

[1338] Output: Collected employee skill sets and experience data.

[1339] Step 3:

[1340] Selecting the best team using AI models

[1341] The server inputs the collected personnel information and project requirements into an AI model to select the optimal team.

[1342] Inputs: Employee skill sets and experience data, project requirement data.

[1343] Specific operation: The server inputs data into the TensorFlow model and calculates the optimal team member combination.

[1344] Output: A list of optimal team members.

[1345] Step 4:

[1346] View team suggestions

[1347] The terminal displays the optimum team proposal sent from the server to the user.

[1348] Input: A list of suitable team members.

[1349] Specific operation: The device screen will display "Recommended team members: Tanaka Taro (Java, 7th year), Suzuki Hanako (Python, 6th year)."

[1350] Output: The team proposals displayed to the user.

[1351] Step 5:

[1352] Collecting Emotional Data

[1353] The device collects the user's facial expressions and voice through a camera and microphone.

[1354] Input: User's facial expression data, voice data.

[1355] Specific operation: The device's camera captures the user's face and the microphone records the user's voice.

[1356] Output: Collected emotion data.

[1357] Step 6:

[1358] Emotional Data Analysis

[1359] The terminal inputs the collected emotion data into an emotion recognition module and analyzes the user's emotions.

[1360] Input: Collected emotion data.

[1361] Specific operation: The device analyzes the facial image captured by the device using OpenCV and recognizes it as "high motivation."

[1362] Output: Parsed emotion data.

[1363] Step 7:

[1364] Predicting the probability of success

[1365] The server predicts the success probability of the project based on the analyzed emotion data using a success probability prediction module.

[1366] Input: Parsed sentiment data, past project data.

[1367] Specific operation: The server inputs emotional data and past project data and predicts an "80% chance of success."

[1368] Output: Predicted probability of success.

[1369] Step 8:

[1370] Displaying success probability

[1371] The terminal displays the success probability sent from the server to the user.

[1372] Input: Predicted probability of success.

[1373] Specific operation: The device screen will display "Current project success probability: 80%."

[1374] Output: Probability of success displayed to the user.

[1375] (Application example 2)

[1376] Next, a description will be given of 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 glasses 214 will be referred to as a "terminal."

[1377] With conventional project management systems, it was difficult to form appropriate teams and predict the probability of project success. Furthermore, there was a lack of real-time project management within the factory and a means to grasp the emotional state of team members, which led to problems with project efficiency and success rates. This often resulted in project progress being delayed and results not being achieved as expected.

[1378] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1379] In this invention, the server includes a means for inputting personnel information, a means for inputting information such as experience, projects, specialties, qualifications, and areas of interest, an AI means for proposing a best-mix team plan across organizations based on the input information, a means for utilizing the proposed team plan for team formation, human resource development, skill improvement, and recruitment, an emotion recognition module for recognizing a user's emotion, a success probability prediction module for predicting the probability of project success based on the recognized emotion, and a smart glasses application for supporting project management within a factory. This enables appropriate team formation and prediction of the probability of project success, enabling real-time project management within a factory and understanding the emotional states of team members.

[1380] "Human resources information" refers to information such as employee skills, experience, qualifications, position, and evaluations.

[1381] "Experienced measures" refers to information on measures and initiatives implemented in past projects and business operations.

[1382] A "project" is a set of activities or tasks planned and carried out to achieve a specific purpose.

[1383] "Specialty" refers to advanced knowledge and skills in a particular field or technology.

[1384] "Qualification" refers to the certification or certificate required to perform a particular job or function.

[1385] "Areas of interest" refers to areas or themes that employees are interested in and want to actively work on.

[1386] "AI means" refers to a system that uses artificial intelligence technology to analyze data and predict optimal team composition and the probability of project success.

[1387] An "emotion recognition module" refers to software or hardware for recognizing emotions from a user's facial expressions, voice, etc.

[1388] "Success Probability Prediction Module" refers to software or hardware for predicting the probability of project success based on perceived sentiment and past data.

[1389] "Smart glasses application" refers to software that is installed on smart glasses and is used to manage projects within factories and display the emotional state of team members in real time.

[1390] To implement this invention, the following hardware and software are required: Smart glasses equipped with a camera and a display are required for the hardware, and OpenCV, EmotionRecognizer, TeamOptimizer, and SuccessPredictor are required for the software.

[1391] The server first acquires video from the camera. The acquired video is processed in real time using OpenCV. Next, the EmotionRecognizer is used to recognize the user's emotions. This emotion recognition module extracts emotions from the user's facial expressions and voice, and sends them as data to the server.

[1392] Based on the received emotion data, the server uses TeamOptimizer to propose the optimal team. TeamOptimizer analyzes information such as employee personnel information, experience, projects, specialties, qualifications, and areas of interest to form the optimal team for the project.

[1393] Furthermore, the server uses SuccessPredictor to predict the success probability of the project based on the recognized emotions and past project data. The success probability prediction module receives emotion data and team composition data as input and calculates the success probability of the project.

[1394] These results are displayed in real time on the smart glasses display, allowing users to check the optimal team composition and the probability of project success through the smart glasses.

[1395] As a concrete example, consider a project to launch a new product line in a factory. For this project, members with the appropriate skills are selected, and their emotional states are monitored in real time to predict the probability of success. This information is provided to factory managers through smart glasses, enabling them to efficiently manage the progress of the project.

[1396] An example of a prompt to input to a generative AI model is as follows:

[1397] For a new product line launch project, select members with the appropriate skills, and develop an application that monitors their emotional state in real time to predict the probability of success. The hardware used is smart glasses, and the software used is OpenCV, EmotionRecognizer, TeamOptimizer, and SuccessPredictor.

[1398] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1399] Step 1:

[1400] The server acquires video from the camera of the smart glasses. The input is the camera image, and the output is real-time video data. Specifically, it uses OpenCV to capture video from the camera and processes each frame.

[1401] Step 2:

[1402] The server inputs the acquired video data into EmotionRecognizer to recognize the user's emotions. The input is video data and the output is emotional data. Specifically, EmotionRecognizer analyzes the user's facial expressions and voice from the video data to identify their emotions.

[1403] Step 3:

[1404] The server uses TeamOptimizer to propose the optimal team based on the recognized emotion data. The input is emotion data and information such as personnel information, experience, projects, specialties, qualifications, and areas of interest, and the output is optimal team composition data. Specifically, TeamOptimizer analyzes this data and selects the best members for the project.

[1405] Step 4:

[1406] The server inputs the proposed team composition data and emotion data into SuccessPredictor to predict the success probability of the project. The input is team composition data and emotion data, and the output is success probability data. Specifically, SuccessPredictor calculates the success probability based on past project data and current emotion data.

[1407] Step 5:

[1408] The server displays the success probability data and team composition data on the smart glasses display. The input is the success probability data and team composition data, and the output is the information displayed on the display. Specifically, the optimal team composition and project success probability are displayed in real time on the smart glasses display so that the user can check them.

[1409] Example 3

[1410] Next, a description will be given of 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 glasses 214 will be referred to as a "terminal."

[1411] Conventional team formation systems have the problem of being difficult to form optimal teams that take into account not only the skills of the members and the requirements of the project, but also the emotions of the users. Furthermore, it is not possible to fully simulate a project in a specific field with specific members, making it difficult to predict the probability of project success and the resources required. This has led to issues such as delays in project progress and increased burdens on members.

[1412] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1413] In this invention, the server includes means for inputting personnel information, means for inputting information such as experience, projects, specialties, qualifications, and areas of interest, artificial intelligence means for proposing a best mix team plan across organizations based on the input information, means for utilizing the proposed team plan in team formation, human resource development, skill improvement, and recruitment, means for enabling a simulation of a project in a specific field with specific members, and means for recognizing user emotions and optimizing team composition based on the emotions. This makes it possible to predict the success rate of a project and the required resources, and further realizes optimal team formation taking user emotions into consideration.

[1414] "Human resources information" refers to information such as employee skills, experience, qualifications, position, and evaluations.

[1415] "Experienced measures" refer to specific measures and initiatives in projects or work in which an employee has been involved in the past.

[1416] A "project" is a set of activities planned and carried out within an organization to achieve a specific goal.

[1417] "Specialty" refers to a field or skill in which an employee is particularly skilled.

[1418] "Qualification" refers to any official certification or certificate obtained by an employee.

[1419] "Areas of interest" refers to areas or topics that an employee is personally interested in.

[1420] "Artificial intelligence means" refers to technology that uses machine learning and data analysis to create optimal team formation and project simulations based on input information.

[1421] "Team formation" refers to selecting and organizing the best members to carry out a specific project or task.

[1422] "Human resource development" refers to education and training to improve employees' skills and abilities.

[1423] "Skill improvement" refers to efforts to improve employees' expertise and skills.

[1424] "Recruitment" refers to the process of selecting and bringing new employees into an organization.

[1425] "Simulation" refers to a virtual experiment to predict the progress and results of a project under specific conditions.

[1426] "Emotion recognition" refers to technology that analyzes and recognizes emotions from a user's facial expressions, tone of voice, choice of words, etc.

[1427] "Optimizing team composition" refers to determining the most effective team composition by taking into account the user's emotions and skills.

[1428] The present invention is a system that enables simulation of a project in a specific field with specific members, and further has the function of recognizing the user's emotions and optimizing the team composition based on those emotions.

[1429] System configuration

[1430] Hardware

[1431] This system consists of three main components: a server, a terminal, and a user. The server is a computer with high-performance computing capabilities, and the terminal is a device operated by the user (e.g., a PC or smartphone).

[1432] software

[1433] The system includes the following main software modules:

[1434] Artificial intelligence tools (AI models): Built using TensorFlow and PyTorch.

[1435] Emotion Recognition Module: Built using OpenCV and Google Cloud Speech-to-Text.

[1436] Team Optimization Module: Built using Scikit-learn and Keras.

[1437] Program processing

[1438] Project Simulation Function

[1439] 1. A user enters the requirements for a new project into a terminal, for example, details of a marketing campaign.

[1440] 2. The server retrieves the member's skill data from the database, such as marketing experience, design skills, and data analysis ability.

[1441] 3. The server uses TensorFlow to compare the skills of members with the project requirements, running a skill matching algorithm to calculate the suitability of each member.

[1442] 4. The server simulates the project's success probability and required resources. For example, it calculates that the project has an 80% success rate and that an additional designer is required.

[1443] 5. The server sends the simulation results to the terminal.

[1444] 6. The device displays the simulation results to the user, for example, "The probability of project success is 80%. Additional designers are required."

[1445] Example prompt sentence:

[1446] "To launch a new marketing project, compare team members' skills with the project requirements and simulate the probability of success and resources required."

[1447] Emotion engine function

[1448] 1. The user talks to the device about the progress of the project and the stress they are feeling.

[1449] 2. The device uses OpenCV and Google Cloud Speech-to-Text to analyze the user's facial expressions, tone of voice, and word choice. For example, it detects if the user's face looks tired or if their voice tone is low.

[1450] 3. The device sends the analysis results to the server, such as "The user is feeling stressed."

[1451] 4. The server uses Scikit-learn to run a team optimization module based on the emotional data. Specifically, it performs optimization such as adding other members to reduce the burden on members who are feeling stressed.

[1452] 5. The server sends the optimized team configuration to the device.

[1453] 6. The device displays the optimized team configuration to the user, for example, "The new team configuration will include additional members for support."

[1454] Example prompt sentence:

[1455] "Recognize user emotions and optimize team composition to reduce the burden on stressed members."

[1456] summary

[1457] The present invention utilizes AI models and emotion recognition technology to simulate projects and optimize teams. Through specific processing steps, simulation results and optimized team composition are provided based on data entered by the user. This makes it possible to predict the success rate of a project and the resources required, and also realizes optimal team composition that takes user emotions into account. The flow of the specific processing in Example 3 is explained using Figure 21.

[1458] Project Simulation Function

[1459] Step 1:

[1460] A user enters the requirements for a new project into a terminal.

[1461] Input: Project details (e.g., marketing campaign goals, duration, budget, etc.)

[1462] Output: Project requirements data entered into the terminal

[1463] Specific operation: The user enters project details into the input form on the terminal and presses the submit button.

[1464] Step 2:

[1465] The server retrieves the member's skill data from the database.

[1466] Input: Project requirements data

[1467] Output: Member skill data (e.g., marketing experience, design skills, data analysis ability, etc.)

[1468] Specific operation: The server queries and retrieves relevant member skill data from the database based on the project requirements.

[1469] Step 3:

[1470] The server uses TensorFlow to compare members' skills with the project requirements.

[1471] Input: Member skill data, project requirement data

[1472] Output: Fitness data for each member

[1473] What happens: The server runs a skill matching algorithm to calculate how well each member's skills match the project requirements.

[1474] Step 4:

[1475] The server simulates the project's success rate and required resources.

[1476] Input: Fitness data for each member

[1477] Output: Probability of project success, required resource data

[1478] Specific operation: The server runs a simulation algorithm to calculate the probability of success of the project and the additional resources required.

[1479] Step 5:

[1480] The server transmits the simulation results to the terminal.

[1481] Input: Project success probability, required resource data

[1482] Output: Simulation results sent to the terminal

[1483] Specific operation: The server sends data using a communication protocol for sending the calculation results to the terminal.

[1484] Step 6:

[1485] The terminal displays the simulation results to the user.

[1486] Input: Simulation result data

[1487] Output: Simulation results displayed to the user

[1488] Specific operation: The device displays the simulation results received on the user interface, for example, "The probability of project success is 80%. Additional designers are required."

[1489] Emotion engine function

[1490] Step 1:

[1491] The user talks to the device about the progress of the project and the stress they are feeling.

[1492] Input: User's voice data, facial expression data

[1493] Output: Voice data and facial expression data input to the device

[1494] Specific operation: The user speaks into the device's microphone and camera, and the device captures the audio and video.

[1495] Step 2:

[1496] The device uses OpenCV and Google Cloud Speech-to-Text to analyze the user's facial expressions, tone of voice, and word choice.

[1497] Input: Voice data, facial expression data

[1498] Output: Parsed emotion data (e.g., stress, fatigue, joy, etc.)

[1499] Specific operation: The device converts voice data into text and analyzes facial expression data to recognize emotions.

[1500] Step 3:

[1501] The device sends the analysis results to the server.

[1502] Input: Parsed emotion data

[1503] Output: Emotion data sent to the server

[1504] Specific operation: The terminal transmits data using a communication protocol for transmitting analysis results to the server.

[1505] Step 4:

[1506] The server uses Scikit-learn to run the team optimization module based on the emotion data.

[1507] Input: Emotion data

[1508] Output: Optimized team composition data

[1509] Specific operation: Based on the emotional data, the server calculates the optimal team composition to reduce the burden on members who are feeling stressed.

[1510] Step 5:

[1511] The server sends the optimized team composition to the device.

[1512] Input: Optimized team composition data

[1513] Output: Optimized team composition data sent to the device

[1514] Specific operation: The server sends data using a communication protocol for sending the calculation results to the terminal.

[1515] Step 6:

[1516] The device displays the optimized team configuration to the user.

[1517] Input: Optimized team composition data

[1518] Output: The optimized team composition displayed to the user

[1519] Specific operation: The device displays the optimized team configuration received on the user interface, for example, "The new team configuration will include additional members for support."

[1520] (Application example 3)

[1521] Next, a description will be given of 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 glasses 214 will be referred to as a "terminal."

[1522] While traditional project management systems can organize teams based on the skills and experience of each member, they cannot take into account the emotions of each member or real-time situations, which can lead to reduced work efficiency and the probability of project success. Furthermore, it is difficult to properly distribute the workload among workers within the factory, which can lead to the accumulation of stress and fatigue. This can lead to delays in project progress and a decline in quality.

[1523] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1524] In this invention, the server includes: means for inputting personnel information; means for inputting information such as experience, projects, specialties, qualifications, and areas of interest; artificial intelligence means for proposing a best-mix team plan across organizations based on the input information; means for utilizing the proposed team plan in team formation, human resource development, skill improvement, and recruitment; an emotion recognition module for recognizing emotions; a team optimization module for optimizing team composition based on the recognized emotions; means for enabling a simulation of a project in a specific field with specific members; means for recognizing the skills and emotions of workers in a factory in real time and simulating the project success probability and required resources; and means for optimizing team composition based on the emotions of the workers to improve work efficiency. This enables optimal team formation taking into account the emotions of the members and real-time situations, thereby improving work efficiency and the project success probability.

[1525] "Human resources information" refers to information necessary for human resources management within an organization, such as an employee's personal information, work history, skills, qualifications, and evaluations.

[1526] "Experience measures" refer to the experience and achievements that employees have gained in projects and work they have participated in in the past.

[1527] A "project" is a set of activities or tasks planned and carried out to achieve a specific purpose.

[1528] "Specialty" refers to having advanced knowledge and skills in a particular field or technology.

[1529] "Qualification" refers to the certification or certificate required to perform a particular job or function.

[1530] "Areas of interest" refers to areas or topics that an employee is personally interested in.

[1531] "Artificial intelligence means" refers to a system that uses machine learning and data analysis to optimally organize teams and manage projects based on input information.

[1532] The "emotion recognition module" refers to a system that recognizes emotions from employees' facial expressions, tone of voice, choice of words, etc.

[1533] The "team optimization module" refers to a system for forming optimal teams based on recognized emotions and skill information.

[1534] "Means enabling simulation" refers to a system for predicting the probability of success and the resources required when a project in a specific field is carried out by specific members.

[1535] "Factory workers" refers to employees who work in factories, including those who perform tasks such as manufacturing and assembly.

[1536] "Real-time recognition" refers to instantly grasping and analyzing the current situation and condition.

[1537] "Project success probability" is a measure of the likelihood that a particular project will be completed as planned.

[1538] "Necessary resources" refers to the human resources, equipment, time, funds, etc. required to make the project successful.

[1539] "Work efficiency" is an index that indicates how much work can be done effectively within a certain amount of time.

[1540] A system for carrying out the present invention has the following configuration: a server includes means for inputting personnel information, means for inputting information such as experience measures, projects, specialties, qualifications, and areas of interest, artificial intelligence means for proposing a best-mix team plan across organizations based on the input information, means for utilizing the proposed team plan in team formation, human resource development, skill improvement, and recruitment, an emotion recognition module for recognizing emotions, a team optimization module for optimizing team composition based on the recognized emotions, means for enabling a simulation of a project in a specific field with specific members, means for recognizing the skills and emotions of workers in a factory in real time and simulating the probability of project success and the required resources, and means for optimizing team composition based on the emotions of the workers to improve work efficiency.

[1541] Hardware and software used

[1542] The server uses the following hardware and software:

[1543] Hardware: Factory robots, cameras, microphones

[1544] Software: Python, scikit-learn, TfidfVectorizer

[1545] Data processing and calculation

[1546] The server processes the data and performs calculations as follows:

[1547] 1. Emotion Recognition Module: Using a camera and microphone, the system captures a worker's facial expressions, tone of voice, and choice of words in real time to recognize their emotions. This is achieved through image processing and voice analysis technologies.

[1548] 2. Comparing skills and project requirements: Using TfidfVectorizer, we vectorize the skills of members and project requirements, and calculate the similarity using cosine_similarity. This allows us to evaluate how well the skills of members match the project requirements.

[1549] 3. Team optimization module: Forms optimal teams based on the perceived similarity of emotions and skills, and suggests measures such as adding additional members to relieve the burden on stressed workers.

[1550] Specific examples

[1551] For example, consider a project to set up a new assembly line in a factory. This project requires the skills of "welding" and "assembly." The server recognizes the skills and emotions of workers in real time and organizes the optimal team. For workers who are feeling stressed, the server suggests measures such as adding other members to reduce the burden.

[1552] Prompt Sentence Examples

[1553] Project requirements: "Welding, assembly"

[1554] Member information: [

[1555] {"name": "Worker A", "skills": "welding, assembly", "face_expression": "neutral", "voice_tone": "calm", "word_choice": "positive"},

[1556] {"name": "Worker B", "skills": "Painting, Quality Control", "face_expression": "stressed", "voice_tone": "tense", "word_choice": "negative"},

[1557] {"name": "Worker C", "skills": "Assembly, Inspection", "face_expression": "happy", "voice_tone": "cheerful", "word_choice": "positive"}

[1558] ]

[1559] By inputting this prompt into the generative AI model, we can obtain simulation results for optimal team composition.

[1560] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1561] Step 1:

[1562] The server uses a camera and microphone to capture the facial expressions, tone of voice, and word choice of factory workers in real time. The inputs are camera footage and audio data, and the output is sent to an emotion recognition module. Specifically, the camera captures the worker's face, and the microphone records the worker's voice.

[1563] Step 2:

[1564] The server uses an emotion recognition module to recognize the worker's emotions from the captured facial expressions, tone of voice, and choice of words. The input is the video and audio data acquired in step 1, and the output is the generated recognized emotion data. Specifically, it uses image processing and audio analysis technologies to classify the worker's emotions into categories such as "happy," "stressed," and "neutral."

[1565] Step 3:

[1566] The server acquires worker skill information and project requirement information. The inputs are the worker skill database and project requirement data, and the output is sent to the skill comparison module. Specifically, the server reads worker skill information from the database and acquires project requirement information.

[1567] Step 4:

[1568] The server uses TfidfVectorizer to vectorize the worker skills and project requirements, and calculates the similarity using cosine_similarity. The inputs are the skill information and project requirement information obtained in step 3, and the output is skill similarity data. Specifically, the skill information and project requirement information are vectorized as text data, and the similarity is calculated.

[1569] Step 5:

[1570] The server organizes an optimal team based on the recognized emotion data and skill similarity data. The inputs are the emotion data obtained in step 2 and the skill similarity data obtained in step 4, and the output is an optimized team organization proposal. Specifically, the server takes the emotion data into consideration and proposes measures such as adding other members to reduce the burden on workers who are feeling stressed.

[1571] Step 6:

[1572] The server sends the optimized team composition plan to the project management system and reflects it in the actual team composition. The input is the team composition plan generated in step 5, and the output is the team composition reflected in the project management system. Specifically, the generated team composition plan is sent to the project management system and reflected in the actual team composition.

[1573] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1574] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ) and other generative AIs. Data generation models 58

[1575] , obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in the data format of voice data, text data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1576] Another example of generative AI is Gemini (internet search engine). <url: https: gemini.google.com ?hl="ja">) are listed.

[1577] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1578] [Third embodiment]

[1579] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1580] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1581] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1582] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1583] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1584] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1585] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1586] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1587] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1588] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1589] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1590] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1591] "Example 1"

[1592] The system of the present invention has a means for inputting information such as personnel information, experience, projects, specialties, qualifications, and areas of interest. Specifically, this information is stored in a database and analyzed by AI. Based on this information, the AI ​​proposes a best-mix team proposal across organizations. For example, for a specific project, it selects members with the optimal skills and experience and proposes their combination.

[1593] "Example 2"

[1594] The system of the present invention also has the ability to propose teams suitable for specific projects. Specifically, the AI ​​compares project requirements with personnel information and proposes the optimal team composition. For example, for a new software development project, it selects members with the appropriate programming skills and experience and proposes their combination.

[1595] "Example 3"

[1596] Furthermore, the system of the present invention has a function that enables simulation of a project in a specific field with specific members. Specifically, the AI ​​compares the members' skills with the project requirements and performs a simulation based on the results. For example, if a specific member is to carry out a new marketing project, the AI ​​compares the member's marketing skills with the project requirements and simulates the project's success probability and required resources based on the results.

[1597] The processing flow of each embodiment will be described below.

[1598] "Example 1"

[1599] Step 1: Enter personnel information and experience, projects, specialties, qualifications, areas of interest, etc. into the database.

[1600] Step 2: AI analyzes this information and proposes the best mix of teams across the organization.

[1601] Step 3: Utilize the proposed team plan for team formation, human resource development, skill development, and recruitment. "Format Example 2"

[1602] Step 1: Define the requirements for your specific project.

[1603] Step 2: AI compares the project requirements with personnel information and suggests the optimal team composition.

[1604] Step 3: Apply the proposed team structure to the project.

[1605] "Example 3"

[1606] Step 1: Define a project with specific members and in a specific field.

[1607] Step 2: The AI ​​compares the skills of members with the project requirements and performs a simulation based on the results.

[1608] Step 3: Based on the simulation results, evaluate the probability of project success and the resources required.

[1609] Example 1

[1610] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1611] With conventional personnel management systems, it was difficult to effectively utilize the skills and experience of individual employees to form optimal teams. Furthermore, there was a lack of objective criteria for selecting the best members for specific projects, making it difficult to improve the efficiency of the entire organization. Furthermore, there was a lack of concrete methods for utilizing the proposed team plans in actual team formation, human resource development, skill improvement, and recruitment.

[1612] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1613] In this invention, the server includes: a means for inputting personnel information; a means for inputting information such as experience, projects, specialties, qualifications, and areas of interest; a means for storing the input information in a database; a means for using a generative AI model to analyze the stored information; a means for inputting a prompt to the generative AI model to generate a cross-organizational best-mix team proposal; a means for presenting the generated team proposal to the user; and a means for utilizing the proposed team proposal in team formation, human resource development, skill improvement, and recruitment. This makes it possible to maximize the skills and experience of individual employees and select the optimal members for a specific project. Furthermore, the proposed team proposal can be utilized in specific personnel policies, improving the efficiency of the entire organization.

[1614] "Human resources information" refers to data such as an employee's basic information, work history, skills, evaluations, and qualifications.

[1615] "Experience measures" refer to the experience and achievements of employees in projects and work they have participated in in the past.

[1616] A "project" refers to a set of activities or tasks carried out within an organization to achieve a specific purpose.

[1617] "Specialty" refers to the specialized knowledge and skills an employee has in a particular field or technology.

[1618] "Qualification" refers to any official certification or certificate obtained by an employee.

[1619] "Areas of interest" refers to areas or topics in which employees have personal interests.

[1620] A "database" refers to a system that systematically organizes and stores information so that it can be searched and used as needed.

[1621] A "generative AI model" is a model that uses artificial intelligence to analyze data and perform specific tasks.

[1622] A "prompt" refers to an instruction or question input to a generative AI model.

[1623] A "best mix team proposal" refers to a proposal that proposes a combination of members with the optimal skills and experience for a specific project.

[1624] "User" refers to a person who uses the system to input information and receive results.

[1625] "Team formation" refers to the process of selecting the best members to form a team to achieve a specific purpose.

[1626] "Human resource development" refers to education and training to improve employees' skills and abilities.

[1627] "Skill improvement" refers to activities aimed at further enhancing employees' skills and knowledge.

[1628] "Recruitment" refers to the process of selecting and adding new employees to an organization.

[1629] The present invention is a system in which a server, a terminal, and a user work in cooperation with each other. A specific embodiment of this system will be described below.

[1630] Server Operation

[1631] The server receives information provided by users, such as personnel information, experience, projects, specialties, qualifications, and areas of interest. This information is sent in JSON format via HTTP requests. The server stores the received information in a relational database such as MySQL or PostgreSQL.

[1632] The server then uses a generative AI model to analyze the stored information. Specifically, it uses a Python API to call OpenAI's GPT-4 model and generate a prompt. By inputting the prompt into the generative AI model, it generates a best-mix team proposal across organizations.

[1633] The generated team proposals are sent from the server to the device as an HTTP response in JSON format, allowing the user to check the optimal team member combinations.

[1634] Device behavior

[1635] The terminal receives information entered by the user through an input form, such as personnel information, experience, projects, specialties, qualifications, and areas of interest. This information is collected using a form on the web browser and JavaScript.

[1636] The collected information is sent to the server in JSON format using an AJAX request. The best mix team proposal received from the server is analyzed using JavaScript and dynamically reflected in HTML, allowing users to view the team proposal on their device screen.

[1637] User Actions

[1638] Users use their terminals to enter information such as personnel information, experience, projects, specialties, qualifications, and areas of interest. Specifically, they enter the required information into a form on a web browser. Once the information is complete, the terminal sends it to the server.

[1639] After receiving the best mix team proposal from the server, the user can check the team proposal displayed on the device screen, select the optimal team members, and take specific actions to ensure the success of the project.

[1640] Specific examples

[1641] For example, suppose a user wants to select the best team members to start a new project. The user uses a terminal to enter the following information:

[1642] Project name: New product development project

[1643] Required skills: Machine learning, data analysis, project management

[1644] Project duration: 6 months

[1645] The server receives this information, stores it in a database, and then uses a generative AI model to select the best team members and propose a team plan like this:

[1646] Member 1: Machine learning expert with 5 years of experience

[1647] Member 2: Data analysis expert with 3 years of experience

[1648] Member 3: Project management expert with 10 years of experience

[1649] Prompt Sentence Examples

[1650] "Please suggest the best team members with machine learning, data analysis, and project management skills for a new product development project. The project will last six months."

[1651] In this way, users can easily select the most suitable team members.

[1652] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1653] Step 1:

[1654] Users use their devices to enter information such as personnel information, experience, projects, specialties, qualifications, and areas of interest. Specifically, they enter the required information into a form on a web browser. The entered information is converted into JSON format using JavaScript.

[1655] Input: Information entered by the user, such as personnel information, experience, projects, specialties, qualifications, and areas of interest

[1656] Output: JSON format data

[1657] Step 2:

[1658] The terminal sends the input information to the server. Specifically, it uses an AJAX request to send JSON format data to the server as an HTTP request.

[1659] Input: JSON format data

[1660] Output: HTTP request to the server

[1661] Step 3:

[1662] The server receives the information sent from the device. Specifically, it analyzes the JSON format data received through the HTTP request and extracts the necessary information.

[1663] Input: JSON format data received as an HTTP request

[1664] Output: Extracted information

[1665] Step 4:

[1666] The server stores the received information in a database. Specifically, it uses a relational database such as MySQL or PostgreSQL and stores the data using an INSERT statement.

[1667] Input: Extracted information

[1668] Output: Information stored in the database

[1669] Step 5:

[1670] The server then invokes a generative AI model to analyze the stored information. Specifically, it uses a Python API to invoke OpenAI's GPT-4 model and generate a prompt.

[1671] Input: Information stored in a database

[1672] Output: Generated prompt statement

[1673] Step 6:

[1674] The server inputs prompt statements into the generative AI model to generate a best-mix team proposal across organizations. Specifically, it analyzes the results returned by the generative AI model and creates a list of appropriate members.

[1675] Input: Generated prompt text

[1676] Output: Best Mix Team Proposal

[1677] Step 7:

[1678] The server sends the generated team proposals to the device, specifically returning the results in JSON format as an HTTP response.

[1679] Input: Best Mix Team Proposal

[1680] Output: JSON formatted data as an HTTP response to the terminal

[1681] Step 8:

[1682] The device displays the best mix team proposal received from the server to the user. Specifically, it parses the received JSON data using JavaScript and dynamically reflects it in HTML.

[1683] Input: JSON format data as an HTTP response from the server

[1684] Output: Team proposals displayed to the user

[1685] Step 9:

[1686] Users can review the team proposals displayed on their device screen, select the most suitable team members, and take concrete actions to ensure the project's success.

[1687] Input: Team proposal displayed on the terminal

[1688] Output: User confirmation and action

[1689] (Application example 1)

[1690] Next, a description will be given of 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 headset type terminal 314 will be referred to as a "terminal."

[1691] In conventional factories, it was difficult to form optimal teams that took into account the skills and experience of workers, making it difficult to carry out work efficiently. Furthermore, there was no system for selecting the best workers for a specific project, which sometimes led to reduced work efficiency and project delays. This resulted in a decline in productivity throughout the factory and a loss of competitiveness.

[1692] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1693] In this invention, the server includes means for inputting personnel information, means for inputting information such as experience, projects, specialties, qualifications, and areas of interest, AI means for proposing a best mix team plan across organizations based on the input information, means for utilizing the proposed team plan in team formation, human resource development, skill improvement, and recruitment, and means for storing information such as the skills, experience, qualifications, and areas of interest of workers in the factory in a database and proposing the optimal work team for a specific task or project. This makes it possible to form the optimal work team in the factory, improving work efficiency and smooth project execution.

[1694] "Personnel information" refers to information about individuals, such as an employee's name, age, work history, skills, qualifications, and evaluations.

[1695] "Experience measures" refers to information that indicates the specific experience and achievements of an employee in projects or work that the employee has participated in in the past.

[1696] A "project" is a set of tasks or activities planned and carried out to achieve a specific purpose.

[1697] "Specialty" refers to the field, skill, or knowledge in which an employee is particularly skilled.

[1698] "Qualifications" refers to any official certifications, certificates, licenses, etc. that an employee has obtained.

[1699] "Areas of interest" refers to areas or topics that employees have a personal interest in.

[1700] "AI means" refers to systems and algorithms that use artificial intelligence technology to analyze data and make optimal team composition and proposals.

[1701] A "database" is a collection of information that is systematically organized and made available for efficient search and use.

[1702] A "work team" is a group of workers organized to accomplish a specific task or project.

[1703] "Team formation" is the process of selecting the best members to form a team for a specific purpose or project.

[1704] "Human resource development" refers to the activities of providing education and training to improve employees' skills and knowledge.

[1705] "Skill Up" refers to improving employees' skills and abilities.

[1706] "Recruitment" is the process of selecting and hiring new employees.

[1707] A system for carrying out this invention is configured as follows: The server includes means for inputting personnel information, means for inputting information such as experience measures, projects, specialties, qualifications, and areas of interest, AI means for proposing a best mix team plan across organizations based on the input information, means for utilizing the proposed team plan in team formation, human resource development, skill improvement, and recruitment, and means for storing information such as the skills, experience, qualifications, and areas of interest of factory workers in a database and proposing the optimal work team for a specific task or project.

[1708] The server runs the program using Python and uses SQLite as the database. The scikit-learn library is used for AI analysis. Specifically, worker information is stored in the database and the profiles are vectorized using a TF-IDF vectorizer. The cosine similarity between the project requirements and the worker profiles is calculated to suggest the optimal work team.

[1709] Users access the system using a smartphone or tablet and input the project requirements. The server then proposes the optimal work team based on the input requirements. For example, if the project requirements are "robotics, automation, and maintenance," the AI ​​will select the workers most suited to this.

[1710] An example prompt might be, "Enter 'Robotics, automation, maintenance' as your project requirements. Let the AI ​​suggest the best work team."

[1711] This system enables the optimal organization of work teams within the factory, improving work efficiency and ensuring smooth project execution.

[1712] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1713] Step 1:

[1714] Users access the system using a smartphone or tablet and enter project requirements.

[1715] Input: Project requirements (e.g., "Robotics, Automation, Maintenance")

[1716] Output: The input project requirements

[1717] Step 2:

[1718] The server receives the input project requirements and retrieves the worker information from the database.

[1719] Input: Project Requirements

[1720] Output: Worker information (e.g., skills, experience, qualifications, areas of interest)

[1721] Step 3:

[1722] The server vectorizes the worker information using a TF-IDF vectorizer.

[1723] Input: Worker information

[1724] Output: Vectorized worker profiles

[1725] Step 4:

[1726] The server vectorizes the project requirements and calculates the cosine similarity with the worker profiles.

[1727] Inputs: Vectorized project requirements, Vectorized worker profiles

[1728] Output: Cosine similarity score

[1729] Step 5:

[1730] The server selects the best working team based on the cosine similarity score.

[1731] Input: Cosine similarity score

[1732] Output: A list of optimal work team members

[1733] Step 6:

[1734] The server displays the optimal work team suggestions to the user.

[1735] Input: List of suitable work team members

[1736] Output: Optimal work team proposals displayed to the user

[1737] Step 7:

[1738] The user reviews the proposed work team and makes adjustments as needed.

[1739] Input: Optimal work team proposal

[1740] Output: Coordinated work team member list

[1741] In this way, the system proposes the optimal work team based on the project requirements entered by the user, and the user can confirm and adjust the proposal, resulting in efficient work team formation within the factory.

[1742] Example 2

[1743] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1744] Conventional team formation systems have difficulty efficiently comparing project requirements with personnel information and proposing optimal team compositions. Furthermore, they have problems in that they are unable to perform simulations based on the proposed team compositions or perform advanced analysis using generative AI models.

[1745] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for inputting personnel information, means for inputting information such as experience, projects, specialties, qualifications, and areas of interest, artificial intelligence means for proposing a best-mix team plan across organizations based on the input information, means for utilizing the proposed team plan in team formation, human resource development, skill improvement, and recruitment, means for generating prompt statements based on project requirements and personnel information, means for inputting the generated prompt statements into a generative AI model to propose an optimal team composition, and means for displaying the proposed team composition. This makes it possible to efficiently propose a team composition optimal for project requirements and further perform simulations and advanced analyses based on the proposal.

[1746] "Human Resources Information" refers to information such as an employee's skill set, years of experience, qualifications, and past project history.

[1747] "Experience measures" refer to the content and results of the experience an employee has had in projects or work they have participated in in the past.

[1748] A "project" is a set of tasks or activities planned to achieve a specific purpose.

[1749] "Specialty" refers to a field or skill in which an employee is particularly skilled.

[1750] "Qualification" refers to any official certification or certificate obtained by an employee.

[1751] "Areas of interest" refers to areas or topics that employees are interested in.

[1752] "Artificial intelligence means" refers to algorithms and models that suggest optimal team compositions based on collected data.

[1753] A "prompt" refers to an instruction or question that is input into a generative AI model.

[1754] A "generative AI model" refers to an artificial intelligence model that suggests optimal team composition based on input prompt text.

[1755] "Team formation" refers to selecting the best members for a specific project and forming a team.

[1756] "Human resource development" refers to education and training to improve employees' skills and abilities.

[1757] "Skill improvement" refers to improving employees' skills and knowledge.

[1758] "Recruitment" refers to the process of selecting and hiring new employees.

[1759] The present invention is a system for proposing a team suitable for a specific project. A specific embodiment of this system will be described below.

[1760] First, a user accesses the system's web interface using a terminal and enters the project requirements, including the required programming language, years of experience, and other skills. For example, the user might enter requirements such as "Python, JavaScript, 5+ years of experience, database management, and cloud services experience."

[1761] Next, the server retrieves relevant personnel information from a database based on the project requirements entered by the user. The database stores each member's skill set, years of experience, past project history, and other information. The server connects to the MySQL database and retrieves the personnel information using an SQL query. For example, it executes a query such as "SELECT FROM HR INFORMATION WHERE SKILLS LIKE '%Python%' AND YEARS OF EXPERIENCE >= 5."

[1762] The server generates a prompt to be input to the generative AI model based on the acquired personnel information. This prompt contains detailed descriptions of the project requirements and the skills and experience of each member. For example, the following prompts can be generated:

[1763] Project requirements:

[1764] Programming languages: Python, JavaScript

[1765] Years of experience: 5 years or more

[1766] Other skills: Database management, cloud services experience

[1767] Personnel information:

[1768] Member A: Python (5 years), JavaScript (3 years), Database Management (2 years)

[1769] Member B: Python (6 years), JavaScript (5 years), Cloud Services (4 years)

[1770] Member C: Python (4 years), JavaScript (6 years), Database Management (5 years)

[1771] Please suggest the best team composition.

[1772] The server inputs the generated prompt to a generative AI model (e.g., OpenAI's GPT-4) via an API request. The generative AI model then proposes the optimal team composition based on the input prompt. For example, it returns a suggestion such as, "Member B and Member C are optimal."

[1773] Finally, the server displays the proposal received from the generative AI model on a web interface. The user can review the proposed team composition and modify or approve it as needed. For example, a message such as "Members B and C have been selected" may be displayed.

[1774] This system efficiently proposes the team composition that best suits the project requirements, and also enables simulations and advanced analysis based on those proposals.

[1775] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1776] Step 1:

[1777] A user accesses the system's web interface using a terminal and enters project requirements, including the required programming language, years of experience, and other skills. For example, a requirement might be "Python, JavaScript, 5+ years of experience, database management, and cloud service experience." The input data is then sent to the server.

[1778] Step 2:

[1779] The server receives project requirements submitted by users and retrieves the relevant personnel information from the database. The server connects to the MySQL database and retrieves the personnel information using an SQL query. For example, it executes a query such as "SELECT FROM HR INFORMATION WHERE SKILLS LIKE '%Python%' AND YEARS OF EXPERIENCE >= 5". The input is the project requirements and the output is the retrieved personnel information.

[1780] Step 3:

[1781] The server generates a prompt sentence to be input to the generative AI model based on the acquired personnel information. The server generates the prompt sentence using a Python script. For example, it generates the following prompt sentence:

[1782] Project requirements:

[1783] Programming languages: Python, JavaScript

[1784] Years of experience: 5 years or more

[1785] Other skills: Database management, cloud services experience

[1786] Personnel information:

[1787] Member A: Python (5 years), JavaScript (3 years), Database Management (2 years)

[1788] Member B: Python (6 years), JavaScript (5 years), Cloud Services (4 years)

[1789] Member C: Python (4 years), JavaScript (6 years), Database Management (5 years)

[1790] Please suggest the best team composition.

[1791] The input is the personnel information obtained and the output is the generated prompt sentence.

[1792] Step 4:

[1793] The server inputs the generated prompt to a generative AI model (for example, OpenAI's GPT-4) via an API request. The generative AI model then proposes the optimal team composition based on the input prompt. For example, it returns a suggestion such as "Member B and Member C are optimal." The input is the generated prompt, and the output is the suggestion from the generative AI model.

[1794] Step 5:

[1795] The server displays the proposal received from the generative AI model on a web interface. The user can review the proposed team composition and make any necessary modifications or approvals. For example, a message such as "Members B and C have been selected" is displayed. The input is the proposal from the generative AI model, and the output is the team composition displayed to the user.

[1796] (Application example 2)

[1797] Next, a description will be given of 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 headset type terminal 314 will be referred to as a "terminal."

[1798] Previous systems only considered human resources when proposing a team suitable for a specific project, making it difficult to form an optimal team that took into account the skill sets and operating status of the machines and robots in the factory. Furthermore, the system lacked the functionality to automatically generate operating schedules for the proposed team, making efficient project management difficult.

[1799] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for inputting personnel information; means for inputting information such as experience, projects, specialties, qualifications, and areas of interest; AI means for proposing a best-mix team plan across organizations based on the input information; means for utilizing the proposed team plan in team formation, human resource development, skill improvement, and recruitment; means for managing the skill sets and operating status of each machine in the factory; means for inputting requirements for a new manufacturing project; means for AI to propose an optimal machine team; and means for automatically generating an operating schedule for the proposed team. This enables optimal team formation and efficient project management that takes into account both human and machine resources.

[1800] "Human Resources Information" refers to information such as an employee's skills, experience, qualifications, areas of expertise, and areas of interest.

[1801] "Experience measures" refer to the experience of projects and work that employees have previously participated in.

[1802] A "project" is a set of activities planned and carried out to achieve a specific purpose.

[1803] "Specialty" refers to advanced knowledge and skills in a particular field.

[1804] "Qualification" refers to the certification or attestation required to perform a particular job or function.

[1805] "Areas of interest" refers to areas or topics that an employee is personally interested in.

[1806] "Best Mix Team Proposal" refers to a plan that proposes the combination of members that best suits the project requirements.

[1807] "AI means" refers to a function that uses artificial intelligence to analyze data and propose optimal team composition and schedules.

[1808] "Team formation" refers to the process of selecting the best members for a particular project and building a team.

[1809] "Human resource development" refers to education and training to improve employees' skills and abilities.

[1810] "Skill Up" refers to improving employees' skills and knowledge.

[1811] "Recruitment" refers to the process of selecting and hiring new employees.

[1812] The "skill set of each machine in the factory" refers to the specific functions and capabilities of each machine or robot used in the factory.

[1813] "Operational status" refers to the current state in which a machine or robot is operating or is available for operation.

[1814] "New Manufacturing Project Requirements" refers to the conditions and specifications required for a new manufacturing project.

[1815] The "optimal machine team" refers to the combination of machines and robots that best meets the project requirements.

[1816] "Work schedule" refers to a plan showing when each member of the proposed team will be available.

[1817] A system for carrying out this invention has the following configuration: A server includes means for inputting personnel information, means for inputting information such as experience measures, projects, specialties, qualifications, and areas of interest, AI means for proposing a best mix team plan across organizations based on the input information, means for utilizing the proposed team plan in team formation, human resource development, skill improvement, and recruitment, means for managing the skill set and operating status of each machine in a factory, means for inputting requirements for a new manufacturing project, means for AI to propose an optimal machine team, and means for automatically generating an operating schedule for the proposed team.

[1818] Hardware and software used

[1819] Hardware: Servers, smartphones

[1820] Software: Python, scikit-learn, NumPy

[1821] Data processing and calculation

[1822] The server first inputs information such as personnel information, experience, projects, specialties, qualifications, and areas of interest into a database. Next, it collects data to manage the skill sets and operating status of each machine in the factory and inputs the requirements for a new manufacturing project. Based on this data, the AI ​​means proposes the optimal machine team. The AI ​​means uses scikit-learn's cosine_similarity to calculate the similarity between the project requirements and the machine skill sets and selects the optimal team. Furthermore, it processes the data using NumPy to automatically generate the operating schedule for the proposed team.

[1823] Specific examples

[1824] For example, if the requirements for a new manufacturing project are Skill A, Skill B, and Skill C, then Robot 1 in the factory has the skill set [1, 0, 1] and the available date is "2023-10-01", Robot 2 has the skill set [0, 1, 1] and the available date is "2023-10-05", and Robot 3 has the skill set [1, 1, 0] and the available date is "2023-10-03". In this case, the AI ​​tool will propose the optimal team based on this information and automatically generate an operating schedule.

[1825] Prompt Sentence Examples

[1826] A new manufacturing project requires skills A, B, and C. Please propose the optimal team taking into account the skill sets and operational status of the robots in the factory.

[1827] This enables optimal team formation and efficient project management that takes into account both human and machine resources.

[1828] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1829] Step 1:

[1830] The server inputs information such as personnel information and experience policies, projects, specialties, qualifications, areas of interest, etc. into the database, including employee skill sets, past project experience, etc. The input data is stored in the database for later processing.

[1831] Step 2:

[1832] The server collects data to manage the skill sets and operational status of each machine in the factory. Specifically, it inputs information such as the functions, capabilities, and available days of each machine or robot into a database. This data is used to optimally organize the machines into teams.

[1833] Step 3:

[1834] Users enter requirements for new manufacturing projects into the server, including the skills and capabilities needed, project start and finish dates, etc. The project requirements are then stored in a database.

[1835] Step 4:

[1836] The server processes the data to propose the optimal team based on the input project requirements and the personnel and machine information in the database. Specifically, it uses scikit-learn's cosine_similarity to calculate the similarity between the project requirements and the skill sets of each machine. Based on the calculation results, it selects the optimal machine team.

[1837] Step 5:

[1838] The server automatically generates a work schedule for the proposed team. Specifically, it uses NumPy to create a schedule based on the available days for the selected machines and robots. The generated schedule provides an optimal work plan between the start and end dates of the project.

[1839] Step 6:

[1840] The server presents the proposed team and work schedule to the user. The user reviews the proposed team composition and schedule, and makes any necessary modifications or approvals. The final team composition and schedule are finalized as the project execution plan.

[1841] In this way, the server achieves optimal team formation and efficient project management that takes into account both human and machine resources.

[1842] Example 3

[1843] Next, a third embodiment of the third embodiment will be described. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1844] With conventional project management systems, it was difficult to properly match member skills with ...

Claims

1. A means for obtaining personnel information; a means for capturing information including experience, projects, expertise, qualifications, and areas of interest; A means for storing the acquired information in a database; A means for inputting a prompt sentence into a generating AI model that analyzes the stored information to generate a best mix team proposal across organizations; A means for presenting the generated team proposal to a user; A system including:

2. The system of claim 1 , wherein the generative AI model is capable of suggesting a suitable team for a particular project.

3. The system of claim 1 , wherein the generative AI model has a function of enabling a simulation of a project in a specific field being carried out by specific members.

Images