System

Abstract

A system is provided.SOLUTION: The system includes a means for collecting data such as skills, experiences, interests, and department interaction histories of employees, a means for proposing appropriate matching for building a useful relationship between a specific employee and other employees on the basis of the collected data, and a means for visualizing communication patterns between employees and specifying connections in an organization and a latent isolation tendency.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In large and medium-sized companies, communication barriers exist between departments, limiting opportunities for meaningful mentoring and networking. Employee skill sets are often isolated, resulting in underutilization of the talent and expertise within the organization. The invention aims to solve these issues, improve the quality of communication between employees, and promote innovative ideas and effective collaboration. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for collecting data such as employee skills, experience, interests, and departmental interaction history; a means for proposing appropriate matches based on the collected data to build beneficial relationships between specific employees and other employees; and a means for visualizing communication patterns between employees and identifying connections and potential isolation trends within the organization. The system may also include a means for notifying a user of the collected data and the proposed results via their device, and a means for automatically collecting employees' emails, chat histories, and calendar data. This enables efficient mentoring and networking between employees and improves collaboration throughout the organization.

[0006] A "collection tool" is a device or software capable of capturing data such as employee skills, experience, interests, and department interaction history.

[0007] The "matching suggestion means" is a device or software that has the function of instructing appropriate pairing or group formation to build beneficial relationships between a specific employee and other employees based on collected data.

[0008] A "visualization tool" is a device or software that visually displays communication patterns between employees in the form of graphs, network diagrams, etc., and has the function of identifying connections within the organization and potential trends of isolation.

[0009] The "notification means" is a device or software that has the function of collecting data and sending the proposed content to the user's terminal and issuing a notification.

[0010] An "automated collection method" is a device or software that has the function of continuously collecting employee emails, chat history, calendar data, etc.

[0011] An "employee" is an individual with specific responsibilities within a company who has skills, experience, and interests.

[0012] "Devices" are electronic devices used by employees, such as computers, smartphones, and tablets.

[0013] A "server" is a central processing unit that performs various processes such as data collection, analysis, proposal generation, and notification.

[0014] "Department interaction history" refers to records of communication and collaboration, such as emails, chats, and meetings, between the departments to which an employee belongs.

[0015] "Visualized data" refers to visual information such as graphs and network diagrams generated based on the results of data analysis. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0037] The system of the present invention aims to collect data such as employee skills, experience, interests, and departmental interaction history, and based on the collected data, propose appropriate matches to build beneficial relationships, and visualize communication patterns between employees to identify connections within the organization and potential tendencies toward isolation.

[0038] System Overview

[0039] This system can be implemented mainly in the following configuration.

[0040] 1. Data collection method (server)

[0041] 2. Matching proposal method (server)

[0042] 3. Visualization Method (Server)

[0043] 4. Notification method (terminal)

[0044] 5. Automatic collection means (terminal)

[0045] Program processing

[0046] Data collection

[0047] The server collects data including employees' skills, experience, interests, and department interaction history. Specifically, the server obtains employees' project history, training, and skill assessment results through APIs. Based on the user's permissions, the device automatically collects employees' emails, chat history, and calendar data and periodically sends them to the server.

[0048] Data analysis

[0049] The server normalizes the collected data and anonymizes it if necessary. It then uses machine learning algorithms to match employees with the best mentoring and networking opportunities based on their skill sets and interests. The server analyzes the data and selects the best mentoring pairs and groups.

[0050] Matching proposals

[0051] Based on the data analysis, the server develops mentoring and networking plans to suggest suitable matches, including details of each employee's skills, interests and mutual benefits.

[0052] Proposal Notification

[0053] The server sends the proposal to the device, which then notifies the user via a pop-up notification or email, giving the user the option to review the proposal and accept or reject it.

[0054] Visualizing communication patterns

[0055] The server analyzes communication data such as emails, chats, and meeting frequency between employees. Based on the analysis results, it generates visualization data such as network diagrams and graphs and sends them to the device. The device then displays the visualization data to the user in the form of a dashboard or report.

[0056] Specific examples

[0057] For example, suppose Person A is an employee with deep knowledge of Python programming, while Person B is a new employee who wants to learn Python. If Person B enters his / her interest in Python into the terminal, and Person A also enters his / her skill set, the server will collect this information and perform analysis.

[0058] The server uses a machine learning algorithm to determine that Person A is a suitable mentor for Person B. The server then creates a matching proposal and notifies Person A and Person B of the proposal's contents to their devices. The users (Person A and Person B) check the notification and, if they approve the proposal, a mentoring session is set up.

[0059] Furthermore, the server analyzes the interactions and schedules between Person A and Person B and visualizes their communication patterns. The device displays this visualized data on a dashboard, making it possible to visualize the relationship between the two.

[0060] As described above, the system of the present invention can promote efficient mentoring and networking among employees, improve collaboration throughout the organization, and maximize the use of employees' skill sets.

[0061] The processing flow will be explained below.

[0062] Step 1:

[0063] Users enter information about their skills, experience, and interests into the terminal, such as "5 years of experience in Python programming" or "interested in machine learning."

[0064] Step 2:

[0065] The terminal transmits the input data to the server, where it formats the data and encrypts it as necessary.

[0066] Step 3:

[0067] The server stores the received data in a database, where it may be normalized and anonymized to protect privacy before being stored.

[0068] Step 4:

[0069] The server collects additional data from other business software (e.g., project management tools, mail servers) through APIs, including project history and communication history.

[0070] Step 5:

[0071] With the user's permission, the device automatically collects emails, chat history, and calendar data and sends them to the server, thereby obtaining the latest communication data.

[0072] Step 6:

[0073] The server analyzes all collected data and uses machine learning algorithms to extract features of employees' skills and interests, then calculates optimal mentoring and networking matches.

[0074] Step 7:

[0075] Based on the analysis results, the server generates a specific matching proposal for each user. For example, if Person A is suitable as a mentor for Person B, the server will provide a detailed description of "why Person A should be Person B's mentor."

[0076] Step 8:

[0077] The server sends the generated proposal to the target user's device, which receives the notification and notifies the user via a pop-up or email notification.

[0078] Step 9:

[0079] The user reviews the proposal from their device and has the option to accept or reject the proposal, and if accepted, a mentoring session is set up.

[0080] Step 10:

[0081] The server continuously collects and analyzes the mentoring sessions and communication history between users, thereby monitoring how the relationships between users are developing.

[0082] Step 11:

[0083] The server generates the analysis results as visualized data and displays them to the user in the form of a network diagram or graph. This visualized data is displayed on a dashboard on the terminal, allowing the user to easily check it.

[0084] These are the steps in the program, which will enable effective mentoring and networking among employees and significantly improve collaboration across the organization.

[0085] Example 1

[0086] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0087] In modern organizations, it is common for employees with diverse skills and interests to gather in one place. However, due to a lack of communication between employees and a lack of appropriate mentoring, their skills and experiences are often not fully utilized. As a result, not only is the building of beneficial relationships and collaboration between employees hindered, but it can also lead to a potential tendency for employees to become isolated. To solve these issues, a system is needed that can effectively collect and analyze employee data, propose appropriate matching, and visualize communication patterns.

[0088] 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.

[0089] In this invention, the server includes: means for collecting data such as employee skills, experience, interests, and department interaction history; means for proposing appropriate matches for building beneficial relationships between specific employees and other employees based on the collected data; means for visualizing communication patterns between employees and identifying connections within the organization and potential isolation tendencies; means for analyzing employees' skill sets and interests using machine learning algorithms to match them for optimal mentoring and networking; and means for sending notifications to terminals and providing users with the option to review and accept or reject the suggestions, thereby promoting efficient mentoring and networking between employees, improving collaboration across the organization, and making the most of employees' skill sets.

[0090] A "skill" is the knowledge, technique, or ability required to effectively perform a particular job or role.

[0091] "Experience" refers to practical knowledge and skills gained through previous work or projects.

[0092] "Interest" refers to the interest or curiosity an employee has in a particular field or activity.

[0093] "Interaction history" refers to records and log information regarding interactions and communications between employees.

[0094] "Matching" is the process of identifying and recommending employees who can build mutually beneficial relationships based on collected data.

[0095] "Communication patterns" are data that show the trends and frequency of dialogue and information exchange between employees.

[0096] "Visualization" is a method of displaying data using visual representations such as graphs and figures to make it easier to understand intuitively.

[0097] A "server" is a computer system for collecting and analyzing data and providing results.

[0098] A "terminal" is a device that is directly operated by a user and receives notifications and data from a server.

[0099] A "machine learning algorithm" is a computational method for learning patterns and rules from data and making future predictions and classifications.

[0100] A "notification" is a message or alert that provides information from the server to the terminal.

[0101] "Mentoring" is an activity in which experienced employees impart knowledge and skills to junior employees and support their growth.

[0102] "Networking" is the act of building relationships among employees to share information and resources and support each other.

[0103] "Analysis" is the process of examining collected data in detail to derive patterns and trends.

[0104] System Overview

[0105] The system of this invention effectively collects data such as employee skills, experience, interests, and departmental interaction history, and then uses this data to suggest optimal mentoring and networking opportunities. Furthermore, by visualizing communication patterns between employees, it identifies connections within the organization and potential isolationist tendencies. It mainly consists of the following components:

[0106] 1. Data collection method (server)

[0107] 2. Matching proposal method (server)

[0108] 3. Visualization Method (Server)

[0109] 4. Notification method (terminal)

[0110] 5. Automatic collection means (terminal)

[0111] server

[0112] The server is mainly responsible for data collection, analysis, matching proposals, visualization, etc. The server uses the following specific software and hardware:

[0113] Data collection method: Employees enter their skills, experience, interests, and project history through an API (e.g., a RESTful API). Data is acquired using the Python library Requests.

[0114] Data analysis methods: Normalize the collected data and anonymize it if necessary. For example, use Python's pandas library to manipulate data frames and hash personally identifiable information.

[0115] Machine learning tools: We use machine learning algorithms to analyze employee skill sets and interests. Specifically, we use the scikit-learn library to perform clustering and classification algorithms.

[0116] Matching proposal method: Based on the analysis results, the optimal mentoring pair or group is selected. Proposals are generated using a Python script.

[0117] Visualization method: Analyze communication data between employees and generate network diagrams and graphs. Visualization is performed using Matplotlib and networkx libraries.

[0118] Terminal

[0119] A terminal is a device that a user directly operates and that receives notifications and data from a server. A terminal includes the following specific software:

[0120] Data input method: Provides an interface for users to input data such as skills and interests. A front-end application written in JavaScript is used.

[0121] Automatic collection method: The device periodically collects the user's email, chat history, and calendar data and sends it to the server. For example, a cron job can be set up to upload the data to the server on a fixed schedule.

[0122] Notification method: Proposals and notifications from the server are displayed to the user. JavaScript's Notification API is used to display pop-up notifications in the browser.

[0123] Visualization data display method: Display the received visualization data in the form of dashboards and reports. Generate interactive network diagrams using the D3.js library.

[0124] Specific examples

[0125] For example, suppose Person A is an employee with strong Python skills, and Person B is a new employee who wants to learn Python. Person B enters his / her interest in Python into the terminal, and Person A also enters his / her own skill set. The terminal collects this information and sends it to the server at 2:00 AM every day.

[0126] The server normalizes the received data, analyzes it using the scikit-learn library, and determines that Person A is suitable as a mentor for Person B. The server then creates a matching proposal and sends it to the devices of Person A and Person B. The devices notify Person A and Person B of the proposal via a pop-up notification, and the users can review the proposal and accept or reject it.

[0127] Once approved, the server analyzes the communication data between Person A and Person B and creates a visualized network diagram. The device displays this visualized data on a dashboard, visualizing the relationship between Person A and Person B.

[0128] Prompt Sentence Examples

[0129] "I want to develop a model to collect employee skills, experience, interests, and department interaction history to suggest optimal mentoring pairs or groups. Please explain how you will collect the data, analyze it, inform your suggestions, and visualize communication patterns."

[0130] As described above, the system of the present invention promotes effective mentoring and networking among employees, improving collaboration throughout the organization and making the most of employees' skill sets.

[0131] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0132] Step 1:

[0133] The terminal accepts data input from the user. The user enters their skills, experience, and interests into a form. This input data is stored in a local database. Specifically, when a user enters skills (e.g., Python, project management), experience (e.g., 5 years of software development experience), and interests (e.g., machine learning) into a web form and presses the submit button, an application written in JavaScript collects this data and stores it in IndexedDB.

[0134] Step 2:

[0135] The device periodically sends data to the server. For example, a cron job can be set up at 2:00 AM every day to securely upload the stored data to the server using the HTTPS protocol. The input data is in JSON format and is included in the request header along with any necessary authentication information. Specifically, the device runs the cron job and sends the data to the server using the Python Requests library.

[0136] Step 3:

[0137] The server normalizes the received data. For example, it represents each employee's data in a uniform format and handles missing values. The input data is in JSON format, and the output data is also in a similarly normalized JSON format. Specifically, the server uses the Python pandas library to convert the received data into a data frame and normalize each field.

[0138] Step 4:

[0139] The server anonymizes the data. For example, it hashes personally identifiable information to protect privacy. The input data is in JSON format, and the output data is also anonymized JSON. Specifically, the server hashes personally identifiable information using Python's hashlib library.

[0140] Step 5:

[0141] The server uses machine learning algorithms to analyze the collected data. For example, it clusters employees' skill sets and interests to find the most suitable mentoring pairs. The input data is anonymized JSON format, and the output data is a list of matching results. Specifically, the server uses the scikit-learn library to perform k-means clustering to determine suitable matches.

[0142] Step 6:

[0143] The server creates matching proposals, for example, generating proposal documents containing details of suitable mentor candidates or networking partners for each employee based on the analysis results. The input data is a list of analysis results, and the output data is a JSON format containing proposal details. Specifically, the server uses a Python script to generate proposal documents for each pair.

[0144] Step 7:

[0145] The server sends the proposal content to the device. For example, details of the generated proposal are sent to each employee's device via email or push notification. The input data is JSON format containing the proposal details, and the output data is the notification sending status. Specifically, the server configures an SMTP server and sends emails.

[0146] Step 8:

[0147] The device displays a notification to the user, for example, a pop-up notification or email with the proposal so that the user can review it. The input data are the proposal details, and the output data is the user's response (accept or reject). Specifically, the device uses JavaScript's Notification API to display a pop-up notification in the browser.

[0148] Step 9:

[0149] The user reviews the proposal and responds by either accepting or rejecting it. The input data is the proposal details, and the output data is the user's response (accept or reject). Specifically, after the user reviews the proposal, they click the confirm button, and the response is sent to the server.

[0150] Step 10:

[0151] The server receives the user's response and sets up a mentoring session or networking event, for example, by adding an event to a calendar if approved. The input data is the user's response, and the output data is the details of the set up event. Specifically, the server sets up a mentoring session using the Google Calendar API.

[0152] Step 11:

[0153] The server collects, analyzes, and visualizes communication data between employees. For example, it analyzes the frequency of emails and chats to create a communication network. The input data is communication history, and the output data is in graph format for visualization. Specifically, the server analyzes communication patterns using the networkx library and visualizes them using Matplotlib.

[0154] Step 12:

[0155] The terminal displays the visualized data on a dashboard, such as an interactive network diagram or graph, to help employees easily understand it. The input data is the visualized graph, and the output data is the display on the dashboard. Specifically, the terminal uses the D3.js library to display the visualized data on the browser.

[0156] The above are the specific processing steps of the program of this system.

[0157] (Application example 1)

[0158] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0159] Communication and skill matching between staff members in brick-and-mortar stores are important factors in streamlining store operations and improving staff performance. However, conventional methods make it difficult to efficiently pair staff members appropriately, taking into account each staff member's skills, experience, and interests. It is also difficult to visualize communication patterns between staff members and understand their relationships and potential isolation. This can lead to interpersonal friction, a sense of unfairness in evaluations, and even a decline in the operational efficiency of the entire store. To solve these issues, a system is needed that can propose optimal pairings based on staff members' skills and interests, and visualize their communication patterns.

[0160] 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.

[0161] In this invention, the server includes: means for collecting data such as employee (staff) skills, experience, interests, and department (shift) interaction history; means for proposing appropriate matching based on the collected data to build beneficial relationships between specific employees (staff) and other employees (staff); means for visualizing communication patterns between employees (staff) and identifying connections and potential isolation tendencies within the organization (store); means for proposing optimal pairings between staff in a physical store based on the collected and analyzed data to promote skill improvement and work efficiency; and means for visualizing communication patterns between staff and identifying relationships and isolation tendencies within the store. This makes it possible to improve the operational efficiency of physical stores, maximize staff capabilities, and perform fair evaluations.

[0162] "Employees (staff)" refers to people employed by a company, organization, or specific store, who have roles and responsibilities necessary for carrying out business. This also includes staff who contribute to the operation of physical stores.

[0163] "Skills" are the abilities and techniques required to carry out specific tasks or work, and their acquisition requires training and experience.

[0164] "Experience" refers to the knowledge and know-how that employees (staff) have gained through past work and projects, which contributes to improving their ability to carry out their work.

[0165] "Interest" refers to the interest and enthusiasm that employees (staff) have in a particular field or skill, and their motivation to learn new things based on this.

[0166] A "department (shift)" refers to a group or team that performs a specific task or role within a company or organization. In a physical store, it also includes the working hours and schedule of staff.

[0167] "Interaction history" refers to records of communication and collaboration between employees (staff), and includes data such as emails, chats, and meetings.

[0168] "Matching" refers to optimally pairing employees (staff) with each other based on specific criteria or algorithms, with the aim of complementing each other's skills and interests and improving work efficiency.

[0169] "Pairing" refers to creating optimal pairs based on skills, experience, and interests, with the aim of improving the work performance and capabilities of store staff.

[0170] "Communication patterns" indicate the method, frequency, and content of interactions between employees (staff), and analyzing these can visualize the relationships and cooperation within an organization.

[0171] "Visualization" refers to displaying analyzed data in a visual format such as graphs, charts, or network diagrams, making it easier to understand and gain insight into the information.

[0172] The system of the present invention collects and analyzes data such as the skills, experience, and interests of employees (staff), and the interaction history of departments (shifts), thereby visualizing optimal matching and communication patterns. This system can be implemented as follows based on the claims of the present invention.

[0173] composition

[0174] The system includes the following components:

[0175] 1. Data collection method (server)

[0176] 2. Matching proposal method (server)

[0177] 3. Visualization Method (Server)

[0178] 4. Notification method (terminal)

[0179] 5. Automatic collection means (terminal)

[0180] Data collection

[0181] The server periodically collects data through the API, including staff skills, experience, interests, and shift history, including information staff enter into their profiles and information retrieved through the scheduling application, as well as email, chat history, and calendar data automatically collected from devices.

[0182] Data analysis

[0183] The collected data is normalized and, if necessary, anonymized on the server. Machine learning algorithms (e.g., K-means clustering) are used to optimally pair staff based on their skill sets and interests. Based on the results of this analysis, optimal mentoring and team formation are suggested.

[0184] Matching proposals

[0185] The server then generates optimal matching suggestions based on the analysis, creating a list of specific mentoring pairs or teams, including detailed information about staff skills, interests, and mutual benefits.

[0186] Proposal Notification

[0187] The proposal is sent to the device, which notifies the staff member via a pop-up notification or email, and the staff member is given the option to review the proposal and accept or reject it.

[0188] Visualizing communication patterns

[0189] The server analyzes communication data such as emails, chats, and meeting frequency to generate network diagrams and graphs, visually displaying relationships between staff and potential isolation trends. This visualized data is provided in the form of dashboards and reports on the device.

[0190] Specific examples

[0191] For example, if staff member A is fluent in Spanish and staff member B wants to learn that skill, their information is entered into their devices and analyzed by the server. Based on the analysis results, A and B are identified as suitable pairing candidates, and this information is notified to both their devices. Upon receiving the notification, A and B can begin a mentoring session based on the proposed pairing.

[0192] Example prompts for generative AI models

[0193] Please suggest the best matching pair based on the following data:

[0194] Staff A: Spanish skill level 5, Interests: Teaching

[0195] Staff B: Spanish skill level 2, Interests: Learning

[0196] Staff C: Planning Skill Level 4, Interests: Leadership

[0197] Staff D: Planning skill level 3, Interests: Learning

[0198] Proposal format: [Staff pair / group, reason]

[0199] As described above, by using the system of the present invention, it is possible to improve the operational efficiency of physical stores, maximize the capabilities of staff, and achieve fair evaluations.

[0200] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0201] Step 1: Data collection

[0202] The server collects data including staff skills, experience, interests, and shift history through an API. This data comes from information entered in each staff member's profile and data obtained from the scheduling app. The collected data is then normalized and stored. This data includes staff skill levels, interest categories, and shift times. This allows for the management of distributed data in a unified format.

[0203] Step 2: Additional automated data collection

[0204] The devices automatically collect staff emails, chat history, and calendar data. This data is periodically sent to the server with the user's permission. Specifically, the devices analyze the staff's communication history and extract information such as the number of emails, chat frequency, and meeting schedules. This data is sent to the server and used as data for analysis.

[0205] Step 3: Data analysis

[0206] The server normalizes the collected data and anonymizes it if necessary. It then uses machine learning algorithms (e.g., K-means clustering) to optimally pair staff based on skill sets and interests. For example, it clusters each staff member's skill level and areas of interest as a feature vector, and groups staff members with similar characteristics. This enables pairings that are expected to complement each other's skills and harmonize their interests.

[0207] Step 4: Generate matching proposals

[0208] The server generates optimal matching proposals based on the results of the data analysis. Specifically, it creates a list for each clustered group or pair, detailing the reasons for each match and the benefits of the pairing. This proposal list is organized to include information on staff skills, interests, and mutual benefits. This allows it to propose optimal mentoring and team formation among staff.

[0209] Step 5: Notification of proposal

[0210] The server sends the generated matching proposal to the terminal. The terminal notifies the staff of the proposal via a pop-up notification or email. The user can then review the details of the proposal based on the notification and select the option to approve or reject it. This allows the user to decide whether or not to proceed with the proposed match and proceed to the next step.

[0211] Step 6: Visualize communication patterns

[0212] The server analyzes communication data such as emails, chats, and frequency of meetings between staff members. Based on the analysis results, it generates visualized data such as network diagrams and graphs. Specifically, by analyzing the communication data and illustrating the contact points and frequency of each staff member using node and edge relationships, it clarifies the relationships within the organization and potential isolation trends. This visualized data is sent to the terminal and displayed to the user in the form of a dashboard or report.

[0213] 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.

[0214] The system of the present invention aims to collect data such as employee skills, experience, interests, departmental interaction history, and employee emotions, propose matches to build beneficial relationships, and visualize communication patterns between employees to identify connections within the organization and potential trends toward isolation. By utilizing an emotion engine that recognizes user emotions, more advanced and accurate matching becomes possible.

[0215] System Overview

[0216] The system of the present invention can be implemented in the following configuration:

[0217] 1. Data collection method (server)

[0218] 2. Emotion engine (server)

[0219] 3. Matching proposal method (server)

[0220] 4. Visualization Method (Server)

[0221] 5. Notification Method (Terminal)

[0222] 6. Automatic collection means (terminal)

[0223] Program processing

[0224] Data collection

[0225] The server collects data including employees' skills, experience, interests, department interaction history, and emotional state. Users input their skills and interests into their devices, which then send the data to the server. Furthermore, with the user's permission, the device automatically collects email, chat history, and calendar data and sends them to the server. The emotion engine analyzes the user's emotions from this text and voice data and sends the results to the server.

[0226] Data analysis

[0227] The server normalizes the collected data and anonymizes it as necessary. It then uses a machine learning algorithm to extract features based on employees' skills, experience, interests, and emotional state, and calculates optimal mentoring and networking matches. It also analyzes the results of the emotion engine, taking emotional compatibility into account.

[0228] Matching proposals

[0229] The server generates appropriate matching proposals based on the results of data analysis. The proposals take into account each employee's skills, experience, interests, emotional state, and mutual benefits. For example, if Person A is familiar with Python and Person B wants to learn Python, the server will generate a proposal that Person A would be a good mentor for Person B. The results of the emotion engine are also taken into account, and the proposal is adjusted to be made when Person A and Person B are in a good emotional state.

[0230] Proposal Notification

[0231] The server sends the generated proposal to the target user's device, which notifies the user via a pop-up notification or email notification. The user can review the proposal and choose the option to accept or reject it.

[0232] Visualizing communication patterns

[0233] The server analyzes communication data between users, such as the frequency of emails, chats, and meetings, and generates visualized data in the form of network diagrams and graphs. The results of the emotion engine are also reflected in the visualized data, so the user's emotional state is also displayed. The device displays the visualized data in a dashboard format, making it easy for the user to check.

[0234] Specific examples

[0235] For example, suppose Person A has deep knowledge of Python programming, and Person B is a new employee who wants to learn Python. Person B enters his / her interest in Python into the device, and Person A enters his / her skill set. The device sends this data to the server, and the emotion engine then analyzes the emails, chat contents, and voice data of these users and sends their emotional state to the server.

[0236] The server analyzes all data, including skills, interests, and emotional state. If A is the best mentor for B to learn Python, and both parties are in a good emotional state, the server creates a matching proposal and notifies A and B's devices. If both parties confirm the proposal and approve it, a mentoring session is set up.

[0237] In this way, the system of the present invention enables efficient mentoring and networking among employees, effectively utilizes employees' skill sets, and improves collaboration across the organization by taking into account emotional matching.

[0238] The processing flow will be explained below.

[0239] Step 1:

[0240] Users enter information about their skills, experience, and interests into the device, such as "5 years of Python programming experience" or "interested in machine learning."

[0241] Step 2:

[0242] The terminal transmits the input data to the server, where it is formatted and encrypted.

[0243] Step 3:

[0244] The server stores the received data in a database, normalizing and, if necessary, anonymizing the data before storing it.

[0245] Step 4:

[0246] If the user gives permission, the device will automatically collect email, chat history, and calendar data on a regular basis and send it to the server.

[0247] Step 5:

[0248] The server retrieves relevant data from other business software (e.g., project management tools, mail servers) through APIs, including project history and communication history.

[0249] Step 6:

[0250] The emotion engine analyzes the text data and voice data of the user's emails and chats to identify the user's emotional state, and then sends the analysis results to the server.

[0251] Step 7:

[0252] The server normalizes all collected data and uses machine learning algorithms to extract employee skills, experience, interests, and emotional states as features.

[0253] Step 8:

[0254] The server calculates optimal mentoring and networking matches between users based on the feature values, taking into account the results of the emotion engine, and reflecting emotional compatibility in the matching.

[0255] Step 9:

[0256] The server generates specific match proposals based on the valid matches, including details of each user's skills, experience, interests, emotional state, and mutual interests.

[0257] Step 10:

[0258] The server sends the generated proposal to the target user's device. For example, it sends a proposal that person A is suitable to be person B's mentor.

[0259] Step 11:

[0260] The device will receive the suggestion and notify the user via a pop-up or email notification, giving the user the option to review the suggestion and accept or reject it.

[0261] Step 12:

[0262] If the user accepts the proposal, the device provides a scheduling function for setting up mentoring sessions and networking events.

[0263] Step 13:

[0264] The server continuously collects and analyzes the mentoring sessions and communication history between users, thereby monitoring how the relationships between users are developing.

[0265] Step 14:

[0266] The server generates the analysis results as visualized data and displays them as graphs and network diagrams. It also visually displays the user's emotional state, reflecting the results of the emotion engine.

[0267] Step 15:

[0268] The device displays the visualized data in a dashboard format, allowing users to easily check the analysis results, and understand their own communication patterns and emotional state.

[0269] In this way, the system of the present invention realizes efficient mentoring and networking among employees, and by taking into consideration emotional matching, it is possible to improve collaboration throughout the organization.

[0270] Example 2

[0271] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0272] In modern companies, a key challenge is to maximize the use of individual employee characteristics, such as skills, experience, and interests, to promote communication and cooperation among employees. However, it is extremely difficult to properly match these characteristics and understand emotional compatibility, employee connections, and potential tendencies toward isolation. Conventional systems often lack the accuracy of data collection, analysis, and matching proposals, resulting in ineffective relationship building. Therefore, there is a need for a system that can achieve high-precision matching that takes into account employee skills and emotional states, and visualize communication patterns.

[0273] 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.

[0274] In this invention, the server includes means for collecting data including employee skills, experience, interests, department interaction history, and emotional state, means for proposing appropriate matches for building beneficial relationships between specific employees and other employees based on the collected data, means for analyzing the emotional data and taking emotional compatibility into account in the collected data, and means for visualizing communication patterns between employees and identifying connections within the organization and potential tendencies toward isolation. This enables highly accurate matching based on employee skills and emotional state, thereby improving communication and cooperation within the company.

[0275] "Employee skills" refers to the specialized knowledge and abilities possessed by individual employees.

[0276] "Experience" refers to the accumulation of practical knowledge and skills that employees have acquired through their work.

[0277] "Interests" refer to areas or activities that interest employees.

[0278] "Department interaction history" refers to records of business interactions and communications between employees.

[0279] "Emotional state" refers to data that shows an employee's emotional state, such as joy or stress.

[0280] "Means of collecting data" refers to the methods and devices used to collect information entered by employees and data collected automatically.

[0281] "Means for suggesting matches" refers to methods or systems that use collected data to help connect specific employees with other employees to beneficial relationships.

[0282] "Means for analyzing emotional data" refers to methods and algorithms for analyzing collected emotional data and understanding emotional compatibility and state.

[0283] "Means for visualizing communication patterns" refers to methods and tools for displaying the frequency and form of communication between employees in the form of graphs, network diagrams, etc.

[0284] The system of the present invention aims to collect data such as employee skills, experience, interests, department interaction history, and emotional state, propose matches to build beneficial relationships, and further visualize communication patterns between employees to identify connections within the organization and potential tendencies toward isolation. The following describes in detail the modes for implementing the present invention.

[0285] System Configuration

[0286] The system of the present invention can be implemented in the following configuration:

[0287] 1. Data collection method (server)

[0288] 2. Emotion engine (server)

[0289] 3. Matching proposal method (server)

[0290] 4. Visualization Method (Server)

[0291] 5. Notification Method (Terminal)

[0292] 6. Automatic collection means (terminal)

[0293] Data collection

[0294] The server collects data including employees' skills, experience, interests, department interaction history, and emotional state. Users input their skills and interests into their devices, which then send the data to the server. Furthermore, with the user's permission, the device automatically collects email, chat history, and calendar data and sends them to the server. The emotion engine analyzes the user's emotions from this text and voice data and sends the results to the server.

[0295] Data analysis

[0296] The server normalizes the collected data and anonymizes it as necessary. It then uses a machine learning algorithm to extract features based on employees' skills, experience, interests, and emotional state, and calculates optimal mentoring and networking matches. It also analyzes the results of the emotion engine, taking emotional compatibility into account.

[0297] Matching proposals

[0298] The server generates appropriate matching proposals based on the results of data analysis. For example, if one employee is familiar with Python and another employee wants to learn Python, it will generate a proposal that the two are suitable for a mentor-learner relationship. By incorporating the results of the emotion engine, the server also evaluates the emotional compatibility between the two parties.

[0299] Proposal Notification

[0300] The server sends the generated proposal to the target user's device, where the device notifies the user of the proposal via a pop-up notification or email notification. The user can review the proposal and choose to accept or reject it.

[0301] Visualizing communication patterns

[0302] The server analyzes communication data between users, such as emails, chats, and frequency of meetings, and generates visualized data in the form of network diagrams and graphs. The results of the emotion engine are also reflected in the visualized data, so the user's emotional state is also displayed. The device displays the visualized data in a dashboard format, making it easy for users to check.

[0303] Specific examples

[0304] For example, suppose Person A has deep knowledge of Python programming, and Person B is a new employee who wants to learn Python. Person B enters his / her interest in Python into the device, and Person A enters his / her skill set. The device sends this data to the server, and the emotion engine analyzes the emails, chat contents, and voice data of these users and sends their emotional state to the server.

[0305] The server analyzes all data, including skills, interests, and emotional states. If A is the best mentor for B to learn Python, and both parties are in a good emotional state, the server creates a matching proposal and notifies A and B's devices. If both A and B accept the proposal, a mentoring session is set up. In this way, the system of the present invention realizes efficient mentoring and networking among employees, effectively utilizing employees' skill sets, and improves collaboration across the organization by taking emotional matching into consideration.

[0306] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0307] Step 1: Enter and collect data

[0308] 1.1 User Input

[0309] The user enters their skills, experience, and interests into the terminal. For example, they might enter, "I'm interested in Python programming and have basic knowledge."

[0310] The terminal collects the data entered by the user and transmits it to the server.

[0311] Input: Skills, experience, and interest data entered by the user.

[0312] Output: Data sent from the device to the server.

[0313] 1.2 Automatic Data Collection

[0314] With the user's permission, the device automatically collects email, chat history, and calendar data.

[0315] The terminal transmits the collected data to the server.

[0316] Input: User permission, email and chat history, calendar data.

[0317] Output: Email, chat history, and calendar data sent from the device to the server.

[0318] 1.3 Emotion Data Analysis

[0319] The emotion engine analyzes the user's emotions from collected text and voice data. For example, it can extract emotions such as "feeling stressed" from the content of an email.

[0320] The emotion engine sends the analysis results as data to the server.

[0321] Input: text and audio data.

[0322] Output: Sentiment analysis results sent to the server.

[0323] Step 2: Normalize and anonymize data

[0324] 2.1 Data normalization

[0325] The server unifies and normalizes the collected data formats, for example, unifying due dates and skill levels across different formats.

[0326] Input: Raw data collected.

[0327] Output: Normalized data.

[0328] 2.2 Data anonymization

[0329] The server anonymizes the data as needed, for example by replacing employee identifying information with a random identifier.

[0330] Input: Normalized data.

[0331] Output: Anonymized data.

[0332] Step 3: Feature extraction and matching calculation

[0333] 3.1 Feature extraction

[0334] The server uses machine learning algorithms to extract features such as skills, experience, interests, and emotional state. For example, a user's skill set might be extracted as "Python: intermediate, data analysis: beginner."

[0335] Input: Normalized data, anonymized data.

[0336] Output: Data extracted as features.

[0337] 3.2 Matching Calculation

[0338] The server calculates the optimal match based on the extracted features, deriving a result such as "Person A is the best mentor for Person B."

[0339] The server also takes into account the results of the emotion engine and incorporates emotional compatibility into its calculations, for example, "Make a proposal when A and B are in a good emotional state."

[0340] Input: Data extracted as features, sentiment analysis results.

[0341] Output: Best matching suggestion.

[0342] Step 4: Generate and notify matching proposals

[0343] 4.1 Generating Matching Proposals

[0344] The server generates appropriate matching proposals based on the results of the data analysis, for example, "Propose that person A mentor person B in Python."

[0345] Input: Best matching proposal data.

[0346] Output: Specific matching suggestions.

[0347] 4.2 Proposal Notification

[0348] The server sends the generated proposal to the target user's device. For example, it notifies the devices of user A and user B that "a mentoring proposal is available."

[0349] The device will notify the user of the suggestions via a pop-up notification or email notification.

[0350] The user reviews the proposal and has the option to accept or reject it.

[0351] Input: A specific matching suggestion.

[0352] Output: Notifications to the terminal and responses from the user.

[0353] Step 5: Visualize communication patterns

[0354] 5.1 Data Analysis

[0355] The server analyzes communication data such as the frequency of emails, chats, and meetings between users. For example, it collects data such as "Person A and Person B frequently email or chat."

[0356] The results of the emotion engine are also reflected in the visualization data, so the user's emotional state is also displayed.

[0357] Input: Communication data between users, sentiment analysis results.

[0358] Output: Analysis results of communication patterns.

[0359] 5.2 Generating visualization data

[0360] The server generates visualization data in the form of network diagrams and graphs based on the analysis results. For example, it creates a network diagram showing the communication patterns between person A and person B.

[0361] Input: Analysis results of communication patterns.

[0362] Output: Visualized data as network diagrams and graphs.

[0363] 5.3 Viewing the Dashboard

[0364] The device displays visualized data in a dashboard format for easy viewing by the user. For example, it provides a dashboard displaying the communication patterns and emotional states of person A and person B.

[0365] Input: Visualization data.

[0366] Output: Display in dashboard format.

[0367] (Application example 2)

[0368] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0369] It is necessary to optimize the work efficiency of automated machines operating in factories and realize team formation that makes the most of each machine's skills, work history, and interest level. It is also necessary to improve productivity by visualizing communication patterns between automated machines and identifying potential inefficiencies.

[0370] 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.

[0371] In this invention, the server includes means for collecting data such as the skills, work history, interest level, and team interaction history of automated machines operating in a factory, means for proposing beneficial team formation and work distribution between a specific automated machine and other automated machines based on the collected data, and means for visualizing communication patterns between the automated machines and identifying efficiencies and potential inefficiencies in the workplace. This enables effective team formation and work distribution that makes the most of the skills and work history of the automated machines, thereby improving productivity in the factory.

[0372] "Automatic machines" refers to robots and mechanical devices operating in factories, and is a general term for machines that perform tasks automatically.

[0373] "Skill" refers to the ability to perform a specific task or action that an automated machine can perform.

[0374] "Work history" is a record of work that an automated machine has performed in the past, and includes data such as the success rate and work time.

[0375] "Interest" refers to the degree of interest in tasks that automated machines excel at or have shown a high success rate in the past.

[0376] "Team interaction history" refers to the history of past collaborative and cooperative work between automated machines.

[0377] "Communication pattern" is a concept that indicates the format and frequency of data exchange and operational coordination between automated machines.

[0378] An "operation log" is a detailed record of the operations of an automated machine recorded while it is in operation, including operating status and error information.

[0379] An "error log" refers to a record of errors or malfunctions that occur while an automated machine is operating.

[0380] "Visualization" refers to the process of displaying data as graphs or charts so that it can be understood at a glance.

[0381] "Control device" refers to a server or terminal device used to monitor and manage automated machinery.

[0382] The present invention is a system for optimizing work efficiency and productivity using automated machines operating in a factory. The system includes the following components:

[0383] 1. Data collection method (server)

[0384] The server collects data on the skills, work history, interest level, team interaction history, operation logs, error logs, etc. of the automated machines operating in the factory. A Python script is used to collect data, which is then sent to the management server in real time.

[0385] 2. Machine learning algorithm (server)

[0386] The server normalizes the collected data and anonymizes it if necessary. It then uses machine learning algorithms to extract features based on each machine's skills, work history, and interest levels, and calculates optimal team composition and work distribution. The machine learning algorithms used include scikit-learn and TensorFlow.

[0387] 3. Matching proposal method (server)

[0388] Based on the collected and analyzed data, the server proposes beneficial team formation and work distribution between specific automated machines and other automated machines. The proposal is optimized taking into account the skills, work history, and interest of each automated machine, and the proposal is notified to the control device.

[0389] 4. Proposal notification means (control device)

[0390] The server notifies the control device of the generated proposal, allowing engineers and operators in the factory to review the proposed team formation and work distribution and approve them as necessary.

[0391] 5. Visualization tools (dashboards)

[0392] The server analyzes the frequency of data exchange and collaboration between automated machines and generates visualized data in the form of network diagrams and graphs. Tools used for visualization include Tableau and D3.js. This visualized data is displayed in a dashboard format so that operators can easily check it.

[0393] Specific examples

[0394] For example, suppose that automatic machine A is responsible for assembly work in a factory, and automatic machine B is responsible for inspection work. The operation logs and work history of automatic machines A and B are sent to a server, which analyzes them. Based on the analysis results, the server proposes the optimal way for automatic machines A and B to work together and notifies the control device.

[0395] Once the engineers review the proposals on the dashboard and approve the proposed teaming and work distribution, new collaborations can begin, improving productivity within the factory and making the most of the skills and work history of each automated machine.

[0396] ---

[0397] Example prompts for input to a generative AI model:

[0398] "Factory robot A specializes in assembly work, and robot B specializes in inspection work. Please generate a proposal for the optimal collaboration work based on past success stories."

[0399] ---

[0400] In this way, the system of the present invention realizes efficient and highly productive factory operations, and maximizes the capabilities of automated machines.

[0401] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0402] Step 1:

[0403] The server collects data such as the skills, work history, interest level, team interaction history, operation logs, and error logs of the automated machines operating in the factory. This data sent from each automated machine is sent to the server in real time using a Python script. The input is various data, and the output is a normalized dataset.

[0404] Step 2:

[0405] The server normalizes the collected data and anonymizes it if necessary, standardizing the data format and concealing personally identifiable information to protect privacy. The input is the collected raw data, and the output is the normalized and anonymized data.

[0406] Step 3:

[0407] The server analyzes the data using machine learning algorithms. It extracts features such as the skills, work history, and interest of each automated machine, and then calculates optimal team composition and work distribution. The algorithms used include scikit-learn and TensorFlow. The input is normalized data, and the output is a proposal for optimal team composition and work distribution.

[0408] Step 4:

[0409] The server generates matching proposals and notifies the control device. The proposals are optimized taking into account the skills, work history, and interests of each automated machine. The input is the output of the machine learning algorithm, and the output is a proposal notification sent to the control device.

[0410] Step 5:

[0411] The control device displays the generated proposals on a dashboard, allowing engineers and operators to review the proposals and providing them in a visually easy-to-understand format. The input is the proposal notification sent from the server, and the output is the display data on the dashboard.

[0412] Step 6:

[0413] Engineers review the proposals on the dashboard and approve them if necessary. Once approved, new team formation and work distribution to the automated machines is initiated. The input is the proposal on the dashboard, and the output is approval feedback.

[0414] Step 7:

[0415] Based on the engineer's approval, the automated machines initiate new team formation and work distribution. Data is exchanged and actions are coordinated between the automated machines to carry out the work. The input is approval feedback, and the output is the actual work results.

[0416] In this way, a system is built that makes maximum use of the skills and work history of the automated machines in the factory through each processing step, achieving efficient and highly productive factory operations.

[0417] 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.

[0418] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0419] 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.

[0420] [Second embodiment]

[0421] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0422] 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.

[0423] 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).

[0424] 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.

[0425] 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.

[0426] 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).

[0427] 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.

[0428] 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.

[0429] 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.

[0430] 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.

[0431] 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.

[0432] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0433] The system of the present invention aims to collect data such as employee skills, experience, interests, and departmental interaction history, and based on the collected data, propose appropriate matches to build beneficial relationships, and visualize communication patterns between employees to identify connections within the organization and potential tendencies toward isolation.

[0434] System Overview

[0435] This system can be implemented mainly in the following configuration.

[0436] 1. Data collection method (server)

[0437] 2. Matching proposal method (server)

[0438] 3. Visualization Method (Server)

[0439] 4. Notification method (terminal)

[0440] 5. Automatic collection means (terminal)

[0441] Program processing

[0442] Data collection

[0443] The server collects data including employees' skills, experience, interests, and department interaction history. Specifically, the server obtains employees' project history, training, and skill assessment results through APIs. Based on the user's permissions, the device automatically collects employees' emails, chat history, and calendar data and periodically sends them to the server.

[0444] Data analysis

[0445] The server normalizes the collected data and anonymizes it if necessary. It then uses machine learning algorithms to match employees with the best mentoring and networking opportunities based on their skill sets and interests. The server analyzes the data and selects the best mentoring pairs and groups.

[0446] Matching proposals

[0447] Based on the data analysis, the server develops mentoring and networking plans to suggest suitable matches, including details of each employee's skills, interests and mutual benefits.

[0448] Proposal Notification

[0449] The server sends the proposal to the device, which then notifies the user via a pop-up notification or email, giving the user the option to review the proposal and accept or reject it.

[0450] Visualizing communication patterns

[0451] The server analyzes communication data such as emails, chats, and meeting frequency between employees. Based on the analysis results, it generates visualization data such as network diagrams and graphs and sends them to the device. The device then displays the visualization data to the user in the form of a dashboard or report.

[0452] Specific examples

[0453] For example, suppose Person A is an employee with deep knowledge of Python programming, while Person B is a new employee who wants to learn Python. If Person B enters his / her interest in Python into the terminal, and Person A also enters his / her skill set, the server will collect this information and perform analysis.

[0454] The server uses a machine learning algorithm to determine that Person A is a suitable mentor for Person B. The server then creates a matching proposal and notifies Person A and Person B of the proposal's contents to their devices. The users (Person A and Person B) check the notification and, if they approve the proposal, a mentoring session is set up.

[0455] Furthermore, the server analyzes the interactions and schedules between Person A and Person B and visualizes their communication patterns. The device displays this visualized data on a dashboard, making it possible to visualize the relationship between the two.

[0456] As described above, the system of the present invention can promote efficient mentoring and networking among employees, improve collaboration throughout the organization, and maximize the use of employees' skill sets.

[0457] The processing flow will be explained below.

[0458] Step 1:

[0459] Users enter information about their skills, experience, and interests into the terminal, such as "5 years of experience in Python programming" or "interested in machine learning."

[0460] Step 2:

[0461] The terminal transmits the input data to the server, where it formats the data and encrypts it as necessary.

[0462] Step 3:

[0463] The server stores the received data in a database, where it may be normalized and anonymized to protect privacy before being stored.

[0464] Step 4:

[0465] The server collects additional data from other business software (e.g., project management tools, mail servers) through APIs, including project history and communication history.

[0466] Step 5:

[0467] With the user's permission, the device automatically collects emails, chat history, and calendar data and sends them to the server, thereby obtaining the latest communication data.

[0468] Step 6:

[0469] The server analyzes all collected data and uses machine learning algorithms to extract features of employees' skills and interests, then calculates optimal mentoring and networking matches.

[0470] Step 7:

[0471] Based on the analysis results, the server generates a specific matching proposal for each user. For example, if Person A is suitable as a mentor for Person B, the server will provide a detailed description of "why Person A should be Person B's mentor."

[0472] Step 8:

[0473] The server sends the generated proposal to the target user's device, which receives the notification and notifies the user via a pop-up or email notification.

[0474] Step 9:

[0475] The user reviews the proposal from their device and has the option to accept or reject the proposal, and if accepted, a mentoring session is set up.

[0476] Step 10:

[0477] The server continuously collects and analyzes the mentoring sessions and communication history between users, thereby monitoring how the relationships between users are developing.

[0478] Step 11:

[0479] The server generates the analysis results as visualized data and displays them to the user in the form of a network diagram or graph. This visualized data is displayed on a dashboard on the terminal, allowing the user to easily check it.

[0480] These are the steps in the program, which will enable effective mentoring and networking among employees and significantly improve collaboration across the organization.

[0481] Example 1

[0482] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0483] In modern organizations, it is common for employees with diverse skills and interests to gather in one place. However, due to a lack of communication between employees and a lack of appropriate mentoring, their skills and experiences are often not fully utilized. As a result, not only is the building of beneficial relationships and collaboration between employees hindered, but it can also lead to a potential tendency for employees to become isolated. To solve these issues, a system is needed that can effectively collect and analyze employee data, propose appropriate matching, and visualize communication patterns.

[0484] 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.

[0485] In this invention, the server includes: means for collecting data such as employee skills, experience, interests, and department interaction history; means for proposing appropriate matches for building beneficial relationships between specific employees and other employees based on the collected data; means for visualizing communication patterns between employees and identifying connections within the organization and potential isolation tendencies; means for analyzing employees' skill sets and interests using machine learning algorithms to match them for optimal mentoring and networking; and means for sending notifications to terminals and providing users with the option to review and accept or reject the suggestions, thereby promoting efficient mentoring and networking between employees, improving collaboration across the organization, and making the most of employees' skill sets.

[0486] A "skill" is the knowledge, technique, or ability required to effectively perform a particular job or role.

[0487] "Experience" refers to practical knowledge and skills gained through previous work or projects.

[0488] "Interest" refers to the interest or curiosity an employee has in a particular field or activity.

[0489] "Interaction history" refers to records and log information regarding interactions and communications between employees.

[0490] "Matching" is the process of identifying and recommending employees who can build mutually beneficial relationships based on collected data.

[0491] "Communication patterns" are data that show the trends and frequency of dialogue and information exchange between employees.

[0492] "Visualization" is a method of displaying data using visual representations such as graphs and figures to make it easier to understand intuitively.

[0493] A "server" is a computer system for collecting and analyzing data and providing results.

[0494] A "terminal" is a device that is directly operated by a user and receives notifications and data from a server.

[0495] A "machine learning algorithm" is a computational method for learning patterns and rules from data and making future predictions and classifications.

[0496] A "notification" is a message or alert that provides information from the server to the terminal.

[0497] "Mentoring" is an activity in which experienced employees impart knowledge and skills to junior employees and support their growth.

[0498] "Networking" is the act of building relationships among employees to share information and resources and support each other.

[0499] "Analysis" is the process of examining collected data in detail to derive patterns and trends.

[0500] System Overview

[0501] The system of this invention effectively collects data such as employee skills, experience, interests, and departmental interaction history, and then uses this data to suggest optimal mentoring and networking opportunities. Furthermore, by visualizing communication patterns between employees, it identifies connections within the organization and potential isolationist tendencies. It mainly consists of the following components:

[0502] 1. Data collection method (server)

[0503] 2. Matching proposal method (server)

[0504] 3. Visualization Method (Server)

[0505] 4. Notification method (terminal)

[0506] 5. Automatic collection means (terminal)

[0507] server

[0508] The server is mainly responsible for data collection, analysis, matching proposals, visualization, etc. The server uses the following specific software and hardware:

[0509] Data collection method: Employees enter their skills, experience, interests, and project history through an API (e.g., a RESTful API). Data is acquired using the Python library Requests.

[0510] Data analysis methods: Normalize the collected data and anonymize it if necessary. For example, use Python's pandas library to manipulate data frames and hash personally identifiable information.

[0511] Machine learning tools: We use machine learning algorithms to analyze employee skill sets and interests. Specifically, we use the scikit-learn library to perform clustering and classification algorithms.

[0512] Matching proposal method: Based on the analysis results, the optimal mentoring pair or group is selected. Proposals are generated using a Python script.

[0513] Visualization method: Analyze communication data between employees and generate network diagrams and graphs. Visualization is performed using Matplotlib and networkx libraries.

[0514] Terminal

[0515] A terminal is a device that a user directly operates and that receives notifications and data from a server. A terminal includes the following specific software:

[0516] Data input method: Provides an interface for users to input data such as skills and interests. A front-end application written in JavaScript is used.

[0517] Automatic collection method: The device periodically collects the user's email, chat history, and calendar data and sends it to the server. For example, a cron job can be set up to upload the data to the server on a fixed schedule.

[0518] Notification method: Proposals and notifications from the server are displayed to the user. JavaScript's Notification API is used to display pop-up notifications in the browser.

[0519] Visualization data display method: Display the received visualization data in the form of dashboards and reports. Generate interactive network diagrams using the D3.js library.

[0520] Specific examples

[0521] For example, suppose Person A is an employee with strong Python skills, and Person B is a new employee who wants to learn Python. Person B enters his / her interest in Python into the terminal, and Person A also enters his / her own skill set. The terminal collects this information and sends it to the server at 2:00 AM every day.

[0522] The server normalizes the received data, analyzes it using the scikit-learn library, and determines that Person A is suitable as a mentor for Person B. The server then creates a matching proposal and sends it to the devices of Person A and Person B. The devices notify Person A and Person B of the proposal via a pop-up notification, and the users can review the proposal and accept or reject it.

[0523] Once approved, the server analyzes the communication data between Person A and Person B and creates a visualized network diagram. The device displays this visualized data on a dashboard, visualizing the relationship between Person A and Person B.

[0524] Prompt Sentence Examples

[0525] "I want to develop a model to collect employee skills, experience, interests, and department interaction history to suggest optimal mentoring pairs or groups. Please explain how you will collect the data, analyze it, inform your suggestions, and visualize communication patterns."

[0526] As described above, the system of the present invention promotes effective mentoring and networking among employees, improving collaboration throughout the organization and making the most of employees' skill sets.

[0527] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0528] Step 1:

[0529] The terminal accepts data input from the user. The user enters their skills, experience, and interests into a form. This input data is stored in a local database. Specifically, when a user enters skills (e.g., Python, project management), experience (e.g., 5 years of software development experience), and interests (e.g., machine learning) into a web form and presses the submit button, an application written in JavaScript collects this data and stores it in IndexedDB.

[0530] Step 2:

[0531] The device periodically sends data to the server. For example, a cron job can be set up at 2:00 AM every day to securely upload the stored data to the server using the HTTPS protocol. The input data is in JSON format and is included in the request header along with any necessary authentication information. Specifically, the device runs the cron job and sends the data to the server using the Python Requests library.

[0532] Step 3:

[0533] The server normalizes the received data. For example, it represents each employee's data in a uniform format and handles missing values. The input data is in JSON format, and the output data is also in a similarly normalized JSON format. Specifically, the server uses the Python pandas library to convert the received data into a data frame and normalize each field.

[0534] Step 4:

[0535] The server anonymizes the data. For example, it hashes personally identifiable information to protect privacy. The input data is in JSON format, and the output data is also anonymized JSON. Specifically, the server hashes personally identifiable information using Python's hashlib library.

[0536] Step 5:

[0537] The server uses machine learning algorithms to analyze the collected data. For example, it clusters employees' skill sets and interests to find the most suitable mentoring pairs. The input data is anonymized JSON format, and the output data is a list of matching results. Specifically, the server uses the scikit-learn library to perform k-means clustering to determine suitable matches.

[0538] Step 6:

[0539] The server creates matching proposals, for example, generating proposal documents containing details of suitable mentor candidates or networking partners for each employee based on the analysis results. The input data is a list of analysis results, and the output data is a JSON format containing proposal details. Specifically, the server uses a Python script to generate proposal documents for each pair.

[0540] Step 7:

[0541] The server sends the proposal content to the device. For example, details of the generated proposal are sent to each employee's device via email or push notification. The input data is JSON format containing the proposal details, and the output data is the notification sending status. Specifically, the server configures an SMTP server and sends emails.

[0542] Step 8:

[0543] The device displays a notification to the user, for example, a pop-up notification or email with the proposal so that the user can review it. The input data are the proposal details, and the output data is the user's response (accept or reject). Specifically, the device uses JavaScript's Notification API to display a pop-up notification in the browser.

[0544] Step 9:

[0545] The user reviews the proposal and responds by either accepting or rejecting it. The input data is the proposal details, and the output data is the user's response (accept or reject). Specifically, after the user reviews the proposal, they click the confirm button, and the response is sent to the server.

[0546] Step 10:

[0547] The server receives the user's response and sets up a mentoring session or networking event, for example, by adding an event to a calendar if approved. The input data is the user's response, and the output data is the details of the set up event. Specifically, the server sets up a mentoring session using the Google Calendar API.

[0548] Step 11:

[0549] The server collects, analyzes, and visualizes communication data between employees. For example, it analyzes the frequency of emails and chats to create a communication network. The input data is communication history, and the output data is in graph format for visualization. Specifically, the server analyzes communication patterns using the networkx library and visualizes them using Matplotlib.

[0550] Step 12:

[0551] The terminal displays the visualized data on a dashboard, such as an interactive network diagram or graph, to help employees easily understand it. The input data is the visualized graph, and the output data is the display on the dashboard. Specifically, the terminal uses the D3.js library to display the visualized data on the browser.

[0552] The above are the specific processing steps of the program of this system.

[0553] (Application example 1)

[0554] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0555] Communication and skill matching between staff members in brick-and-mortar stores are important factors in streamlining store operations and improving staff performance. However, conventional methods make it difficult to efficiently pair staff members appropriately, taking into account each staff member's skills, experience, and interests. It is also difficult to visualize communication patterns between staff members and understand their relationships and potential isolation. This can lead to interpersonal friction, a sense of unfairness in evaluations, and even a decline in the operational efficiency of the entire store. To solve these issues, a system is needed that can propose optimal pairings based on staff members' skills and interests, and visualize their communication patterns.

[0556] 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.

[0557] In this invention, the server includes: means for collecting data such as employee (staff) skills, experience, interests, and department (shift) interaction history; means for proposing appropriate matching based on the collected data to build beneficial relationships between specific employees (staff) and other employees (staff); means for visualizing communication patterns between employees (staff) and identifying connections and potential isolation tendencies within the organization (store); means for proposing optimal pairings between staff in a physical store based on the collected and analyzed data to promote skill improvement and work efficiency; and means for visualizing communication patterns between staff and identifying relationships and isolation tendencies within the store. This makes it possible to improve the operational efficiency of physical stores, maximize staff capabilities, and perform fair evaluations.

[0558] "Employees (staff)" refers to people employed by a company, organization, or specific store, who have roles and responsibilities necessary for carrying out business. This also includes staff who contribute to the operation of physical stores.

[0559] "Skills" are the abilities and techniques required to carry out specific tasks or work, and their acquisition requires training and experience.

[0560] "Experience" refers to the knowledge and know-how that employees (staff) have gained through past work and projects, which contributes to improving their ability to carry out their work.

[0561] "Interest" refers to the interest and enthusiasm that employees (staff) have in a particular field or skill, and their motivation to learn new things based on this.

[0562] A "department (shift)" refers to a group or team that performs a specific task or role within a company or organization. In a physical store, it also includes the working hours and schedule of staff.

[0563] "Interaction history" refers to records of communication and collaboration between employees (staff), and includes data such as emails, chats, and meetings.

[0564] "Matching" refers to optimally pairing employees (staff) with each other based on specific criteria or algorithms, with the aim of complementing each other's skills and interests and improving work efficiency.

[0565] "Pairing" refers to creating optimal pairs based on skills, experience, and interests, with the aim of improving the work performance and capabilities of store staff.

[0566] "Communication patterns" indicate the method, frequency, and content of interactions between employees (staff), and analyzing these can visualize the relationships and cooperation within an organization.

[0567] "Visualization" refers to displaying analyzed data in a visual format such as graphs, charts, or network diagrams, making it easier to understand and gain insight into the information.

[0568] The system of the present invention collects and analyzes data such as the skills, experience, and interests of employees (staff), and the interaction history of departments (shifts), thereby visualizing optimal matching and communication patterns. This system can be implemented as follows based on the claims of the present invention.

[0569] composition

[0570] The system includes the following components:

[0571] 1. Data collection method (server)

[0572] 2. Matching proposal method (server)

[0573] 3. Visualization Method (Server)

[0574] 4. Notification method (terminal)

[0575] 5. Automatic collection means (terminal)

[0576] Data collection

[0577] The server periodically collects data through the API, including staff skills, experience, interests, and shift history, including information staff enter into their profiles and information retrieved through the scheduling application, as well as email, chat history, and calendar data automatically collected from devices.

[0578] Data analysis

[0579] The collected data is normalized and, if necessary, anonymized on the server. Machine learning algorithms (e.g., K-means clustering) are used to optimally pair staff based on their skill sets and interests. Based on the results of this analysis, optimal mentoring and team formation are suggested.

[0580] Matching proposals

[0581] The server then generates optimal matching suggestions based on the analysis, creating a list of specific mentoring pairs or teams, including detailed information about staff skills, interests, and mutual benefits.

[0582] Proposal Notification

[0583] The proposal is sent to the device, which notifies the staff member via a pop-up notification or email, and the staff member is given the option to review the proposal and accept or reject it.

[0584] Visualizing communication patterns

[0585] The server analyzes communication data such as emails, chats, and meeting frequency to generate network diagrams and graphs, visually displaying relationships between staff and potential isolation trends. This visualized data is provided in the form of dashboards and reports on the device.

[0586] Specific examples

[0587] For example, if staff member A is fluent in Spanish and staff member B wants to learn that skill, their information is entered into their devices and analyzed by the server. Based on the analysis results, A and B are identified as suitable pairing candidates, and this information is notified to both their devices. Upon receiving the notification, A and B can begin a mentoring session based on the proposed pairing.

[0588] Example prompts for generative AI models

[0589] Please suggest the best matching pair based on the following data:

[0590] Staff A: Spanish skill level 5, Interests: Teaching

[0591] Staff B: Spanish skill level 2, Interests: Learning

[0592] Staff C: Planning Skill Level 4, Interests: Leadership

[0593] Staff D: Planning skill level 3, Interests: Learning

[0594] Proposal format: [Staff pair / group, reason]

[0595] As described above, by using the system of the present invention, it is possible to improve the operational efficiency of physical stores, maximize the capabilities of staff, and achieve fair evaluations.

[0596] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0597] Step 1: Data collection

[0598] The server collects data including staff skills, experience, interests, and shift history through an API. This data comes from information entered in each staff member's profile and data obtained from the scheduling app. The collected data is then normalized and stored. This data includes staff skill levels, interest categories, and shift times. This allows for the management of distributed data in a unified format.

[0599] Step 2: Additional automated data collection

[0600] The devices automatically collect staff emails, chat history, and calendar data. This data is periodically sent to the server with the user's permission. Specifically, the devices analyze the staff's communication history and extract information such as the number of emails, chat frequency, and meeting schedules. This data is sent to the server and used as data for analysis.

[0601] Step 3: Data analysis

[0602] The server normalizes the collected data and anonymizes it if necessary. It then uses machine learning algorithms (e.g., K-means clustering) to optimally pair staff based on skill sets and interests. For example, it clusters each staff member's skill level and areas of interest as a feature vector, and groups staff members with similar characteristics. This enables pairings that are expected to complement each other's skills and harmonize their interests.

[0603] Step 4: Generate matching proposals

[0604] The server generates optimal matching proposals based on the results of the data analysis. Specifically, it creates a list for each clustered group or pair, detailing the reasons for each match and the benefits of the pairing. This proposal list is organized to include information on staff skills, interests, and mutual benefits. This allows it to propose optimal mentoring and team formation among staff.

[0605] Step 5: Notification of proposal

[0606] The server sends the generated matching proposal to the terminal. The terminal notifies the staff of the proposal via a pop-up notification or email. The user can then review the details of the proposal based on the notification and select the option to approve or reject it. This allows the user to decide whether or not to proceed with the proposed match and proceed to the next step.

[0607] Step 6: Visualize communication patterns

[0608] The server analyzes communication data such as emails, chats, and frequency of meetings between staff members. Based on the analysis results, it generates visualized data such as network diagrams and graphs. Specifically, by analyzing the communication data and illustrating the contact points and frequency of each staff member using node and edge relationships, it clarifies the relationships within the organization and potential isolation trends. This visualized data is sent to the terminal and displayed to the user in the form of a dashboard or report.

[0609] 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.

[0610] The system of the present invention aims to collect data such as employee skills, experience, interests, departmental interaction history, and employee emotions, propose matches to build beneficial relationships, and visualize communication patterns between employees to identify connections within the organization and potential trends toward isolation. By utilizing an emotion engine that recognizes user emotions, more advanced and accurate matching becomes possible.

[0611] System Overview

[0612] The system of the present invention can be implemented in the following configuration:

[0613] 1. Data collection method (server)

[0614] 2. Emotion engine (server)

[0615] 3. Matching proposal method (server)

[0616] 4. Visualization Method (Server)

[0617] 5. Notification Method (Terminal)

[0618] 6. Automatic collection means (terminal)

[0619] Program processing

[0620] Data collection

[0621] The server collects data including employees' skills, experience, interests, department interaction history, and emotional state. Users input their skills and interests into their devices, which then send the data to the server. Furthermore, with the user's permission, the device automatically collects email, chat history, and calendar data and sends them to the server. The emotion engine analyzes the user's emotions from this text and voice data and sends the results to the server.

[0622] Data analysis

[0623] The server normalizes the collected data and anonymizes it as necessary. It then uses a machine learning algorithm to extract features based on employees' skills, experience, interests, and emotional state, and calculates optimal mentoring and networking matches. It also analyzes the results of the emotion engine, taking emotional compatibility into account.

[0624] Matching proposals

[0625] The server generates appropriate matching proposals based on the results of data analysis. The proposals take into account each employee's skills, experience, interests, emotional state, and mutual benefits. For example, if Person A is familiar with Python and Person B wants to learn Python, the server will generate a proposal that Person A would be a good mentor for Person B. The results of the emotion engine are also taken into account, and the proposal is adjusted to be made when Person A and Person B are in a good emotional state.

[0626] Proposal Notification

[0627] The server sends the generated proposal to the target user's device, which notifies the user via a pop-up notification or email notification. The user can review the proposal and choose the option to accept or reject it.

[0628] Visualizing communication patterns

[0629] The server analyzes communication data between users, such as the frequency of emails, chats, and meetings, and generates visualized data in the form of network diagrams and graphs. The results of the emotion engine are also reflected in the visualized data, so the user's emotional state is also displayed. The device displays the visualized data in a dashboard format, making it easy for the user to check.

[0630] Specific examples

[0631] For example, suppose Person A has deep knowledge of Python programming, and Person B is a new employee who wants to learn Python. Person B enters his / her interest in Python into the device, and Person A enters his / her skill set. The device sends this data to the server, and the emotion engine then analyzes the emails, chat contents, and voice data of these users and sends their emotional state to the server.

[0632] The server analyzes all data, including skills, interests, and emotional state. If A is the best mentor for B to learn Python, and both parties are in a good emotional state, the server creates a matching proposal and notifies A and B's devices. If both parties confirm the proposal and approve it, a mentoring session is set up.

[0633] In this way, the system of the present invention enables efficient mentoring and networking among employees, effectively utilizes employees' skill sets, and improves collaboration across the organization by taking into account emotional matching.

[0634] The processing flow will be explained below.

[0635] Step 1:

[0636] Users enter information about their skills, experience, and interests into the device, such as "5 years of Python programming experience" or "interested in machine learning."

[0637] Step 2:

[0638] The terminal transmits the input data to the server, where it is formatted and encrypted.

[0639] Step 3:

[0640] The server stores the received data in a database, normalizing and, if necessary, anonymizing the data before storing it.

[0641] Step 4:

[0642] If the user gives permission, the device will automatically collect email, chat history, and calendar data on a regular basis and send it to the server.

[0643] Step 5:

[0644] The server retrieves relevant data from other business software (e.g., project management tools, mail servers) through APIs, including project history and communication history.

[0645] Step 6:

[0646] The emotion engine analyzes the text data and voice data of the user's emails and chats to identify the user's emotional state, and then sends the analysis results to the server.

[0647] Step 7:

[0648] The server normalizes all collected data and uses machine learning algorithms to extract employee skills, experience, interests, and emotional states as features.

[0649] Step 8:

[0650] The server calculates optimal mentoring and networking matches between users based on the feature values, taking into account the results of the emotion engine, and reflecting emotional compatibility in the matching.

[0651] Step 9:

[0652] The server generates specific match proposals based on the valid matches, including details of each user's skills, experience, interests, emotional state, and mutual interests.

[0653] Step 10:

[0654] The server sends the generated proposal to the target user's device. For example, it sends a proposal that person A is suitable to be person B's mentor.

[0655] Step 11:

[0656] The device will receive the suggestion and notify the user via a pop-up or email notification, giving the user the option to review the suggestion and accept or reject it.

[0657] Step 12:

[0658] If the user accepts the proposal, the device provides a scheduling function for setting up mentoring sessions and networking events.

[0659] Step 13:

[0660] The server continuously collects and analyzes the mentoring sessions and communication history between users, thereby monitoring how the relationships between users are developing.

[0661] Step 14:

[0662] The server generates the analysis results as visualized data and displays them as graphs and network diagrams. It also visually displays the user's emotional state, reflecting the results of the emotion engine.

[0663] Step 15:

[0664] The device displays the visualized data in a dashboard format, allowing users to easily check the analysis results, and understand their own communication patterns and emotional state.

[0665] In this way, the system of the present invention realizes efficient mentoring and networking among employees, and by taking into consideration emotional matching, it is possible to improve collaboration throughout the organization.

[0666] Example 2

[0667] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0668] In modern companies, a key challenge is to maximize the use of individual employee characteristics, such as skills, experience, and interests, to promote communication and cooperation among employees. However, it is extremely difficult to properly match these characteristics and understand emotional compatibility, employee connections, and potential tendencies toward isolation. Conventional systems often lack the accuracy of data collection, analysis, and matching proposals, resulting in ineffective relationship building. Therefore, there is a need for a system that can achieve high-precision matching that takes into account employee skills and emotional states, and visualize communication patterns.

[0669] 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.

[0670] In this invention, the server includes means for collecting data including employee skills, experience, interests, department interaction history, and emotional state, means for proposing appropriate matches for building beneficial relationships between specific employees and other employees based on the collected data, means for analyzing the emotional data and taking emotional compatibility into account in the collected data, and means for visualizing communication patterns between employees and identifying connections within the organization and potential tendencies toward isolation. This enables highly accurate matching based on employee skills and emotional state, thereby improving communication and cooperation within the company.

[0671] "Employee skills" refers to the specialized knowledge and abilities possessed by individual employees.

[0672] "Experience" refers to the accumulation of practical knowledge and skills that employees have acquired through their work.

[0673] "Interests" refer to areas or activities that interest employees.

[0674] "Department interaction history" refers to records of business interactions and communications between employees.

[0675] "Emotional state" refers to data that shows an employee's emotional state, such as joy or stress.

[0676] "Means of collecting data" refers to the methods and devices used to collect information entered by employees and data collected automatically.

[0677] "Means for suggesting matches" refers to methods or systems that use collected data to help connect specific employees with other employees to beneficial relationships.

[0678] "Means for analyzing emotional data" refers to methods and algorithms for analyzing collected emotional data and understanding emotional compatibility and state.

[0679] "Means for visualizing communication patterns" refers to methods and tools for displaying the frequency and form of communication between employees in the form of graphs, network diagrams, etc.

[0680] The system of the present invention aims to collect data such as employee skills, experience, interests, department interaction history, and emotional state, propose matches to build beneficial relationships, and further visualize communication patterns between employees to identify connections within the organization and potential tendencies toward isolation. The following describes in detail the modes for implementing the present invention.

[0681] System Configuration

[0682] The system of the present invention can be implemented in the following configuration:

[0683] 1. Data collection method (server)

[0684] 2. Emotion engine (server)

[0685] 3. Matching proposal method (server)

[0686] 4. Visualization Method (Server)

[0687] 5. Notification Method (Terminal)

[0688] 6. Automatic collection means (terminal)

[0689] Data collection

[0690] The server collects data including employees' skills, experience, interests, department interaction history, and emotional state. Users input their skills and interests into their devices, which then send the data to the server. Furthermore, with the user's permission, the device automatically collects email, chat history, and calendar data and sends them to the server. The emotion engine analyzes the user's emotions from this text and voice data and sends the results to the server.

[0691] Data analysis

[0692] The server normalizes the collected data and anonymizes it as necessary. It then uses a machine learning algorithm to extract features based on employees' skills, experience, interests, and emotional state, and calculates optimal mentoring and networking matches. It also analyzes the results of the emotion engine, taking emotional compatibility into account.

[0693] Matching proposals

[0694] The server generates appropriate matching proposals based on the results of data analysis. For example, if one employee is familiar with Python and another employee wants to learn Python, it will generate a proposal that the two are suitable for a mentor-learner relationship. By incorporating the results of the emotion engine, the server also evaluates the emotional compatibility between the two parties.

[0695] Proposal Notification

[0696] The server sends the generated proposal to the target user's device, where the device notifies the user of the proposal via a pop-up notification or email notification. The user can review the proposal and choose to accept or reject it.

[0697] Visualizing communication patterns

[0698] The server analyzes communication data between users, such as emails, chats, and frequency of meetings, and generates visualized data in the form of network diagrams and graphs. The results of the emotion engine are also reflected in the visualized data, so the user's emotional state is also displayed. The device displays the visualized data in a dashboard format, making it easy for users to check.

[0699] Specific examples

[0700] For example, suppose Person A has deep knowledge of Python programming, and Person B is a new employee who wants to learn Python. Person B enters his / her interest in Python into the device, and Person A enters his / her skill set. The device sends this data to the server, and the emotion engine analyzes the emails, chat contents, and voice data of these users and sends their emotional state to the server.

[0701] The server analyzes all data, including skills, interests, and emotional states. If A is the best mentor for B to learn Python, and both parties are in a good emotional state, the server creates a matching proposal and notifies A and B's devices. If both A and B accept the proposal, a mentoring session is set up. In this way, the system of the present invention realizes efficient mentoring and networking among employees, effectively utilizing employees' skill sets, and improves collaboration across the organization by taking emotional matching into consideration.

[0702] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0703] Step 1: Enter and collect data

[0704] 1.1 User Input

[0705] The user enters their skills, experience, and interests into the terminal. For example, they might enter, "I'm interested in Python programming and have basic knowledge."

[0706] The terminal collects the data entered by the user and transmits it to the server.

[0707] Input: Skills, experience, and interest data entered by the user.

[0708] Output: Data sent from the device to the server.

[0709] 1.2 Automatic Data Collection

[0710] With the user's permission, the device automatically collects email, chat history, and calendar data.

[0711] The terminal transmits the collected data to the server.

[0712] Input: User permission, email and chat history, calendar data.

[0713] Output: Email, chat history, and calendar data sent from the device to the server.

[0714] 1.3 Emotion Data Analysis

[0715] The emotion engine analyzes the user's emotions from collected text and voice data. For example, it can extract emotions such as "feeling stressed" from the content of an email.

[0716] The emotion engine sends the analysis results as data to the server.

[0717] Input: text and audio data.

[0718] Output: Sentiment analysis results sent to the server.

[0719] Step 2: Normalize and anonymize data

[0720] 2.1 Data normalization

[0721] The server unifies and normalizes the collected data formats, for example, unifying due dates and skill levels across different formats.

[0722] Input: Raw data collected.

[0723] Output: Normalized data.

[0724] 2.2 Data anonymization

[0725] The server anonymizes the data as needed, for example by replacing employee identifying information with a random identifier.

[0726] Input: Normalized data.

[0727] Output: Anonymized data.

[0728] Step 3: Feature extraction and matching calculation

[0729] 3.1 Feature extraction

[0730] The server uses machine learning algorithms to extract features such as skills, experience, interests, and emotional state. For example, a user's skill set might be extracted as "Python: intermediate, data analysis: beginner."

[0731] Input: Normalized data, anonymized data.

[0732] Output: Data extracted as features.

[0733] 3.2 Matching Calculation

[0734] The server calculates the optimal match based on the extracted features, deriving a result such as "Person A is the best mentor for Person B."

[0735] The server also takes into account the results of the emotion engine and incorporates emotional compatibility into its calculations, for example, "Make a proposal when A and B are in a good emotional state."

[0736] Input: Data extracted as features, sentiment analysis results.

[0737] Output: Best matching suggestion.

[0738] Step 4: Generate and notify matching proposals

[0739] 4.1 Generating Matching Proposals

[0740] The server generates appropriate matching proposals based on the results of the data analysis, for example, "Propose that person A mentor person B in Python."

[0741] Input: Best matching proposal data.

[0742] Output: Specific matching suggestions.

[0743] 4.2 Proposal Notification

[0744] The server sends the generated proposal to the target user's device. For example, it notifies the devices of user A and user B that "a mentoring proposal is available."

[0745] The device will notify the user of the suggestions via a pop-up notification or email notification.

[0746] The user reviews the proposal and has the option to accept or reject it.

[0747] Input: A specific matching suggestion.

[0748] Output: Notifications to the terminal and responses from the user.

[0749] Step 5: Visualize communication patterns

[0750] 5.1 Data Analysis

[0751] The server analyzes communication data such as the frequency of emails, chats, and meetings between users. For example, it collects data such as "Person A and Person B frequently email or chat."

[0752] The results of the emotion engine are also reflected in the visualization data, so the user's emotional state is also displayed.

[0753] Input: Communication data between users, sentiment analysis results.

[0754] Output: Analysis results of communication patterns.

[0755] 5.2 Generating visualization data

[0756] The server generates visualization data in the form of network diagrams and graphs based on the analysis results. For example, it creates a network diagram showing the communication patterns between person A and person B.

[0757] Input: Analysis results of communication patterns.

[0758] Output: Visualized data as network diagrams and graphs.

[0759] 5.3 Viewing the Dashboard

[0760] The device displays visualized data in a dashboard format for easy viewing by the user. For example, it provides a dashboard displaying the communication patterns and emotional states of person A and person B.

[0761] Input: Visualization data.

[0762] Output: Display in dashboard format.

[0763] (Application example 2)

[0764] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0765] It is necessary to optimize the work efficiency of automated machines operating in factories and realize team formation that makes the most of each machine's skills, work history, and interest level. It is also necessary to improve productivity by visualizing communication patterns between automated machines and identifying potential inefficiencies.

[0766] 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.

[0767] In this invention, the server includes means for collecting data such as the skills, work history, interest level, and team interaction history of automated machines operating in a factory, means for proposing beneficial team formation and work distribution between a specific automated machine and other automated machines based on the collected data, and means for visualizing communication patterns between the automated machines and identifying efficiencies and potential inefficiencies in the workplace. This enables effective team formation and work distribution that makes the most of the skills and work history of the automated machines, thereby improving productivity in the factory.

[0768] "Automatic machines" refers to robots and mechanical devices operating in factories, and is a general term for machines that perform tasks automatically.

[0769] "Skill" refers to the ability to perform a specific task or action that an automated machine can perform.

[0770] "Work history" is a record of work that an automated machine has performed in the past, and includes data such as the success rate and work time.

[0771] "Interest" refers to the degree of interest in tasks that automated machines excel at or have shown a high success rate in the past.

[0772] "Team interaction history" refers to the history of past collaborative and cooperative work between automated machines.

[0773] "Communication pattern" is a concept that indicates the format and frequency of data exchange and operational coordination between automated machines.

[0774] An "operation log" is a detailed record of the operations of an automated machine recorded while it is in operation, including operating status and error information.

[0775] An "error log" refers to a record of errors or malfunctions that occur while an automated machine is operating.

[0776] "Visualization" refers to the process of displaying data as graphs or charts so that it can be understood at a glance.

[0777] "Control device" refers to a server or terminal device used to monitor and manage automated machinery.

[0778] The present invention is a system for optimizing work efficiency and productivity using automated machines operating in a factory. The system includes the following components:

[0779] 1. Data collection method (server)

[0780] The server collects data on the skills, work history, interest level, team interaction history, operation logs, error logs, etc. of the automated machines operating in the factory. A Python script is used to collect data, which is then sent to the management server in real time.

[0781] 2. Machine learning algorithm (server)

[0782] The server normalizes the collected data and anonymizes it if necessary. It then uses machine learning algorithms to extract features based on each machine's skills, work history, and interest levels, and calculates optimal team composition and work distribution. The machine learning algorithms used include scikit-learn and TensorFlow.

[0783] 3. Matching proposal method (server)

[0784] Based on the collected and analyzed data, the server proposes beneficial team formation and work distribution between specific automated machines and other automated machines. The proposal is optimized taking into account the skills, work history, and interest of each automated machine, and the proposal is notified to the control device.

[0785] 4. Proposal notification means (control device)

[0786] The server notifies the control device of the generated proposal, allowing engineers and operators in the factory to review the proposed team formation and work distribution and approve them as necessary.

[0787] 5. Visualization tools (dashboards)

[0788] The server analyzes the frequency of data exchange and collaboration between automated machines and generates visualized data in the form of network diagrams and graphs. Tools used for visualization include Tableau and D3.js. This visualized data is displayed in a dashboard format so that operators can easily check it.

[0789] Specific examples

[0790] For example, suppose that automatic machine A is responsible for assembly work in a factory, and automatic machine B is responsible for inspection work. The operation logs and work history of automatic machines A and B are sent to a server, which analyzes them. Based on the analysis results, the server proposes the optimal way for automatic machines A and B to work together and notifies the control device.

[0791] Once the engineers review the proposals on the dashboard and approve the proposed teaming and work distribution, new collaborations can begin, improving productivity within the factory and making the most of the skills and work history of each automated machine.

[0792] ---

[0793] Example prompts for input to a generative AI model:

[0794] "Factory robot A specializes in assembly work, and robot B specializes in inspection work. Please generate a proposal for the optimal collaboration work based on past success stories."

[0795] ---

[0796] In this way, the system of the present invention realizes efficient and highly productive factory operations, and maximizes the capabilities of automated machines.

[0797] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0798] Step 1:

[0799] The server collects data such as the skills, work history, interest level, team interaction history, operation logs, and error logs of the automated machines operating in the factory. This data sent from each automated machine is sent to the server in real time using a Python script. The input is various data, and the output is a normalized dataset.

[0800] Step 2:

[0801] The server normalizes the collected data and anonymizes it if necessary, standardizing the data format and concealing personally identifiable information to protect privacy. The input is the collected raw data, and the output is the normalized and anonymized data.

[0802] Step 3:

[0803] The server analyzes the data using machine learning algorithms. It extracts features such as the skills, work history, and interest of each automated machine, and then calculates optimal team composition and work distribution. The algorithms used include scikit-learn and TensorFlow. The input is normalized data, and the output is a proposal for optimal team composition and work distribution.

[0804] Step 4:

[0805] The server generates matching proposals and notifies the control device. The proposals are optimized taking into account the skills, work history, and interests of each automated machine. The input is the output of the machine learning algorithm, and the output is a proposal notification sent to the control device.

[0806] Step 5:

[0807] The control device displays the generated proposals on a dashboard, allowing engineers and operators to review the proposals and providing them in a visually easy-to-understand format. The input is the proposal notification sent from the server, and the output is the display data on the dashboard.

[0808] Step 6:

[0809] Engineers review the proposals on the dashboard and approve them if necessary. Once approved, new team formation and work distribution to the automated machines is initiated. The input is the proposal on the dashboard, and the output is approval feedback.

[0810] Step 7:

[0811] Based on the engineer's approval, the automated machines initiate new team formation and work distribution. Data is exchanged and actions are coordinated between the automated machines to carry out the work. The input is approval feedback, and the output is the actual work results.

[0812] In this way, a system is built that makes maximum use of the skills and work history of the automated machines in the factory through each processing step, achieving efficient and highly productive factory operations.

[0813] 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.

[0814] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0815] 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.

[0816] [Third embodiment]

[0817] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0818] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0819] 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).

[0820] 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.

[0821] 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.

[0822] 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).

[0823] 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.

[0824] 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.

[0825] 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.

[0826] 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.

[0827] 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.

[0828] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0829] The system of the present invention aims to collect data such as employee skills, experience, interests, and departmental interaction history, and based on the collected data, propose appropriate matches to build beneficial relationships, and visualize communication patterns between employees to identify connections within the organization and potential tendencies toward isolation.

[0830] System Overview

[0831] This system can be implemented mainly in the following configuration.

[0832] 1. Data collection method (server)

[0833] 2. Matching proposal method (server)

[0834] 3. Visualization Method (Server)

[0835] 4. Notification method (terminal)

[0836] 5. Automatic collection means (terminal)

[0837] Program processing

[0838] Data collection

[0839] The server collects data including employees' skills, experience, interests, and department interaction history. Specifically, the server obtains employees' project history, training, and skill assessment results through APIs. Based on the user's permissions, the device automatically collects employees' emails, chat history, and calendar data and periodically sends them to the server.

[0840] Data analysis

[0841] The server normalizes the collected data and anonymizes it if necessary. It then uses machine learning algorithms to match employees with the best mentoring and networking opportunities based on their skill sets and interests. The server analyzes the data and selects the best mentoring pairs and groups.

[0842] Matching proposals

[0843] Based on the data analysis, the server develops mentoring and networking plans to suggest suitable matches, including details of each employee's skills, interests and mutual benefits.

[0844] Proposal Notification

[0845] The server sends the proposal to the device, which then notifies the user via a pop-up notification or email, giving the user the option to review the proposal and accept or reject it.

[0846] Visualizing communication patterns

[0847] The server analyzes communication data such as emails, chats, and meeting frequency between employees. Based on the analysis results, it generates visualization data such as network diagrams and graphs and sends them to the device. The device then displays the visualization data to the user in the form of a dashboard or report.

[0848] Specific examples

[0849] For example, suppose Person A is an employee with deep knowledge of Python programming, while Person B is a new employee who wants to learn Python. If Person B enters his / her interest in Python into the terminal, and Person A also enters his / her skill set, the server will collect this information and perform analysis.

[0850] The server uses a machine learning algorithm to determine that Person A is a suitable mentor for Person B. The server then creates a matching proposal and notifies Person A and Person B of the proposal's contents to their devices. The users (Person A and Person B) check the notification and, if they approve the proposal, a mentoring session is set up.

[0851] Furthermore, the server analyzes the interactions and schedules between Person A and Person B and visualizes their communication patterns. The device displays this visualized data on a dashboard, making it possible to visualize the relationship between the two.

[0852] As described above, the system of the present invention can promote efficient mentoring and networking among employees, improve collaboration throughout the organization, and maximize the use of employees' skill sets.

[0853] The processing flow will be explained below.

[0854] Step 1:

[0855] Users enter information about their skills, experience, and interests into the terminal, such as "5 years of experience in Python programming" or "interested in machine learning."

[0856] Step 2:

[0857] The terminal transmits the input data to the server, where it formats the data and encrypts it as necessary.

[0858] Step 3:

[0859] The server stores the received data in a database, where it may be normalized and anonymized to protect privacy before being stored.

[0860] Step 4:

[0861] The server collects additional data from other business software (e.g., project management tools, mail servers) through APIs, including project history and communication history.

[0862] Step 5:

[0863] With the user's permission, the device automatically collects emails, chat history, and calendar data and sends them to the server, thereby obtaining the latest communication data.

[0864] Step 6:

[0865] The server analyzes all collected data and uses machine learning algorithms to extract features of employees' skills and interests, then calculates optimal mentoring and networking matches.

[0866] Step 7:

[0867] Based on the analysis results, the server generates a specific matching proposal for each user. For example, if Person A is suitable as a mentor for Person B, the server will provide a detailed description of "why Person A should be Person B's mentor."

[0868] Step 8:

[0869] The server sends the generated proposal to the target user's device, which receives the notification and notifies the user via a pop-up or email notification.

[0870] Step 9:

[0871] The user reviews the proposal from their device and has the option to accept or reject the proposal, and if accepted, a mentoring session is set up.

[0872] Step 10:

[0873] The server continuously collects and analyzes the mentoring sessions and communication history between users, thereby monitoring how the relationships between users are developing.

[0874] Step 11:

[0875] The server generates the analysis results as visualized data and displays them to the user in the form of a network diagram or graph. This visualized data is displayed on a dashboard on the terminal, allowing the user to easily check it.

[0876] These are the steps in the program, which will enable effective mentoring and networking among employees and significantly improve collaboration across the organization.

[0877] Example 1

[0878] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0879] In modern organizations, it is common for employees with diverse skills and interests to gather in one place. However, due to a lack of communication between employees and a lack of appropriate mentoring, their skills and experiences are often not fully utilized. As a result, not only is the building of beneficial relationships and collaboration between employees hindered, but it can also lead to a potential tendency for employees to become isolated. To solve these issues, a system is needed that can effectively collect and analyze employee data, propose appropriate matching, and visualize communication patterns.

[0880] 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.

[0881] In this invention, the server includes: means for collecting data such as employee skills, experience, interests, and department interaction history; means for proposing appropriate matches for building beneficial relationships between specific employees and other employees based on the collected data; means for visualizing communication patterns between employees and identifying connections within the organization and potential isolation tendencies; means for analyzing employees' skill sets and interests using machine learning algorithms to match them for optimal mentoring and networking; and means for sending notifications to terminals and providing users with the option to review and accept or reject the suggestions, thereby promoting efficient mentoring and networking between employees, improving collaboration across the organization, and making the most of employees' skill sets.

[0882] A "skill" is the knowledge, technique, or ability required to effectively perform a particular job or role.

[0883] "Experience" refers to practical knowledge and skills gained through previous work or projects.

[0884] "Interest" refers to the interest or curiosity an employee has in a particular field or activity.

[0885] "Interaction history" refers to records and log information regarding interactions and communications between employees.

[0886] "Matching" is the process of identifying and recommending employees who can build mutually beneficial relationships based on collected data.

[0887] "Communication patterns" are data that show the trends and frequency of dialogue and information exchange between employees.

[0888] "Visualization" is a method of displaying data using visual representations such as graphs and figures to make it easier to understand intuitively.

[0889] A "server" is a computer system for collecting and analyzing data and providing results.

[0890] A "terminal" is a device that is directly operated by a user and receives notifications and data from a server.

[0891] A "machine learning algorithm" is a computational method for learning patterns and rules from data and making future predictions and classifications.

[0892] A "notification" is a message or alert that provides information from the server to the terminal.

[0893] "Mentoring" is an activity in which experienced employees impart knowledge and skills to junior employees and support their growth.

[0894] "Networking" is the act of building relationships among employees to share information and resources and support each other.

[0895] "Analysis" is the process of examining collected data in detail to derive patterns and trends.

[0896] System Overview

[0897] The system of this invention effectively collects data such as employee skills, experience, interests, and departmental interaction history, and then uses this data to suggest optimal mentoring and networking opportunities. Furthermore, by visualizing communication patterns between employees, it identifies connections within the organization and potential isolationist tendencies. It mainly consists of the following components:

[0898] 1. Data collection method (server)

[0899] 2. Matching proposal method (server)

[0900] 3. Visualization Method (Server)

[0901] 4. Notification method (terminal)

[0902] 5. Automatic collection means (terminal)

[0903] server

[0904] The server is mainly responsible for data collection, analysis, matching proposals, visualization, etc. The server uses the following specific software and hardware:

[0905] Data collection method: Employees enter their skills, experience, interests, and project history through an API (e.g., a RESTful API). Data is acquired using the Python library Requests.

[0906] Data analysis methods: Normalize the collected data and anonymize it if necessary. For example, use Python's pandas library to manipulate data frames and hash personally identifiable information.

[0907] Machine learning tools: We use machine learning algorithms to analyze employee skill sets and interests. Specifically, we use the scikit-learn library to perform clustering and classification algorithms.

[0908] Matching proposal method: Based on the analysis results, the optimal mentoring pair or group is selected. Proposals are generated using a Python script.

[0909] Visualization method: Analyze communication data between employees and generate network diagrams and graphs. Visualization is performed using Matplotlib and networkx libraries.

[0910] Terminal

[0911] A terminal is a device that a user directly operates and that receives notifications and data from a server. A terminal includes the following specific software:

[0912] Data input method: Provides an interface for users to input data such as skills and interests. A front-end application written in JavaScript is used.

[0913] Automatic collection method: The device periodically collects the user's email, chat history, and calendar data and sends it to the server. For example, a cron job can be set up to upload the data to the server on a fixed schedule.

[0914] Notification method: Proposals and notifications from the server are displayed to the user. JavaScript's Notification API is used to display pop-up notifications in the browser.

[0915] Visualization data display method: Display the received visualization data in the form of dashboards and reports. Generate interactive network diagrams using the D3.js library.

[0916] Specific examples

[0917] For example, suppose Person A is an employee with strong Python skills, and Person B is a new employee who wants to learn Python. Person B enters his / her interest in Python into the terminal, and Person A also enters his / her own skill set. The terminal collects this information and sends it to the server at 2:00 AM every day.

[0918] The server normalizes the received data, analyzes it using the scikit-learn library, and determines that Person A is suitable as a mentor for Person B. The server then creates a matching proposal and sends it to the devices of Person A and Person B. The devices notify Person A and Person B of the proposal via a pop-up notification, and the users can review the proposal and accept or reject it.

[0919] Once approved, the server analyzes the communication data between Person A and Person B and creates a visualized network diagram. The device displays this visualized data on a dashboard, visualizing the relationship between Person A and Person B.

[0920] Prompt Sentence Examples

[0921] "I want to develop a model to collect employee skills, experience, interests, and department interaction history to suggest optimal mentoring pairs or groups. Please explain how you will collect the data, analyze it, inform your suggestions, and visualize communication patterns."

[0922] As described above, the system of the present invention promotes effective mentoring and networking among employees, improving collaboration throughout the organization and making the most of employees' skill sets.

[0923] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0924] Step 1:

[0925] The terminal accepts data input from the user. The user enters their skills, experience, and interests into a form. This input data is stored in a local database. Specifically, when a user enters skills (e.g., Python, project management), experience (e.g., 5 years of software development experience), and interests (e.g., machine learning) into a web form and presses the submit button, an application written in JavaScript collects this data and stores it in IndexedDB.

[0926] Step 2:

[0927] The device periodically sends data to the server. For example, a cron job can be set up at 2:00 AM every day to securely upload the stored data to the server using the HTTPS protocol. The input data is in JSON format and is included in the request header along with any necessary authentication information. Specifically, the device runs the cron job and sends the data to the server using the Python Requests library.

[0928] Step 3:

[0929] The server normalizes the received data. For example, it represents each employee's data in a uniform format and handles missing values. The input data is in JSON format, and the output data is also in a similarly normalized JSON format. Specifically, the server uses the Python pandas library to convert the received data into a data frame and normalize each field.

[0930] Step 4:

[0931] The server anonymizes the data. For example, it hashes personally identifiable information to protect privacy. The input data is in JSON format, and the output data is also anonymized JSON. Specifically, the server hashes personally identifiable information using Python's hashlib library.

[0932] Step 5:

[0933] The server uses machine learning algorithms to analyze the collected data. For example, it clusters employees' skill sets and interests to find the most suitable mentoring pairs. The input data is anonymized JSON format, and the output data is a list of matching results. Specifically, the server uses the scikit-learn library to perform k-means clustering to determine suitable matches.

[0934] Step 6:

[0935] The server creates matching proposals, for example, generating proposal documents containing details of suitable mentor candidates or networking partners for each employee based on the analysis results. The input data is a list of analysis results, and the output data is a JSON format containing proposal details. Specifically, the server uses a Python script to generate proposal documents for each pair.

[0936] Step 7:

[0937] The server sends the proposal content to the device. For example, details of the generated proposal are sent to each employee's device via email or push notification. The input data is JSON format containing the proposal details, and the output data is the notification sending status. Specifically, the server configures an SMTP server and sends emails.

[0938] Step 8:

[0939] The device displays a notification to the user, for example, a pop-up notification or email with the proposal so that the user can review it. The input data are the proposal details, and the output data is the user's response (accept or reject). Specifically, the device uses JavaScript's Notification API to display a pop-up notification in the browser.

[0940] Step 9:

[0941] The user reviews the proposal and responds by either accepting or rejecting it. The input data is the proposal details, and the output data is the user's response (accept or reject). Specifically, after the user reviews the proposal, they click the confirm button, and the response is sent to the server.

[0942] Step 10:

[0943] The server receives the user's response and sets up a mentoring session or networking event, for example, by adding an event to a calendar if approved. The input data is the user's response, and the output data is the details of the set up event. Specifically, the server sets up a mentoring session using the Google Calendar API.

[0944] Step 11:

[0945] The server collects, analyzes, and visualizes communication data between employees. For example, it analyzes the frequency of emails and chats to create a communication network. The input data is communication history, and the output data is in graph format for visualization. Specifically, the server analyzes communication patterns using the networkx library and visualizes them using Matplotlib.

[0946] Step 12:

[0947] The terminal displays the visualized data on a dashboard, such as an interactive network diagram or graph, to help employees easily understand it. The input data is the visualized graph, and the output data is the display on the dashboard. Specifically, the terminal uses the D3.js library to display the visualized data on the browser.

[0948] The above are the specific processing steps of the program of this system.

[0949] (Application example 1)

[0950] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0951] Communication and skill matching between staff members in brick-and-mortar stores are important factors in streamlining store operations and improving staff performance. However, conventional methods make it difficult to efficiently pair staff members appropriately, taking into account each staff member's skills, experience, and interests. It is also difficult to visualize communication patterns between staff members and understand their relationships and potential isolation. This can lead to interpersonal friction, a sense of unfairness in evaluations, and even a decline in the operational efficiency of the entire store. To solve these issues, a system is needed that can propose optimal pairings based on staff members' skills and interests, and visualize their communication patterns.

[0952] 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.

[0953] In this invention, the server includes: means for collecting data such as employee (staff) skills, experience, interests, and department (shift) interaction history; means for proposing appropriate matching based on the collected data to build beneficial relationships between specific employees (staff) and other employees (staff); means for visualizing communication patterns between employees (staff) and identifying connections and potential isolation tendencies within the organization (store); means for proposing optimal pairings between staff in a physical store based on the collected and analyzed data to promote skill improvement and work efficiency; and means for visualizing communication patterns between staff and identifying relationships and isolation tendencies within the store. This makes it possible to improve the operational efficiency of physical stores, maximize staff capabilities, and perform fair evaluations.

[0954] "Employees (staff)" refers to people employed by a company, organization, or specific store, who have roles and responsibilities necessary for carrying out business. This also includes staff who contribute to the operation of physical stores.

[0955] "Skills" are the abilities and techniques required to carry out specific tasks or work, and their acquisition requires training and experience.

[0956] "Experience" refers to the knowledge and know-how that employees (staff) have gained through past work and projects, which contributes to improving their ability to carry out their work.

[0957] "Interest" refers to the interest and enthusiasm that employees (staff) have in a particular field or skill, and their motivation to learn new things based on this.

[0958] A "department (shift)" refers to a group or team that performs a specific task or role within a company or organization. In a physical store, it also includes the working hours and schedule of staff.

[0959] "Interaction history" refers to records of communication and collaboration between employees (staff), and includes data such as emails, chats, and meetings.

[0960] "Matching" refers to optimally pairing employees (staff) with each other based on specific criteria or algorithms, with the aim of complementing each other's skills and interests and improving work efficiency.

[0961] "Pairing" refers to creating optimal pairs based on skills, experience, and interests, with the aim of improving the work performance and capabilities of store staff.

[0962] "Communication patterns" indicate the method, frequency, and content of interactions between employees (staff), and analyzing these can visualize the relationships and cooperation within an organization.

[0963] "Visualization" refers to displaying analyzed data in a visual format such as graphs, charts, or network diagrams, making it easier to understand and gain insight into the information.

[0964] The system of the present invention collects and analyzes data such as the skills, experience, and interests of employees (staff), and the interaction history of departments (shifts), thereby visualizing optimal matching and communication patterns. This system can be implemented as follows based on the claims of the present invention.

[0965] composition

[0966] The system includes the following components:

[0967] 1. Data collection method (server)

[0968] 2. Matching proposal method (server)

[0969] 3. Visualization Method (Server)

[0970] 4. Notification method (terminal)

[0971] 5. Automatic collection means (terminal)

[0972] Data collection

[0973] The server periodically collects data through the API, including staff skills, experience, interests, and shift history, including information staff enter into their profiles and information retrieved through the scheduling application, as well as email, chat history, and calendar data automatically collected from devices.

[0974] Data analysis

[0975] The collected data is normalized and, if necessary, anonymized on the server. Machine learning algorithms (e.g., K-means clustering) are used to optimally pair staff based on their skill sets and interests. Based on the results of this analysis, optimal mentoring and team formation are suggested.

[0976] Matching proposals

[0977] The server then generates optimal matching suggestions based on the analysis, creating a list of specific mentoring pairs or teams, including detailed information about staff skills, interests, and mutual benefits.

[0978] Proposal Notification

[0979] The proposal is sent to the device, which notifies the staff member via a pop-up notification or email, and the staff member is given the option to review the proposal and accept or reject it.

[0980] Visualizing communication patterns

[0981] The server analyzes communication data such as emails, chats, and meeting frequency to generate network diagrams and graphs, visually displaying relationships between staff and potential isolation trends. This visualized data is provided in the form of dashboards and reports on the device.

[0982] Specific examples

[0983] For example, if staff member A is fluent in Spanish and staff member B wants to learn that skill, their information is entered into their devices and analyzed by the server. Based on the analysis results, A and B are identified as suitable pairing candidates, and this information is notified to both their devices. Upon receiving the notification, A and B can begin a mentoring session based on the proposed pairing.

[0984] Example prompts for generative AI models

[0985] Please suggest the best matching pair based on the following data:

[0986] Staff A: Spanish skill level 5, Interests: Teaching

[0987] Staff B: Spanish skill level 2, Interests: Learning

[0988] Staff C: Planning Skill Level 4, Interests: Leadership

[0989] Staff D: Planning skill level 3, Interests: Learning

[0990] Proposal format: [Staff pair / group, reason]

[0991] As described above, by using the system of the present invention, it is possible to improve the operational efficiency of physical stores, maximize the capabilities of staff, and achieve fair evaluations.

[0992] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0993] Step 1: Data collection

[0994] The server collects data including staff skills, experience, interests, and shift history through an API. This data comes from information entered in each staff member's profile and data obtained from the scheduling app. The collected data is then normalized and stored. This data includes staff skill levels, interest categories, and shift times. This allows for the management of distributed data in a unified format.

[0995] Step 2: Additional automated data collection

[0996] The devices automatically collect staff emails, chat history, and calendar data. This data is periodically sent to the server with the user's permission. Specifically, the devices analyze the staff's communication history and extract information such as the number of emails, chat frequency, and meeting schedules. This data is sent to the server and used as data for analysis.

[0997] Step 3: Data analysis

[0998] The server normalizes the collected data and anonymizes it if necessary. It then uses machine learning algorithms (e.g., K-means clustering) to optimally pair staff based on skill sets and interests. For example, it clusters each staff member's skill level and areas of interest as a feature vector, and groups staff members with similar characteristics. This enables pairings that are expected to complement each other's skills and harmonize their interests.

[0999] Step 4: Generate matching proposals

[1000] The server generates optimal matching proposals based on the results of the data analysis. Specifically, it creates a list for each clustered group or pair, detailing the reasons for each match and the benefits of the pairing. This proposal list is organized to include information on staff skills, interests, and mutual benefits. This allows it to propose optimal mentoring and team formation among staff.

[1001] Step 5: Notification of proposal

[1002] The server sends the generated matching proposal to the terminal. The terminal notifies the staff of the proposal via a pop-up notification or email. The user can then review the details of the proposal based on the notification and select the option to approve or reject it. This allows the user to decide whether or not to proceed with the proposed match and proceed to the next step.

[1003] Step 6: Visualize communication patterns

[1004] The server analyzes communication data such as emails, chats, and frequency of meetings between staff members. Based on the analysis results, it generates visualized data such as network diagrams and graphs. Specifically, by analyzing the communication data and illustrating the contact points and frequency of each staff member using node and edge relationships, it clarifies the relationships within the organization and potential isolation trends. This visualized data is sent to the terminal and displayed to the user in the form of a dashboard or report.

[1005] 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.

[1006] The system of the present invention aims to collect data such as employee skills, experience, interests, departmental interaction history, and employee emotions, propose matches to build beneficial relationships, and visualize communication patterns between employees to identify connections within the organization and potential trends toward isolation. By utilizing an emotion engine that recognizes user emotions, more advanced and accurate matching becomes possible.

[1007] System Overview

[1008] The system of the present invention can be implemented in the following configuration:

[1009] 1. Data collection method (server)

[1010] 2. Emotion engine (server)

[1011] 3. Matching proposal method (server)

[1012] 4. Visualization Method (Server)

[1013] 5. Notification Method (Terminal)

[1014] 6. Automatic collection means (terminal)

[1015] Program processing

[1016] Data collection

[1017] The server collects data including employees' skills, experience, interests, department interaction history, and emotional state. Users input their skills and interests into their devices, which then send the data to the server. Furthermore, with the user's permission, the device automatically collects email, chat history, and calendar data and sends them to the server. The emotion engine analyzes the user's emotions from this text and voice data and sends the results to the server.

[1018] Data analysis

[1019] The server normalizes the collected data and anonymizes it as necessary. It then uses a machine learning algorithm to extract features based on employees' skills, experience, interests, and emotional state, and calculates optimal mentoring and networking matches. It also analyzes the results of the emotion engine, taking emotional compatibility into account.

[1020] Matching proposals

[1021] The server generates appropriate matching proposals based on the results of data analysis. The proposals take into account each employee's skills, experience, interests, emotional state, and mutual benefits. For example, if Person A is familiar with Python and Person B wants to learn Python, the server will generate a proposal that Person A would be a good mentor for Person B. The results of the emotion engine are also taken into account, and the proposal is adjusted to be made when Person A and Person B are in a good emotional state.

[1022] Proposal Notification

[1023] The server sends the generated proposal to the target user's device, which notifies the user via a pop-up notification or email notification. The user can review the proposal and choose the option to accept or reject it.

[1024] Visualizing communication patterns

[1025] The server analyzes communication data between users, such as the frequency of emails, chats, and meetings, and generates visualized data in the form of network diagrams and graphs. The results of the emotion engine are also reflected in the visualized data, so the user's emotional state is also displayed. The device displays the visualized data in a dashboard format, making it easy for the user to check.

[1026] Specific examples

[1027] For example, suppose Person A has deep knowledge of Python programming, and Person B is a new employee who wants to learn Python. Person B enters his / her interest in Python into the device, and Person A enters his / her skill set. The device sends this data to the server, and the emotion engine then analyzes the emails, chat contents, and voice data of these users and sends their emotional state to the server.

[1028] The server analyzes all data, including skills, interests, and emotional state. If A is the best mentor for B to learn Python, and both parties are in a good emotional state, the server creates a matching proposal and notifies A and B's devices. If both parties confirm the proposal and approve it, a mentoring session is set up.

[1029] In this way, the system of the present invention enables efficient mentoring and networking among employees, effectively utilizes employees' skill sets, and improves collaboration across the organization by taking into account emotional matching.

[1030] The processing flow will be explained below.

[1031] Step 1:

[1032] Users enter information about their skills, experience, and interests into the device, such as "5 years of Python programming experience" or "interested in machine learning."

[1033] Step 2:

[1034] The terminal transmits the input data to the server, where it is formatted and encrypted.

[1035] Step 3:

[1036] The server stores the received data in a database, normalizing and, if necessary, anonymizing the data before storing it.

[1037] Step 4:

[1038] If the user gives permission, the device will automatically collect email, chat history, and calendar data on a regular basis and send it to the server.

[1039] Step 5:

[1040] The server retrieves relevant data from other business software (e.g., project management tools, mail servers) through APIs, including project history and communication history.

[1041] Step 6:

[1042] The emotion engine analyzes the text data and voice data of the user's emails and chats to identify the user's emotional state, and then sends the analysis results to the server.

[1043] Step 7:

[1044] The server normalizes all collected data and uses machine learning algorithms to extract employee skills, experience, interests, and emotional states as features.

[1045] Step 8:

[1046] The server calculates optimal mentoring and networking matches between users based on the feature values, taking into account the results of the emotion engine, and reflecting emotional compatibility in the matching.

[1047] Step 9:

[1048] The server generates specific match proposals based on the valid matches, including details of each user's skills, experience, interests, emotional state, and mutual interests.

[1049] Step 10:

[1050] The server sends the generated proposal to the target user's device. For example, it sends a proposal that person A is suitable to be person B's mentor.

[1051] Step 11:

[1052] The device will receive the suggestion and notify the user via a pop-up or email notification, giving the user the option to review the suggestion and accept or reject it.

[1053] Step 12:

[1054] If the user accepts the proposal, the device provides a scheduling function for setting up mentoring sessions and networking events.

[1055] Step 13:

[1056] The server continuously collects and analyzes the mentoring sessions and communication history between users, thereby monitoring how the relationships between users are developing.

[1057] Step 14:

[1058] The server generates the analysis results as visualized data and displays them as graphs and network diagrams. It also visually displays the user's emotional state, reflecting the results of the emotion engine.

[1059] Step 15:

[1060] The device displays the visualized data in a dashboard format, allowing users to easily check the analysis results, and understand their own communication patterns and emotional state.

[1061] In this way, the system of the present invention realizes efficient mentoring and networking among employees, and by taking into consideration emotional matching, it is possible to improve collaboration throughout the organization.

[1062] Example 2

[1063] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1064] In modern companies, a key challenge is to maximize the use of individual employee characteristics, such as skills, experience, and interests, to promote communication and cooperation among employees. However, it is extremely difficult to properly match these characteristics and understand emotional compatibility, employee connections, and potential tendencies toward isolation. Conventional systems often lack the accuracy of data collection, analysis, and matching proposals, resulting in ineffective relationship building. Therefore, there is a need for a system that can achieve high-precision matching that takes into account employee skills and emotional states, and visualize communication patterns.

[1065] 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.

[1066] In this invention, the server includes means for collecting data including employee skills, experience, interests, department interaction history, and emotional state, means for proposing appropriate matches for building beneficial relationships between specific employees and other employees based on the collected data, means for analyzing the emotional data and taking emotional compatibility into account in the collected data, and means for visualizing communication patterns between employees and identifying connections within the organization and potential tendencies toward isolation. This enables highly accurate matching based on employee skills and emotional state, thereby improving communication and cooperation within the company.

[1067] "Employee skills" refers to the specialized knowledge and abilities possessed by individual employees.

[1068] "Experience" refers to the accumulation of practical knowledge and skills that employees have acquired through their work.

[1069] "Interests" refer to areas or activities that interest employees.

[1070] "Department interaction history" refers to records of business interactions and communications between employees.

[1071] "Emotional state" refers to data that shows an employee's emotional state, such as joy or stress.

[1072] "Means of collecting data" refers to the methods and devices used to collect information entered by employees and data collected automatically.

[1073] "Means for suggesting matches" refers to methods or systems that use collected data to help connect specific employees with other employees to beneficial relationships.

[1074] "Means for analyzing emotional data" refers to methods and algorithms for analyzing collected emotional data and understanding emotional compatibility and state.

[1075] "Means for visualizing communication patterns" refers to methods and tools for displaying the frequency and form of communication between employees in the form of graphs, network diagrams, etc.

[1076] The system of the present invention aims to collect data such as employee skills, experience, interests, department interaction history, and emotional state, propose matches to build beneficial relationships, and further visualize communication patterns between employees to identify connections within the organization and potential tendencies toward isolation. The following describes in detail the modes for implementing the present invention.

[1077] System Configuration

[1078] The system of the present invention can be implemented in the following configuration:

[1079] 1. Data collection method (server)

[1080] 2. Emotion engine (server)

[1081] 3. Matching proposal method (server)

[1082] 4. Visualization Method (Server)

[1083] 5. Notification Method (Terminal)

[1084] 6. Automatic collection means (terminal)

[1085] Data collection

[1086] The server collects data including employees' skills, experience, interests, department interaction history, and emotional state. Users input their skills and interests into their devices, which then send the data to the server. Furthermore, with the user's permission, the device automatically collects email, chat history, and calendar data and sends them to the server. The emotion engine analyzes the user's emotions from this text and voice data and sends the results to the server.

[1087] Data analysis

[1088] The server normalizes the collected data and anonymizes it as necessary. It then uses a machine learning algorithm to extract features based on employees' skills, experience, interests, and emotional state, and calculates optimal mentoring and networking matches. It also analyzes the results of the emotion engine, taking emotional compatibility into account.

[1089] Matching proposals

[1090] The server generates appropriate matching proposals based on the results of data analysis. For example, if one employee is familiar with Python and another employee wants to learn Python, it will generate a proposal that the two are suitable for a mentor-learner relationship. By incorporating the results of the emotion engine, the server also evaluates the emotional compatibility between the two parties.

[1091] Proposal Notification

[1092] The server sends the generated proposal to the target user's device, where the device notifies the user of the proposal via a pop-up notification or email notification. The user can review the proposal and choose to accept or reject it.

[1093] Visualizing communication patterns

[1094] The server analyzes communication data between users, such as emails, chats, and frequency of meetings, and generates visualized data in the form of network diagrams and graphs. The results of the emotion engine are also reflected in the visualized data, so the user's emotional state is also displayed. The device displays the visualized data in a dashboard format, making it easy for users to check.

[1095] Specific examples

[1096] For example, suppose Person A has deep knowledge of Python programming, and Person B is a new employee who wants to learn Python. Person B enters his / her interest in Python into the device, and Person A enters his / her skill set. The device sends this data to the server, and the emotion engine analyzes the emails, chat contents, and voice data of these users and sends their emotional state to the server.

[1097] The server analyzes all data, including skills, interests, and emotional states. If A is the best mentor for B to learn Python, and both parties are in a good emotional state, the server creates a matching proposal and notifies A and B's devices. If both A and B accept the proposal, a mentoring session is set up. In this way, the system of the present invention realizes efficient mentoring and networking among employees, effectively utilizing employees' skill sets, and improves collaboration across the organization by taking emotional matching into consideration.

[1098] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1099] Step 1: Enter and collect data

[1100] 1.1 User Input

[1101] The user enters their skills, experience, and interests into the terminal. For example, they might enter, "I'm interested in Python programming and have basic knowledge."

[1102] The terminal collects the data entered by the user and transmits it to the server.

[1103] Input: Skills, experience, and interest data entered by the user.

[1104] Output: Data sent from the device to the server.

[1105] 1.2 Automatic Data Collection

[1106] With the user's permission, the device automatically collects email, chat history, and calendar data.

[1107] The terminal transmits the collected data to the server.

[1108] Input: User permission, email and chat history, calendar data.

[1109] Output: Email, chat history, and calendar data sent from the device to the server.

[1110] 1.3 Emotion Data Analysis

[1111] The emotion engine analyzes the user's emotions from collected text and voice data. For example, it can extract emotions such as "feeling stressed" from the content of an email.

[1112] The emotion engine sends the analysis results as data to the server.

[1113] Input: text and audio data.

[1114] Output: Sentiment analysis results sent to the server.

[1115] Step 2: Normalize and anonymize data

[1116] 2.1 Data normalization

[1117] The server unifies and normalizes the collected data formats, for example, unifying due dates and skill levels across different formats.

[1118] Input: Raw data collected.

[1119] Output: Normalized data.

[1120] 2.2 Data anonymization

[1121] The server anonymizes the data as needed, for example by replacing employee identifying information with a random identifier.

[1122] Input: Normalized data.

[1123] Output: Anonymized data.

[1124] Step 3: Feature extraction and matching calculation

[1125] 3.1 Feature extraction

[1126] The server uses machine learning algorithms to extract features such as skills, experience, interests, and emotional state. For example, a user's skill set might be extracted as "Python: intermediate, data analysis: beginner."

[1127] Input: Normalized data, anonymized data.

[1128] Output: Data extracted as features.

[1129] 3.2 Matching Calculation

[1130] The server calculates the optimal match based on the extracted features, deriving a result such as "Person A is the best mentor for Person B."

[1131] The server also takes into account the results of the emotion engine and incorporates emotional compatibility into its calculations, for example, "Make a proposal when A and B are in a good emotional state."

[1132] Input: Data extracted as features, sentiment analysis results.

[1133] Output: Best matching suggestion.

[1134] Step 4: Generate and notify matching proposals

[1135] 4.1 Generating Matching Proposals

[1136] The server generates appropriate matching proposals based on the results of the data analysis, for example, "Propose that person A mentor person B in Python."

[1137] Input: Best matching proposal data.

[1138] Output: Specific matching suggestions.

[1139] 4.2 Proposal Notification

[1140] The server sends the generated proposal to the target user's device. For example, it notifies the devices of user A and user B that "a mentoring proposal is available."

[1141] The device will notify the user of the suggestions via a pop-up notification or email notification.

[1142] The user reviews the proposal and has the option to accept or reject it.

[1143] Input: A specific matching suggestion.

[1144] Output: Notifications to the terminal and responses from the user.

[1145] Step 5: Visualize communication patterns

[1146] 5.1 Data Analysis

[1147] The server analyzes communication data such as the frequency of emails, chats, and meetings between users. For example, it collects data such as "Person A and Person B frequently email or chat."

[1148] The results of the emotion engine are also reflected in the visualization data, so the user's emotional state is also displayed.

[1149] Input: Communication data between users, sentiment analysis results.

[1150] Output: Analysis results of communication patterns.

[1151] 5.2 Generating visualization data

[1152] The server generates visualization data in the form of network diagrams and graphs based on the analysis results. For example, it creates a network diagram showing the communication patterns between person A and person B.

[1153] Input: Analysis results of communication patterns.

[1154] Output: Visualized data as network diagrams and graphs.

[1155] 5.3 Viewing the Dashboard

[1156] The device displays visualized data in a dashboard format for easy viewing by the user. For example, it provides a dashboard displaying the communication patterns and emotional states of person A and person B.

[1157] Input: Visualization data.

[1158] Output: Display in dashboard format.

[1159] (Application example 2)

[1160] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1161] It is necessary to optimize the work efficiency of automated machines operating in factories and realize team formation that makes the most of each machine's skills, work history, and interest level. It is also necessary to improve productivity by visualizing communication patterns between automated machines and identifying potential inefficiencies.

[1162] 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.

[1163] In this invention, the server includes means for collecting data such as the skills, work history, interest level, and team interaction history of automated machines operating in a factory, means for proposing beneficial team formation and work distribution between a specific automated machine and other automated machines based on the collected data, and means for visualizing communication patterns between the automated machines and identifying efficiencies and potential inefficiencies in the workplace. This enables effective team formation and work distribution that makes the most of the skills and work history of the automated machines, thereby improving productivity in the factory.

[1164] "Automatic machines" refers to robots and mechanical devices operating in factories, and is a general term for machines that perform tasks automatically.

[1165] "Skill" refers to the ability to perform a specific task or action that an automated machine can perform.

[1166] "Work history" is a record of work that an automated machine has performed in the past, and includes data such as the success rate and work time.

[1167] "Interest" refers to the degree of interest in tasks that automated machines excel at or have shown a high success rate in the past.

[1168] "Team interaction history" refers to the history of past collaborative and cooperative work between automated machines.

[1169] "Communication pattern" is a concept that indicates the format and frequency of data exchange and operational coordination between automated machines.

[1170] An "operation log" is a detailed record of the operations of an automated machine recorded while it is in operation, including operating status and error information.

[1171] An "error log" refers to a record of errors or malfunctions that occur while an automated machine is operating.

[1172] "Visualization" refers to the process of displaying data as graphs or charts so that it can be understood at a glance.

[1173] "Control device" refers to a server or terminal device used to monitor and manage automated machinery.

[1174] The present invention is a system for optimizing work efficiency and productivity using automated machines operating in a factory. The system includes the following components:

[1175] 1. Data collection method (server)

[1176] The server collects data on the skills, work history, interest level, team interaction history, operation logs, error logs, etc. of the automated machines operating in the factory. A Python script is used to collect data, which is then sent to the management server in real time.

[1177] 2. Machine learning algorithm (server)

[1178] The server normalizes the collected data and anonymizes it if necessary. It then uses machine learning algorithms to extract features based on each machine's skills, work history, and interest levels, and calculates optimal team composition and work distribution. The machine learning algorithms used include scikit-learn and TensorFlow.

[1179] 3. Matching proposal method (server)

[1180] Based on the collected and analyzed data, the server proposes beneficial team formation and work distribution between specific automated machines and other automated machines. The proposal is optimized taking into account the skills, work history, and interest of each automated machine, and the proposal is notified to the control device.

[1181] 4. Proposal notification means (control device)

[1182] The server notifies the control device of the generated proposal, allowing engineers and operators in the factory to review the proposed team formation and work distribution and approve them as necessary.

[1183] 5. Visualization tools (dashboards)

[1184] The server analyzes the frequency of data exchange and collaboration between automated machines and generates visualized data in the form of network diagrams and graphs. Tools used for visualization include Tableau and D3.js. This visualized data is displayed in a dashboard format so that operators can easily check it.

[1185] Specific examples

[1186] For example, suppose that automatic machine A is responsible for assembly work in a factory, and automatic machine B is responsible for inspection work. The operation logs and work history of automatic machines A and B are sent to a server, which analyzes them. Based on the analysis results, the server proposes the optimal way for automatic machines A and B to work together and notifies the control device.

[1187] Once the engineers review the proposals on the dashboard and approve the proposed teaming and work distribution, new collaborations can begin, improving productivity within the factory and making the most of the skills and work history of each automated machine.

[1188] ---

[1189] Example prompts for input to a generative AI model:

[1190] "Factory robot A specializes in assembly work, and robot B specializes in inspection work. Please generate a proposal for the optimal collaboration work based on past success stories."

[1191] ---

[1192] In this way, the system of the present invention realizes efficient and highly productive factory operations, and maximizes the capabilities of automated machines.

[1193] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1194] Step 1:

[1195] The server collects data such as the skills, work history, interest level, team interaction history, operation logs, and error logs of the automated machines operating in the factory. This data sent from each automated machine is sent to the server in real time using a Python script. The input is various data, and the output is a normalized dataset.

[1196] Step 2:

[1197] The server normalizes the collected data and anonymizes it if necessary, standardizing the data format and concealing personally identifiable information to protect privacy. The input is the collected raw data, and the output is the normalized and anonymized data.

[1198] Step 3:

[1199] The server analyzes the data using machine learning algorithms. It extracts features such as the skills, work history, and interest of each automated machine, and then calculates optimal team composition and work distribution. The algorithms used include scikit-learn and TensorFlow. The input is normalized data, and the output is a proposal for optimal team composition and work distribution.

[1200] Step 4:

[1201] The server generates matching proposals and notifies the control device. The proposals are optimized taking into account the skills, work history, and interests of each automated machine. The input is the output of the machine learning algorithm, and the output is a proposal notification sent to the control device.

[1202] Step 5:

[1203] The control device displays the generated proposals on a dashboard, allowing engineers and operators to review the proposals and providing them in a visually easy-to-understand format. The input is the proposal notification sent from the server, and the output is the display data on the dashboard.

[1204] Step 6:

[1205] Engineers review the proposals on the dashboard and approve them if necessary. Once approved, new team formation and work distribution to the automated machines is initiated. The input is the proposal on the dashboard, and the output is approval feedback.

[1206] Step 7:

[1207] Based on the engineer's approval, the automated machines initiate new team formation and work distribution. Data is exchanged and actions are coordinated between the automated machines to carry out the work. The input is approval feedback, and the output is the actual work results.

[1208] In this way, a system is built that makes maximum use of the skills and work history of the automated machines in the factory through each processing step, achieving efficient and highly productive factory operations.

[1209] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1210] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1211] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1212] [Fourth embodiment]

[1213] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1214] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1215] 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).

[1216] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1217] 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.

[1218] 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).

[1219] 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.

[1220] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1221] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1222] 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.

[1223] 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.

[1224] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1225] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1226] The system of the present invention aims to collect data such as employee skills, experience, interests, and departmental interaction history, and based on the collected data, propose appropriate matches to build beneficial relationships, and visualize communication patterns between employees to identify connections within the organization and potential tendencies toward isolation.

[1227] System Overview

[1228] This system can be implemented mainly in the following configuration.

[1229] 1. Data collection method (server)

[1230] 2. Matching proposal method (server)

[1231] 3. Visualization Method (Server)

[1232] 4. Notification method (terminal)

[1233] 5. Automatic collection means (terminal)

[1234] Program processing

[1235] Data collection

[1236] The server collects data including employees' skills, experience, interests, and department interaction history. Specifically, the server obtains employees' project history, training, and skill assessment results through APIs. Based on the user's permissions, the device automatically collects employees' emails, chat history, and calendar data and periodically sends them to the server.

[1237] Data analysis

[1238] The server normalizes the collected data and anonymizes it if necessary. It then uses machine learning algorithms to match employees with the best mentoring and networking opportunities based on their skill sets and interests. The server analyzes the data and selects the best mentoring pairs and groups.

[1239] Matching proposals

[1240] Based on the data analysis, the server develops mentoring and networking plans to suggest suitable matches, including details of each employee's skills, interests and mutual benefits.

[1241] Proposal Notification

[1242] The server sends the proposal to the device, which then notifies the user via a pop-up notification or email, giving the user the option to review the proposal and accept or reject it.

[1243] Visualizing communication patterns

[1244] The server analyzes communication data such as emails, chats, and meeting frequency between employees. Based on the analysis results, it generates visualization data such as network diagrams and graphs and sends them to the device. The device then displays the visualization data to the user in the form of a dashboard or report.

[1245] Specific examples

[1246] For example, suppose Person A is an employee with deep knowledge of Python programming, while Person B is a new employee who wants to learn Python. If Person B enters his / her interest in Python into the terminal, and Person A also enters his / her skill set, the server will collect this information and perform analysis.

[1247] The server uses a machine learning algorithm to determine that Person A is a suitable mentor for Person B. The server then creates a matching proposal and notifies Person A and Person B of the proposal's contents to their devices. The users (Person A and Person B) check the notification and, if they approve the proposal, a mentoring session is set up.

[1248] Furthermore, the server analyzes the interactions and schedules between Person A and Person B and visualizes their communication patterns. The device displays this visualized data on a dashboard, making it possible to visualize the relationship between the two.

[1249] As described above, the system of the present invention can promote efficient mentoring and networking among employees, improve collaboration throughout the organization, and maximize the use of employees' skill sets.

[1250] The processing flow will be explained below.

[1251] Step 1:

[1252] Users enter information about their skills, experience, and interests into the terminal, such as "5 years of experience in Python programming" or "interested in machine learning."

[1253] Step 2:

[1254] The terminal transmits the input data to the server, where it formats the data and encrypts it as necessary.

[1255] Step 3:

[1256] The server stores the received data in a database, where it may be normalized and anonymized to protect privacy before being stored.

[1257] Step 4:

[1258] The server collects additional data from other business software (e.g., project management tools, mail servers) through APIs, including project history and communication history.

[1259] Step 5:

[1260] With the user's permission, the device automatically collects emails, chat history, and calendar data and sends them to the server, thereby obtaining the latest communication data.

[1261] Step 6:

[1262] The server analyzes all collected data and uses machine learning algorithms to extract features of employees' skills and interests, then calculates optimal mentoring and networking matches.

[1263] Step 7:

[1264] Based on the analysis results, the server generates a specific matching proposal for each user. For example, if Person A is suitable as a mentor for Person B, the server will provide a detailed description of "why Person A should be Person B's mentor."

[1265] Step 8:

[1266] The server sends the generated proposal to the target user's device, which receives the notification and notifies the user via a pop-up or email notification.

[1267] Step 9:

[1268] The user reviews the proposal from their device and has the option to accept or reject the proposal, and if accepted, a mentoring session is set up.

[1269] Step 10:

[1270] The server continuously collects and analyzes the mentoring sessions and communication history between users, thereby monitoring how the relationships between users are developing.

[1271] Step 11:

[1272] The server generates the analysis results as visualized data and displays them to the user in the form of a network diagram or graph. This visualized data is displayed on a dashboard on the terminal, allowing the user to easily check it.

[1273] These are the steps in the program, which will enable effective mentoring and networking among employees and significantly improve collaboration across the organization.

[1274] Example 1

[1275] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1276] In modern organizations, it is common for employees with diverse skills and interests to gather in one place. However, due to a lack of communication between employees and a lack of appropriate mentoring, their skills and experiences are often not fully utilized. As a result, not only is the building of beneficial relationships and collaboration between employees hindered, but it can also lead to a potential tendency for employees to become isolated. To solve these issues, a system is needed that can effectively collect and analyze employee data, propose appropriate matching, and visualize communication patterns.

[1277] 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.

[1278] In this invention, the server includes: means for collecting data such as employee skills, experience, interests, and department interaction history; means for proposing appropriate matches for building beneficial relationships between specific employees and other employees based on the collected data; means for visualizing communication patterns between employees and identifying connections within the organization and potential isolation tendencies; means for analyzing employees' skill sets and interests using machine learning algorithms to match them for optimal mentoring and networking; and means for sending notifications to terminals and providing users with the option to review and accept or reject the suggestions, thereby promoting efficient mentoring and networking between employees, improving collaboration across the organization, and making the most of employees' skill sets.

[1279] A "skill" is the knowledge, technique, or ability required to effectively perform a particular job or role.

[1280] "Experience" refers to practical knowledge and skills gained through previous work or projects.

[1281] "Interest" refers to the interest or curiosity an employee has in a particular field or activity.

[1282] "Interaction history" refers to records and log information regarding interactions and communications between employees.

[1283] "Matching" is the process of identifying and recommending employees who can build mutually beneficial relationships based on collected data.

[1284] "Communication patterns" are data that show the trends and frequency of dialogue and information exchange between employees.

[1285] "Visualization" is a method of displaying data using visual representations such as graphs and figures to make it easier to understand intuitively.

[1286] A "server" is a computer system for collecting and analyzing data and providing results.

[1287] A "terminal" is a device that is directly operated by a user and receives notifications and data from a server.

[1288] A "machine learning algorithm" is a computational method for learning patterns and rules from data and making future predictions and classifications.

[1289] A "notification" is a message or alert that provides information from the server to the terminal.

[1290] "Mentoring" is an activity in which experienced employees impart knowledge and skills to junior employees and support their growth.

[1291] "Networking" is the act of building relationships among employees to share information and resources and support each other.

[1292] "Analysis" is the process of examining collected data in detail to derive patterns and trends.

[1293] System Overview

[1294] The system of this invention effectively collects data such as employee skills, experience, interests, and departmental interaction history, and then uses this data to suggest optimal mentoring and networking opportunities. Furthermore, by visualizing communication patterns between employees, it identifies connections within the organization and potential isolationist tendencies. It mainly consists of the following components:

[1295] 1. Data collection method (server)

[1296] 2. Matching proposal method (server)

[1297] 3. Visualization Method (Server)

[1298] 4. Notification method (terminal)

[1299] 5. Automatic collection means (terminal)

[1300] server

[1301] The server is mainly responsible for data collection, analysis, matching proposals, visualization, etc. The server uses the following specific software and hardware:

[1302] Data collection method: Employees enter their skills, experience, interests, and project history through an API (e.g., a RESTful API). Data is acquired using the Python library Requests.

[1303] Data analysis methods: Normalize the collected data and anonymize it if necessary. For example, use Python's pandas library to manipulate data frames and hash personally identifiable information.

[1304] Machine learning tools: We use machine learning algorithms to analyze employee skill sets and interests. Specifically, we use the scikit-learn library to perform clustering and classification algorithms.

[1305] Matching proposal method: Based on the analysis results, the optimal mentoring pair or group is selected. Proposals are generated using a Python script.

[1306] Visualization method: Analyze communication data between employees and generate network diagrams and graphs. Visualization is performed using Matplotlib and networkx libraries.

[1307] Terminal

[1308] A terminal is a device that a user directly operates and that receives notifications and data from a server. A terminal includes the following specific software:

[1309] Data input method: Provides an interface for users to input data such as skills and interests. A front-end application written in JavaScript is used.

[1310] Automatic collection method: The device periodically collects the user's email, chat history, and calendar data and sends it to the server. For example, a cron job can be set up to upload the data to the server on a fixed schedule.

[1311] Notification method: Proposals and notifications from the server are displayed to the user. JavaScript's Notification API is used to display pop-up notifications in the browser.

[1312] Visualization data display method: Display the received visualization data in the form of dashboards and reports. Generate interactive network diagrams using the D3.js library.

[1313] Specific examples

[1314] For example, suppose Person A is an employee with strong Python skills, and Person B is a new employee who wants to learn Python. Person B enters his / her interest in Python into the terminal, and Person A also enters his / her own skill set. The terminal collects this information and sends it to the server at 2:00 AM every day.

[1315] The server normalizes the received data, analyzes it using the scikit-learn library, and determines that Person A is suitable as a mentor for Person B. The server then creates a matching proposal and sends it to the devices of Person A and Person B. The devices notify Person A and Person B of the proposal via a pop-up notification, and the users can review the proposal and accept or reject it.

[1316] Once approved, the server analyzes the communication data between Person A and Person B and creates a visualized network diagram. The device displays this visualized data on a dashboard, visualizing the relationship between Person A and Person B.

[1317] Prompt Sentence Examples

[1318] "I want to develop a model to collect employee skills, experience, interests, and department interaction history to suggest optimal mentoring pairs or groups. Please explain how you will collect the data, analyze it, inform your suggestions, and visualize communication patterns."

[1319] As described above, the system of the present invention promotes effective mentoring and networking among employees, improving collaboration throughout the organization and making the most of employees' skill sets.

[1320] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1321] Step 1:

[1322] The terminal accepts data input from the user. The user enters their skills, experience, and interests into a form. This input data is stored in a local database. Specifically, when a user enters skills (e.g., Python, project management), experience (e.g., 5 years of software development experience), and interests (e.g., machine learning) into a web form and presses the submit button, an application written in JavaScript collects this data and stores it in IndexedDB.

[1323] Step 2:

[1324] The device periodically sends data to the server. For example, a cron job can be set up at 2:00 AM every day to securely upload the stored data to the server using the HTTPS protocol. The input data is in JSON format and is included in the request header along with any necessary authentication information. Specifically, the device runs the cron job and sends the data to the server using the Python Requests library.

[1325] Step 3:

[1326] The server normalizes the received data. For example, it represents each employee's data in a uniform format and handles missing values. The input data is in JSON format, and the output data is also in a similarly normalized JSON format. Specifically, the server uses the Python pandas library to convert the received data into a data frame and normalize each field.

[1327] Step 4:

[1328] The server anonymizes the data. For example, it hashes personally identifiable information to protect privacy. The input data is in JSON format, and the output data is also anonymized JSON. Specifically, the server hashes personally identifiable information using Python's hashlib library.

[1329] Step 5:

[1330] The server uses machine learning algorithms to analyze the collected data. For example, it clusters employees' skill sets and interests to find the most suitable mentoring pairs. The input data is anonymized JSON format, and the output data is a list of matching results. Specifically, the server uses the scikit-learn library to perform k-means clustering to determine suitable matches.

[1331] Step 6:

[1332] The server creates matching proposals, for example, generating proposal documents containing details of suitable mentor candidates or networking partners for each employee based on the analysis results. The input data is a list of analysis results, and the output data is a JSON format containing proposal details. Specifically, the server uses a Python script to generate proposal documents for each pair.

[1333] Step 7:

[1334] The server sends the proposal content to the device. For example, details of the generated proposal are sent to each employee's device via email or push notification. The input data is JSON format containing the proposal details, and the output data is the notification sending status. Specifically, the server configures an SMTP server and sends emails.

[1335] Step 8:

[1336] The device displays a notification to the user, for example, a pop-up notification or email with the proposal so that the user can review it. The input data are the proposal details, and the output data is the user's response (accept or reject). Specifically, the device uses JavaScript's Notification API to display a pop-up notification in the browser.

[1337] Step 9:

[1338] The user reviews the proposal and responds by either accepting or rejecting it. The input data is the proposal details, and the output data is the user's response (accept or reject). Specifically, after the user reviews the proposal, they click the confirm button, and the response is sent to the server.

[1339] Step 10:

[1340] The server receives the user's response and sets up a mentoring session or networking event, for example, by adding an event to a calendar if approved. The input data is the user's response, and the output data is the details of the set up event. Specifically, the server sets up a mentoring session using the Google Calendar API.

[1341] Step 11:

[1342] The server collects, analyzes, and visualizes communication data between employees. For example, it analyzes the frequency of emails and chats to create a communication network. The input data is communication history, and the output data is in graph format for visualization. Specifically, the server analyzes communication patterns using the networkx library and visualizes them using Matplotlib.

[1343] Step 12:

[1344] The terminal displays the visualized data on a dashboard, such as an interactive network diagram or graph, to help employees easily understand it. The input data is the visualized graph, and the output data is the display on the dashboard. Specifically, the terminal uses the D3.js library to display the visualized data on the browser.

[1345] The above are the specific processing steps of the program of this system.

[1346] (Application example 1)

[1347] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1348] Communication and skill matching between staff members in brick-and-mortar stores are important factors in streamlining store operations and improving staff performance. However, conventional methods make it difficult to efficiently pair staff members appropriately, taking into account each staff member's skills, experience, and interests. It is also difficult to visualize communication patterns between staff members and understand their relationships and potential isolation. This can lead to interpersonal friction, a sense of unfairness in evaluations, and even a decline in the operational efficiency of the entire store. To solve these issues, a system is needed that can propose optimal pairings based on staff members' skills and interests, and visualize their communication patterns.

[1349] 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.

[1350] In this invention, the server includes: means for collecting data such as employee (staff) skills, experience, interests, and department (shift) interaction history; means for proposing appropriate matching based on the collected data to build beneficial relationships between specific employees (staff) and other employees (staff); means for visualizing communication patterns between employees (staff) and identifying connections and potential isolation tendencies within the organization (store); means for proposing optimal pairings between staff in a physical store based on the collected and analyzed data to promote skill improvement and work efficiency; and means for visualizing communication patterns between staff and identifying relationships and isolation tendencies within the store. This makes it possible to improve the operational efficiency of physical stores, maximize staff capabilities, and perform fair evaluations.

[1351] "Employees (staff)" refers to people employed by a company, organization, or specific store, who have roles and responsibilities necessary for carrying out business. This also includes staff who contribute to the operation of physical stores.

[1352] "Skills" are the abilities and techniques required to carry out specific tasks or work, and their acquisition requires training and experience.

[1353] "Experience" refers to the knowledge and know-how that employees (staff) have gained through past work and projects, which contributes to improving their ability to carry out their work.

[1354] "Interest" refers to the interest and enthusiasm that employees (staff) have in a particular field or skill, and their motivation to learn new things based on this.

[1355] A "department (shift)" refers to a group or team that performs a specific task or role within a company or organization. In a physical store, it also includes the working hours and schedule of staff.

[1356] "Interaction history" refers to records of communication and collaboration between employees (staff), and includes data such as emails, chats, and meetings.

[1357] "Matching" refers to optimally pairing employees (staff) with each other based on specific criteria or algorithms, with the aim of complementing each other's skills and interests and improving work efficiency.

[1358] "Pairing" refers to creating optimal pairs based on skills, experience, and interests, with the aim of improving the work performance and capabilities of store staff.

[1359] "Communication patterns" indicate the method, frequency, and content of interactions between employees (staff), and analyzing these can visualize the relationships and cooperation within an organization.

[1360] "Visualization" refers to displaying analyzed data in a visual format such as graphs, charts, or network diagrams, making it easier to understand and gain insight into the information.

[1361] The system of the present invention collects and analyzes data such as the skills, experience, and interests of employees (staff), and the interaction history of departments (shifts), thereby visualizing optimal matching and communication patterns. This system can be implemented as follows based on the claims of the present invention.

[1362] composition

[1363] The system includes the following components:

[1364] 1. Data collection method (server)

[1365] 2. Matching proposal method (server)

[1366] 3. Visualization Method (Server)

[1367] 4. Notification method (terminal)

[1368] 5. Automatic collection means (terminal)

[1369] Data collection

[1370] The server periodically collects data through the API, including staff skills, experience, interests, and shift history, including information staff enter into their profiles and information retrieved through the scheduling application, as well as email, chat history, and calendar data automatically collected from devices.

[1371] Data analysis

[1372] The collected data is normalized and, if necessary, anonymized on the server. Machine learning algorithms (e.g., K-means clustering) are used to optimally pair staff based on their skill sets and interests. Based on the results of this analysis, optimal mentoring and team formation are suggested.

[1373] Matching proposals

[1374] The server then generates optimal matching suggestions based on the analysis, creating a list of specific mentoring pairs or teams, including detailed information about staff skills, interests, and mutual benefits.

[1375] Proposal Notification

[1376] The proposal is sent to the device, which notifies the staff member via a pop-up notification or email, and the staff member is given the option to review the proposal and accept or reject it.

[1377] Visualizing communication patterns

[1378] The server analyzes communication data such as emails, chats, and meeting frequency to generate network diagrams and graphs, visually displaying relationships between staff and potential isolation trends. This visualized data is provided in the form of dashboards and reports on the device.

[1379] Specific examples

[1380] For example, if staff member A is fluent in Spanish and staff member B wants to learn that skill, their information is entered into their devices and analyzed by the server. Based on the analysis results, A and B are identified as suitable pairing candidates, and this information is notified to both their devices. Upon receiving the notification, A and B can begin a mentoring session based on the proposed pairing.

[1381] Example prompts for generative AI models

[1382] Please suggest the best matching pair based on the following data:

[1383] Staff A: Spanish skill level 5, Interests: Teaching

[1384] Staff B: Spanish skill level 2, Interests: Learning

[1385] Staff C: Planning Skill Level 4, Interests: Leadership

[1386] Staff D: Planning skill level 3, Interests: Learning

[1387] Proposal format: [Staff pair / group, reason]

[1388] As described above, by using the system of the present invention, it is possible to improve the operational efficiency of physical stores, maximize the capabilities of staff, and achieve fair evaluations.

[1389] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1390] Step 1: Data collection

[1391] The server collects data including staff skills, experience, interests, and shift history through an API. This data comes from information entered in each staff member's profile and data obtained from the scheduling app. The collected data is then normalized and stored. This data includes staff skill levels, interest categories, and shift times. This allows for the management of distributed data in a unified format.

[1392] Step 2: Additional automated data collection

[1393] The devices automatically collect staff emails, chat history, and calendar data. This data is periodically sent to the server with the user's permission. Specifically, the devices analyze the staff's communication history and extract information such as the number of emails, chat frequency, and meeting schedules. This data is sent to the server and used as data for analysis.

[1394] Step 3: Data analysis

[1395] The server normalizes the collected data and anonymizes it if necessary. It then uses machine learning algorithms (e.g., K-means clustering) to optimally pair staff based on skill sets and interests. For example, it clusters each staff member's skill level and areas of interest as a feature vector, and groups staff members with similar characteristics. This enables pairings that are expected to complement each other's skills and harmonize their interests.

[1396] Step 4: Generate matching proposals

[1397] The server generates optimal matching proposals based on the results of the data analysis. Specifically, it creates a list for each clustered group or pair, detailing the reasons for each match and the benefits of the pairing. This proposal list is organized to include information on staff skills, interests, and mutual benefits. This allows it to propose optimal mentoring and team formation among staff.

[1398] Step 5: Notification of proposal

[1399] The server sends the generated matching proposal to the terminal. The terminal notifies the staff of the proposal via a pop-up notification or email. The user can then review the details of the proposal based on the notification and select the option to approve or reject it. This allows the user to decide whether or not to proceed with the proposed match and proceed to the next step.

[1400] Step 6: Visualize communication patterns

[1401] The server analyzes communication data such as emails, chats, and frequency of meetings between staff members. Based on the analysis results, it generates visualized data such as network diagrams and graphs. Specifically, by analyzing the communication data and illustrating the contact points and frequency of each staff member using node and edge relationships, it clarifies the relationships within the organization and potential isolation trends. This visualized data is sent to the terminal and displayed to the user in the form of a dashboard or report.

[1402] 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.

[1403] The system of the present invention aims to collect data such as employee skills, experience, interests, departmental interaction history, and employee emotions, propose matches to build beneficial relationships, and visualize communication patterns between employees to identify connections within the organization and potential trends toward isolation. By utilizing an emotion engine that recognizes user emotions, more advanced and accurate matching becomes possible.

[1404] System Overview

[1405] The system of the present invention can be implemented in the following configuration:

[1406] 1. Data collection method (server)

[1407] 2. Emotion engine (server)

[1408] 3. Matching proposal method (server)

[1409] 4. Visualization Method (Server)

[1410] 5. Notification Method (Terminal)

[1411] 6. Automatic collection means (terminal)

[1412] Program processing

[1413] Data collection

[1414] The server collects data including employees' skills, experience, interests, department interaction history, and emotional state. Users input their skills and interests into their devices, which then send the data to the server. Furthermore, with the user's permission, the device automatically collects email, chat history, and calendar data and sends them to the server. The emotion engine analyzes the user's emotions from this text and voice data and sends the results to the server.

[1415] Data analysis

[1416] The server normalizes the collected data and anonymizes it as necessary. It then uses a machine learning algorithm to extract features based on employees' skills, experience, interests, and emotional state, and calculates optimal mentoring and networking matches. It also analyzes the results of the emotion engine, taking emotional compatibility into account.

[1417] Matching proposals

[1418] The server generates appropriate matching proposals based on the results of data analysis. The proposals take into account each employee's skills, experience, interests, emotional state, and mutual benefits. For example, if Person A is familiar with Python and Person B wants to learn Python, the server will generate a proposal that Person A would be a good mentor for Person B. The results of the emotion engine are also taken into account, and the proposal is adjusted to be made when Person A and Person B are in a good emotional state.

[1419] Proposal Notification

[1420] The server sends the generated proposal to the target user's device, which notifies the user via a pop-up notification or email notification. The user can review the proposal and choose the option to accept or reject it.

[1421] Visualizing communication patterns

[1422] The server analyzes communication data between users, such as the frequency of emails, chats, and meetings, and generates visualized data in the form of network diagrams and graphs. The results of the emotion engine are also reflected in the visualized data, so the user's emotional state is also displayed. The device displays the visualized data in a dashboard format, making it easy for the user to check.

[1423] Specific examples

[1424] For example, suppose Person A has deep knowledge of Python programming, and Person B is a new employee who wants to learn Python. Person B enters his / her interest in Python into the device, and Person A enters his / her skill set. The device sends this data to the server, and the emotion engine then analyzes the emails, chat contents, and voice data of these users and sends their emotional state to the server.

[1425] The server analyzes all data, including skills, interests, and emotional state. If A is the best mentor for B to learn Python, and both parties are in a good emotional state, the server creates a matching proposal and notifies A and B's devices. If both parties confirm the proposal and approve it, a mentoring session is set up.

[1426] In this way, the system of the present invention enables efficient mentoring and networking among employees, effectively utilizes employees' skill sets, and improves collaboration across the organization by taking into account emotional matching.

[1427] The processing flow will be explained below.

[1428] Step 1:

[1429] Users enter information about their skills, experience, and interests into the device, such as "5 years of Python programming experience" or "interested in machine learning."

[1430] Step 2:

[1431] The terminal transmits the input data to the server, where it is formatted and encrypted.

[1432] Step 3:

[1433] The server stores the received data in a database, normalizing and, if necessary, anonymizing the data before storing it.

[1434] Step 4:

[1435] If the user gives permission, the device will automatically collect email, chat history, and calendar data on a regular basis and send it to the server.

[1436] Step 5:

[1437] The server retrieves relevant data from other business software (e.g., project management tools, mail servers) through APIs, including project history and communication history.

[1438] Step 6:

[1439] The emotion engine analyzes the text data and voice data of the user's emails and chats to identify the user's emotional state, and then sends the analysis results to the server.

[1440] Step 7:

[1441] The server normalizes all collected data and uses machine learning algorithms to extract employee skills, experience, interests, and emotional states as features.

[1442] Step 8:

[1443] The server calculates optimal mentoring and networking matches between users based on the feature values, taking into account the results of the emotion engine, and reflecting emotional compatibility in the matching.

[1444] Step 9:

[1445] The server generates specific match proposals based on the valid matches, including details of each user's skills, experience, interests, emotional state, and mutual interests.

[1446] Step 10:

[1447] The server sends the generated proposal to the target user's device. For example, it sends a proposal that person A is suitable to be person B's mentor.

[1448] Step 11:

[1449] The device will receive the suggestion and notify the user via a pop-up or email notification, giving the user the option to review the suggestion and accept or reject it.

[1450] Step 12:

[1451] If the user accepts the proposal, the device provides a scheduling function for setting up mentoring sessions and networking events.

[1452] Step 13:

[1453] The server continuously collects and analyzes the mentoring sessions and communication history between users, thereby monitoring how the relationships between users are developing.

[1454] Step 14:

[1455] The server generates the analysis results as visualized data and displays them as graphs and network diagrams. It also visually displays the user's emotional state, reflecting the results of the emotion engine.

[1456] Step 15:

[1457] The device displays the visualized data in a dashboard format, allowing users to easily check the analysis results, and understand their own communication patterns and emotional state.

[1458] In this way, the system of the present invention realizes efficient mentoring and networking among employees, and by taking into consideration emotional matching, it is possible to improve collaboration throughout the organization.

[1459] Example 2

[1460] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1461] In modern companies, a key challenge is to maximize the use of individual employee characteristics, such as skills, experience, and interests, to promote communication and cooperation among employees. However, it is extremely difficult to properly match these characteristics and understand emotional compatibility, employee connections, and potential tendencies toward isolation. Conventional systems often lack the accuracy of data collection, analysis, and matching proposals, resulting in ineffective relationship building. Therefore, there is a need for a system that can achieve high-precision matching that takes into account employee skills and emotional states, and visualize communication patterns.

[1462] 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.

[1463] In this invention, the server includes means for collecting data including employee skills, experience, interests, department interaction history, and emotional state, means for proposing appropriate matches for building beneficial relationships between specific employees and other employees based on the collected data, means for analyzing the emotional data and taking emotional compatibility into account in the collected data, and means for visualizing communication patterns between employees and identifying connections within the organization and potential tendencies toward isolation. This enables highly accurate matching based on employee skills and emotional state, thereby improving communication and cooperation within the company.

[1464] "Employee skills" refers to the specialized knowledge and abilities possessed by individual employees.

[1465] "Experience" refers to the accumulation of practical knowledge and skills that employees have acquired through their work.

[1466] "Interests" refer to areas or activities that interest employees.

[1467] "Department interaction history" refers to records of business interactions and communications between employees.

[1468] "Emotional state" refers to data that shows an employee's emotional state, such as joy or stress.

[1469] "Means of collecting data" refers to the methods and devices used to collect information entered by employees and data collected automatically.

[1470] "Means for suggesting matches" refers to methods or systems that use collected data to help connect specific employees with other employees to beneficial relationships.

[1471] "Means for analyzing emotional data" refers to methods and algorithms for analyzing collected emotional data and understanding emotional compatibility and state.

[1472] "Means for visualizing communication patterns" refers to methods and tools for displaying the frequency and form of communication between employees in the form of graphs, network diagrams, etc.

[1473] The system of the present invention aims to collect data such as employee skills, experience, interests, department interaction history, and emotional state, propose matches to build beneficial relationships, and further visualize communication patterns between employees to identify connections within the organization and potential tendencies toward isolation. The following describes in detail the modes for implementing the present invention.

[1474] System Configuration

[1475] The system of the present invention can be implemented in the following configuration:

[1476] 1. Data collection method (server)

[1477] 2. Emotion engine (server)

[1478] 3. Matching proposal method (server)

[1479] 4. Visualization Method (Server)

[1480] 5. Notification Method (Terminal)

[1481] 6. Automatic collection means (terminal)

[1482] Data collection

[1483] The server collects data including employees' skills, experience, interests, department interaction history, and emotional state. Users input their skills and interests into their devices, which then send the data to the server. Furthermore, with the user's permission, the device automatically collects email, chat history, and calendar data and sends them to the server. The emotion engine analyzes the user's emotions from this text and voice data and sends the results to the server.

[1484] Data analysis

[1485] The server normalizes the collected data and anonymizes it as necessary. It then uses a machine learning algorithm to extract features based on employees' skills, experience, interests, and emotional state, and calculates optimal mentoring and networking matches. It also analyzes the results of the emotion engine, taking emotional compatibility into account.

[1486] Matching proposals

[1487] The server generates appropriate matching proposals based on the results of data analysis. For example, if one employee is familiar with Python and another employee wants to learn Python, it will generate a proposal that the two are suitable for a mentor-learner relationship. By incorporating the results of the emotion engine, the server also evaluates the emotional compatibility between the two parties.

[1488] Proposal Notification

[1489] The server sends the generated proposal to the target user's device, where the device notifies the user of the proposal via a pop-up notification or email notification. The user can review the proposal and choose to accept or reject it.

[1490] Visualizing communication patterns

[1491] The server analyzes communication data between users, such as emails, chats, and frequency of meetings, and generates visualized data in the form of network diagrams and graphs. The results of the emotion engine are also reflected in the visualized data, so the user's emotional state is also displayed. The device displays the visualized data in a dashboard format, making it easy for users to check.

[1492] Specific examples

[1493] For example, suppose Person A has deep knowledge of Python programming, and Person B is a new employee who wants to learn Python. Person B enters his / her interest in Python into the device, and Person A enters his / her skill set. The device sends this data to the server, and the emotion engine analyzes the emails, chat contents, and voice data of these users and sends their emotional state to the server.

[1494] The server analyzes all data, including skills, interests, and emotional states. If A is the best mentor for B to learn Python, and both parties are in a good emotional state, the server creates a matching proposal and notifies A and B's devices. If both A and B accept the proposal, a mentoring session is set up. In this way, the system of the present invention realizes efficient mentoring and networking among employees, effectively utilizing employees' skill sets, and improves collaboration across the organization by taking emotional matching into consideration.

[1495] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1496] Step 1: Enter and collect data

[1497] 1.1 User Input

[1498] The user enters their skills, experience, and interests into the terminal. For example, they might enter, "I'm interested in Python programming and have basic knowledge."

[1499] The terminal collects the data entered by the user and transmits it to the server.

[1500] Input: Skills, experience, and interest data entered by the user.

[1501] Output: Data sent from the device to the server.

[1502] 1.2 Automatic Data Collection

[1503] With the user's permission, the device automatically collects email, chat history, and calendar data.

[1504] The terminal transmits the collected data to the server.

[1505] Input: User permission, email and chat history, calendar data.

[1506] Output: Email, chat history, and calendar data sent from the device to the server.

[1507] 1.3 Emotion Data Analysis

[1508] The emotion engine analyzes the user's emotions from collected text and voice data. For example, it can extract emotions such as "feeling stressed" from the content of an email.

[1509] The emotion engine sends the analysis results as data to the server.

[1510] Input: text and audio data.

[1511] Output: Sentiment analysis results sent to the server.

[1512] Step 2: Normalize and anonymize data

[1513] 2.1 Data normalization

[1514] The server unifies and normalizes the collected data formats, for example, unifying due dates and skill levels across different formats.

[1515] Input: Raw data collected.

[1516] Output: Normalized data.

[1517] 2.2 Data anonymization

[1518] The server anonymizes the data as needed, for example by replacing employee identifying information with a random identifier.

[1519] Input: Normalized data.

[1520] Output: Anonymized data.

[1521] Step 3: Feature extraction and matching calculation

[1522] 3.1 Feature extraction

[1523] The server uses machine learning algorithms to extract features such as skills, experience, interests, and emotional state. For example, a user's skill set might be extracted as "Python: intermediate, data analysis: beginner."

[1524] Input: Normalized data, anonymized data.

[1525] Output: Data extracted as features.

[1526] 3.2 Matching Calculation

[1527] The server calculates the optimal match based on the extracted features, deriving a result such as "Person A is the best mentor for Person B."

[1528] The server also takes into account the results of the emotion engine and incorporates emotional compatibility into its calculations, for example, "Make a proposal when A and B are in a good emotional state."

[1529] Input: Data extracted as features, sentiment analysis results.

[1530] Output: Best matching suggestion.

[1531] Step 4: Generate and notify matching proposals

[1532] 4.1 Generating Matching Proposals

[1533] The server generates appropriate matching proposals based on the results of the data analysis, for example, "Propose that person A mentor person B in Python."

[1534] Input: Best matching proposal data.

[1535] Output: Specific matching suggestions.

[1536] 4.2 Proposal Notification

[1537] The server sends the generated proposal to the target user's device. For example, it notifies the devices of user A and user B that "a mentoring proposal is available."

[1538] The device will notify the user of the suggestions via a pop-up notification or email notification.

[1539] The user reviews the proposal and has the option to accept or reject it.

[1540] Input: A specific matching suggestion.

[1541] Output: Notifications to the terminal and responses from the user.

[1542] Step 5: Visualize communication patterns

[1543] 5.1 Data Analysis

[1544] The server analyzes communication data such as the frequency of emails, chats, and meetings between users. For example, it collects data such as "Person A and Person B frequently email or chat."

[1545] The results of the emotion engine are also reflected in the visualization data, so the user's emotional state is also displayed.

[1546] Input: Communication data between users, sentiment analysis results.

[1547] Output: Analysis results of communication patterns.

[1548] 5.2 Generating visualization data

[1549] The server generates visualization data in the form of network diagrams and graphs based on the analysis results. For example, it creates a network diagram showing the communication patterns between person A and person B.

[1550] Input: Analysis results of communication patterns.

[1551] Output: Visualized data as network diagrams and graphs.

[1552] 5.3 Viewing the Dashboard

[1553] The device displays visualized data in a dashboard format for easy viewing by the user. For example, it provides a dashboard displaying the communication patterns and emotional states of person A and person B.

[1554] Input: Visualization data.

[1555] Output: Display in dashboard format.

[1556] (Application example 2)

[1557] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1558] It is necessary to optimize the work efficiency of automated machines operating in factories and realize team formation that makes the most of each machine's skills, work history, and interest level. It is also necessary to improve productivity by visualizing communication patterns between automated machines and identifying potential inefficiencies.

[1559] 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.

[1560] In this invention, the server includes means for collecting data such as the skills, work history, interest level, and team interaction history of automated machines operating in a factory, means for proposing beneficial team formation and work distribution between a specific automated machine and other automated machines based on the collected data, and means for visualizing communication patterns between the automated machines and identifying efficiencies and potential inefficiencies in the workplace. This enables effective team formation and work distribution that makes the most of the skills and work history of the automated machines, thereby improving productivity in the factory.

[1561] "Automatic machines" refers to robots and mechanical devices operating in factories, and is a general term for machines that perform tasks automatically.

[1562] "Skill" refers to the ability to perform a specific task or action that an automated machine can perform.

[1563] "Work history" is a record of work that an automated machine has performed in the past, and includes data such as the success rate and work time.

[1564] "Interest" refers to the degree of interest in tasks that automated machines excel at or have shown a high success rate in the past.

[1565] "Team interaction history" refers to the history of past collaborative and cooperative work between automated machines.

[1566] "Communication pattern" is a concept that indicates the format and frequency of data exchange and operational coordination between automated machines.

[1567] An "operation log" is a detailed record of the operations of an automated machine recorded while it is in operation, including operating status and error information.

[1568] An "error log" refers to a record of errors or malfunctions that occur while an automated machine is operating.

[1569] "Visualization" refers to the process of displaying data as graphs or charts so that it can be understood at a glance.

[1570] "Control device" refers to a server or terminal device used to monitor and manage automated machinery.

[1571] The present invention is a system for optimizing work efficiency and productivity using automated machines operating in a factory. The system includes the following components:

[1572] 1. Data collection method (server)

[1573] The server collects data on the skills, work history, interest level, team interaction history, operation logs, error logs, etc. of the automated machines operating in the factory. A Python script is used to collect data, which is then sent to the management server in real time.

[1574] 2. Machine learning algorithm (server)

[1575] The server normalizes the collected data and anonymizes it if necessary. It then uses machine learning algorithms to extract features based on each machine's skills, work history, and interest levels, and calculates optimal team composition and work distribution. The machine learning algorithms used include scikit-learn and TensorFlow.

[1576] 3. Matching proposal method (server)

[1577] Based on the collected and analyzed data, the server proposes beneficial team formation and work distribution between specific automated machines and other automated machines. The proposal is optimized taking into account the skills, work history, and interest of each automated machine, and the proposal is notified to the control device.

[1578] 4. Proposal notification means (control device)

[1579] The server notifies the control device of the generated proposal, allowing engineers and operators in the factory to review the proposed team formation and work distribution and approve them as necessary.

[1580] 5. Visualization tools (dashboards)

[1581] The server analyzes the frequency of data exchange and collaboration between automated machines and generates visualized data in the form of network diagrams and graphs. Tools used for visualization include Tableau and D3.js. This visualized data is displayed in a dashboard format so that operators can easily check it.

[1582] Specific examples

[1583] For example, suppose that automatic machine A is responsible for assembly work in a factory, and automatic machine B is responsible for inspection work. The operation logs and work history of automatic machines A and B are sent to a server, which analyzes them. Based on the analysis results, the server proposes the optimal way for automatic machines A and B to work together and notifies the control device.

[1584] Once the engineers review the proposals on the dashboard and approve the proposed teaming and work distribution, new collaborations can begin, improving productivity within the factory and making the most of the skills and work history of each automated machine.

[1585] ---

[1586] Example prompts for input to a generative AI model:

[1587] "Factory robot A specializes in assembly work, and robot B specializes in inspection work. Please generate a proposal for the optimal collaboration work based on past success stories."

[1588] ---

[1589] In this way, the system of the present invention realizes efficient and highly productive factory operations, and maximizes the capabilities of automated machines.

[1590] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1591] Step 1:

[1592] The server collects data such as the skills, work history, interest level, team interaction history, operation logs, and error logs of the automated machines operating in the factory. This data sent from each automated machine is sent to the server in real time using a Python script. The input is various data, and the output is a normalized dataset.

[1593] Step 2:

[1594] The server normalizes the collected data and anonymizes it if necessary, standardizing the data format and concealing personally identifiable information to protect privacy. The input is the collected raw data, and the output is the normalized and anonymized data.

[1595] Step 3:

[1596] The server analyzes the data using machine learning algorithms. It extracts features such as the skills, work history, and interest of each automated machine, and then calculates optimal team composition and work distribution. The algorithms used include scikit-learn and TensorFlow. The input is normalized data, and the output is a proposal for optimal team composition and work distribution.

[1597] Step 4:

[1598] The server generates matching proposals and notifies the control device. The proposals are optimized taking into account the skills, work history, and interests of each automated machine. The input is the output of the machine learning algorithm, and the output is a proposal notification sent to the control device.

[1599] Step 5:

[1600] The control device displays the generated proposals on a dashboard, allowing engineers and operators to review the proposals and providing them in a visually easy-to-understand format. The input is the proposal notification sent from the server, and the output is the display data on the dashboard.

[1601] Step 6:

[1602] Engineers review the proposals on the dashboard and approve them if necessary. Once approved, new team formation and work distribution to the automated machines is initiated. The input is the proposal on the dashboard, and the output is approval feedback.

[1603] Step 7:

[1604] Based on the engineer's approval, the automated machines initiate new team formation and work distribution. Data is exchanged and actions are coordinated between the automated machines to carry out the work. The input is approval feedback, and the output is the actual work results.

[1605] In this way, a system is built that makes maximum use of the skills and work history of the automated machines in the factory through each processing step, achieving efficient and highly productive factory operations.

[1606] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1607] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1608] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1609] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1610] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1611] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1612] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1613] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1614] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1615] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1616] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1617] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1618] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1619] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1620] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1621] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1622] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1623] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1624] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1625] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1626] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1627] The following is further disclosed regarding the above embodiment.

[1628] (Claim 1)

[1629] A means of collecting data such as employee skills, experience, interests, and department interaction history;

[1630] Based on the collected data, we propose appropriate matches between specific employees and other employees to build beneficial relationships.

[1631] A means to visualize communication patterns between employees and identify connections within the organization and potential isolation trends,

[1632] A system including:

[1633] (Claim 2)

[1634] 2. The system according to claim 1, further comprising means for notifying a user terminal of data collection and suggestion contents.

[1635] (Claim 3)

[1636] 10. The system of claim 1, further comprising means for automatically collecting employee email, chat history, and calendar data.

[1637] "Example 1"

[1638] (Claim 1)

[1639] A means of collecting data such as employee skills, experience, interests, and department interaction history;

[1640] Based on the collected data, we propose appropriate matches between specific employees and other employees to build beneficial relationships.

[1641] A means to visualize communication patterns between employees and identify connections within the organization and potential isolation trends,

[1642] A means of using machine learning algorithms to analyze employees' skill sets and interests and match them for optimal mentoring and networking opportunities;

[1643] a means for sending a notification to the device and providing the user with the option to review the proposal and accept or reject it;

[1644] A system including:

[1645] (Claim 2)

[1646] 2. The system according to claim 1, further comprising means for notifying a user terminal of data collection and suggestion contents.

[1647] (Claim 3)

[1648] 10. The system of claim 1, further comprising means for automatically collecting employee email, chat history, and calendar data.

[1649] "Application Example 1"

[1650] (Claim 1)

[1651] A means of collecting data such as employee skills, experience, interests, and department interaction history;

[1652] Based on the collected data, we propose appropriate matches between specific employees and other employees to build beneficial relationships.

[1653] A means to visualize communication patterns between employees and identify connections within the organization and potential isolation trends,

[1654] Based on the collected and analyzed data, we will propose optimal pairings between staff in physical stores, and promote skill improvement and work efficiency.

[1655] Visualize communication patterns between staff members to identify relationships and isolation within the store.

[1656] A system including:

[1657] (Claim 2)

[1658] 2. The system according to claim 1, further comprising means for notifying a user terminal of data collection and suggestion contents.

[1659] (Claim 3)

[1660] 10. The system of claim 1, further comprising means for automatically collecting employee email, chat history, and calendar data.

[1661] "Example 2: Combining Emotion Engines"

[1662] (Claim 1)

[1663] A means of collecting data including employee skills, experience, interests, department interaction history, and emotional state;

[1664] Based on the collected data, we propose appropriate matches between specific employees and other employees to build beneficial relationships.

[1665] A means of analyzing emotional data and taking emotional compatibility into account in the collected data;

[1666] A means to visualize communication patterns between employees and identify connections within the organization and potential isolation trends,

[1667] A system including:

[1668] (Claim 2)

[1669] 2. The system according to claim 1, further comprising means for notifying a user terminal of data collection and suggestion contents.

[1670] (Claim 3)

[1671] 10. The system of claim 1, further comprising means for automatically collecting employee email, chat history, and calendar data.

[1672] "Application example 2 when combining emotion engines"

[1673] (Claim 1)

[1674] A means of collecting data such as the skills, work history, interest level, and team interaction history of automated machines operating in the factory;

[1675] A means for suggesting beneficial teaming and work distribution between specific automated machines and other automated machines based on the collected data; and

[1676] A means to visualize communication patterns between automated machines and identify efficiencies and potential inefficiencies within the workplace;

[1677] A system including:

[1678] (Claim 2)

[1679] 10. The system of claim 1, further comprising means for collecting data and notifying the controller of the recommendations.

[1680] (Claim 3)

[1681] 10. The system of claim 1, further comprising means for automatically collecting operation logs and error logs of the automated machine. [Explanation of symbols]

[1682] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting data such as employee skills, experience, interests, and department interaction history; Based on the collected data, we propose appropriate matches between specific employees and other employees to build beneficial relationships. A means to visualize communication patterns between employees and identify connections within the organization and potential isolation trends, A system including:

2. 2. The system according to claim 1, further comprising means for notifying the user's terminal of the data collection and the content of the proposal.

3. 10. The system of claim 1, further comprising means for automatically collecting employee email, chat history, and calendar data.

Images