system

Abstract

Provide a system. [Solution] A means for collecting employee job information, specialized skills, and position information; A means for matching employees who share common areas of interest based on the collected job information, professional skills, and job title information; A means to automatically schedule meetings between matched employees; a means of collecting and storing feedback on the outcome of the meeting; A system including:

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 modern companies, it is important to increase opportunities for employees from different departments and with different specialized skills to naturally interact and collaborate. However, finding the right opportunities for employees to meet and start collaborating can be difficult. Manually matching employees to utilize their respective specialized skills is time-consuming, labor-intensive, and inefficient, especially as employees are focused on their own duties and tasks. Furthermore, spaces such as office lounges that are designed to promote employee interaction are often underutilized. Therefore, a system that efficiently promotes employee interaction and creates opportunities for innovation is needed. [Means for solving the problem]

[0005] The present invention provides a means for collecting employee job information, specialized skills, and position information, and a means for matching employees with common areas of interest based on the collected information. Furthermore, the system includes a means for automatically scheduling meetings between matched employees and a means for collecting and saving feedback on the meeting results. The system also includes a means for comparing employee availability and setting meetings based on the earliest available time, as well as an ON / OFF function that allows employees to voluntarily choose whether or not to participate in matching, thereby efficiently and flexibly promoting interaction between employees and providing an environment that fosters innovation. These means also enable the effective use of space such as office lounges.

[0006] "Employee job information" is information that indicates the specific job content and role that an employee is in charge of within a company.

[0007] "Specialized skills" refers to information that indicates an employee's abilities in a specific technical or knowledge area.

[0008] "Job title information" is information that indicates an employee's job rank or position, and clearly indicates the hierarchical structure and scope of responsibility within the company.

[0009] "Collection means" refers to methods, systems, and technologies for systematically collecting information.

[0010] "Matching means" refers to a method or system that pairs employees with common areas of interest or potential complementary skills based on collected information.

[0011] "Means for automatically scheduling meetings" refers to a method or system that automatically analyzes employees' available time and sets optimal meeting times.

[0012] "Means for collecting and storing feedback" refers to a method or system for collecting and storing employee evaluations and comments regarding the results of meetings.

[0013] "Availability comparison means" means a method or system for comparing employee schedule information to identify the earliest common availability.

[0014] The "ON / OFF function" is a feature that allows employees to voluntarily choose to participate in matching, and is a means of individually enabling or disabling use of the system. [Brief explanation of the drawings]

[0015] [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

[0016] 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.

[0017] First, the terms used in the following description will be explained.

[0018] 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).

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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."

[0036] The present invention is a system that collects employee job information, specialized skills, and position information, matches employees with common areas of interest, and automatically schedules meetings. It also includes a function for collecting and saving feedback on the results of meetings. A specific embodiment of the present invention will be described below.

[0037] First, the server collects employee job information, specialized skills, and position information. This information is obtained from the company's internal database and analyzed by the server. Employee information, including the job duties, skills, and position, is stored in the database.

[0038] The server then uses the collected information to match employees with common interests, such as employees with the same specialized skills or complementary skills, with the matching process driven by pre-defined rules and AI algorithms.

[0039] Once matching is complete, the server automatically schedules a meeting between the matched employees. At this time, the employees' free time slots are compared and the earliest common free time is selected. Employees can also choose whether or not to participate in matching, allowing for flexible participation settings.

[0040] After the meeting is held, the server collects and stores feedback on the meeting results. This feedback is a means of collecting evaluations and comments from employees and is used as reference material for future improvements. The feedback is aggregated by the server and stored in a database.

[0041] For example, if a company's engineers and marketing staff are interested in AI technology and SEO strategies, respectively, the server will match them and schedule a meeting based on their availability. After the meeting, the server will collect feedback and use it for future projects.

[0042] In this way, the system of the present invention increases opportunities for innovation by making it easier for different types of employees within a company to meet and collaborate efficiently. Furthermore, it also makes more effective use of spaces such as office lounges that encourage employee interaction.

[0043] The processing flow will be explained below.

[0044] Step 1:

[0045] The server receives an employee ID from the user. It calls the get_employee_info function to retrieve the corresponding employee information from the database using this ID. The server searches for the job information, expertise, and position information of the employee that matches the ID and stores this information in memory.

[0046] Step 2:

[0047] The server performs a matching process based on the acquired employee information. Specifically, the server compares the job information and professional skills of other employees and analyzes them to identify common areas of interest and complementary skills. This analysis is performed using the match_employees function to find employees with common skills.

[0048] Step 3:

[0049] The server schedules meetings between successfully matched employee pairs. It uses the create_meeting function to compare the availability of both parties and identify the earliest common available time. Based on this time, the meeting details are set.

[0050] Step 4:

[0051] The user receives notifications from the server of matches and scheduled meetings, including the date and time of the meeting, the names of the employees they will be interacting with, and other relevant information.

[0052] Step 5:

[0053] The server collects feedback from employees after the meeting has taken place and saves it to the database using the save_meeting_feedback function, which will be used to improve the matching algorithm and progress the project in the future.

[0054] Step 6:

[0055] Users submit their feedback and opinions to the server, which aggregates the feedback through the system's rating mechanism and analyzes it on the server.

[0056] Step 7:

[0057] Based on the collected feedback, the server will improve the system and develop new matching algorithms, which will improve the accuracy of future matches and more effectively promote employee interaction and generate innovation.

[0058] Example 1

[0059] 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."

[0060] Modern companies have a large number of employees with diverse job functions and specialized skills, and efficient talent matching is essential. However, manually collecting employee information, creating appropriate pairs, and scheduling meetings is extremely time-consuming and labor-intensive. Furthermore, there is a lack of a system for properly collecting and saving feedback on meeting results, making it difficult to identify areas for improvement or collect reference materials for future use. This creates problems that delay the efficiency of internal communication and the promotion of collaboration among employees.

[0061] 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.

[0062] In this invention, the server includes means for collecting employee job information, specialized skills, and position information, means for analyzing the collected job information, specialized skills, and position information and storing it in a database, means for matching employees with common areas of interest based on preset rules and AI algorithms, means for automatically scheduling meetings between matched employees and obtaining employee free time and setting the earliest common free time, and means for collecting feedback from employees on the meeting results and storing it in a database, thereby enabling efficient matching between employees, automating meetings, and systematically collecting and storing feedback.

[0063] "Employee job information" is data related to the job content and role that an employee is responsible for within the company.

[0064] "Specialized skills" refers to information about the specific knowledge and skills that an employee has acquired.

[0065] "Position information" is information relating to an employee's position or status within the company.

[0066] "Means of collection" refers to the methods and devices used to extract and collect the necessary data.

[0067] "Means for analysis and storage" are methods or devices that process collected data, convert it into an understandable form, and then record it.

[0068] A "matching means" is a method or device for finding suitable matches based on specific criteria.

[0069] A "scheduling means" is a method or device for planning, coordinating, and determining the date and time of a particular event or activity.

[0070] The "means for obtaining available time" refers to a method or device for checking and extracting the available time of each employee.

[0071] "Feedback collection and storage means" refers to the methods and devices used to collect and record employee evaluations and opinions.

[0072] The present invention is a system that collects employee job information, specialized skills, and position information, matches employees with common areas of interest based on this data, and automatically schedules meetings. It also includes a function to collect and save feedback on the results of the meetings. This system is realized through the following processing steps.

[0073] The server collects employee job information, specialized skills, and position information. This information is collected using an internal company database, such as MySQL (registered trademark) or PostgreSQL. The server extracts the information from the database, analyzes it using Python's Pandas library, and saves it in the database. This allows detailed information such as employee responsibilities, skills, and position to be organized.

[0074] The server then analyzes the collected information and matches employees with common interests. This process is carried out using pre-defined rules and AI algorithms (e.g., Scikit-learn or TENSORFLOW®). Specifically, the server uses a clustering algorithm to group employees' skills and interests, and pairs employees in the same cluster.

[0075] The server automatically schedules meetings between matched employees. At this time, the server uses Microsoft® Exchange Server or Google® Calendar API to obtain employees' free time. It selects the earliest common free time and automatically schedules the meeting. Employees can also choose to participate in the schedule using the ON / OFF function.

[0076] After the meeting is held, the server collects feedback from employees through a dedicated web form. This web form is built using HTML and JavaScript (registered trademark). The collected feedback is stored in a database and used as information for future improvements and refinements. A web framework such as Django is used for this storage.

[0077] As a concrete example, if engineer A at a company is interested in AI technology and marketing staff member B is interested in SEO strategy, the server retrieves their information from the database and matches them using an AI algorithm. It then retrieves their free time slots and schedules a meeting for the earliest common free time. After the meeting, B enters their evaluation and comments into a web form and provides feedback to the server, contributing to improvements to the overall system.

[0078] An example prompt might be, "We want to develop a new meeting system. The system will collect employee job information, professional skills, and position information, and match employees with common interests based on this data. It will then automatically schedule meetings and collect and store feedback on the meeting results. Please write program code that describes this process in detail."

[0079] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0080] Step 1:

[0081] Collection of employee information

[0082] The server collects employee job information, expertise, and position information from the company's database. It queries the database and executes SQL queries to retrieve employee information. The input is the database connection information and the required query syntax, and the output is a set of employee information.

[0083] Specifically, the server executes the following SQL query:

[0084] SELECT FROM employee_data;

[0085] The retrieved data is converted to a Pandas DataFrame.

[0086] Step 2:

[0087] Data analysis and storage

[0088] The server analyzes the acquired employee information and stores it in a database. The input is employee information in DataFrame format, and the output is the analyzed results stored in the database. Specific analysis processes include data cleaning and extraction of specific columns. After analysis, the information is stored in a separate table.

[0089] Specifically, it uses Pandas to clean the data.

[0090] python

[0091] import pandas as pd

[0092] df = pd.DataFrame(data)

[0093] Data cleaning and analysis

[0094] df_cleaned = df.dropna().query('role != "intern"')

[0095] df_cleaned.to_sql('parsed_employee_data', con=engine, if_exists='replace')

[0096] Step 3:

[0097] Setting matching conditions

[0098] The server uses an AI algorithm to set the conditions for matching employees. The input is the analyzed employee data, and the output is the cluster information for each employee. Specifically, clustering is performed using Scikit-learn's KMeans algorithm.

[0099] Specifically, the KMeans algorithm is applied as follows:

[0100] python

[0101] from sklearn.cluster import KMeans

[0102] kmeans = KMeans(n_clusters=5).fit(df_cleaned)

[0103] clusters = kmeans.labels_

[0104] df_cleaned['cluster'] = clusters

[0105] Step 4:

[0106] Scheduling a Meeting

[0107] The server schedules meetings between matching employees. The input is a list of matches and the employees' calendar information, and the output is the scheduled meeting details. The server uses the Google Calendar API to get the employees' free time and schedules the meeting at the earliest common free time.

[0108] Specifically, it uses the Google Calendar API to obtain available time.

[0109] python

[0110] from googleapiclient.discovery import build

[0111] service = build('calendar', 'v3', credentials=creds)

[0112] events = service.events().list(calendarId='primary').execute()

[0113] common_free_time = find_common_time(events)

[0114] schedule_meeting(common_free_time)

[0115] Step 5:

[0116] Collecting and storing feedback

[0117] The server collects feedback from employees after the meeting and stores it in a database. The input is the feedback entered by employees through a web form, and the output is the feedback data stored in the database.

[0118] Specifically, the user enters feedback into a web form.

[0119] html

[0120] <form action=" / submit_feedback" method="post">

[0121] <textarea name="feedback" rows="4" cols="50">< / textarea>

[0122] <input type="submit" value="Submit">

[0123] < / form>

[0124] Feedback is collected on the server side and stored in a database.

[0125] python

[0126] from django.shortcuts import render

[0127] from .models import Feedback

[0128] def submit_feedback(request):

[0129] if request.method == 'POST':

[0130] feedback = request.POST['feedback']

[0131] Feedback.objects.create(content=feedback)

[0132] return render(request, 'thank_you.html')

[0133] (Application example 1)

[0134] 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."

[0135] To facilitate knowledge sharing and collaboration among employees within a company, a system is needed that allows employees with similar expertise and interests to naturally meet, exchange information, and collaborate. However, manually matching employees and scheduling meetings is time-consuming and inefficient. Furthermore, there is a lack of a system for efficiently collecting feedback after meetings and using it to improve operations. Furthermore, information sharing between robot operators is important in the field, and there is a need for an efficient method for this process that utilizes smartphones and head-mounted displays.

[0136] 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.

[0137] In this invention, the server includes a means for collecting employee job information, specialized skills, and position information, a means for matching employees with common areas of interest based on the collected job information, specialized skills, and position information, a means for automatically scheduling meetings between the matched employees, a means for collecting and storing feedback on the results of the meetings, a means for using a clustering algorithm to analyze operator data, and a means for finding optimal pairs according to a specified algorithm. This enables efficient matching between employees and robot operators with common areas of interest and scheduling of meetings. In addition, continuous system improvement is achieved through the collection of feedback.

[0138] "Employee job information" is information relating to the work content and role that an employee is responsible for within a company.

[0139] "Specialized skills" refers to the skills and knowledge an employee possesses in a specific field.

[0140] "Position information" is information about an employee's current position or title.

[0141] "Means of collection" refers to a method for obtaining employee job information, specialized skills, and position information using a server or database.

[0142] "Matching methods" are methods for matching employees with common areas of interest based on collected information.

[0143] A "scheduling method" is a method for automatically scheduling and scheduling meetings between matched employees.

[0144] "Means for collecting and storing feedback" refers to the method for collecting evaluations and comments from employees after the meeting and storing that data.

[0145] A "clustering algorithm" is a mathematical and statistical method used to analyze data and separate it into groups that share common characteristics.

[0146] The "means for finding the best pair" is a method for selecting the best pair to be matched based on the results of the clustering algorithm.

[0147] This invention is a system that collects employee job information, specialized skills, and position information, performs matching, automatic scheduling, and feedback collection, and particularly supports efficient information sharing among robot operators within factories.

[0148] 1. System Configuration

[0149] The server collects and analyzes employee job information, specialized skills, and position information from the company's internal database. The collected data is stored in, for example, an SQLite database. Data such as the operator's specialized skills and job information is analyzed using a clustering algorithm (e.g., K-Means clustering), and operators who share common areas of interest are automatically matched.

[0150] 2. Data analysis and matching

[0151] The server uses the collected data to run a clustering algorithm, using the Python library Scikit-learn. Specifically, it creates a data matrix based on the operator's specialized skills and applies K-Means clustering to match operators who belong to the same cluster.

[0152] 3. Automatic Meeting Scheduling

[0153] Once matching is complete, the server uses the schedule data to find the earliest common free time and automatically schedules the meeting, using time data retrieved from the company's internal calendar system (e.g., Google Calendar API).

[0154] 4. Collecting and storing feedback

[0155] After the meeting, the server collects feedback from participants and stores it in a database. The feedback form used at this stage is implemented, for example, as a web application (using Flask). The feedback is later analyzed to improve the system and provide new suggestions.

[0156] 5. Hardware and Software Used

[0157] The system is implemented using the following hardware and software:

[0158] Hardware: Smartphones, smart glasses, head-mounted displays

[0159] Software: Python, Flask, SQLite, Scikit-learn

[0160] 6. Specific Examples

[0161] For example, if there is Engineer A in charge of robot maintenance in a factory and Engineer B, a new employee interested in the same field, the server clusters their data and confirms that they belong to the same cluster. It then finds a common free time and automatically schedules a meeting. It then uses the feedback collected after the meeting to make future improvements.

[0162] Example prompt (input for generative AI model)

[0163] "This application is designed for factory robot operators. It collects information about the operators' job functions, specialized skills, and job titles, matches operators with common areas of interest, and schedules meetings for information exchange. Specifically, it analyzes the operator data using K-Means clustering, finds the best pairs, and schedules meetings. It also collects feedback to help with future improvements."

[0164] This system will promote efficient information sharing among robot operators within the factory, contributing to the improvement of knowledge and skills.

[0165] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0166] Step 1:

[0167] The server collects employee job information, specialized skills, and position information from the company's internal database. The input for data collection is the access privileges of the company's existing information systems and databases. The output is a set of job information, specialized skills, and position information organized for each employee. When collecting data, SQL queries are used to extract the necessary data and store it in an SQLite database.

[0168] Step 2:

[0169] The server applies a clustering algorithm based on the collected job information, specialized skills, and position information. The employee dataset collected in step 1 is used as input. The output is the results of employees being divided into clusters based on their common areas of interest. For clustering, Python's Scikit-learn library is used to perform K-Means clustering. Specifically, the employee specialized skills are vectorized, a data matrix is ​​created, and then clustering is performed.

[0170] Step 3:

[0171] The server matches employees with common areas of interest based on the clustered data. The input is the clustering results from step 2. The output is a list of matched employee pairs. Specifically, employees belonging to the same cluster are paired together, and each pair is listed.

[0172] Step 4:

[0173] The server automatically schedules meetings between matched employees based on the schedule data. The input is a pair list of matched employees and each employee's free time data. The output is a list of scheduled meeting dates and times. Specifically, the server retrieves each employee's schedule from the company's internal calendar system (e.g., Google Calendar API), finds the earliest common free time, and schedules the meeting.

[0174] Step 5:

[0175] The server collects and stores feedback from employees after the meeting ends. The input is the ratings and comments of employees who attended the meeting. The output is the aggregated feedback data. Feedback is collected through a web application (e.g., created using Flask) and stored in a database. Specifically, a feedback form is provided, the ratings and comments entered by employees are collected, and the data is stored in an SQL database.

[0176] Examples of prompt statements used:

[0177] "This application is designed for factory robot operators. It collects information about the operators' job functions, specialized skills, and job titles, matches operators with common areas of interest, and schedules meetings for information exchange. Specifically, it analyzes the operator data using K-Means clustering, finds the best pairs, and schedules meetings. It also collects feedback to help with future improvements."

[0178] Following these steps not only enables efficient information sharing among employees and robot operators, but also allows for continuous system improvement through feedback after meetings.

[0179] 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.

[0180] The present invention is a system that collects employee job information, specialized skills, and position information, matches employees with common areas of interest based on that information, and automatically schedules meetings. Furthermore, the system also supports a function that collects and saves feedback on the results of meetings, and an emotion engine that recognizes employee emotions. Below, specific embodiments of the present invention will be described.

[0181] First, the server collects employee job information, specialized skills, and position information. This information is extracted from the company's database and centrally managed on the server. Employee information includes details such as the work they are responsible for, their specialized skills, and their position.

[0182] The server then analyzes this collected information and matches employees with common interests, such as an engineer interested in AI technology with a marketing staff member. This matching process is carried out using pre-defined rules and AI algorithms.

[0183] After a match is made, the server will compare the employees' free time slots to automatically schedule a meeting, choosing the earliest common free time slot to schedule the meeting.

[0184] Furthermore, the present invention uses an emotion engine. The emotion engine recognizes employees' emotional states in real time and collects that data. For example, it senses the emotional state of employees during a meeting and sends that information to a server. This allows employee emotional data to be used for meeting matching and feedback.

[0185] After the meeting, the server collects employee feedback and stores it in a database. The function save_meeting_feedback centralizes the feedback and sentiment data. This feedback can be used to improve the matching algorithm and ensure the success of the project.

[0186] For example, to set up a meeting between an engineer and a marketing staff member, the server analyzes their professional skills and job information. If a common area of ​​interest is found, the server schedules the meeting based on their availability. During the meeting, an emotion engine monitors the employee's emotions and sends appropriate emotion data to the server. After the meeting, feedback and emotion data from the employees are collected and used to improve the system in the future.

[0187] As a result, the system of the present invention efficiently matches different employees within a company, promoting interaction, and by using an emotion engine, providing a higher quality meeting experience. Using this system also makes effective use of space such as office lounges, increasing opportunities for innovation.

[0188] The processing flow will be explained below.

[0189] Step 1:

[0190] The server collects employee job information, expertise, and position information from a database, which includes information entered by each employee or extracted from the company's human resources system, and then centrally manages this information.

[0191] Step 2:

[0192] The server analyzes the collected information to find employees with common interests and expertise. At this stage, the match_employees function is used to match employees with common skill sets. The server pairs employees with matching skills and interests.

[0193] Step 3:

[0194] The server retrieves the schedules of the matched employees and compares their free time. It then uses the create_meeting function to identify the earliest common free time and schedule a meeting at that time. The meeting date, time, and attendee names are automatically set.

[0195] Step 4:

[0196] The user receives a meeting notification. The server sends the details of the scheduled meeting to the user's device. The notification includes the meeting date, time, location, and attendee information.

[0197] Step 5:

[0198] When a meeting is scheduled, the device activates an emotion engine that monitors employees' emotional states in real time and collects data, such as tone of voice and facial expression recognition technology, to perform emotion analysis.

[0199] Step 6:

[0200] The server receives the emotion data sent from the emotion engine and associates it with the meeting situation and feedback. This emotion data is used to evaluate the atmosphere of the meeting and the reactions of the participants.

[0201] Step 7:

[0202] Users provide feedback after the meeting. The server saves the feedback and sentiment data to a database using the save_meeting_feedback function, allowing us to determine the effectiveness of the meeting and the satisfaction of the participants.

[0203] Step 8:

[0204] The server analyzes the collected feedback and sentiment data to improve the matching algorithm and system in the future, which will help set up future meetings more effectively and further promote interaction between employees.

[0205] Example 2

[0206] 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."

[0207] It was difficult to promote efficient communication between employees and effectively match employees with common interests. Furthermore, to improve the quality of meetings, there was also a need to understand employee sentiment in real time and reflect it in feedback. Conventional systems were unable to meet these requirements, and further technological improvements were necessary.

[0208] 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.

[0209] In this invention, the server includes means for collecting employee work information, expertise, and job title information, means for matching employees with common areas of interest based on the collected work information, expertise, and job title information, means for automatically scheduling a meeting between the matched employees, means for collecting and saving evaluations of the results of the meeting, and means for collecting emotional data during the meeting using an emotion engine that recognizes the emotional states of employees. This enables effective matching based on common areas of interest between employees, understanding of their emotional states during the meeting, and reflecting that in feedback.

[0210] "Business information" refers to the job duties that employees perform within a company and detailed information related to those jobs.

[0211] "Expertise" refers to an employee's specific techniques and skills, as well as their experience and knowledge in that field.

[0212] "Position information" is information related to the position or role that an employee holds within a company.

[0213] "Matching" is the process of pairing employees with common areas of interest.

[0214] "Schedule" means setting up a meeting or event for a specific date and time.

[0215] "Evaluation" refers to employees' feedback and thoughts on the results and progress of the meeting.

[0216] The "emotion engine" is a system that has the ability to recognize and digitize the emotional state of employees in real time.

[0217] "Feedback" refers to the opinions and thoughts employees provide after a meeting, which the system collects and uses to improve.

[0218] "Free time" refers to free time in an employee's schedule that does not have other commitments.

[0219] The present invention is a system that collects employee work information, expertise, and job title information, matches employees with common areas of interest based on this information, and automatically schedules meetings. Furthermore, the system also supports a function that collects and stores feedback on the results of meetings, and a system that combines an emotion engine that recognizes employee emotions. A specific embodiment of the present invention will be described below.

[0220] First, the server collects employee information, expertise, and job titles from the company's database using API calls. Specifically, it obtains employee names, job responsibilities, expertise, and job titles. This information is then centrally managed on the server.

[0221] The server then analyzes this collected information and matches employees with common interests using AI algorithms that apply pre-defined rules and machine learning models to classify employees' expertise and areas of interest and find suitable pairs.

[0222] After a match is made, the server retrieves the employee's calendar information and searches for a common free time. It automatically schedules a meeting based on the earliest free time. It also retrieves the calendar information using the fetch_calendar_data function and schedules the meeting at the most appropriate time using the schedule_meeting function.

[0223] Furthermore, the present invention uses an emotion engine. The emotion engine monitors the emotional state of employees in real time and collects the data. The emotion data acquired through the terminal is sent to the server in real time. For example, if an employee is "nervous" during a meeting, the data is sent to the server.

[0224] The server analyzes this emotional data and reflects it in meeting matching and feedback. After the meeting ends, the server collects feedback from employees and saves it in a database. By using the save_meeting_feedback function, the feedback content and emotional data are managed centrally.

[0225] For example, to set up a meeting between an engineer and a marketing person, the server analyzes their expertise and work information. If a common area of ​​interest is found, the server schedules the meeting based on the availability of both parties. For example, the meeting is set for next Tuesday at 2:00 PM. During the meeting, the emotion engine monitors employees' emotions, and if it detects "tension," it sends that information to the server. After the meeting, feedback from the engineer and marketing person is collected and used to improve the system in the future.

[0226] Example prompts to input to a generative AI model:

[0227] text

[0228] prompt:

[0229] Please explain the specific steps of the system that collects employee information, expertise, and job titles, matches employees with common interests based on that information, and automatically schedules meetings. Also, please explain in detail how the system incorporates an emotion engine to collect and utilize real-time emotion data.

[0230] The system of the present invention efficiently matches different employees, promotes interaction, and provides a high-quality meeting experience by using an emotion engine. Utilizing this system is expected to increase the effective use of space within a company and opportunities for innovation.

[0231] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0232] Step 1: Gather information

[0233] Server: The server uses an API to collect employee job information, expertise, and job title information from the company database. Specifically, it uses the API call get_employee_data. The input to this API call is the database connection information and query, and the output is a list of employee details. The server manages this information centrally.

[0234] Input: Database connection information and query

[0235] Output: Employee details (job description, expertise, job title)

[0236] Step 2: Information analysis and matching

[0237] Server: The server analyzes the collected employee information and matches employees with common areas of interest. This is done using AI algorithms and machine learning models. Specifically, it uses the analyze_and_match function. The input to this function is a list of employee information, and the output is matched employee pairs.

[0238] Input: List of employee information

[0239] Output: Matched employee pairs

[0240] Step 3: Schedule a meeting

[0241] Server: The server retrieves the calendar information of the matched employees, finds the earliest common free time, and schedules a meeting. Specifically, it uses the fetch_calendar_data and schedule_meeting functions. The input of each function is the API call information to the calendar application and the matched employee pair. The output is the set meeting date.

[0242] Input: Calendar API call information, matched employee pairs

[0243] Output: Meeting dates set

[0244] Step 4: Use the Emotion Engine

[0245] Terminal: The terminal uses the emotion engine to collect employee emotion data in real time. Specifically, it uses the monitor_emotions function. The input of this function is the terminal's sensor information and employee data, and the output is the collected emotion data. The terminal then sends this emotion data to the server.

[0246] Input: Device sensor information, employee data

[0247] Output: Collected emotion data

[0248] Step 5: Collect and store feedback

[0249] Server: The server collects feedback from employees after the meeting ends by using the request_feedback and save_meeting_feedback functions. The inputs to these functions are the meeting details and the feedback provided by the employees, and the output is the feedback data stored in the database.

[0250] Input: Meeting details, feedback data

[0251] Output: Stored feedback data (ratings and sentiment data)

[0252] This allows for an efficient process of collecting information, matching, scheduling meetings, monitoring emotions in real time, and collecting and storing feedback.

[0253] (Application example 2)

[0254] 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."

[0255] Modern factories are required to have highly specialized robots working together to perform a wide variety of tasks. However, it is difficult to properly match these robots and to schedule tasks optimally so that they can work together efficiently. Furthermore, there is a lack of a system for monitoring each robot's performance and operating status in real time and utilizing feedback. This makes it difficult to improve work efficiency and detect defects early.

[0256] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting job information, specialized skills, and position information of workers, means for matching workers with common areas of interest based on the collected job information, specialized skills, and position information, means for automatically scheduling collaborative tasks between the matched workers, means for collecting and saving feedback on the results of the collaborative tasks, and means for monitoring the movements and performance of workers in real time and collecting that data. This enables efficient collaboration and task scheduling of robots, as well as real-time movement monitoring and feedback collection.

[0257] A "worker" is a robot or machine that performs a specific role or task in a factory or industrial facility.

[0258] "Job information" is data indicating the tasks and work content that a worker is responsible for.

[0259] "Specialized skills" is data that indicates the specific skills and abilities that a worker possesses.

[0260] "Position information" is data relating to the position and role of a worker.

[0261] "Common areas of interest" refer to the business or technical interests that multiple workers share in common.

[0262] "Matching" is the process of pairing workers with common goals and interests based on collected data.

[0263] A "collaborative task" is a task or project that is carried out by multiple workers together.

[0264] "Automatically scheduling" means that software or a server schedules tasks or meetings without human intervention.

[0265] "Feedback" refers to information and opinions obtained as a result of or during a collaborative task.

[0266] "Monitoring operations and performance in real time" refers to monitoring the movements of workers and work results in real time.

[0267] "Collecting data" means obtaining information from various sensors and monitoring systems, and storing and organizing it.

[0268] The present invention is a system for automatically matching and scheduling efficient collaborative tasks among workers in a factory, and for monitoring their behavior and performance in real time. This system has the function of collecting job information, specialized skills, and position information of each worker, and matching workers who share common areas of interest based on this information. The following describes an embodiment of the present invention.

[0269] First, the server collects information on the worker's job, specialized skills, and position. This information is obtained from databases and sensor systems within the factory and centrally managed on the server. Worker information includes details such as the process they are responsible for, their specialized skills, and their position.

[0270] The server then analyzes the collected information and matches workers with common interests. This matching process is carried out using pre-defined rules and AI algorithms. For example, a worker with welding expertise can be paired with another worker who also has an interest in welding technology.

[0271] After matching is established, the server automatically schedules collaborative tasks, comparing the working hours of the workers and scheduling collaborative tasks based on the earliest working time, thus enabling efficient task execution.

[0272] Furthermore, the present invention uses an emotion engine that monitors the worker's actions and performance in real time. The emotion engine recognizes the worker's actions and performance in real time and sends the data to the server. This allows the worker to grasp the problems and efficiency of the work in real time.

[0273] After a collaborative task is completed, the server collects feedback from the workers and stores it in a database. This feedback can later be used to improve the system and optimize the matching algorithm. It also combines the feedback with real-time collected behavior data to make the next collaboration more efficient.

[0274] As a concrete example, the server sets up a collaborative task between worker A, who has welding skills, and worker B, who is interested in welding technology. To perform the welding work together, a schedule is automatically set based on the working hours of both workers. During the work, the emotion engine monitors the behavior and sends the data to the server. After the work is completed, feedback and monitoring data are collected and used to optimize the next collaborative task.

[0275] An example of a specific prompt is as follows:

[0276] robot_data = [

[0277] {"id": 1, "skill": "welding", "performance": 90},

[0278] {"id": 2, "skill": "assembly", "performance": 85},

[0279] Other robot data

[0280] ]

[0281] matched_pairs = match_robots(robot_data)

[0282] Example output: [({"id": 1, "skill": "welding", "performance": 90}, {"id": 3, "skill": "welding", "performance": 88})]

[0283] schedule_tasks(matched_pairs)

[0284] Example output: Scheduled Task: {'robots': [1, 3], 'task': 'welding', 'schedule_time': '2023-10-03 14:00:00'}

[0285] feedback = collect_feedback()

[0286] Example output: Collected Feedback: {"performance": 95, "issues": null}

[0287] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0288] Step 1:

[0289] The server collects information on the worker's job, specialized skills, and position. This information is obtained from the factory's database and sensor system. For example, each robot's ID, specialized skill (welding, assembly, etc.), and current performance data (such as task success rate) are extracted from the database and centrally managed.

[0290] Step 2:

[0291] The server analyzes the collected job information, expertise, and job title information, and uses AI algorithms to process the data and match workers with common interests, specifically pairing robots with the same expertise or complementary skills.

[0292] Step 3:

[0293] The server compares the working hours of the matched robots and automatically schedules collaborative tasks based on the earliest working time. The scheduling is calculated based on the free time data of each robot, and a schedule table is generated as a result.

[0294] Step 4:

[0295] When a collaborative task is being carried out, the server monitors the robot's behavior and performance in real time. Using an emotion engine, the server collects and transmits each robot's behavior and performance data to the server. For example, the server monitors the robot's speed, success rate, and error frequency.

[0296] Step 5:

[0297] After a collaborative task is completed, the server collects feedback from the workers, including evaluations of the work, issues identified, and suggestions for improvement. The feedback is stored in a database and used to optimize the next collaborative task.

[0298] Step 6:

[0299] The server analyzes the collected feedback and real-time behavioral data to improve the system and optimize the matching algorithm, so that the next collaborative task will be performed more efficiently and effectively. The analysis results are used to adjust the algorithm and update parameters.

[0300] Step 7:

[0301] If necessary, the server uses this data to update the generative AI model to provide more accurate matching and scheduling by inputting new data sets into the generative AI model and training the algorithm.

[0302] An example prompt would be:

[0303] robot_data = [

[0304] {"id": 1, "skill": "welding", "performance": 90},

[0305] {"id": 2, "skill": "assembly", "performance": 85},

[0306] Other robot data

[0307] ]

[0308] matched_pairs = match_robots(robot_data)

[0309] Example output: [({"id": 1, "skill": "welding", "performance": 90}, {"id": 3, "skill": "welding", "performance": 88})]

[0310] schedule_tasks(matched_pairs)

[0311] Example output: Scheduled Task: {'robots': [1, 3], 'task': 'welding', 'schedule_time': '2023-10-03 14:00:00'}

[0312] feedback = collect_feedback()

[0313] Example output: Collected Feedback: {"performance": 95, "issues": null}

[0314] 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.

[0315] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0316] 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.

[0317] [Second embodiment]

[0318] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0319] 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.

[0320] 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).

[0321] 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.

[0322] 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.

[0323] 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).

[0324] 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.

[0325] 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.

[0326] 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.

[0327] 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.

[0328] 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.

[0329] 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."

[0330] The present invention is a system that collects employee job information, specialized skills, and position information, matches employees with common areas of interest, and automatically schedules meetings. It also includes a function for collecting and saving feedback on the results of meetings. A specific embodiment of the present invention will be described below.

[0331] First, the server collects employee job information, specialized skills, and position information. This information is obtained from the company's internal database and analyzed by the server. Employee information, including the job duties, skills, and position, is stored in the database.

[0332] The server then uses the collected information to match employees with common interests, such as employees with the same specialized skills or complementary skills, with the matching process driven by pre-defined rules and AI algorithms.

[0333] Once matching is complete, the server automatically schedules a meeting between the matched employees. At this time, the employees' free time slots are compared and the earliest common free time is selected. Employees can also choose whether or not to participate in matching, allowing for flexible participation settings.

[0334] After the meeting is held, the server collects and stores feedback on the meeting results. This feedback is a means of collecting evaluations and comments from employees and is used as reference material for future improvements. The feedback is aggregated by the server and stored in a database.

[0335] For example, if a company's engineers and marketing staff are interested in AI technology and SEO strategies, respectively, the server will match them and schedule a meeting based on their availability. After the meeting, the server will collect feedback and use it for future projects.

[0336] In this way, the system of the present invention increases opportunities for innovation by making it easier for different types of employees within a company to meet and collaborate efficiently. Furthermore, it also makes more effective use of spaces such as office lounges that encourage employee interaction.

[0337] The processing flow will be explained below.

[0338] Step 1:

[0339] The server receives an employee ID from the user. It calls the get_employee_info function to retrieve the corresponding employee information from the database using this ID. The server searches for the job information, expertise, and position information of the employee that matches the ID and stores this information in memory.

[0340] Step 2:

[0341] The server performs a matching process based on the acquired employee information. Specifically, the server compares the job information and professional skills of other employees and analyzes them to identify common areas of interest and complementary skills. This analysis is performed using the match_employees function to find employees with common skills.

[0342] Step 3:

[0343] The server schedules meetings between successfully matched employee pairs. It uses the create_meeting function to compare the availability of both parties and identify the earliest common available time. Based on this time, the meeting details are set.

[0344] Step 4:

[0345] The user receives notifications from the server of matches and scheduled meetings, including the date and time of the meeting, the names of the employees they will be interacting with, and other relevant information.

[0346] Step 5:

[0347] The server collects feedback from employees after the meeting has taken place and saves it to the database using the save_meeting_feedback function, which will be used to improve the matching algorithm and progress the project in the future.

[0348] Step 6:

[0349] Users submit their feedback and opinions to the server, which aggregates the feedback through the system's rating mechanism and analyzes it on the server.

[0350] Step 7:

[0351] Based on the collected feedback, the server will improve the system and develop new matching algorithms, which will improve the accuracy of future matches and more effectively promote employee interaction and generate innovation.

[0352] Example 1

[0353] 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."

[0354] Modern companies have a large number of employees with diverse job functions and specialized skills, and efficient talent matching is essential. However, manually collecting employee information, creating appropriate pairs, and scheduling meetings is extremely time-consuming and labor-intensive. Furthermore, there is a lack of a system for properly collecting and saving feedback on meeting results, making it difficult to identify areas for improvement or collect reference materials for future use. This creates problems that delay the efficiency of internal communication and the promotion of collaboration among employees.

[0355] 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.

[0356] In this invention, the server includes means for collecting employee job information, specialized skills, and position information, means for analyzing the collected job information, specialized skills, and position information and storing it in a database, means for matching employees with common areas of interest based on preset rules and AI algorithms, means for automatically scheduling meetings between matched employees and obtaining employee free time and setting the earliest common free time, and means for collecting feedback from employees on the meeting results and storing it in a database, thereby enabling efficient matching between employees, automating meetings, and systematically collecting and storing feedback.

[0357] "Employee job information" is data related to the job content and role that an employee is responsible for within the company.

[0358] "Specialized skills" refers to information about the specific knowledge and skills that an employee has acquired.

[0359] "Position information" is information relating to an employee's position or status within the company.

[0360] "Means of collection" refers to the methods and devices used to extract and collect the necessary data.

[0361] "Means for analysis and storage" are methods or devices that process collected data, convert it into an understandable form, and then record it.

[0362] A "matching means" is a method or device for finding suitable matches based on specific criteria.

[0363] A "scheduling means" is a method or device for planning, coordinating, and determining the date and time of a particular event or activity.

[0364] The "means for obtaining available time" refers to a method or device for checking and extracting the available time of each employee.

[0365] "Feedback collection and storage means" refers to the methods and devices used to collect and record employee evaluations and opinions.

[0366] The present invention is a system that collects employee job information, specialized skills, and position information, matches employees with common areas of interest based on this data, and automatically schedules meetings. It also includes a function to collect and save feedback on the results of the meetings. This system is realized through the following processing steps.

[0367] The server collects employee job information, specialized skills, and position information. This information is collected using an internal company database, such as MySQL or PostgreSQL. The server extracts the information from the database, analyzes it using Python's Pandas library, and saves it in the database. This allows detailed information such as employee responsibilities, skills, and position to be organized.

[0368] The server then analyzes the collected information and matches employees with common interests. This process is performed using pre-defined rules and AI algorithms (e.g., Scikit-learn and TensorFlow). Specifically, the server uses a clustering algorithm to group employees' skills and interests, and pairs employees in the same cluster with each other.

[0369] The server automatically schedules meetings between matched employees. At this time, the server uses Microsoft Exchange Server or Google Calendar API to obtain employees' free time. It selects the earliest common free time and automatically schedules the meeting. Employees can also choose to participate in the schedule using the ON / OFF function.

[0370] After the meeting is held, the server collects feedback from employees through a dedicated web form. This web form is built using HTML and JavaScript. The collected feedback is stored in a database and used as information for future improvements and refinements. For example, a web framework such as Django is used for this storage.

[0371] As a concrete example, if engineer A at a company is interested in AI technology and marketing staff member B is interested in SEO strategy, the server retrieves their information from the database and matches them using an AI algorithm. It then retrieves their free time slots and schedules a meeting for the earliest common free time. After the meeting, B enters their evaluation and comments into a web form and provides feedback to the server, contributing to improvements to the overall system.

[0372] An example prompt might be, "We want to develop a new meeting system. The system will collect employee job information, professional skills, and position information, and match employees with common interests based on this data. It will then automatically schedule meetings and collect and store feedback on the meeting results. Please write program code that describes this process in detail."

[0373] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0374] Step 1:

[0375] Collection of employee information

[0376] The server collects employee job information, expertise, and position information from the company's database. It queries the database and executes SQL queries to retrieve employee information. The input is the database connection information and the required query syntax, and the output is a set of employee information.

[0377] Specifically, the server executes the following SQL query:

[0378] SELECT FROM employee_data;

[0379] The retrieved data is converted to a Pandas DataFrame.

[0380] Step 2:

[0381] Data analysis and storage

[0382] The server analyzes the acquired employee information and stores it in a database. The input is employee information in DataFrame format, and the output is the analyzed results stored in the database. Specific analysis processes include data cleaning and extraction of specific columns. After analysis, the information is stored in a separate table.

[0383] Specifically, it uses Pandas to clean the data.

[0384] python

[0385] import pandas as pd

[0386] df = pd.DataFrame(data)

[0387] Data cleaning and analysis

[0388] df_cleaned = df.dropna().query('role != "intern"')

[0389] df_cleaned.to_sql('parsed_employee_data', con=engine, if_exists='replace')

[0390] Step 3:

[0391] Setting matching conditions

[0392] The server uses an AI algorithm to set the conditions for matching employees. The input is the analyzed employee data, and the output is the cluster information for each employee. Specifically, clustering is performed using Scikit-learn's KMeans algorithm.

[0393] Specifically, the KMeans algorithm is applied as follows:

[0394] python

[0395] from sklearn.cluster import KMeans

[0396] kmeans = KMeans(n_clusters=5).fit(df_cleaned)

[0397] clusters = kmeans.labels_

[0398] df_cleaned['cluster'] = clusters

[0399] Step 4:

[0400] Scheduling a Meeting

[0401] The server schedules meetings between matching employees. The input is a list of matches and the employees' calendar information, and the output is the scheduled meeting details. The server uses the Google Calendar API to get the employees' free time and schedules the meeting at the earliest common free time.

[0402] Specifically, it uses the Google Calendar API to obtain available time.

[0403] python

[0404] from googleapiclient.discovery import build

[0405] service = build('calendar', 'v3', credentials=creds)

[0406] events = service.events().list(calendarId='primary').execute()

[0407] common_free_time = find_common_time(events)

[0408] schedule_meeting(common_free_time)

[0409] Step 5:

[0410] Collecting and storing feedback

[0411] The server collects feedback from employees after the meeting and stores it in a database. The input is the feedback entered by employees through a web form, and the output is the feedback data stored in the database.

[0412] Specifically, the user enters feedback into a web form.

[0413] html

[0414] <form action=" / submit_feedback" method="post">

[0415] <textarea name="feedback" rows="4" cols="50">< / textarea>

[0416] <input type="submit" value="Submit">

[0417] < / form>

[0418] Feedback is collected on the server side and stored in a database.

[0419] python

[0420] from django.shortcuts import render

[0421] from .models import Feedback

[0422] def submit_feedback(request):

[0423] if request.method == 'POST':

[0424] feedback = request.POST['feedback']

[0425] Feedback.objects.create(content=feedback)

[0426] return render(request, 'thank_you.html')

[0427] (Application example 1)

[0428] 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."

[0429] To facilitate knowledge sharing and collaboration among employees within a company, a system is needed that allows employees with similar expertise and interests to naturally meet, exchange information, and collaborate. However, manually matching employees and scheduling meetings is time-consuming and inefficient. Furthermore, there is a lack of a system for efficiently collecting feedback after meetings and using it to improve operations. Furthermore, information sharing between robot operators is important in the field, and there is a need for an efficient method for this process that utilizes smartphones and head-mounted displays.

[0430] 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.

[0431] In this invention, the server includes a means for collecting employee job information, specialized skills, and position information, a means for matching employees with common areas of interest based on the collected job information, specialized skills, and position information, a means for automatically scheduling meetings between the matched employees, a means for collecting and storing feedback on the results of the meetings, a means for using a clustering algorithm to analyze operator data, and a means for finding optimal pairs according to a specified algorithm. This enables efficient matching between employees and robot operators with common areas of interest and scheduling of meetings. In addition, continuous system improvement is achieved through the collection of feedback.

[0432] "Employee job information" is information relating to the work content and role that an employee is responsible for within a company.

[0433] "Specialized skills" refers to the skills and knowledge an employee possesses in a specific field.

[0434] "Position information" is information about an employee's current position or title.

[0435] "Means of collection" refers to a method for obtaining employee job information, specialized skills, and position information using a server or database.

[0436] "Matching methods" are methods for matching employees with common areas of interest based on collected information.

[0437] A "scheduling method" is a method for automatically scheduling and scheduling meetings between matched employees.

[0438] "Means for collecting and storing feedback" refers to the method for collecting evaluations and comments from employees after the meeting and storing that data.

[0439] A "clustering algorithm" is a mathematical and statistical method used to analyze data and separate it into groups that share common characteristics.

[0440] The "means for finding the best pair" is a method for selecting the best pair to be matched based on the results of the clustering algorithm.

[0441] This invention is a system that collects employee job information, specialized skills, and position information, performs matching, automatic scheduling, and feedback collection, and particularly supports efficient information sharing among robot operators within factories.

[0442] 1. System Configuration

[0443] The server collects and analyzes employee job information, specialized skills, and position information from the company's internal database. The collected data is stored in, for example, an SQLite database. Data such as the operator's specialized skills and job information is analyzed using a clustering algorithm (e.g., K-Means clustering), and operators who share common areas of interest are automatically matched.

[0444] 2. Data analysis and matching

[0445] The server uses the collected data to run a clustering algorithm, using the Python library Scikit-learn. Specifically, it creates a data matrix based on the operator's specialized skills and applies K-Means clustering to match operators who belong to the same cluster.

[0446] 3. Automatic Meeting Scheduling

[0447] Once matching is complete, the server uses the schedule data to find the earliest common free time and automatically schedules the meeting, using time data retrieved from the company's internal calendar system (e.g., Google Calendar API).

[0448] 4. Collecting and storing feedback

[0449] After the meeting, the server collects feedback from participants and stores it in a database. The feedback form used at this stage is implemented, for example, as a web application (using Flask). The feedback is later analyzed to improve the system and provide new suggestions.

[0450] 5. Hardware and Software Used

[0451] The system is implemented using the following hardware and software:

[0452] Hardware: Smartphones, smart glasses, head-mounted displays

[0453] Software: Python, Flask, SQLite, Scikit-learn

[0454] 6. Specific Examples

[0455] For example, if there is Engineer A in charge of robot maintenance in a factory and Engineer B, a new employee interested in the same field, the server clusters their data and confirms that they belong to the same cluster. It then finds a common free time and automatically schedules a meeting. It then uses the feedback collected after the meeting to make future improvements.

[0456] Example prompt (input for generative AI model)

[0457] "This application is designed for factory robot operators. It collects information about the operators' job functions, specialized skills, and job titles, matches operators with common areas of interest, and schedules meetings for information exchange. Specifically, it analyzes the operator data using K-Means clustering, finds the best pairs, and schedules meetings. It also collects feedback to help with future improvements."

[0458] This system will promote efficient information sharing among robot operators within the factory, contributing to the improvement of knowledge and skills.

[0459] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0460] Step 1:

[0461] The server collects employee job information, specialized skills, and position information from the company's internal database. The input for data collection is the access privileges of the company's existing information systems and databases. The output is a set of job information, specialized skills, and position information organized for each employee. When collecting data, SQL queries are used to extract the necessary data and store it in an SQLite database.

[0462] Step 2:

[0463] The server applies a clustering algorithm based on the collected job information, specialized skills, and position information. The employee dataset collected in step 1 is used as input. The output is the results of employees being divided into clusters based on their common areas of interest. For clustering, Python's Scikit-learn library is used to perform K-Means clustering. Specifically, the employee specialized skills are vectorized, a data matrix is ​​created, and then clustering is performed.

[0464] Step 3:

[0465] The server matches employees with common areas of interest based on the clustered data. The input is the clustering results from step 2. The output is a list of matched employee pairs. Specifically, employees belonging to the same cluster are paired together, and each pair is listed.

[0466] Step 4:

[0467] The server automatically schedules meetings between matched employees based on the schedule data. The input is a pair list of matched employees and each employee's free time data. The output is a list of scheduled meeting dates and times. Specifically, the server retrieves each employee's schedule from the company's internal calendar system (e.g., Google Calendar API), finds the earliest common free time, and schedules the meeting.

[0468] Step 5:

[0469] The server collects and stores feedback from employees after the meeting ends. The input is the ratings and comments of employees who attended the meeting. The output is the aggregated feedback data. Feedback is collected through a web application (e.g., created using Flask) and stored in a database. Specifically, a feedback form is provided, the ratings and comments entered by employees are collected, and the data is stored in an SQL database.

[0470] Examples of prompt statements used:

[0471] "This application is designed for factory robot operators. It collects information about the operators' job functions, specialized skills, and job titles, matches operators with common areas of interest, and schedules meetings for information exchange. Specifically, it analyzes the operator data using K-Means clustering, finds the best pairs, and schedules meetings. It also collects feedback to help with future improvements."

[0472] Following these steps not only enables efficient information sharing among employees and robot operators, but also allows for continuous system improvement through feedback after meetings.

[0473] 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.

[0474] The present invention is a system that collects employee job information, specialized skills, and position information, matches employees with common areas of interest based on that information, and automatically schedules meetings. Furthermore, the system also supports a function that collects and saves feedback on the results of meetings, and an emotion engine that recognizes employee emotions. Below, specific embodiments of the present invention will be described.

[0475] First, the server collects employee job information, specialized skills, and position information. This information is extracted from the company's database and centrally managed on the server. Employee information includes details such as the work they are responsible for, their specialized skills, and their position.

[0476] The server then analyzes this collected information and matches employees with common interests, such as an engineer interested in AI technology with a marketing staff member. This matching process is carried out using pre-defined rules and AI algorithms.

[0477] After a match is made, the server will compare the employees' free time slots to automatically schedule a meeting, choosing the earliest common free time slot to schedule the meeting.

[0478] Furthermore, the present invention uses an emotion engine. The emotion engine recognizes employees' emotional states in real time and collects that data. For example, it senses the emotional state of employees during a meeting and sends that information to a server. This allows employee emotional data to be used for meeting matching and feedback.

[0479] After the meeting, the server collects employee feedback and stores it in a database. The function save_meeting_feedback centralizes the feedback and sentiment data. This feedback can be used to improve the matching algorithm and ensure the success of the project.

[0480] For example, to set up a meeting between an engineer and a marketing staff member, the server analyzes their professional skills and job information. If a common area of ​​interest is found, the server schedules the meeting based on their availability. During the meeting, an emotion engine monitors the employee's emotions and sends appropriate emotion data to the server. After the meeting, feedback and emotion data from the employees are collected and used to improve the system in the future.

[0481] As a result, the system of the present invention efficiently matches different employees within a company, promoting interaction, and by using an emotion engine, providing a higher quality meeting experience. Using this system also makes effective use of space such as office lounges, increasing opportunities for innovation.

[0482] The processing flow will be explained below.

[0483] Step 1:

[0484] The server collects employee job information, expertise, and position information from a database, which includes information entered by each employee or extracted from the company's human resources system, and then centrally manages this information.

[0485] Step 2:

[0486] The server analyzes the collected information to find employees with common interests and expertise. At this stage, the match_employees function is used to match employees with common skill sets. The server pairs employees with matching skills and interests.

[0487] Step 3:

[0488] The server retrieves the schedules of the matched employees and compares their free time. It then uses the create_meeting function to identify the earliest common free time and schedule a meeting at that time. The meeting date, time, and attendee names are automatically set.

[0489] Step 4:

[0490] The user receives a meeting notification. The server sends the details of the scheduled meeting to the user's device. The notification includes the meeting date, time, location, and attendee information.

[0491] Step 5:

[0492] When a meeting is scheduled, the device activates an emotion engine that monitors employees' emotional states in real time and collects data, such as tone of voice and facial expression recognition technology, to perform emotion analysis.

[0493] Step 6:

[0494] The server receives the emotion data sent from the emotion engine and associates it with the meeting situation and feedback. This emotion data is used to evaluate the atmosphere of the meeting and the reactions of the participants.

[0495] Step 7:

[0496] Users provide feedback after the meeting. The server saves the feedback and sentiment data to a database using the save_meeting_feedback function, allowing us to determine the effectiveness of the meeting and the satisfaction of the participants.

[0497] Step 8:

[0498] The server analyzes the collected feedback and sentiment data to improve the matching algorithm and system in the future, which will help set up future meetings more effectively and further promote interaction between employees.

[0499] Example 2

[0500] 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."

[0501] It was difficult to promote efficient communication between employees and effectively match employees with common interests. Furthermore, to improve the quality of meetings, there was also a need to understand employee sentiment in real time and reflect it in feedback. Conventional systems were unable to meet these requirements, and further technological improvements were necessary.

[0502] 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.

[0503] In this invention, the server includes means for collecting employee work information, expertise, and job title information, means for matching employees with common areas of interest based on the collected work information, expertise, and job title information, means for automatically scheduling a meeting between the matched employees, means for collecting and saving evaluations of the results of the meeting, and means for collecting emotional data during the meeting using an emotion engine that recognizes the emotional states of employees. This enables effective matching based on common areas of interest between employees, understanding of their emotional states during the meeting, and reflecting that in feedback.

[0504] "Business information" refers to the job duties that employees perform within a company and detailed information related to those jobs.

[0505] "Expertise" refers to an employee's specific techniques and skills, as well as their experience and knowledge in that field.

[0506] "Position information" is information related to the position or role that an employee holds within a company.

[0507] "Matching" is the process of pairing employees with common areas of interest.

[0508] "Schedule" means setting up a meeting or event for a specific date and time.

[0509] "Evaluation" refers to employees' feedback and thoughts on the results and progress of the meeting.

[0510] The "emotion engine" is a system that has the ability to recognize and digitize the emotional state of employees in real time.

[0511] "Feedback" refers to the opinions and thoughts employees provide after a meeting, which the system collects and uses to improve.

[0512] "Free time" refers to free time in an employee's schedule that does not have other commitments.

[0513] The present invention is a system that collects employee work information, expertise, and job title information, matches employees with common areas of interest based on this information, and automatically schedules meetings. Furthermore, the system also supports a function that collects and stores feedback on the results of meetings, and a system that combines an emotion engine that recognizes employee emotions. A specific embodiment of the present invention will be described below.

[0514] First, the server collects employee information, expertise, and job titles from the company's database using API calls. Specifically, it obtains employee names, job responsibilities, expertise, and job titles. This information is then centrally managed on the server.

[0515] The server then analyzes this collected information and matches employees with common interests using AI algorithms that apply pre-defined rules and machine learning models to classify employees' expertise and areas of interest and find suitable pairs.

[0516] After a match is made, the server retrieves the employee's calendar information and searches for a common free time. It automatically schedules a meeting based on the earliest free time. It also retrieves the calendar information using the fetch_calendar_data function and schedules the meeting at the most appropriate time using the schedule_meeting function.

[0517] Furthermore, the present invention uses an emotion engine. The emotion engine monitors the emotional state of employees in real time and collects the data. The emotion data acquired through the terminal is sent to the server in real time. For example, if an employee is "nervous" during a meeting, the data is sent to the server.

[0518] The server analyzes this emotional data and reflects it in meeting matching and feedback. After the meeting ends, the server collects feedback from employees and saves it in a database. By using the save_meeting_feedback function, the feedback content and emotional data are managed centrally.

[0519] For example, to set up a meeting between an engineer and a marketing person, the server analyzes their expertise and work information. If a common area of ​​interest is found, the server schedules the meeting based on the availability of both parties. For example, the meeting is set for next Tuesday at 2:00 PM. During the meeting, the emotion engine monitors employees' emotions, and if it detects "tension," it sends that information to the server. After the meeting, feedback from the engineer and marketing person is collected and used to improve the system in the future.

[0520] Example prompts to input to a generative AI model:

[0521] text

[0522] prompt:

[0523] Please explain the specific steps of the system that collects employee information, expertise, and job titles, matches employees with common interests based on that information, and automatically schedules meetings. Also, please explain in detail how the system incorporates an emotion engine to collect and utilize real-time emotion data.

[0524] The system of the present invention efficiently matches different employees, promotes interaction, and provides a high-quality meeting experience by using an emotion engine. Utilizing this system is expected to increase the effective use of space within a company and opportunities for innovation.

[0525] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0526] Step 1: Gather information

[0527] Server: The server uses an API to collect employee job information, expertise, and job title information from the company database. Specifically, it uses the API call get_employee_data. The input to this API call is the database connection information and query, and the output is a list of employee details. The server manages this information centrally.

[0528] Input: Database connection information and query

[0529] Output: Employee details (job description, expertise, job title)

[0530] Step 2: Information analysis and matching

[0531] Server: The server analyzes the collected employee information and matches employees with common areas of interest. This is done using AI algorithms and machine learning models. Specifically, it uses the analyze_and_match function. The input to this function is a list of employee information, and the output is matched employee pairs.

[0532] Input: List of employee information

[0533] Output: Matched employee pairs

[0534] Step 3: Schedule a meeting

[0535] Server: The server retrieves the calendar information of the matched employees, finds the earliest common free time, and schedules a meeting. Specifically, it uses the fetch_calendar_data and schedule_meeting functions. The input of each function is the API call information to the calendar application and the matched employee pair. The output is the set meeting date.

[0536] Input: Calendar API call information, matched employee pairs

[0537] Output: Meeting dates set

[0538] Step 4: Use the Emotion Engine

[0539] Terminal: The terminal uses the emotion engine to collect employee emotion data in real time. Specifically, it uses the monitor_emotions function. The input of this function is the terminal's sensor information and employee data, and the output is the collected emotion data. The terminal then sends this emotion data to the server.

[0540] Input: Device sensor information, employee data

[0541] Output: Collected emotion data

[0542] Step 5: Collect and store feedback

[0543] Server: The server collects feedback from employees after the meeting ends by using the request_feedback and save_meeting_feedback functions. The inputs to these functions are the meeting details and the feedback provided by the employees, and the output is the feedback data stored in the database.

[0544] Input: Meeting details, feedback data

[0545] Output: Stored feedback data (ratings and sentiment data)

[0546] This allows for an efficient process of collecting information, matching, scheduling meetings, monitoring emotions in real time, and collecting and storing feedback.

[0547] (Application example 2)

[0548] 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."

[0549] Modern factories are required to have highly specialized robots working together to perform a wide variety of tasks. However, it is difficult to properly match these robots and to schedule tasks optimally so that they can work together efficiently. Furthermore, there is a lack of a system for monitoring each robot's performance and operating status in real time and utilizing feedback. This makes it difficult to improve work efficiency and detect defects early.

[0550] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting job information, specialized skills, and position information of workers, means for matching workers with common areas of interest based on the collected job information, specialized skills, and position information, means for automatically scheduling collaborative tasks between the matched workers, means for collecting and saving feedback on the results of the collaborative tasks, and means for monitoring the movements and performance of workers in real time and collecting that data. This enables efficient collaboration and task scheduling of robots, as well as real-time movement monitoring and feedback collection.

[0551] A "worker" is a robot or machine that performs a specific role or task in a factory or industrial facility.

[0552] "Job information" is data indicating the tasks and work content that a worker is responsible for.

[0553] "Specialized skills" is data that indicates the specific skills and abilities that a worker possesses.

[0554] "Position information" is data relating to the position and role of a worker.

[0555] "Common areas of interest" refer to the business or technical interests that multiple workers share in common.

[0556] "Matching" is the process of pairing workers with common goals and interests based on collected data.

[0557] A "collaborative task" is a task or project that is carried out by multiple workers together.

[0558] "Automatically scheduling" means that software or a server schedules tasks or meetings without human intervention.

[0559] "Feedback" refers to information and opinions obtained as a result of or during a collaborative task.

[0560] "Monitoring operations and performance in real time" refers to monitoring the movements of workers and work results in real time.

[0561] "Collecting data" means obtaining information from various sensors and monitoring systems, and storing and organizing it.

[0562] The present invention is a system for automatically matching and scheduling efficient collaborative tasks among workers in a factory, and for monitoring their behavior and performance in real time. This system has the function of collecting job information, specialized skills, and position information of each worker, and matching workers who share common areas of interest based on this information. The following describes an embodiment of the present invention.

[0563] First, the server collects information on the worker's job, specialized skills, and position. This information is obtained from databases and sensor systems within the factory and centrally managed on the server. Worker information includes details such as the process they are responsible for, their specialized skills, and their position.

[0564] The server then analyzes the collected information and matches workers with common interests. This matching process is carried out using pre-defined rules and AI algorithms. For example, a worker with welding expertise can be paired with another worker who also has an interest in welding technology.

[0565] After matching is established, the server automatically schedules collaborative tasks, comparing the working hours of the workers and scheduling collaborative tasks based on the earliest working time, thus enabling efficient task execution.

[0566] Furthermore, the present invention uses an emotion engine that monitors the worker's actions and performance in real time. The emotion engine recognizes the worker's actions and performance in real time and sends the data to the server. This allows the worker to grasp the problems and efficiency of the work in real time.

[0567] After a collaborative task is completed, the server collects feedback from the workers and stores it in a database. This feedback can later be used to improve the system and optimize the matching algorithm. It also combines the feedback with real-time collected behavior data to make the next collaboration more efficient.

[0568] As a concrete example, the server sets up a collaborative task between worker A, who has welding skills, and worker B, who is interested in welding technology. To perform the welding work together, a schedule is automatically set based on the working hours of both workers. During the work, the emotion engine monitors the behavior and sends the data to the server. After the work is completed, feedback and monitoring data are collected and used to optimize the next collaborative task.

[0569] An example of a specific prompt is as follows:

[0570] robot_data = [

[0571] {"id": 1, "skill": "welding", "performance": 90},

[0572] {"id": 2, "skill": "assembly", "performance": 85},

[0573] Other robot data

[0574] ]

[0575] matched_pairs = match_robots(robot_data)

[0576] Example output: [({"id": 1, "skill": "welding", "performance": 90}, {"id": 3, "skill": "welding", "performance": 88})]

[0577] schedule_tasks(matched_pairs)

[0578] Example output: Scheduled Task: {'robots': [1, 3], 'task': 'welding', 'schedule_time': '2023-10-03 14:00:00'}

[0579] feedback = collect_feedback()

[0580] Example output: Collected Feedback: {"performance": 95, "issues": null}

[0581] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0582] Step 1:

[0583] The server collects information on the worker's job, specialized skills, and position. This information is obtained from the factory's database and sensor system. For example, each robot's ID, specialized skill (welding, assembly, etc.), and current performance data (such as task success rate) are extracted from the database and centrally managed.

[0584] Step 2:

[0585] The server analyzes the collected job information, expertise, and job title information, and uses AI algorithms to process the data and match workers with common interests, specifically pairing robots with the same expertise or complementary skills.

[0586] Step 3:

[0587] The server compares the working hours of the matched robots and automatically schedules collaborative tasks based on the earliest working time. The scheduling is calculated based on the free time data of each robot, and a schedule table is generated as a result.

[0588] Step 4:

[0589] When a collaborative task is being carried out, the server monitors the robot's behavior and performance in real time. Using an emotion engine, the server collects and transmits each robot's behavior and performance data to the server. For example, the server monitors the robot's speed, success rate, and error frequency.

[0590] Step 5:

[0591] After a collaborative task is completed, the server collects feedback from the workers, including evaluations of the work, issues identified, and suggestions for improvement. The feedback is stored in a database and used to optimize the next collaborative task.

[0592] Step 6:

[0593] The server analyzes the collected feedback and real-time behavioral data to improve the system and optimize the matching algorithm, so that the next collaborative task will be performed more efficiently and effectively. The analysis results are used to adjust the algorithm and update parameters.

[0594] Step 7:

[0595] If necessary, the server uses this data to update the generative AI model to provide more accurate matching and scheduling by inputting new data sets into the generative AI model and training the algorithm.

[0596] An example prompt would be:

[0597] robot_data = [

[0598] {"id": 1, "skill": "welding", "performance": 90},

[0599] {"id": 2, "skill": "assembly", "performance": 85},

[0600] Other robot data

[0601] ]

[0602] matched_pairs = match_robots(robot_data)

[0603] Example output: [({"id": 1, "skill": "welding", "performance": 90}, {"id": 3, "skill": "welding", "performance": 88})]

[0604] schedule_tasks(matched_pairs)

[0605] Example output: Scheduled Task: {'robots': [1, 3], 'task': 'welding', 'schedule_time': '2023-10-03 14:00:00'}

[0606] feedback = collect_feedback()

[0607] Example output: Collected Feedback: {"performance": 95, "issues": null}

[0608] 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.

[0609] 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.

[0610] 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.

[0611] [Third embodiment]

[0612] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0613] 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.

[0614] 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).

[0615] 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.

[0616] 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.

[0617] 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).

[0618] 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.

[0619] 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.

[0620] 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.

[0621] 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.

[0622] 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.

[0623] 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."

[0624] The present invention is a system that collects employee job information, specialized skills, and position information, matches employees with common areas of interest, and automatically schedules meetings. It also includes a function for collecting and saving feedback on the results of meetings. A specific embodiment of the present invention will be described below.

[0625] First, the server collects employee job information, specialized skills, and position information. This information is obtained from the company's internal database and analyzed by the server. Employee information, including the job duties, skills, and position, is stored in the database.

[0626] The server then uses the collected information to match employees with common interests, such as employees with the same specialized skills or complementary skills, with the matching process driven by pre-defined rules and AI algorithms.

[0627] Once matching is complete, the server automatically schedules a meeting between the matched employees. At this time, the employees' free time slots are compared and the earliest common free time is selected. Employees can also choose whether or not to participate in matching, allowing for flexible participation settings.

[0628] After the meeting is held, the server collects and stores feedback on the meeting results. This feedback is a means of collecting evaluations and comments from employees and is used as reference material for future improvements. The feedback is aggregated by the server and stored in a database.

[0629] For example, if a company's engineers and marketing staff are interested in AI technology and SEO strategies, respectively, the server will match them and schedule a meeting based on their availability. After the meeting, the server will collect feedback and use it for future projects.

[0630] In this way, the system of the present invention increases opportunities for innovation by making it easier for different types of employees within a company to meet and collaborate efficiently. Furthermore, it also makes more effective use of spaces such as office lounges that encourage employee interaction.

[0631] The processing flow will be explained below.

[0632] Step 1:

[0633] The server receives an employee ID from the user. It calls the get_employee_info function to retrieve the corresponding employee information from the database using this ID. The server searches for the job information, expertise, and position information of the employee that matches the ID and stores this information in memory.

[0634] Step 2:

[0635] The server performs a matching process based on the acquired employee information. Specifically, the server compares the job information and professional skills of other employees and analyzes them to identify common areas of interest and complementary skills. This analysis is performed using the match_employees function to find employees with common skills.

[0636] Step 3:

[0637] The server schedules meetings between successfully matched employee pairs. It uses the create_meeting function to compare the availability of both parties and identify the earliest common available time. Based on this time, the meeting details are set.

[0638] Step 4:

[0639] The user receives notifications from the server of matches and scheduled meetings, including the date and time of the meeting, the names of the employees they will be interacting with, and other relevant information.

[0640] Step 5:

[0641] The server collects feedback from employees after the meeting has taken place and saves it to the database using the save_meeting_feedback function, which will be used to improve the matching algorithm and progress the project in the future.

[0642] Step 6:

[0643] Users submit their feedback and opinions to the server, which aggregates the feedback through the system's rating mechanism and analyzes it on the server.

[0644] Step 7:

[0645] Based on the collected feedback, the server will improve the system and develop new matching algorithms, which will improve the accuracy of future matches and more effectively promote employee interaction and generate innovation.

[0646] Example 1

[0647] 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."

[0648] Modern companies have a large number of employees with diverse job functions and specialized skills, and efficient talent matching is essential. However, manually collecting employee information, creating appropriate pairs, and scheduling meetings is extremely time-consuming and labor-intensive. Furthermore, there is a lack of a system for properly collecting and saving feedback on meeting results, making it difficult to identify areas for improvement or collect reference materials for future use. This creates problems that delay the efficiency of internal communication and the promotion of collaboration among employees.

[0649] 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.

[0650] In this invention, the server includes means for collecting employee job information, specialized skills, and position information, means for analyzing the collected job information, specialized skills, and position information and storing it in a database, means for matching employees with common areas of interest based on preset rules and AI algorithms, means for automatically scheduling meetings between matched employees and obtaining employee free time and setting the earliest common free time, and means for collecting feedback from employees on the meeting results and storing it in a database, thereby enabling efficient matching between employees, automating meetings, and systematically collecting and storing feedback.

[0651] "Employee job information" is data related to the job content and role that an employee is responsible for within the company.

[0652] "Specialized skills" refers to information about the specific knowledge and skills that an employee has acquired.

[0653] "Position information" is information relating to an employee's position or status within the company.

[0654] "Means of collection" refers to the methods and devices used to extract and collect the necessary data.

[0655] "Means for analysis and storage" are methods or devices that process collected data, convert it into an understandable form, and then record it.

[0656] A "matching means" is a method or device for finding suitable matches based on specific criteria.

[0657] A "scheduling means" is a method or device for planning, coordinating, and determining the date and time of a particular event or activity.

[0658] The "means for obtaining available time" refers to a method or device for checking and extracting the available time of each employee.

[0659] "Feedback collection and storage means" refers to the methods and devices used to collect and record employee evaluations and opinions.

[0660] The present invention is a system that collects employee job information, specialized skills, and position information, matches employees with common areas of interest based on this data, and automatically schedules meetings. It also includes a function to collect and save feedback on the results of the meetings. This system is realized through the following processing steps.

[0661] The server collects employee job information, specialized skills, and position information. This information is collected using an internal company database, such as MySQL or PostgreSQL. The server extracts the information from the database, analyzes it using Python's Pandas library, and saves it in the database. This allows detailed information such as employee responsibilities, skills, and position to be organized.

[0662] The server then analyzes the collected information and matches employees with common interests. This process is performed using pre-defined rules and AI algorithms (e.g., Scikit-learn and TensorFlow). Specifically, the server uses a clustering algorithm to group employees' skills and interests, and pairs employees in the same cluster with each other.

[0663] The server automatically schedules meetings between matched employees. At this time, the server uses Microsoft Exchange Server or Google Calendar API to obtain employees' free time. It selects the earliest common free time and automatically schedules the meeting. Employees can also choose to participate in the schedule using the ON / OFF function.

[0664] After the meeting is held, the server collects feedback from employees through a dedicated web form. This web form is built using HTML and JavaScript. The collected feedback is stored in a database and used as information for future improvements and refinements. For example, a web framework such as Django is used for this storage.

[0665] As a concrete example, if engineer A at a company is interested in AI technology and marketing staff member B is interested in SEO strategy, the server retrieves their information from the database and matches them using an AI algorithm. It then retrieves their free time slots and schedules a meeting for the earliest common free time. After the meeting, B enters their evaluation and comments into a web form and provides feedback to the server, contributing to improvements to the overall system.

[0666] An example prompt might be, "We want to develop a new meeting system. The system will collect employee job information, professional skills, and position information, and match employees with common interests based on this data. It will then automatically schedule meetings and collect and store feedback on the meeting results. Please write program code that describes this process in detail."

[0667] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0668] Step 1:

[0669] Collection of employee information

[0670] The server collects employee job information, expertise, and position information from the company's database. It queries the database and executes SQL queries to retrieve employee information. The input is the database connection information and the required query syntax, and the output is a set of employee information.

[0671] Specifically, the server executes the following SQL query:

[0672] SELECT FROM employee_data;

[0673] The retrieved data is converted to a Pandas DataFrame.

[0674] Step 2:

[0675] Data analysis and storage

[0676] The server analyzes the acquired employee information and stores it in a database. The input is employee information in DataFrame format, and the output is the analyzed results stored in the database. Specific analysis processes include data cleaning and extraction of specific columns. After analysis, the information is stored in a separate table.

[0677] Specifically, it uses Pandas to clean the data.

[0678] python

[0679] import pandas as pd

[0680] df = pd.DataFrame(data)

[0681] Data cleaning and analysis

[0682] df_cleaned = df.dropna().query('role != "intern"')

[0683] df_cleaned.to_sql('parsed_employee_data', con=engine, if_exists='replace')

[0684] Step 3:

[0685] Setting matching conditions

[0686] The server uses an AI algorithm to set the conditions for matching employees. The input is the analyzed employee data, and the output is the cluster information for each employee. Specifically, clustering is performed using Scikit-learn's KMeans algorithm.

[0687] Specifically, the KMeans algorithm is applied as follows:

[0688] python

[0689] from sklearn.cluster import KMeans

[0690] kmeans = KMeans(n_clusters=5).fit(df_cleaned)

[0691] clusters = kmeans.labels_

[0692] df_cleaned['cluster'] = clusters

[0693] Step 4:

[0694] Scheduling a Meeting

[0695] The server schedules meetings between matching employees. The input is a list of matches and the employees' calendar information, and the output is the scheduled meeting details. The server uses the Google Calendar API to get the employees' free time and schedules the meeting at the earliest common free time.

[0696] Specifically, it uses the Google Calendar API to obtain available time.

[0697] python

[0698] from googleapiclient.discovery import build

[0699] service = build('calendar', 'v3', credentials=creds)

[0700] events = service.events().list(calendarId='primary').execute()

[0701] common_free_time = find_common_time(events)

[0702] schedule_meeting(common_free_time)

[0703] Step 5:

[0704] Collecting and storing feedback

[0705] The server collects feedback from employees after the meeting and stores it in a database. The input is the feedback entered by employees through a web form, and the output is the feedback data stored in the database.

[0706] Specifically, the user enters feedback into a web form.

[0707] html

[0708] <form action=" / submit_feedback" method="post">

[0709] <textarea name="feedback" rows="4" cols="50">< / textarea>

[0710] <input type="submit" value="Submit">

[0711] < / form>

[0712] Feedback is collected on the server side and stored in a database.

[0713] python

[0714] from django.shortcuts import render

[0715] from .models import Feedback

[0716] def submit_feedback(request):

[0717] if request.method == 'POST':

[0718] feedback = request.POST['feedback']

[0719] Feedback.objects.create(content=feedback)

[0720] return render(request, 'thank_you.html')

[0721] (Application example 1)

[0722] 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."

[0723] To facilitate knowledge sharing and collaboration among employees within a company, a system is needed that allows employees with similar expertise and interests to naturally meet, exchange information, and collaborate. However, manually matching employees and scheduling meetings is time-consuming and inefficient. Furthermore, there is a lack of a system for efficiently collecting feedback after meetings and using it to improve operations. Furthermore, information sharing between robot operators is important in the field, and there is a need for an efficient method for this process that utilizes smartphones and head-mounted displays.

[0724] 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.

[0725] In this invention, the server includes a means for collecting employee job information, specialized skills, and position information, a means for matching employees with common areas of interest based on the collected job information, specialized skills, and position information, a means for automatically scheduling meetings between the matched employees, a means for collecting and storing feedback on the results of the meetings, a means for using a clustering algorithm to analyze operator data, and a means for finding optimal pairs according to a specified algorithm. This enables efficient matching between employees and robot operators with common areas of interest and scheduling of meetings. In addition, continuous system improvement is achieved through the collection of feedback.

[0726] "Employee job information" is information relating to the work content and role that an employee is responsible for within a company.

[0727] "Specialized skills" refers to the skills and knowledge an employee possesses in a specific field.

[0728] "Position information" is information about an employee's current position or title.

[0729] "Means of collection" refers to a method for obtaining employee job information, specialized skills, and position information using a server or database.

[0730] "Matching methods" are methods for matching employees with common areas of interest based on collected information.

[0731] A "scheduling method" is a method for automatically scheduling and scheduling meetings between matched employees.

[0732] "Means for collecting and storing feedback" refers to the method for collecting evaluations and comments from employees after the meeting and storing that data.

[0733] A "clustering algorithm" is a mathematical and statistical method used to analyze data and separate it into groups that share common characteristics.

[0734] The "means for finding the best pair" is a method for selecting the best pair to be matched based on the results of the clustering algorithm.

[0735] This invention is a system that collects employee job information, specialized skills, and position information, performs matching, automatic scheduling, and feedback collection, and particularly supports efficient information sharing among robot operators within factories.

[0736] 1. System Configuration

[0737] The server collects and analyzes employee job information, specialized skills, and position information from the company's internal database. The collected data is stored in, for example, an SQLite database. Data such as the operator's specialized skills and job information is analyzed using a clustering algorithm (e.g., K-Means clustering), and operators who share common areas of interest are automatically matched.

[0738] 2. Data analysis and matching

[0739] The server uses the collected data to run a clustering algorithm, using the Python library Scikit-learn. Specifically, it creates a data matrix based on the operator's specialized skills and applies K-Means clustering to match operators who belong to the same cluster.

[0740] 3. Automatic Meeting Scheduling

[0741] Once matching is complete, the server uses the schedule data to find the earliest common free time and automatically schedules the meeting, using time data retrieved from the company's internal calendar system (e.g., Google Calendar API).

[0742] 4. Collecting and storing feedback

[0743] After the meeting, the server collects feedback from participants and stores it in a database. The feedback form used at this stage is implemented, for example, as a web application (using Flask). The feedback is later analyzed to improve the system and provide new suggestions.

[0744] 5. Hardware and Software Used

[0745] The system is implemented using the following hardware and software:

[0746] Hardware: Smartphones, smart glasses, head-mounted displays

[0747] Software: Python, Flask, SQLite, Scikit-learn

[0748] 6. Specific Examples

[0749] For example, if there is Engineer A in charge of robot maintenance in a factory and Engineer B, a new employee interested in the same field, the server clusters their data and confirms that they belong to the same cluster. It then finds a common free time and automatically schedules a meeting. It then uses the feedback collected after the meeting to make future improvements.

[0750] Example prompt (input for generative AI model)

[0751] "This application is designed for factory robot operators. It collects information about the operators' job functions, specialized skills, and job titles, matches operators with common areas of interest, and schedules meetings for information exchange. Specifically, it analyzes the operator data using K-Means clustering, finds the best pairs, and schedules meetings. It also collects feedback to help with future improvements."

[0752] This system will promote efficient information sharing among robot operators within the factory, contributing to the improvement of knowledge and skills.

[0753] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0754] Step 1:

[0755] The server collects employee job information, specialized skills, and position information from the company's internal database. The input for data collection is the access privileges of the company's existing information systems and databases. The output is a set of job information, specialized skills, and position information organized for each employee. When collecting data, SQL queries are used to extract the necessary data and store it in an SQLite database.

[0756] Step 2:

[0757] The server applies a clustering algorithm based on the collected job information, specialized skills, and position information. The employee dataset collected in step 1 is used as input. The output is the results of employees being divided into clusters based on their common areas of interest. For clustering, Python's Scikit-learn library is used to perform K-Means clustering. Specifically, the employee specialized skills are vectorized, a data matrix is ​​created, and then clustering is performed.

[0758] Step 3:

[0759] The server matches employees with common areas of interest based on the clustered data. The input is the clustering results from step 2. The output is a list of matched employee pairs. Specifically, employees belonging to the same cluster are paired together, and each pair is listed.

[0760] Step 4:

[0761] The server automatically schedules meetings between matched employees based on the schedule data. The input is a pair list of matched employees and each employee's free time data. The output is a list of scheduled meeting dates and times. Specifically, the server retrieves each employee's schedule from the company's internal calendar system (e.g., Google Calendar API), finds the earliest common free time, and schedules the meeting.

[0762] Step 5:

[0763] The server collects and stores feedback from employees after the meeting ends. The input is the ratings and comments of employees who attended the meeting. The output is the aggregated feedback data. Feedback is collected through a web application (e.g., created using Flask) and stored in a database. Specifically, a feedback form is provided, the ratings and comments entered by employees are collected, and the data is stored in an SQL database.

[0764] Examples of prompt statements used:

[0765] "This application is designed for factory robot operators. It collects information about the operators' job functions, specialized skills, and job titles, matches operators with common areas of interest, and schedules meetings for information exchange. Specifically, it analyzes the operator data using K-Means clustering, finds the best pairs, and schedules meetings. It also collects feedback to help with future improvements."

[0766] Following these steps not only enables efficient information sharing among employees and robot operators, but also allows for continuous system improvement through feedback after meetings.

[0767] 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.

[0768] The present invention is a system that collects employee job information, specialized skills, and position information, matches employees with common areas of interest based on that information, and automatically schedules meetings. Furthermore, the system also supports a function that collects and saves feedback on the results of meetings, and an emotion engine that recognizes employee emotions. Below, specific embodiments of the present invention will be described.

[0769] First, the server collects employee job information, specialized skills, and position information. This information is extracted from the company's database and centrally managed on the server. Employee information includes details such as the work they are responsible for, their specialized skills, and their position.

[0770] The server then analyzes this collected information and matches employees with common interests, such as an engineer interested in AI technology with a marketing staff member. This matching process is carried out using pre-defined rules and AI algorithms.

[0771] After a match is made, the server will compare the employees' free time slots to automatically schedule a meeting, choosing the earliest common free time slot to schedule the meeting.

[0772] Furthermore, the present invention uses an emotion engine. The emotion engine recognizes employees' emotional states in real time and collects that data. For example, it senses the emotional state of employees during a meeting and sends that information to a server. This allows employee emotional data to be used for meeting matching and feedback.

[0773] After the meeting, the server collects employee feedback and stores it in a database. The function save_meeting_feedback centralizes the feedback and sentiment data. This feedback can be used to improve the matching algorithm and ensure the success of the project.

[0774] For example, to set up a meeting between an engineer and a marketing staff member, the server analyzes their professional skills and job information. If a common area of ​​interest is found, the server schedules the meeting based on their availability. During the meeting, an emotion engine monitors the employee's emotions and sends appropriate emotion data to the server. After the meeting, feedback and emotion data from the employees are collected and used to improve the system in the future.

[0775] As a result, the system of the present invention efficiently matches different employees within a company, promoting interaction, and by using an emotion engine, providing a higher quality meeting experience. Using this system also makes effective use of space such as office lounges, increasing opportunities for innovation.

[0776] The processing flow will be explained below.

[0777] Step 1:

[0778] The server collects employee job information, expertise, and position information from a database, which includes information entered by each employee or extracted from the company's human resources system, and then centrally manages this information.

[0779] Step 2:

[0780] The server analyzes the collected information to find employees with common interests and expertise. At this stage, the match_employees function is used to match employees with common skill sets. The server pairs employees with matching skills and interests.

[0781] Step 3:

[0782] The server retrieves the schedules of the matched employees and compares their free time. It then uses the create_meeting function to identify the earliest common free time and schedule a meeting at that time. The meeting date, time, and attendee names are automatically set.

[0783] Step 4:

[0784] The user receives a meeting notification. The server sends the details of the scheduled meeting to the user's device. The notification includes the meeting date, time, location, and attendee information.

[0785] Step 5:

[0786] When a meeting is scheduled, the device activates an emotion engine that monitors employees' emotional states in real time and collects data, such as tone of voice and facial expression recognition technology, to perform emotion analysis.

[0787] Step 6:

[0788] The server receives the emotion data sent from the emotion engine and associates it with the meeting situation and feedback. This emotion data is used to evaluate the atmosphere of the meeting and the reactions of the participants.

[0789] Step 7:

[0790] Users provide feedback after the meeting. The server saves the feedback and sentiment data to a database using the save_meeting_feedback function, allowing us to determine the effectiveness of the meeting and the satisfaction of the participants.

[0791] Step 8:

[0792] The server analyzes the collected feedback and sentiment data to improve the matching algorithm and system in the future, which will help set up future meetings more effectively and further promote interaction between employees.

[0793] Example 2

[0794] 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."

[0795] It was difficult to promote efficient communication between employees and effectively match employees with common interests. Furthermore, to improve the quality of meetings, there was also a need to understand employee sentiment in real time and reflect it in feedback. Conventional systems were unable to meet these requirements, and further technological improvements were necessary.

[0796] 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.

[0797] In this invention, the server includes means for collecting employee work information, expertise, and job title information, means for matching employees with common areas of interest based on the collected work information, expertise, and job title information, means for automatically scheduling a meeting between the matched employees, means for collecting and saving evaluations of the results of the meeting, and means for collecting emotional data during the meeting using an emotion engine that recognizes the emotional states of employees. This enables effective matching based on common areas of interest between employees, understanding of their emotional states during the meeting, and reflecting that in feedback.

[0798] "Business information" refers to the job duties that employees perform within a company and detailed information related to those jobs.

[0799] "Expertise" refers to an employee's specific techniques and skills, as well as their experience and knowledge in that field.

[0800] "Position information" is information related to the position or role that an employee holds within a company.

[0801] "Matching" is the process of pairing employees with common areas of interest.

[0802] "Schedule" means setting up a meeting or event for a specific date and time.

[0803] "Evaluation" refers to employees' feedback and thoughts on the results and progress of the meeting.

[0804] The "emotion engine" is a system that has the ability to recognize and digitize the emotional state of employees in real time.

[0805] "Feedback" refers to the opinions and thoughts employees provide after a meeting, which the system collects and uses to improve.

[0806] "Free time" refers to free time in an employee's schedule that does not have other commitments.

[0807] The present invention is a system that collects employee work information, expertise, and job title information, matches employees with common areas of interest based on this information, and automatically schedules meetings. Furthermore, the system also supports a function that collects and stores feedback on the results of meetings, and a system that combines an emotion engine that recognizes employee emotions. A specific embodiment of the present invention will be described below.

[0808] First, the server collects employee information, expertise, and job titles from the company's database using API calls. Specifically, it obtains employee names, job responsibilities, expertise, and job titles. This information is then centrally managed on the server.

[0809] The server then analyzes this collected information and matches employees with common interests using AI algorithms that apply pre-defined rules and machine learning models to classify employees' expertise and areas of interest and find suitable pairs.

[0810] After a match is made, the server retrieves the employee's calendar information and searches for a common free time. It automatically schedules a meeting based on the earliest free time. It also retrieves the calendar information using the fetch_calendar_data function and schedules the meeting at the most appropriate time using the schedule_meeting function.

[0811] Furthermore, the present invention uses an emotion engine. The emotion engine monitors the emotional state of employees in real time and collects the data. The emotion data acquired through the terminal is sent to the server in real time. For example, if an employee is "nervous" during a meeting, the data is sent to the server.

[0812] The server analyzes this emotional data and reflects it in meeting matching and feedback. After the meeting ends, the server collects feedback from employees and saves it in a database. By using the save_meeting_feedback function, the feedback content and emotional data are managed centrally.

[0813] For example, to set up a meeting between an engineer and a marketing person, the server analyzes their expertise and work information. If a common area of ​​interest is found, the server schedules the meeting based on the availability of both parties. For example, the meeting is set for next Tuesday at 2:00 PM. During the meeting, the emotion engine monitors employees' emotions, and if it detects "tension," it sends that information to the server. After the meeting, feedback from the engineer and marketing person is collected and used to improve the system in the future.

[0814] Example prompts to input to a generative AI model:

[0815] text

[0816] prompt:

[0817] Please explain the specific steps of the system that collects employee information, expertise, and job titles, matches employees with common interests based on that information, and automatically schedules meetings. Also, please explain in detail how the system incorporates an emotion engine to collect and utilize real-time emotion data.

[0818] The system of the present invention efficiently matches different employees, promotes interaction, and provides a high-quality meeting experience by using an emotion engine. Utilizing this system is expected to increase the effective use of space within a company and opportunities for innovation.

[0819] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0820] Step 1: Gather information

[0821] Server: The server uses an API to collect employee job information, expertise, and job title information from the company database. Specifically, it uses the API call get_employee_data. The input to this API call is the database connection information and query, and the output is a list of employee details. The server manages this information centrally.

[0822] Input: Database connection information and query

[0823] Output: Employee details (job description, expertise, job title)

[0824] Step 2: Information analysis and matching

[0825] Server: The server analyzes the collected employee information and matches employees with common areas of interest. This is done using AI algorithms and machine learning models. Specifically, it uses the analyze_and_match function. The input to this function is a list of employee information, and the output is matched employee pairs.

[0826] Input: List of employee information

[0827] Output: Matched employee pairs

[0828] Step 3: Schedule a meeting

[0829] Server: The server retrieves the calendar information of the matched employees, finds the earliest common free time, and schedules a meeting. Specifically, it uses the fetch_calendar_data and schedule_meeting functions. The input of each function is the API call information to the calendar application and the matched employee pair. The output is the set meeting date.

[0830] Input: Calendar API call information, matched employee pairs

[0831] Output: Meeting dates set

[0832] Step 4: Use the Emotion Engine

[0833] Terminal: The terminal uses the emotion engine to collect employee emotion data in real time. Specifically, it uses the monitor_emotions function. The input of this function is the terminal's sensor information and employee data, and the output is the collected emotion data. The terminal then sends this emotion data to the server.

[0834] Input: Device sensor information, employee data

[0835] Output: Collected emotion data

[0836] Step 5: Collect and store feedback

[0837] Server: The server collects feedback from employees after the meeting ends by using the request_feedback and save_meeting_feedback functions. The inputs to these functions are the meeting details and the feedback provided by the employees, and the output is the feedback data stored in the database.

[0838] Input: Meeting details, feedback data

[0839] Output: Stored feedback data (ratings and sentiment data)

[0840] This allows for an efficient process of collecting information, matching, scheduling meetings, monitoring emotions in real time, and collecting and storing feedback.

[0841] (Application example 2)

[0842] 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."

[0843] Modern factories are required to have highly specialized robots working together to perform a wide variety of tasks. However, it is difficult to properly match these robots and to schedule tasks optimally so that they can work together efficiently. Furthermore, there is a lack of a system for monitoring each robot's performance and operating status in real time and utilizing feedback. This makes it difficult to improve work efficiency and detect defects early.

[0844] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting job information, specialized skills, and position information of workers, means for matching workers with common areas of interest based on the collected job information, specialized skills, and position information, means for automatically scheduling collaborative tasks between the matched workers, means for collecting and saving feedback on the results of the collaborative tasks, and means for monitoring the movements and performance of workers in real time and collecting that data. This enables efficient collaboration and task scheduling of robots, as well as real-time movement monitoring and feedback collection.

[0845] A "worker" is a robot or machine that performs a specific role or task in a factory or industrial facility.

[0846] "Job information" is data indicating the tasks and work content that a worker is responsible for.

[0847] "Specialized skills" is data that indicates the specific skills and abilities that a worker possesses.

[0848] "Position information" is data relating to the position and role of a worker.

[0849] "Common areas of interest" refer to the business or technical interests that multiple workers share in common.

[0850] "Matching" is the process of pairing workers with common goals and interests based on collected data.

[0851] A "collaborative task" is a task or project that is carried out by multiple workers together.

[0852] "Automatically scheduling" means that software or a server schedules tasks or meetings without human intervention.

[0853] "Feedback" refers to information and opinions obtained as a result of or during a collaborative task.

[0854] "Monitoring operations and performance in real time" refers to monitoring the movements of workers and work results in real time.

[0855] "Collecting data" means obtaining information from various sensors and monitoring systems, and storing and organizing it.

[0856] The present invention is a system for automatically matching and scheduling efficient collaborative tasks among workers in a factory, and for monitoring their behavior and performance in real time. This system has the function of collecting job information, specialized skills, and position information of each worker, and matching workers who share common areas of interest based on this information. The following describes an embodiment of the present invention.

[0857] First, the server collects information on the worker's job, specialized skills, and position. This information is obtained from databases and sensor systems within the factory and centrally managed on the server. Worker information includes details such as the process they are responsible for, their specialized skills, and their position.

[0858] The server then analyzes the collected information and matches workers with common interests. This matching process is carried out using pre-defined rules and AI algorithms. For example, a worker with welding expertise can be paired with another worker who also has an interest in welding technology.

[0859] After matching is established, the server automatically schedules collaborative tasks, comparing the working hours of the workers and scheduling collaborative tasks based on the earliest working time, thus enabling efficient task execution.

[0860] Furthermore, the present invention uses an emotion engine that monitors the worker's actions and performance in real time. The emotion engine recognizes the worker's actions and performance in real time and sends the data to the server. This allows the worker to grasp the problems and efficiency of the work in real time.

[0861] After a collaborative task is completed, the server collects feedback from the workers and stores it in a database. This feedback can later be used to improve the system and optimize the matching algorithm. It also combines the feedback with real-time collected behavior data to make the next collaboration more efficient.

[0862] As a concrete example, the server sets up a collaborative task between worker A, who has welding skills, and worker B, who is interested in welding technology. To perform the welding work together, a schedule is automatically set based on the working hours of both workers. During the work, the emotion engine monitors the behavior and sends the data to the server. After the work is completed, feedback and monitoring data are collected and used to optimize the next collaborative task.

[0863] An example of a specific prompt is as follows:

[0864] robot_data = [

[0865] {"id": 1, "skill": "welding", "performance": 90},

[0866] {"id": 2, "skill": "assembly", "performance": 85},

[0867] Other robot data

[0868] ]

[0869] matched_pairs = match_robots(robot_data)

[0870] Example output: [({"id": 1, "skill": "welding", "performance": 90}, {"id": 3, "skill": "welding", "performance": 88})]

[0871] schedule_tasks(matched_pairs)

[0872] Example output: Scheduled Task: {'robots': [1, 3], 'task': 'welding', 'schedule_time': '2023-10-03 14:00:00'}

[0873] feedback = collect_feedback()

[0874] Example output: Collected Feedback: {"performance": 95, "issues": null}

[0875] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0876] Step 1:

[0877] The server collects information on the worker's job, specialized skills, and position. This information is obtained from the factory's database and sensor system. For example, each robot's ID, specialized skill (welding, assembly, etc.), and current performance data (such as task success rate) are extracted from the database and centrally managed.

[0878] Step 2:

[0879] The server analyzes the collected job information, expertise, and job title information, and uses AI algorithms to process the data and match workers with common interests, specifically pairing robots with the same expertise or complementary skills.

[0880] Step 3:

[0881] The server compares the working hours of the matched robots and automatically schedules collaborative tasks based on the earliest working time. The scheduling is calculated based on the free time data of each robot, and a schedule table is generated as a result.

[0882] Step 4:

[0883] When a collaborative task is being carried out, the server monitors the robot's behavior and performance in real time. Using an emotion engine, the server collects and transmits each robot's behavior and performance data to the server. For example, the server monitors the robot's speed, success rate, and error frequency.

[0884] Step 5:

[0885] After a collaborative task is completed, the server collects feedback from the workers, including evaluations of the work, issues identified, and suggestions for improvement. The feedback is stored in a database and used to optimize the next collaborative task.

[0886] Step 6:

[0887] The server analyzes the collected feedback and real-time behavioral data to improve the system and optimize the matching algorithm, so that the next collaborative task will be performed more efficiently and effectively. The analysis results are used to adjust the algorithm and update parameters.

[0888] Step 7:

[0889] If necessary, the server uses this data to update the generative AI model to provide more accurate matching and scheduling by inputting new data sets into the generative AI model and training the algorithm.

[0890] An example prompt would be:

[0891] robot_data = [

[0892] {"id": 1, "skill": "welding", "performance": 90},

[0893] {"id": 2, "skill": "assembly", "performance": 85},

[0894] Other robot data

[0895] ]

[0896] matched_pairs = match_robots(robot_data)

[0897] Example output: [({"id": 1, "skill": "welding", "performance": 90}, {"id": 3, "skill": "welding", "performance": 88})]

[0898] schedule_tasks(matched_pairs)

[0899] Example output: Scheduled Task: {'robots': [1, 3], 'task': 'welding', 'schedule_time': '2023-10-03 14:00:00'}

[0900] feedback = collect_feedback()

[0901] Example output: Collected Feedback: {"performance": 95, "issues": null}

[0902] 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.

[0903] 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.

[0904] 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.

[0905] [Fourth embodiment]

[0906] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0907] 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.

[0908] 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).

[0909] 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.

[0910] 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.

[0911] 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).

[0912] 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.

[0913] 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.

[0914] 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.

[0915] 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.

[0916] 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.

[0917] 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.

[0918] 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."

[0919] The present invention is a system that collects employee job information, specialized skills, and position information, matches employees with common areas of interest, and automatically schedules meetings. It also includes a function for collecting and saving feedback on the results of meetings. A specific embodiment of the present invention will be described below.

[0920] First, the server collects employee job information, specialized skills, and position information. This information is obtained from the company's internal database and analyzed by the server. Employee information, including the job duties, skills, and position, is stored in the database.

[0921] The server then uses the collected information to match employees with common interests, such as employees with the same specialized skills or complementary skills, with the matching process driven by pre-defined rules and AI algorithms.

[0922] Once matching is complete, the server automatically schedules a meeting between the matched employees. At this time, the employees' free time slots are compared and the earliest common free time is selected. Employees can also choose whether or not to participate in matching, allowing for flexible participation settings.

[0923] After the meeting is held, the server collects and stores feedback on the meeting results. This feedback is a means of collecting evaluations and comments from employees and is used as reference material for future improvements. The feedback is aggregated by the server and stored in a database.

[0924] For example, if a company's engineers and marketing staff are interested in AI technology and SEO strategies, respectively, the server will match them and schedule a meeting based on their availability. After the meeting, the server will collect feedback and use it for future projects.

[0925] In this way, the system of the present invention increases opportunities for innovation by making it easier for different types of employees within a company to meet and collaborate efficiently. Furthermore, it also makes more effective use of spaces such as office lounges that encourage employee interaction.

[0926] The processing flow will be explained below.

[0927] Step 1:

[0928] The server receives an employee ID from the user. It calls the get_employee_info function to retrieve the corresponding employee information from the database using this ID. The server searches for the job information, expertise, and position information of the employee that matches the ID and stores this information in memory.

[0929] Step 2:

[0930] The server performs a matching process based on the acquired employee information. Specifically, the server compares the job information and professional skills of other employees and analyzes them to identify common areas of interest and complementary skills. This analysis is performed using the match_employees function to find employees with common skills.

[0931] Step 3:

[0932] The server schedules meetings between successfully matched employee pairs. It uses the create_meeting function to compare the availability of both parties and identify the earliest common available time. Based on this time, the meeting details are set.

[0933] Step 4:

[0934] The user receives notifications from the server of matches and scheduled meetings, including the date and time of the meeting, the names of the employees they will be interacting with, and other relevant information.

[0935] Step 5:

[0936] The server collects feedback from employees after the meeting has taken place and saves it to the database using the save_meeting_feedback function, which will be used to improve the matching algorithm and progress the project in the future.

[0937] Step 6:

[0938] Users submit their feedback and opinions to the server, which aggregates the feedback through the system's rating mechanism and analyzes it on the server.

[0939] Step 7:

[0940] Based on the collected feedback, the server will improve the system and develop new matching algorithms, which will improve the accuracy of future matches and more effectively promote employee interaction and generate innovation.

[0941] Example 1

[0942] 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."

[0943] Modern companies have a large number of employees with diverse job functions and specialized skills, and efficient talent matching is essential. However, manually collecting employee information, creating appropriate pairs, and scheduling meetings is extremely time-consuming and labor-intensive. Furthermore, there is a lack of a system for properly collecting and saving feedback on meeting results, making it difficult to identify areas for improvement or collect reference materials for future use. This creates problems that delay the efficiency of internal communication and the promotion of collaboration among employees.

[0944] 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.

[0945] In this invention, the server includes means for collecting employee job information, specialized skills, and position information, means for analyzing the collected job information, specialized skills, and position information and storing it in a database, means for matching employees with common areas of interest based on preset rules and AI algorithms, means for automatically scheduling meetings between matched employees and obtaining employee free time and setting the earliest common free time, and means for collecting feedback from employees on the meeting results and storing it in a database, thereby enabling efficient matching between employees, automating meetings, and systematically collecting and storing feedback.

[0946] "Employee job information" is data related to the job content and role that an employee is responsible for within the company.

[0947] "Specialized skills" refers to information about the specific knowledge and skills that an employee has acquired.

[0948] "Position information" is information relating to an employee's position or status within the company.

[0949] "Means of collection" refers to the methods and devices used to extract and collect the necessary data.

[0950] "Means for analysis and storage" are methods or devices that process collected data, convert it into an understandable form, and then record it.

[0951] A "matching means" is a method or device for finding suitable matches based on specific criteria.

[0952] A "scheduling means" is a method or device for planning, coordinating, and determining the date and time of a particular event or activity.

[0953] The "means for obtaining available time" refers to a method or device for checking and extracting the available time of each employee.

[0954] "Feedback collection and storage means" refers to the methods and devices used to collect and record employee evaluations and opinions.

[0955] The present invention is a system that collects employee job information, specialized skills, and position information, matches employees with common areas of interest based on this data, and automatically schedules meetings. It also includes a function to collect and save feedback on the results of the meetings. This system is realized through the following processing steps.

[0956] The server collects employee job information, specialized skills, and position information. This information is collected using an internal company database, such as MySQL or PostgreSQL. The server extracts the information from the database, analyzes it using Python's Pandas library, and saves it in the database. This allows detailed information such as employee responsibilities, skills, and position to be organized.

[0957] The server then analyzes the collected information and matches employees with common interests. This process is performed using pre-defined rules and AI algorithms (e.g., Scikit-learn and TensorFlow). Specifically, the server uses a clustering algorithm to group employees' skills and interests, and pairs employees in the same cluster with each other.

[0958] The server automatically schedules meetings between matched employees. At this time, the server uses Microsoft Exchange Server or Google Calendar API to obtain employees' free time. It selects the earliest common free time and automatically schedules the meeting. Employees can also choose to participate in the schedule using the ON / OFF function.

[0959] After the meeting is held, the server collects feedback from employees through a dedicated web form. This web form is built using HTML and JavaScript. The collected feedback is stored in a database and used as information for future improvements and refinements. For example, a web framework such as Django is used for this storage.

[0960] As a concrete example, if engineer A at a company is interested in AI technology and marketing staff member B is interested in SEO strategy, the server retrieves their information from the database and matches them using an AI algorithm. It then retrieves their free time slots and schedules a meeting for the earliest common free time. After the meeting, B enters their evaluation and comments into a web form and provides feedback to the server, contributing to improvements to the overall system.

[0961] An example prompt might be, "We want to develop a new meeting system. The system will collect employee job information, professional skills, and position information, and match employees with common interests based on this data. It will then automatically schedule meetings and collect and store feedback on the meeting results. Please write program code that describes this process in detail."

[0962] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0963] Step 1:

[0964] Collection of employee information

[0965] The server collects employee job information, expertise, and position information from the company's database. It queries the database and executes SQL queries to retrieve employee information. The input is the database connection information and the required query syntax, and the output is a set of employee information.

[0966] Specifically, the server executes the following SQL query:

[0967] SELECT FROM employee_data;

[0968] The retrieved data is converted to a Pandas DataFrame.

[0969] Step 2:

[0970] Data analysis and storage

[0971] The server analyzes the acquired employee information and stores it in a database. The input is employee information in DataFrame format, and the output is the analyzed results stored in the database. Specific analysis processes include data cleaning and extraction of specific columns. After analysis, the information is stored in a separate table.

[0972] Specifically, it uses Pandas to clean the data.

[0973] python

[0974] import pandas as pd

[0975] df = pd.DataFrame(data)

[0976] Data cleaning and analysis

[0977] df_cleaned = df.dropna().query('role != "intern"')

[0978] df_cleaned.to_sql('parsed_employee_data', con=engine, if_exists='replace')

[0979] Step 3:

[0980] Setting matching conditions

[0981] The server uses an AI algorithm to set the conditions for matching employees. The input is the analyzed employee data, and the output is the cluster information for each employee. Specifically, clustering is performed using Scikit-learn's KMeans algorithm.

[0982] Specifically, the KMeans algorithm is applied as follows:

[0983] python

[0984] from sklearn.cluster import KMeans

[0985] kmeans = KMeans(n_clusters=5).fit(df_cleaned)

[0986] clusters = kmeans.labels_

[0987] df_cleaned['cluster'] = clusters

[0988] Step 4:

[0989] Scheduling a Meeting

[0990] The server schedules meetings between matching employees. The input is a list of matches and the employees' calendar information, and the output is the scheduled meeting details. The server uses the Google Calendar API to get the employees' free time and schedules the meeting at the earliest common free time.

[0991] Specifically, it uses the Google Calendar API to obtain available time.

[0992] python

[0993] from googleapiclient.discovery import build

[0994] service = build('calendar', 'v3', credentials=creds)

[0995] events = service.events().list(calendarId='primary').execute()

[0996] common_free_time = find_common_time(events)

[0997] schedule_meeting(common_free_time)

[0998] Step 5:

[0999] Collecting and storing feedback

[1000] The server collects feedback from employees after the meeting and stores it in a database. The input is the feedback entered by employees through a web form, and the output is the feedback data stored in the database.

[1001] Specifically, the user enters feedback into a web form.

[1002] html

[1003] <form action=" / submit_feedback" method="post">

[1004] <textarea name="feedback" rows="4" cols="50">< / textarea>

[1005] <input type="submit" value="Submit">

[1006] < / form>

[1007] Feedback is collected on the server side and stored in a database.

[1008] python

[1009] from django.shortcuts import render

[1010] from .models import Feedback

[1011] def submit_feedback(request):

[1012] if request.method == 'POST':

[1013] feedback = request.POST['feedback']

[1014] Feedback.objects.create(content=feedback)

[1015] return render(request, 'thank_you.html')

[1016] (Application example 1)

[1017] 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."

[1018] To facilitate knowledge sharing and collaboration among employees within a company, a system is needed that allows employees with similar expertise and interests to naturally meet, exchange information, and collaborate. However, manually matching employees and scheduling meetings is time-consuming and inefficient. Furthermore, there is a lack of a system for efficiently collecting feedback after meetings and using it to improve operations. Furthermore, information sharing between robot operators is important in the field, and there is a need for an efficient method for this process that utilizes smartphones and head-mounted displays.

[1019] 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.

[1020] In this invention, the server includes a means for collecting employee job information, specialized skills, and position information, a means for matching employees with common areas of interest based on the collected job information, specialized skills, and position information, a means for automatically scheduling meetings between the matched employees, a means for collecting and storing feedback on the results of the meetings, a means for using a clustering algorithm to analyze operator data, and a means for finding optimal pairs according to a specified algorithm. This enables efficient matching between employees and robot operators with common areas of interest and scheduling of meetings. In addition, continuous system improvement is achieved through the collection of feedback.

[1021] "Employee job information" is information relating to the work content and role that an employee is responsible for within a company.

[1022] "Specialized skills" refers to the skills and knowledge an employee possesses in a specific field.

[1023] "Position information" is information about an employee's current position or title.

[1024] "Means of collection" refers to a method for obtaining employee job information, specialized skills, and position information using a server or database.

[1025] "Matching methods" are methods for matching employees with common areas of interest based on collected information.

[1026] A "scheduling method" is a method for automatically scheduling and scheduling meetings between matched employees.

[1027] "Means for collecting and storing feedback" refers to the method for collecting evaluations and comments from employees after the meeting and storing that data.

[1028] A "clustering algorithm" is a mathematical and statistical method used to analyze data and separate it into groups that share common characteristics.

[1029] The "means for finding the best pair" is a method for selecting the best pair to be matched based on the results of the clustering algorithm.

[1030] This invention is a system that collects employee job information, specialized skills, and position information, performs matching, automatic scheduling, and feedback collection, and particularly supports efficient information sharing among robot operators within factories.

[1031] 1. System Configuration

[1032] The server collects and analyzes employee job information, specialized skills, and position information from the company's internal database. The collected data is stored in, for example, an SQLite database. Data such as the operator's specialized skills and job information is analyzed using a clustering algorithm (e.g., K-Means clustering), and operators who share common areas of interest are automatically matched.

[1033] 2. Data analysis and matching

[1034] The server uses the collected data to run a clustering algorithm, using the Python library Scikit-learn. Specifically, it creates a data matrix based on the operator's specialized skills and applies K-Means clustering to match operators who belong to the same cluster.

[1035] 3. Automatic Meeting Scheduling

[1036] Once matching is complete, the server uses the schedule data to find the earliest common free time and automatically schedules the meeting, using time data retrieved from the company's internal calendar system (e.g., Google Calendar API).

[1037] 4. Collecting and storing feedback

[1038] After the meeting, the server collects feedback from participants and stores it in a database. The feedback form used at this stage is implemented, for example, as a web application (using Flask). The feedback is later analyzed to improve the system and provide new suggestions.

[1039] 5. Hardware and Software Used

[1040] The system is implemented using the following hardware and software:

[1041] Hardware: Smartphones, smart glasses, head-mounted displays

[1042] Software: Python, Flask, SQLite, Scikit-learn

[1043] 6. Specific Examples

[1044] For example, if there is Engineer A in charge of robot maintenance in a factory and Engineer B, a new employee interested in the same field, the server clusters their data and confirms that they belong to the same cluster. It then finds a common free time and automatically schedules a meeting. It then uses the feedback collected after the meeting to make future improvements.

[1045] Example prompt (input for generative AI model)

[1046] "This application is designed for factory robot operators. It collects information about the operators' job functions, specialized skills, and job titles, matches operators with common areas of interest, and schedules meetings for information exchange. Specifically, it analyzes the operator data using K-Means clustering, finds the best pairs, and schedules meetings. It also collects feedback to help with future improvements."

[1047] This system will promote efficient information sharing among robot operators within the factory, contributing to the improvement of knowledge and skills.

[1048] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1049] Step 1:

[1050] The server collects employee job information, specialized skills, and position information from the company's internal database. The input for data collection is the access privileges of the company's existing information systems and databases. The output is a set of job information, specialized skills, and position information organized for each employee. When collecting data, SQL queries are used to extract the necessary data and store it in an SQLite database.

[1051] Step 2:

[1052] The server applies a clustering algorithm based on the collected job information, specialized skills, and position information. The employee dataset collected in step 1 is used as input. The output is the results of employees being divided into clusters based on their common areas of interest. For clustering, Python's Scikit-learn library is used to perform K-Means clustering. Specifically, the employee specialized skills are vectorized, a data matrix is ​​created, and then clustering is performed.

[1053] Step 3:

[1054] The server matches employees with common areas of interest based on the clustered data. The input is the clustering results from step 2. The output is a list of matched employee pairs. Specifically, employees belonging to the same cluster are paired together, and each pair is listed.

[1055] Step 4:

[1056] The server automatically schedules meetings between matched employees based on the schedule data. The input is a pair list of matched employees and each employee's free time data. The output is a list of scheduled meeting dates and times. Specifically, the server retrieves each employee's schedule from the company's internal calendar system (e.g., Google Calendar API), finds the earliest common free time, and schedules the meeting.

[1057] Step 5:

[1058] The server collects and stores feedback from employees after the meeting ends. The input is the ratings and comments of employees who attended the meeting. The output is the aggregated feedback data. Feedback is collected through a web application (e.g., created using Flask) and stored in a database. Specifically, a feedback form is provided, the ratings and comments entered by employees are collected, and the data is stored in an SQL database.

[1059] Examples of prompt statements used:

[1060] "This application is designed for factory robot operators. It collects information about the operators' job functions, specialized skills, and job titles, matches operators with common areas of interest, and schedules meetings for information exchange. Specifically, it analyzes the operator data using K-Means clustering, finds the best pairs, and schedules meetings. It also collects feedback to help with future improvements."

[1061] Following these steps not only enables efficient information sharing among employees and robot operators, but also allows for continuous system improvement through feedback after meetings.

[1062] 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.

[1063] The present invention is a system that collects employee job information, specialized skills, and position information, matches employees with common areas of interest based on that information, and automatically schedules meetings. Furthermore, the system also supports a function that collects and saves feedback on the results of meetings, and an emotion engine that recognizes employee emotions. Below, specific embodiments of the present invention will be described.

[1064] First, the server collects employee job information, specialized skills, and position information. This information is extracted from the company's database and centrally managed on the server. Employee information includes details such as the work they are responsible for, their specialized skills, and their position.

[1065] The server then analyzes this collected information and matches employees with common interests, such as an engineer interested in AI technology with a marketing staff member. This matching process is carried out using pre-defined rules and AI algorithms.

[1066] After a match is made, the server will compare the employees' free time slots to automatically schedule a meeting, choosing the earliest common free time slot to schedule the meeting.

[1067] Furthermore, the present invention uses an emotion engine. The emotion engine recognizes employees' emotional states in real time and collects that data. For example, it senses the emotional state of employees during a meeting and sends that information to a server. This allows employee emotional data to be used for meeting matching and feedback.

[1068] After the meeting, the server collects employee feedback and stores it in a database. The function save_meeting_feedback centralizes the feedback and sentiment data. This feedback can be used to improve the matching algorithm and ensure the success of the project.

[1069] For example, to set up a meeting between an engineer and a marketing staff member, the server analyzes their professional skills and job information. If a common area of ​​interest is found, the server schedules the meeting based on their availability. During the meeting, an emotion engine monitors the employee's emotions and sends appropriate emotion data to the server. After the meeting, feedback and emotion data from the employees are collected and used to improve the system in the future.

[1070] As a result, the system of the present invention efficiently matches different employees within a company, promoting interaction, and by using an emotion engine, providing a higher quality meeting experience. Using this system also makes effective use of space such as office lounges, increasing opportunities for innovation.

[1071] The processing flow will be explained below.

[1072] Step 1:

[1073] The server collects employee job information, expertise, and position information from a database, which includes information entered by each employee or extracted from the company's human resources system, and then centrally manages this information.

[1074] Step 2:

[1075] The server analyzes the collected information to find employees with common interests and expertise. At this stage, the match_employees function is used to match employees with common skill sets. The server pairs employees with matching skills and interests.

[1076] Step 3:

[1077] The server retrieves the schedules of the matched employees and compares their free time. It then uses the create_meeting function to identify the earliest common free time and schedule a meeting at that time. The meeting date, time, and attendee names are automatically set.

[1078] Step 4:

[1079] The user receives a meeting notification. The server sends the details of the scheduled meeting to the user's device. The notification includes the meeting date, time, location, and attendee information.

[1080] Step 5:

[1081] When a meeting is scheduled, the device activates an emotion engine that monitors employees' emotional states in real time and collects data, such as tone of voice and facial expression recognition technology, to perform emotion analysis.

[1082] Step 6:

[1083] The server receives the emotion data sent from the emotion engine and associates it with the meeting situation and feedback. This emotion data is used to evaluate the atmosphere of the meeting and the reactions of the participants.

[1084] Step 7:

[1085] Users provide feedback after the meeting. The server saves the feedback and sentiment data to a database using the save_meeting_feedback function, allowing us to determine the effectiveness of the meeting and the satisfaction of the participants.

[1086] Step 8:

[1087] The server analyzes the collected feedback and sentiment data to improve the matching algorithm and system in the future, which will help set up future meetings more effectively and further promote interaction between employees.

[1088] Example 2

[1089] 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."

[1090] It was difficult to promote efficient communication between employees and effectively match employees with common interests. Furthermore, to improve the quality of meetings, there was also a need to understand employee sentiment in real time and reflect it in feedback. Conventional systems were unable to meet these requirements, and further technological improvements were necessary.

[1091] 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.

[1092] In this invention, the server includes means for collecting employee work information, expertise, and job title information, means for matching employees with common areas of interest based on the collected work information, expertise, and job title information, means for automatically scheduling a meeting between the matched employees, means for collecting and saving evaluations of the results of the meeting, and means for collecting emotional data during the meeting using an emotion engine that recognizes the emotional states of employees. This enables effective matching based on common areas of interest between employees, understanding of their emotional states during the meeting, and reflecting that in feedback.

[1093] "Business information" refers to the job duties that employees perform within a company and detailed information related to those jobs.

[1094] "Expertise" refers to an employee's specific techniques and skills, as well as their experience and knowledge in that field.

[1095] "Position information" is information related to the position or role that an employee holds within a company.

[1096] "Matching" is the process of pairing employees with common areas of interest.

[1097] "Schedule" means setting up a meeting or event for a specific date and time.

[1098] "Evaluation" refers to employees' feedback and thoughts on the results and progress of the meeting.

[1099] The "emotion engine" is a system that has the ability to recognize and digitize the emotional state of employees in real time.

[1100] "Feedback" refers to the opinions and thoughts employees provide after a meeting, which the system collects and uses to improve.

[1101] "Free time" refers to free time in an employee's schedule that does not have other commitments.

[1102] The present invention is a system that collects employee work information, expertise, and job title information, matches employees with common areas of interest based on this information, and automatically schedules meetings. Furthermore, the system also supports a function that collects and stores feedback on the results of meetings, and a system that combines an emotion engine that recognizes employee emotions. A specific embodiment of the present invention will be described below.

[1103] First, the server collects employee information, expertise, and job titles from the company's database using API calls. Specifically, it obtains employee names, job responsibilities, expertise, and job titles. This information is then centrally managed on the server.

[1104] The server then analyzes this collected information and matches employees with common interests using AI algorithms that apply pre-defined rules and machine learning models to classify employees' expertise and areas of interest and find suitable pairs.

[1105] After a match is made, the server retrieves the employee's calendar information and searches for a common free time. It automatically schedules a meeting based on the earliest free time. It also retrieves the calendar information using the fetch_calendar_data function and schedules the meeting at the most appropriate time using the schedule_meeting function.

[1106] Furthermore, the present invention uses an emotion engine. The emotion engine monitors the emotional state of employees in real time and collects the data. The emotion data acquired through the terminal is sent to the server in real time. For example, if an employee is "nervous" during a meeting, the data is sent to the server.

[1107] The server analyzes this emotional data and reflects it in meeting matching and feedback. After the meeting ends, the server collects feedback from employees and saves it in a database. By using the save_meeting_feedback function, the feedback content and emotional data are managed centrally.

[1108] For example, to set up a meeting between an engineer and a marketing person, the server analyzes their expertise and work information. If a common area of ​​interest is found, the server schedules the meeting based on the availability of both parties. For example, the meeting is set for next Tuesday at 2:00 PM. During the meeting, the emotion engine monitors employees' emotions, and if it detects "tension," it sends that information to the server. After the meeting, feedback from the engineer and marketing person is collected and used to improve the system in the future.

[1109] Example prompts to input to a generative AI model:

[1110] text

[1111] prompt:

[1112] Please explain the specific steps of the system that collects employee information, expertise, and job titles, matches employees with common interests based on that information, and automatically schedules meetings. Also, please explain in detail how the system incorporates an emotion engine to collect and utilize real-time emotion data.

[1113] The system of the present invention efficiently matches different employees, promotes interaction, and provides a high-quality meeting experience by using an emotion engine. Utilizing this system is expected to increase the effective use of space within a company and opportunities for innovation.

[1114] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1115] Step 1: Gather information

[1116] Server: The server uses an API to collect employee job information, expertise, and job title information from the company database. Specifically, it uses the API call get_employee_data. The input to this API call is the database connection information and query, and the output is a list of employee details. The server manages this information centrally.

[1117] Input: Database connection information and query

[1118] Output: Employee details (job description, expertise, job title)

[1119] Step 2: Information analysis and matching

[1120] Server: The server analyzes the collected employee information and matches employees with common areas of interest. This is done using AI algorithms and machine learning models. Specifically, it uses the analyze_and_match function. The input to this function is a list of employee information, and the output is matched employee pairs.

[1121] Input: List of employee information

[1122] Output: Matched employee pairs

[1123] Step 3: Schedule a meeting

[1124] Server: The server retrieves the calendar information of the matched employees, finds the earliest common free time, and schedules a meeting. Specifically, it uses the fetch_calendar_data and schedule_meeting functions. The input of each function is the API call information to the calendar application and the matched employee pair. The output is the set meeting date.

[1125] Input: Calendar API call information, matched employee pairs

[1126] Output: Meeting dates set

[1127] Step 4: Use the Emotion Engine

[1128] Terminal: The terminal uses the emotion engine to collect employee emotion data in real time. Specifically, it uses the monitor_emotions function. The input of this function is the terminal's sensor information and employee data, and the output is the collected emotion data. The terminal then sends this emotion data to the server.

[1129] Input: Device sensor information, employee data

[1130] Output: Collected emotion data

[1131] Step 5: Collect and store feedback

[1132] Server: The server collects feedback from employees after the meeting ends by using the request_feedback and save_meeting_feedback functions. The inputs to these functions are the meeting details and the feedback provided by the employees, and the output is the feedback data stored in the database.

[1133] Input: Meeting details, feedback data

[1134] Output: Stored feedback data (ratings and sentiment data)

[1135] This allows for an efficient process of collecting information, matching, scheduling meetings, monitoring emotions in real time, and collecting and storing feedback.

[1136] (Application example 2)

[1137] 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."

[1138] Modern factories are required to have highly specialized robots working together to perform a wide variety of tasks. However, it is difficult to properly match these robots and to schedule tasks optimally so that they can work together efficiently. Furthermore, there is a lack of a system for monitoring each robot's performance and operating status in real time and utilizing feedback. This makes it difficult to improve work efficiency and detect defects early.

[1139] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting job information, specialized skills, and position information of workers, means for matching workers with common areas of interest based on the collected job information, specialized skills, and position information, means for automatically scheduling collaborative tasks between the matched workers, means for collecting and saving feedback on the results of the collaborative tasks, and means for monitoring the movements and performance of workers in real time and collecting that data. This enables efficient collaboration and task scheduling of robots, as well as real-time movement monitoring and feedback collection.

[1140] A "worker" is a robot or machine that performs a specific role or task in a factory or industrial facility.

[1141] "Job information" is data indicating the tasks and work content that a worker is responsible for.

[1142] "Specialized skills" is data that indicates the specific skills and abilities that a worker possesses.

[1143] "Position information" is data relating to the position and role of a worker.

[1144] "Common areas of interest" refer to the business or technical interests that multiple workers share in common.

[1145] "Matching" is the process of pairing workers with common goals and interests based on collected data.

[1146] A "collaborative task" is a task or project that is carried out by multiple workers together.

[1147] "Automatically scheduling" means that software or a server schedules tasks or meetings without human intervention.

[1148] "Feedback" refers to information and opinions obtained as a result of or during a collaborative task.

[1149] "Monitoring operations and performance in real time" refers to monitoring the movements of workers and work results in real time.

[1150] "Collecting data" means obtaining information from various sensors and monitoring systems, and storing and organizing it.

[1151] The present invention is a system for automatically matching and scheduling efficient collaborative tasks among workers in a factory, and for monitoring their behavior and performance in real time. This system has the function of collecting job information, specialized skills, and position information of each worker, and matching workers who share common areas of interest based on this information. The following describes an embodiment of the present invention.

[1152] First, the server collects information on the worker's job, specialized skills, and position. This information is obtained from databases and sensor systems within the factory and centrally managed on the server. Worker information includes details such as the process they are responsible for, their specialized skills, and their position.

[1153] The server then analyzes the collected information and matches workers with common interests. This matching process is carried out using pre-defined rules and AI algorithms. For example, a worker with welding expertise can be paired with another worker who also has an interest in welding technology.

[1154] After matching is established, the server automatically schedules collaborative tasks, comparing the working hours of the workers and scheduling collaborative tasks based on the earliest working time, thus enabling efficient task execution.

[1155] Furthermore, the present invention uses an emotion engine that monitors the worker's actions and performance in real time. The emotion engine recognizes the worker's actions and performance in real time and sends the data to the server. This allows the worker to grasp the problems and efficiency of the work in real time.

[1156] After a collaborative task is completed, the server collects feedback from the workers and stores it in a database. This feedback can later be used to improve the system and optimize the matching algorithm. It also combines the feedback with real-time collected behavior data to make the next collaboration more efficient.

[1157] As a concrete example, the server sets up a collaborative task between worker A, who has welding skills, and worker B, who is interested in welding technology. To perform the welding work together, a schedule is automatically set based on the working hours of both workers. During the work, the emotion engine monitors the behavior and sends the data to the server. After the work is completed, feedback and monitoring data are collected and used to optimize the next collaborative task.

[1158] An example of a specific prompt is as follows:

[1159] robot_data = [

[1160] {"id": 1, "skill": "welding", "performance": 90},

[1161] {"id": 2, "skill": "assembly", "performance": 85},

[1162] Other robot data

[1163] ]

[1164] matched_pairs = match_robots(robot_data)

[1165] Example output: [({"id": 1, "skill": "welding", "performance": 90}, {"id": 3, "skill": "welding", "performance": 88})]

[1166] schedule_tasks(matched_pairs)

[1167] Example output: Scheduled Task: {'robots': [1, 3], 'task': 'welding', 'schedule_time': '2023-10-03 14:00:00'}

[1168] feedback = collect_feedback()

[1169] Example output: Collected Feedback: {"performance": 95, "issues": null}

[1170] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1171] Step 1:

[1172] The server collects information on the worker's job, specialized skills, and position. This information is obtained from the factory's database and sensor system. For example, each robot's ID, specialized skill (welding, assembly, etc.), and current performance data (such as task success rate) are extracted from the database and centrally managed.

[1173] Step 2:

[1174] The server analyzes the collected job information, expertise, and job title information, and uses AI algorithms to process the data and match workers with common interests, specifically pairing robots with the same expertise or complementary skills.

[1175] Step 3:

[1176] The server compares the working hours of the matched robots and automatically schedules collaborative tasks based on the earliest working time. The scheduling is calculated based on the free time data of each robot, and a schedule table is generated as a result.

[1177] Step 4:

[1178] When a collaborative task is being carried out, the server monitors the robot's behavior and performance in real time. Using an emotion engine, the server collects and transmits each robot's behavior and performance data to the server. For example, the server monitors the robot's speed, success rate, and error frequency.

[1179] Step 5:

[1180] After a collaborative task is completed, the server collects feedback from the workers, including evaluations of the work, issues identified, and suggestions for improvement. The feedback is stored in a database and used to optimize the next collaborative task.

[1181] Step 6:

[1182] The server analyzes the collected feedback and real-time behavioral data to improve the system and optimize the matching algorithm, so that the next collaborative task will be performed more efficiently and effectively. The analysis results are used to adjust the algorithm and update parameters.

[1183] Step 7:

[1184] If necessary, the server uses this data to update the generative AI model to provide more accurate matching and scheduling by inputting new data sets into the generative AI model and training the algorithm.

[1185] An example prompt would be:

[1186] robot_data = [

[1187] {"id": 1, "skill": "welding", "performance": 90},

[1188] {"id": 2, "skill": "assembly", "performance": 85},

[1189] Other robot data

[1190] ]

[1191] matched_pairs = match_robots(robot_data)

[1192] Example output: [({"id": 1, "skill": "welding", "performance": 90}, {"id": 3, "skill": "welding", "performance": 88})]

[1193] schedule_tasks(matched_pairs)

[1194] Example output: Scheduled Task: {'robots': [1, 3], 'task': 'welding', 'schedule_time': '2023-10-03 14:00:00'}

[1195] feedback = collect_feedback()

[1196] Example output: Collected Feedback: {"performance": 95, "issues": null}

[1197] 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.

[1198] 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.

[1199] 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.

[1200] 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.

[1201] 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.

[1202] 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.

[1203] 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).

[1204] 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.

[1205] 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."

[1206] 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.

[1207] 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).

[1208] 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.

[1209] 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.

[1210] 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.

[1211] 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.

[1212] 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.

[1213] 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.

[1214] 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.

[1215] 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.

[1216] 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.

[1217] 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.

[1218] The following is further disclosed regarding the above embodiment.

[1219] (Claim 1)

[1220] A means of collecting employee job information, professional skills, and position information;

[1221] A means for matching employees who share common areas of interest based on the collected job information, professional skills, and job title information;

[1222] A means to automatically schedule meetings between matched employees;

[1223] a means of collecting and storing feedback on the outcome of the meeting;

[1224] A system including:

[1225] (Claim 2)

[1226] 10. The system of claim 1, further comprising means for comparing employee availability and setting up a meeting based on the earliest available time.

[1227] (Claim 3)

[1228] 10. The system of claim 1, including an ON / OFF feature that allows employees to voluntarily choose to participate in matching.

[1229] "Example 1"

[1230] (Claim 1)

[1231] A means of collecting employee job information, professional skills, and position information;

[1232] A means for analyzing the collected job information, professional skills, and position information and storing it in a database;

[1233] A means of matching employees with common interests based on pre-defined rules and AI algorithms;

[1234] A means to automatically schedule meetings between matched employees and retrieve employee availability to set the earliest common availability;

[1235] A means of collecting feedback from employees on the meeting results and storing it in a database;

[1236] A system including:

[1237] (Claim 2)

[1238] 10. The system of claim 1, including an on / off feature that allows employees to autonomously select their participation in the schedule.

[1239] (Claim 3)

[1240] 10. The system of claim 1, further comprising: means for providing a dedicated web form for collecting feedback.

[1241] "Application Example 1"

[1242] (Claim 1)

[1243] A means of collecting employee job information, professional skills, and position information;

[1244] A means for matching employees who share common areas of interest based on the collected job information, professional skills, and job title information;

[1245] A means to automatically schedule meetings between matched employees;

[1246] a means of collecting and storing feedback on the outcome of the meeting;

[1247] means for using a clustering algorithm to analyze the operator's data;

[1248] a means for finding the best pair according to a specified algorithm;

[1249] A system including:

[1250] (Claim 2)

[1251] 10. The system of claim 1, further comprising means for comparing employee availability and setting up a meeting based on the earliest available time.

[1252] (Claim 3)

[1253] 10. The system of claim 1, including an ON / OFF feature that allows employees to voluntarily choose to participate in matching.

[1254] "Example 2: Combining Emotion Engines"

[1255] (Claim 1)

[1256] A means of collecting employee job information, expertise, and job title information;

[1257] A means of matching employees with common areas of interest based on collected work information, expertise, and job title information;

[1258] A means to automatically schedule meetings between matched employees;

[1259] a means for collecting and storing evaluations of the results of the meeting;

[1260] a means for collecting emotional data during a meeting using an emotion engine that recognizes the emotional state of employees;

[1261] A system including:

[1262] (Claim 2)

[1263] 10. The system of claim 1, further comprising means for comparing employee availability and setting up a meeting based on the earliest available time.

[1264] (Claim 3)

[1265] 10. The system of claim 1, further comprising means for analyzing sentiment data from employees and incorporating the sentiment data into meeting matching and feedback.

[1266] "Application example 2 when combining emotion engines"

[1267] (Claim 1)

[1268] A means for collecting job information, professional skills, and job title information of workers;

[1269] A means for matching workers who share common areas of interest based on the collected job information, specialized skills, and job title information;

[1270] a means for automatically scheduling collaborative tasks between the matched workers;

[1271] a means for collecting and storing feedback on the results of the collaborative task;

[1272] a means for monitoring and collecting data on worker behavior and performance in real time;

[1273] A system including:

[1274] (Claim 2)

[1275] 10. The system of claim 1, further comprising means for comparing the working times of the workers and setting the collaborative task based on the earliest working time.

[1276] (Claim 3)

[1277] 10. The system of claim 1, including an ON / OFF function that allows a worker to voluntarily choose to participate in matching. [Explanation of symbols]

[1278] 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 employee job information, professional skills, and position information; A means for matching employees who share common areas of interest based on the collected job information, professional skills, and job title information; A means to automatically schedule meetings between matched employees; a means of collecting and storing feedback on the outcome of the meeting; A system including:

2. 10. The system of claim 1, further comprising means for comparing employee availability and setting up a meeting based on the earliest available time.

3. The system of claim 1 , including an ON / OFF feature that allows employees to voluntarily choose to participate in matching.

Images