system

Abstract

Provide a system. [Solution] A data collection means for collecting the contents of meetings held between employees and generative AI; analysis means for analyzing the conference content data collected from the data collection means; a proposal means for proposing appropriate transfers or project participation of employees based on the skills and characteristics of the employees identified by the analysis means; a notification means for notifying relevant departments of the content of the proposal made by the proposal means; a feedback collection means for collecting feedback based on the content of the notification by the notification means; evaluation means for analyzing the feedback collected by the feedback collection means and evaluating the appropriateness of the proposal content; 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] Traditionally, managing and utilizing human resource skills in companies required a significant amount of resources, making it difficult to fully utilize the skills and characteristics of specific employees. This made it difficult to assign the right people to the right positions, resulting in problems such as a decline in the efficiency and performance of the entire organization. Furthermore, resource constraints made it difficult to gather detailed feedback from employees through regular one-on-one meetings, which resulted in insufficient skill discovery and appropriate transfer proposals. [Means for solving the problem]

[0005] In order to solve the above problems, the present invention proposes the following means. First, a data collection means is provided for collecting the contents of meetings held between employees and a generative AI. Second, an analysis means is provided for analyzing the meeting content data collected from the data collection means. Third, a proposal means is provided for proposing appropriate transfers or project participation for employees based on the employee skills and characteristics identified by the analysis means. Fourth, a notification means is provided for notifying relevant departments of the contents of the proposals made by the proposal means. Fifth, a feedback collection means is provided for collecting feedback based on the contents of the notifications made by the notification means. Finally, an evaluation means is provided for analyzing the feedback collected by the feedback collection means and evaluating the appropriateness of the contents of the proposals. These means make it possible to efficiently manage employee skills and characteristics and automatically make appropriate transfer proposals and their evaluations.

[0006] "Data collection means" refers to a device or method for collecting the content of meetings held between employees and generative AI.

[0007] The "analysis means" is a device or method for analyzing the meeting content data collected from the data collection means and identifying the skills and characteristics of employees.

[0008] The "proposal means" is a device or method for proposing appropriate transfers or project participation of employees based on the skills and characteristics of employees identified by the analysis means.

[0009] The "notification means" is a device or method for notifying the relevant department or person in charge of the content of the proposal made by the proposal means.

[0010] The "feedback collection means" is a device or method for collecting feedback obtained based on the content notified by the notification means.

[0011] The "evaluation means" is a device or method for analyzing the feedback collected by the feedback collection means and evaluating the appropriateness of the proposal content.

[0012] "Generative AI" is artificial intelligence that uses natural language processing technology to analyze meeting content data and identify skills and characteristics.

[0013] "Meeting content data" refers to audio and text data generated during meetings between employees and generative AI.

[0014] A "conversion means" is a device or method for converting audio data into text data. [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 provides a system for efficiently managing and utilizing human resource skills within a company. Hereinafter, an embodiment of the present invention will be described in detail.

[0037] System Overview

[0038] This system collects, analyzes, and proposes employee skills and characteristics through regular one-on-one meetings between employees and generative AI. Specifically, it collects and analyzes the content of meetings with employees, proposes appropriate transfers and project participation, and finally collects and evaluates feedback.

[0039] Data collection

[0040] Once a month, users (employees) use company devices to hold one-on-one meetings with generative AI. During these meetings, the devices record the meeting content as audio and simultaneously convert the audio data into text data. This text data is also used as subtitle information for the meeting content. The collected data is sent from the devices to a server.

[0041] Data analysis

[0042] The server stores the received meeting content data in a dedicated database. The data is then passed to a generative AI analysis module. The generative AI uses natural language processing (NLP) to analyze the text data and extract important keywords and phrases. This allows employee skills and characteristics to be identified.

[0043] Suggestions and Notifications

[0044] Based on the analysis results, the server updates the employee skill set and characteristics database. The generative AI then uses this data to create appropriate employee transfer and project participation proposals. The proposals are then notified to managers and staff in the relevant departments via the server.

[0045] Feedback and Ratings

[0046] The person in charge will hold another one-on-one meeting with the employee based on the proposal and receive feedback on the proposal. This feedback information will again be sent from the device to the server and collected. The server will then pass the collected feedback to the generative AI and evaluate the appropriateness of the proposal.

[0047] Specific examples

[0048] For example, employee A belongs to the sales department and holds the following monthly one-on-one meeting. During the meeting, the user says, "This month, I focused particularly on negotiating with new clients, and I felt that my negotiation skills were one of my strengths." The device records this conversation and sends it to the server as text data.

[0049] The server passes the data to the generative AI, which analyzes the text data and extracts keywords such as "negotiation skills" and "new client," thereby identifying that employee A has strengths in negotiation skills. The server then updates the database for employee A, and the generative AI creates a proposal to transfer employee A to a new project and notifies the sales department manager. The manager discusses the proposal with employee A in the next one-on-one meeting and collects feedback. This feedback is again evaluated by the server and the generative AI to determine the appropriateness of the proposal.

[0050] In this way, the present invention can efficiently manage and utilize the skills and characteristics of employees, contributing to the growth and development of a company.

[0051] The processing flow will be explained below.

[0052] Step 1:

[0053] A user (employee) starts a one-on-one meeting with a generative AI using a company device. The user launches a dedicated application and presses the start button.

[0054] Step 2:

[0055] The device records the contents of the meeting as audio data in real time. At the same time, the audio data is converted into text data using natural language processing technology. The converted text data is also used as subtitle information for the meeting.

[0056] Step 3:

[0057] After the meeting ends, the device sends the recorded audio data and converted text data to the server, which then stores the received data in a dedicated database.

[0058] Step 4:

[0059] The server passes the stored text data to the generative AI's analysis module, where the generative AI uses natural language processing technology to analyze the text data.

[0060] Step 5:

[0061] Generative AI extracts important keywords and phrases from meeting content, for example, identifying keywords like "negotiation skills" and "new clients" and identifying employee skills and traits.

[0062] Step 6:

[0063] The server reflects the analysis results in the employee database and updates the employee's skill set and characteristics. In the case of employee A, a new skill data item, "Negotiation Skills: High," is added.

[0064] Step 7:

[0065] Based on the updated data, the generative AI generates proposals for appropriate employee transfers and project participation. For example, it creates a proposal to transfer Employee A to a large contract project in the sales department.

[0066] Step 8:

[0067] The server notifies the manager or person in charge of the relevant department of the proposal, and the notification is sent via email or internal messenger.

[0068] Step 9:

[0069] The user (person in charge) will hold another one-on-one meeting with the employee based on the proposal to discuss the proposal. The contents of this feedback meeting will also be recorded and converted into text.

[0070] Step 10:

[0071] The device sends the feedback meeting data to a server, which then passes it on to the generative AI, which analyzes the feedback and evaluates the appropriateness of the proposals.

[0072] Step 11:

[0073] The server stores the generative AI's evaluation results in a database and, if necessary, starts a new cycle with further suggestions and improvements.

[0074] This series of processes ensures that employee skills and characteristics are managed and utilized efficiently, improving the performance of the entire organization.

[0075] Example 1

[0076] 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."

[0077] Traditionally, the management and utilization of human resource skills within companies has been largely manual, making it difficult to efficiently collect and analyze data. In particular, there has been a lack of methods for accurately understanding employees' skills and characteristics and assigning them to appropriate tasks and projects based on that information. In addition, the process of collecting feedback and evaluating the appropriateness of proposals is cumbersome. This has limited the ability to maximize employee capabilities and promote corporate growth.

[0078] 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.

[0079] In this invention, the server includes information collection means for collecting the contents of meetings held between employees and the generative AI, data analysis means for analyzing the meeting content data collected from the information collection means, proposal generation means for proposing appropriate transfers or work participation for employees based on the employee skills and characteristics identified by the data analysis means, communication means for notifying relevant departments of the contents of the proposals made by the proposal generation means, opinion collection means for collecting feedback based on the contents of the notifications made by the notification means, and aptitude evaluation means for analyzing the feedback collected by the opinion collection means and evaluating the appropriateness of the contents of the proposals. This makes it possible to efficiently collect and analyze employee skills and characteristics, generate appropriate work proposals, and evaluate the feedback based on the proposals.

[0080] "Information collection means" refers to a device or system for collecting the contents of meetings held between employees and generative AI.

[0081] The "data analysis means" is a device or process for analyzing the conference content data collected from the information collection means.

[0082] The "proposal generating means" is a device or system for proposing appropriate transfers or work participation of employees based on the skills and characteristics of the employees identified by the data analysis means.

[0083] The "communication means" is a device or system for notifying the relevant departments of the contents of the proposal made by the proposal generating means.

[0084] The "opinion collection means" is a device or system for collecting feedback based on the content of the notification by the notification means.

[0085] The "suitability evaluation means" is a device or system for analyzing the feedback collected by the opinion collection means and evaluating the suitability of the proposal content.

[0086] "Generative AI" is an artificial intelligence system that uses natural language processing technology to analyze meeting content data and generate appropriate business proposals.

[0087] "Meeting content data" refers to information that records statements and exchanges made during meetings between employees and generative AI.

[0088] The present invention is a system for improving the efficiency of human resource skill management and utilization within a company. Specifically, it includes a process for analyzing data collected through one-on-one meetings between employees and generative AI, and proposing appropriate employee transfers and project participation. An embodiment of this system is described in detail below.

[0089] Data collection

[0090] Once a month, users (employees) use their company devices to hold one-on-one meetings with the generative AI. During these meetings, the devices use the following hardware and software:

[0091] Hardware: Microphones, recording devices

[0092] Software: Google® Cloud Speech-to-Text

[0093] The device records the meeting contents as audio and converts the audio data into text data in real time using Google Cloud Speech-to-Text. This converted text data is also used as subtitle information for the meeting contents. The collected data is sent from the device to the server using HTTPS communication.

[0094] Data reception and storage

[0095] The server receives the text data of the conference contents sent and stores it in a dedicated database. This database uses MySQL (registered trademark) or PostgreSQL. The server performs transaction control to ensure data integrity and security.

[0096] Data analysis

[0097] The server passes the stored text data to a generative AI analysis module, which uses natural language processing (NLP) techniques such as OpenAI's GPT-4 to analyze the text data and extract key keywords and phrases that identify employee skills and traits.

[0098] Proposal creation

[0099] The server updates the employee skill set and characteristics database based on the results of the generative AI analysis. The generative AI then uses the updated data to create appropriate employee transfer and project participation proposals. These proposals are compiled into documents using natural language generation technology.

[0100] proposal notification

[0101] The server notifies the managers and staff of the relevant departments of the content of the proposals created. This notification is sent via communication methods such as email, MICROSOFT (registered trademark) TEAMS (registered trademark), and Slack. The notification also includes the data that formed the basis of the proposal and important keywords.

[0102] Feedback collection and evaluation

[0103] The person in charge holds another one-on-one meeting with the employee based on the proposal content, and enters the feedback obtained from the meeting into the device. The device then sends this feedback information to the server. The server stores the received feedback in a database and passes it on to the generative AI. The generative AI uses the feedback data to evaluate the appropriateness of the proposal content. Sentiment analysis technology and other techniques are used in the evaluation, and the results of this evaluation are reflected in the creation of the next proposal.

[0104] Specific examples

[0105] For example, employee A belongs to the sales department and holds the following monthly one-on-one meeting. During the meeting, the user says, "This month, I focused particularly on negotiating with new clients, and I felt that my negotiation skills were one of my strengths." The device records this conversation, converts it into text data using Google Cloud Speech-to-Text, and sends it to the server.

[0106] The server passes the data to a generative AI (e.g., OpenAI GPT-4), which analyzes the text data and extracts keywords such as "negotiation skills" and "new client." This identifies that employee A has strengths in negotiation skills. The server then updates the database for employee A, and the generative AI creates a proposal to transfer employee A to a new project and notifies the sales department manager. The manager discusses the proposal with employee A in the next one-on-one meeting and collects feedback. This feedback is again evaluated by the server and the generative AI to determine the appropriateness of the proposal.

[0107] Prompt Sentence Examples

[0108] "Employee A mentioned in this month's one-on-one meeting that he focused particularly on negotiating with new clients and felt that negotiation skills were one of his strengths. Based on this, please conduct an analysis of Employee A's skills and characteristics and create an appropriate project participation proposal."

[0109] In this way, the present invention can efficiently manage and utilize the skills and characteristics of employees, contributing to the growth and development of a company.

[0110] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0111] Step 1: Data collection

[0112] Users use company devices to hold regular one-on-one meetings with generative AI. When a meeting begins, the device records audio data through a microphone. This audio data becomes the input. The device then converts the audio data into text data in real time using Google Cloud Speech-to-Text. Here, the audio data is recognized as a string of characters, and data processing is performed to convert each utterance into text format. The converted text data becomes the output and is prepared for the next step.

[0113] Step 2: Send data

[0114] The terminal sends the generated text data to the server via HTTPS. This process uses encryption to ensure data security. The input is the converted text data, and the output is the secure receipt of the data by the server.

[0115] Step 3: Receiving and storing data

[0116] The server receives text data sent from the terminal. The input is text data sent via HTTPS communication, and the server stores the data in a dedicated database. Transaction control is used to maintain the integrity of the database during storage. The output is text data saved in the database.

[0117] Step 4: Data analysis

[0118] The server passes the text data stored in the database to the generative AI analysis module. The input is the text data retrieved from the database. The analysis module (e.g., OpenAI GPT-4) analyzes the data using natural language processing technology and extracts important keywords and phrases. This analysis identifies employee skills and characteristics. The output is the keywords resulting from the analysis and the identified skills and characteristics.

[0119] Step 5: Proposal Generation

[0120] The server updates the employee skill set and characteristics database based on the analysis results output by the generative AI. Using this skill set and characteristics data, the generative AI again creates appropriate transfer and project participation proposals. The input is the analysis results, and the output is the generated proposal.

[0121] Step 6: Proposal Notification

[0122] The server notifies the necessary managers and personnel of the generated proposals. The input is the generated proposal, and the output is a notification via email, Microsoft Teams, or Slack. This notification process also includes the data that formed the basis of the proposal and important keywords.

[0123] Step 7: Gather feedback

[0124] The person in charge holds another one-on-one meeting with the employee based on the proposal, and inputs the feedback obtained during the meeting into the terminal. The input is the feedback obtained during the meeting, and the terminal sends it back to the server. The output is the transmission of the feedback data to the server.

[0125] Step 8: Feedback evaluation

[0126] The server stores the received feedback in a database and passes it to the generative AI. The input is the feedback data, which the generative AI analyzes and evaluates the appropriateness of the proposal. Sentiment analysis technology and other techniques are used for the evaluation. The output is the evaluation result regarding the appropriateness of the proposal, which is reflected in the creation of the next proposal.

[0127] (Application example 1)

[0128] 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."

[0129] Modern companies are required to accurately understand the skills and characteristics of their personnel and propose appropriate transfers and project participation. In particular, in on-site work such as factories, workers' skills are directly linked to work efficiency and productivity, so proper skill management and rapid feedback are essential. However, in current systems, these processes are often carried out manually, which is time-consuming and labor-intensive. Furthermore, worker skill evaluation relies on subjective judgment, which can lead to inappropriate evaluations. A system that can solve these issues is needed.

[0130] 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.

[0131] In this invention, the server includes: a data collection means for collecting the contents of meetings held between employees and the generative AI; an analysis means for analyzing the meeting content data collected by the data collection means; a proposal means for proposing appropriate employee transfers or project participation based on the employee's skills and characteristics identified by the analysis means; a notification means for notifying relevant departments of the contents of the proposals made by the proposal means; a feedback collection means for collecting feedback based on the contents of the notifications made by the notification means; an evaluation means for analyzing the feedback collected by the feedback collection means and evaluating the appropriateness of the proposals; a means for collecting speech and work content during work using a recording device attached to an information processing device used by the worker; a conversion means for converting the collected speech data into text data and transmitting it to the generative AI server; and a proposal means for evaluating the worker's skills based on the text data generated by the conversion means and proposing appropriate reassignment to a work position. This makes it possible to efficiently and accurately grasp the worker's skills and characteristics and quickly propose appropriate transfers and project participation.

[0132] "Data collection means" refers to a means of collecting data such as speech during meetings and work between workers and generative AI, as well as the content of the work, using information processing devices and recording devices.

[0133] The "analysis means" is a means for analyzing the data collected by the data collection means and extracting important information and keywords.

[0134] The "suggestion means" is a means for proposing appropriate transfers or project participation based on the skills and characteristics of employees or workers identified by the analysis means.

[0135] The "notification means" is a means for notifying the relevant departments and managers of the contents of the proposal made by the proposal means.

[0136] The "feedback collection means" is a means for collecting feedback based on the content of the notification by the notification means.

[0137] The "evaluation means" is a means for analyzing the feedback collected by the feedback collection means and evaluating the appropriateness of the proposal content.

[0138] The "recording device" is an information processing device for recording the voices of workers and the details of their work.

[0139] The "conversion means" is a means for converting collected voice data into text data and sending it to the generative AI server.

[0140] "Generative AI" is artificial intelligence that analyzes collected text data and uses natural language processing technology to evaluate skills.

[0141] This invention is a system that efficiently manages the skills and characteristics of human resources within a company and proposes appropriate transfers and project participation. This system utilizes smart glasses and AI technology to automate the skill evaluation and feedback management of field workers.

[0142] System Overview

[0143] The system is configured as follows:

[0144] 1. Data collection methods:

[0145] Smart glasses are information processing devices used by workers that record their speech and the details of their work. Data is collected using a microphone and camera built into the smart glasses, allowing for real-time recording of the worker's work status and voice.

[0146] 2. Conversion method:

[0147] The voice data collected by the smart glasses is converted into text data using voice recognition software (e.g., the SpeechRecognition module). The converted text data is then sent to the generative AI server.

[0148] 3. Analysis method:

[0149] The generative AI server analyzes the collected text data and uses a generative AI model (e.g., OpenAI API) to extract important keywords and phrases from the text data using natural language processing technology and identify the skills of the workers.

[0150] 4. Proposal method:

[0151] Based on the analysis results, the generative AI server evaluates the worker's skill set and proposes appropriate transfers or project participation. These proposals are automated and notified to the worker and relevant department managers as appropriate.

[0152] 5. Means of notification:

[0153] The proposals are then sent to the relevant departments and managers via email or a dedicated application.

[0154] 6. Feedback Collection Methods:

[0155] After the worker performs the work in the new position based on the proposal, the results of the work and their impressions are collected as feedback. Voice data is collected again using smart glasses and converted into text data.

[0156] 7. Evaluation Methods:

[0157] The collected feedback data is reanalyzed to evaluate the appropriateness of the underlying proposals, and a generative AI model is used to derive improvements and new proposals from the feedback.

[0158] Specific examples

[0159] For example, suppose Worker A is installing new wiring and says, "I've learned how to install new wiring. I'm good at detailed work. I quickly discovered a problem with a specific part." The smart glasses will record this voice and convert it into text data.

[0160] The converted text is sent to the generative AI server as the following prompt:

[0161] Example prompt sentence:

[0162] Analyze the statements of the workers below, extract keywords, and evaluate their skill sets.

[0163] "I learned how to install new wiring. I'm good at detailed work. I quickly identified a problem with a specific component."

[0164] The generative AI analyzes this prompt and extracts keywords such as "wiring installation," "detailed work," and "detecting defects in specific components." It then evaluates that Worker A excels in these skills and proposes an appropriate new work position. This proposal is notified to the manager of the relevant department and ultimately fed back to Worker A. The feedback is again collected by the smart glasses and evaluated by the generative AI model. This makes it possible to optimize the proposal.

[0165] In this way, the present invention makes it possible to quickly and accurately evaluate the skills and characteristics of workers and efficiently propose appropriate transfers and project participation.

[0166] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0167] Step 1:

[0168] The user puts on the smart glasses and begins working. The smart glasses' built-in microphone and camera record audio and video while working. This allows the user's work status and comments to be collected in real time. The input is the audio and video of the work being done, and the output is the recorded data.

[0169] Step 2:

[0170] The device converts the collected voice data into text data. Voice recognition software (e.g., SpeechRecognition module) is used to convert the voice data into text information. The input is voice data, and the output is converted text data. This process results in the speech written in natural language.

[0171] Step 3:

[0172] The device sends the converted text data to the generative AI server. Transmission is via internet communication. The input is the text data, and the output is a notification to the generative AI server that data transmission is complete. This passes the text data to the server for analysis.

[0173] Step 4:

[0174] The server uses generative AI to analyze the received text data. Using a generative AI model (e.g., OpenAI's API), keywords and important phrases are extracted through analysis. The input is text data, and the output is the analyzed keywords and phrases. This process identifies the skills and characteristics of the worker.

[0175] Step 5:

[0176] The server creates proposals based on the analysis results. The proposals include new work positions or project participation that are suited to the worker's skills and characteristics. The input is the analyzed keywords and phrases, and the output is the proposals. The proposals are generated automatically.

[0177] Step 6:

[0178] The server notifies the relevant departments and administrators of the proposal contents. Notifications are sent via email or a dedicated application. The input is the proposal contents, and the output is a notification of notification completion, allowing the administrator to check the proposal.

[0179] Step 7:

[0180] The user performs a new task based on the suggestions. After completing the task, they record their impressions and any problems they have as feedback via voice. Data is collected again using smart glasses. The input is the user's voice feedback, and the output is the recorded feedback data.

[0181] Step 8:

[0182] The terminal converts the collected feedback voice data back into text data and sends it to the generative AI server using speech recognition software. The input is the feedback voice data, and the output is the converted feedback text data.

[0183] Step 9:

[0184] The server analyzes the collected feedback data and evaluates the appropriateness of the proposals. A generative AI model is used to derive improvements and new proposals from the feedback. The input is the feedback text data, and the output is the evaluation results and improvement proposals. This process optimizes the proposals for future use.

[0185] 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.

[0186] The present invention provides a system for efficiently managing and utilizing human resource skills and emotions within a company. Hereinafter, an embodiment of the present invention will be described in detail.

[0187] System Overview

[0188] This system collects, analyzes, and proposes employee skills, characteristics, and emotions through regular one-on-one meetings between employees and generative AI. Specifically, it collects the content of meetings with employees, analyzes their emotions using an emotion engine, proposes appropriate transfers or project participation, and finally collects and evaluates feedback.

[0189] Data collection

[0190] Once a month, users (employees) use their company devices to hold one-on-one meetings with the generative AI. The user launches a dedicated application and presses the start button for the meeting. The device then records the contents of the meeting as audio data in real time. At the same time, the audio data is converted into text data. This text data is also used as subtitle information for the meeting. The collected data is sent from the device to a server.

[0191] Emotion analysis

[0192] The server stores the received meeting content data in a dedicated database. The data is then passed to a generative AI analysis module, where an emotion engine is built in to recognize and extract user emotions from the meeting content data. For example, emotions such as joy, sadness, and anger are identified. The emotion engine analyzes emotions from voice tone and text content.

[0193] Data analysis

[0194] The generative AI comprehensively analyzes the emotion data provided by the emotion engine and the text data of meeting contents to identify employee skills and characteristics. Based on the extracted emotion and skill data, it creates proposals for appropriate employee job assignments and project participation.

[0195] Suggestions and Notifications

[0196] The server reflects the analysis results in the employee database, updating the employee's skill set and characteristics. The generative AI then takes emotional data into account and generates suitable transfer and project participation proposals for the employee. The proposals are then sent via the server to managers and staff in the relevant departments.

[0197] Feedback and Ratings

[0198] The person in charge holds another one-on-one meeting with the employee based on the proposal and collects feedback on the results. The contents of this feedback meeting are also recorded and converted into text. The device sends the feedback meeting data to the server, which then passes it on to the generative AI. The generative AI analyzes the feedback and evaluates the appropriateness of the proposal.

[0199] Specific examples

[0200] For example, employee B belongs to the development department and holds the following monthly one-on-one meeting. During the meeting, the user says, "This month I particularly struggled with learning a new technology, but I finally succeeded and I'm very happy." The device records this conversation and sends it to the server as text data. From this content, the emotion engine identifies changes in emotion from distress to joy.

[0201] The generative AI analyzes emotion data along with keywords related to "acquiring new technologies" and identifies that employee B has a high ability to acquire new technologies and feels a sense of accomplishment. The server then updates the database for employee B, and the generative AI proposes employee B's participation in a new project and notifies the development department manager. The manager then discusses the proposal with employee B in the next one-on-one meeting and collects feedback. This feedback is again evaluated by the server and the generative AI to determine the appropriateness of the proposal.

[0202] This series of processes enables efficient management and utilization of employee skills and emotions, contributing to the growth and development of the company.

[0203] The processing flow will be explained below.

[0204] Step 1:

[0205] A user (employee) starts a one-on-one meeting with a generative AI using a company device. The user launches a dedicated application and presses the start button.

[0206] Step 2:

[0207] The device records the contents of the meeting as audio data in real time. At the same time, the audio data is converted into text data using natural language processing technology. The converted text data is also used as subtitle information for the meeting.

[0208] Step 3:

[0209] After the meeting ends, the device sends the recorded audio data and converted text data to the server, which then stores the received data in a dedicated database.

[0210] Step 4:

[0211] The server passes the saved text and audio data to the generative AI analysis module, where the emotion engine analyzes the meeting content data to recognize the user's emotions and extracts emotional data.

[0212] Step 5:

[0213] The emotion engine analyzes the user's emotions from the meeting content based on voice tone and context, identifying emotions such as joy, sadness, and anger.

[0214] Step 6:

[0215] The generative AI comprehensively analyzes the emotional and text data provided by the emotion engine to identify employee skills and traits, including skill extraction based on text analysis and emotional state assessment based on emotion analysis.

[0216] Step 7:

[0217] The server reflects the analysis results in the employee database and updates the employee's skill set, characteristics, and emotional information. For example, for employee A, the data "Negotiation skills: High" and "Recent emotional state: Joy" are added.

[0218] Step 8:

[0219] Based on the updated database, the generative AI generates proposals for appropriate employee transfers and project participation. In doing so, it takes into account not only skill data but also emotional data when creating the proposals. For example, it might make a proposal such as, "Employee A should be transferred to a large contract project. As his emotional state has been stable recently, an environment with less mental stress would be suitable."

[0220] Step 9:

[0221] The server notifies managers and staff in the relevant departments of the generative AI's proposals, via email or internal messenger.

[0222] Step 10:

[0223] The user (person in charge) will hold a one-on-one meeting with the employee based on the proposal and collect feedback on the results. The contents of this feedback meeting will also be recorded and converted into text.

[0224] Step 11:

[0225] The device sends the feedback meeting data to a server, which then passes it on to the generative AI, which analyzes the feedback and evaluates the appropriateness of the proposals.

[0226] Step 12:

[0227] The server stores the results of the generative AI evaluation in a database and initiates a new cycle including further suggestions and improvements as needed, thereby enabling efficient management of employee skills and emotions, contributing to the growth and development of the company as a whole.

[0228] Example 2

[0229] 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."

[0230] Companies are seeking to efficiently manage and utilize the skills and emotions of their employees. Accurately understanding employees' emotions and skills and making appropriate transfer and project participation proposals based on that information is essential for corporate growth. However, traditional methods make it difficult to do this efficiently, and analyzing emotions and collecting and evaluating feedback, in particular, requires a great deal of time and effort.

[0231] 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.

[0232] In this invention, the server includes: a data collection means for collecting the contents of meetings held between employees and the generative AI; a conversion means for converting the conference audio data collected from the data collection means into text data; a transmission means for transmitting the text data and audio data to the server; an analysis means for analyzing the data; an emotion analysis means for analyzing the emotions of employees identified by the analysis means; a data analysis means for identifying the skills and characteristics of employees based on the emotion analysis means and the conference content text data; a proposal means for proposing appropriate transfers or project participation for employees based on the data analysis means; a notification means for notifying relevant departments of the contents of the proposals made by the proposal means; a feedback collection means for collecting feedback based on the contents of the notifications made by the notification means; and an evaluation means for analyzing the feedback collected by the feedback collection means and evaluating the appropriateness of the proposals. This enables efficient management of employees' emotions and skills and the proposal of appropriate transfers or project participation based on the results.

[0233] "Data collection means" refers to a means for collecting the contents of meetings held between employees and generative AI.

[0234] The "conversion means" is a means for converting collected conference voice data into text data.

[0235] The "transmission means" is a means for transmitting text data and voice data to the server.

[0236] "Analysis means" refers to means for analyzing collected data.

[0237] The "emotion analysis means" is a means for analyzing the emotions of the employees identified by the analysis means.

[0238] The "data analysis means" is a means for identifying the skills and characteristics of employees based on the emotion analysis means and the meeting content text data.

[0239] "Proposal means" refers to a means for proposing appropriate transfers or project participation of employees based on data analysis means.

[0240] The "notification means" is a means for notifying the relevant departments of the content of the proposal made by the proposal means.

[0241] The "feedback collection means" is a means for collecting feedback based on the notification content.

[0242] The "evaluation means" is a means for analyzing the feedback collected by the feedback collection means and evaluating the appropriateness of the proposal content.

[0243] The present invention is a system for efficiently managing and utilizing human resource skills and emotions within a company. An embodiment of the present invention will now be described in detail.

[0244] System Overview

[0245] This system collects employee skills, characteristics, and emotions through regular one-on-one meetings between employees and generative AI, and then analyzes and proposes the data. The system includes the following detailed processes:

[0246] Data collection

[0247] Once a month, users (employees) use their company's devices to hold one-on-one meetings with the generative AI. The user launches a dedicated application and presses the start button for the meeting. The device records the meeting content as audio data in real time. At the same time, the audio data is converted into text data. This text data is also used as subtitle information for the conversation. The collected data is sent from the device to a server.

[0248] Emotion analysis

[0249] The server stores the received meeting content data in a dedicated database. The data is then passed to a generative AI analysis module, where an emotion engine is built in to recognize and extract user emotions from the meeting content data. For example, emotions such as joy, sadness, and anger are identified. The emotion engine analyzes emotions from voice tone and text content.

[0250] Data analysis

[0251] The generative AI comprehensively analyzes the emotion data provided by the emotion engine and the text data of meeting contents to identify employee skills and characteristics. Based on the extracted emotion and skill data, it creates proposals for appropriate employee job assignments and project participation.

[0252] Suggestions and Notifications

[0253] The server reflects the analysis results in the employee database, updating the employee's skill set and characteristics. The generative AI then takes emotional data into account and generates suitable transfer and project participation proposals for the employee. The proposals are then sent via the server to managers and staff in the relevant departments.

[0254] Feedback and Ratings

[0255] The person in charge holds another one-on-one meeting with the employee based on the proposal and collects feedback on the results. The contents of this feedback meeting are also recorded and converted into text. The device sends the feedback meeting data to the server, which then passes it on to the generative AI. The generative AI analyzes the feedback and evaluates the appropriateness of the proposal.

[0256] Specific examples

[0257] For example, employee B belongs to the development department and holds the following monthly one-on-one meeting. During the meeting, the user says, "This month I particularly struggled with learning a new technology, but I finally succeeded and I'm very happy." The device records this conversation and sends it to the server as text data. From this content, the emotion engine identifies changes in emotion from distress to joy.

[0258] The generative AI analyzes emotion data along with keywords related to "acquiring new technologies" and identifies that employee B has a high ability to acquire new technologies and feels a sense of accomplishment. The server then updates the database for employee B, and the generative AI proposes employee B's participation in a new project and notifies the development department manager. The manager then discusses the proposal with employee B in the next one-on-one meeting and collects feedback. This feedback is again evaluated by the server and the generative AI to determine the appropriateness of the proposal.

[0259] Prompt Sentence Examples

[0260] Employee B, who works in the development department, said, "I struggled to learn new technology this month, but I finally succeeded and I'm very happy." Analyze this conversation to identify changes in the employee's emotions and skill characteristics.

[0261] The above is an embodiment of the present invention. This system enables efficient management and utilization of human resource skills and emotions within a company.

[0262] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0263] Step 1:

[0264] The user launches the dedicated application on the device and presses the "Start Meeting" button.

[0265] Input: User actions

[0266] Output: Start of meeting

[0267] Specific operation: The user launches the dedicated application and clicks the "Start Conference" button, which puts the device into conference recording mode.

[0268] Step 2:

[0269] The terminal records the contents of the meeting in real time and converts the voice data into text data using a voice recognition engine.

[0270] Input: Meeting audio

[0271] Output: Text data

[0272] How it works: The device records the audio of the meeting and converts the audio data into text data in real time using a speech recognition engine such as Google Cloud Speech-to-Text.

[0273] Step 3:

[0274] The terminal transmits the converted text data and the original voice data to the server.

[0275] Input: Text data and audio data

[0276] Output: Send data to the server

[0277] Specific operation: The device encrypts text data and voice data via the SSL / TLS protocol and sends it to the server.

[0278] Step 4:

[0279] The server stores the received data in a database and passes it on to the generative AI analysis module.

[0280] Input: Text data and audio data

[0281] Output: Storing in a database and passing data to analysis modules

[0282] Specific operation: The server stores the received data in a dedicated database and classifies it by user ID. The data is then passed to the generative AI analysis module.

[0283] Step 5:

[0284] The emotion engine analyzes the data and identifies the user's emotion.

[0285] Input: Text data and audio data

[0286] Output: Emotion data

[0287] What it does: An emotion engine (e.g., IBM Watson® Tone Analyzer) analyzes the text and tone of the voice to identify the user's emotions, such as joy, sadness, or anger.

[0288] Step 6:

[0289] Generative AI comprehensively analyzes emotional data and text data from meeting content to extract employee skills and characteristics.

[0290] Input: Emotion data and text data

[0291] Output: Skill data and attribute data

[0292] How it works: Generative AI integrates emotional and textual data to extract skills and characteristics, such as the speed of technological acquisition and the ability to adapt to challenges.

[0293] Step 7:

[0294] The server reflects the analysis results in the employee database, and the generative AI generates suggestions.

[0295] Input: Skill data and attribute data

[0296] Output: Proposal data

[0297] Specific operation: The server reflects skill data and characteristic data in the employee database, and the generative AI generates appropriate proposals for employee transfers and project participation.

[0298] Step 8:

[0299] The server notifies the manager or person in charge of the relevant department of the proposal.

[0300] Input: Proposal data

[0301] Output: Notification data

[0302] Specific operation: The server notifies the managers and staff of the relevant departments of the generated proposals via email or a dedicated notification system.

[0303] Step 9:

[0304] The person in charge will hold another one-on-one meeting with the employee to discuss the proposal and gather feedback.

[0305] Input: Proposal data

[0306] Output: Feedback data

[0307] Specific operations: The person in charge discusses the proposal with employees, records the audio of the feedback meeting, and converts it into text data.

[0308] Step 10:

[0309] The device sends the feedback meeting data to the server, and the generative AI evaluates it.

[0310] Input: Feedback data

[0311] Output: Evaluation data

[0312] Specific operation: The device sends the text and audio data of the feedback meeting to the server, which then passes the data to the generative AI. The generative AI analyzes the feedback data and evaluates the appropriateness of the proposal.

[0313] These are the processing steps of this system. At each step, data is collected, converted, analyzed, proposed, notified, and feedback is collected and evaluated, allowing for efficient management and utilization of employee skills and emotions.

[0314] (Application example 2)

[0315] 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."

[0316] It is extremely important to understand the skills and characteristics of employees within a company and to make appropriate work plans. However, it is difficult to conduct a comprehensive evaluation that includes employee emotions, which has made improving work efficiency and employee satisfaction a challenge. In addition, it is difficult to collect and analyze data accurately in real time using paper-based or simple digital tools, so a new system to solve these issues was needed.

[0317] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0318] In this invention, the server includes a data collection means for collecting the contents of meetings held between employees and the generative AI, an analysis means for analyzing the meeting content data collected by the data collection means, a proposal means for proposing appropriate employee transfers or project participation based on the employee skills, characteristics, and emotional data identified by the analysis means, a notification means for notifying relevant departments of the contents of the proposals made by the proposal means, a feedback collection means for collecting feedback based on the contents of the notifications made by the notification means, an evaluation means for analyzing the feedback collected by the feedback collection means and evaluating the appropriateness of the contents of the proposals, and an emotion analysis means for grasping employee emotions in real time via smart devices. This allows for a comprehensive evaluation of employee emotions, enabling improved work efficiency and employee satisfaction.

[0319] "Employee" refers to an employee working within a company.

[0320] "Generative AI" refers to the entire system that uses artificial intelligence technology to analyze data and generate proposals.

[0321] "Data collection means" refers to the devices and processes that collect the contents of the meeting in the form of audio, video, etc.

[0322] "Analysis means" refers to the device and its functions that analyze employee skills, characteristics, emotions, etc. based on collected data.

[0323] "Proposal means" refers to a device and its functions that generate proposals for employee transfers and project participation based on the analysis results.

[0324] "Notification means" refers to a device and its function that notifies the manager or person in charge of the relevant department of the content of the generated proposal.

[0325] "Feedback collection means" refers to a device and its functionality for organizing and recording feedback collected based on suggestions.

[0326] "Evaluation means" refers to a device and its functions that analyzes collected feedback and evaluates the appropriateness of suggestions.

[0327] "Emotion analysis means" refers to a device and its functions that analyzes employee emotions in real time using a smart device.

[0328] "Smart devices" refers to portable or wearable electronic devices with advanced information processing capabilities, such as smartphones, smart glasses, and head-mounted displays.

[0329] "Natural language processing technology" refers to the technology that processes, understands, generates, and analyzes human language using a computer.

[0330] The present invention provides a system for improving the work efficiency and satisfaction of employees in a logistics center. As an embodiment of the present invention, a system is described that collects and analyzes work content and emotional data in real time when employees perform their work using smart devices (such as smart glasses).

[0331] System Overview

[0332] Users (employees) wear smart devices (such as smart glasses) to carry out their daily work. The smart devices collect audio and video data in real time while they are working. The audio data is converted into text data, and emotions are analyzed from the video data.

[0333] Data collection

[0334] Smart devices collect real-time audio and video data of employees' work activities. This data is collected by a data collection tool. The audio data is converted into text data using Google Cloud Speech-to-Text, and the video data is subjected to emotion analysis using Microsoft Azure® Face API.

[0335] Emotion analysis

[0336] The server processes the collected audio and video data using analytical means. It performs emotion analysis using the Azure Face API and extracts emotional data. This emotional data is expressed as parameters such as "happiness," "sadness," and "anger."

[0337] Data analysis

[0338] Generative AI identifies employee skills and characteristics by comprehensively analyzing text and emotion data extracted from voice data. This process uses OpenAI's GPT model, which uses natural language processing technology to analyze meeting content data and recognize skills and characteristics.

[0339] Suggestions and Notifications

[0340] Based on the analysis results, the server uses generative AI to propose appropriate employee transfers and project participation. These proposals are then notified to managers and staff in the relevant departments. Notifications are sent via email or internal communication systems.

[0341] Feedback and Ratings

[0342] Based on the proposal, the manager will hold another one-on-one meeting with the employee and collect feedback on the results. This feedback data is also collected as voice data and converted into text data and emotion data. The server passes the feedback data to the generative AI and evaluates the appropriateness of the proposal.

[0343] Specific examples

[0344] For example, suppose Employee A is working at a logistics center, replenishing shelves with products. If Employee A reports, "I struggled at first with the new work procedures, but I was able to complete the work smoothly in the end," the smart device will record this conversation and send it to the server as text data. The emotion analysis means will then identify from this content that the employee is expressing great joy.

[0345] The generative AI analyzes emotional and text data, identifies that Employee A has mastered efficient work procedures, and suggests a similar approach next time. An example of a specific prompt would be: "Analyze the emotions of employees at the logistics center and suggest an efficient process. Consider skills and emotions. Meeting content: Employee A has been very busy this month and had difficulty getting used to new work procedures, but ultimately reported that the work went smoothly. Emotion data: {"Happiness": 0.8, "Sadness": 0.1, "Anger": 0.1}."

[0346] This series of processes allows for a comprehensive evaluation of employee emotions, improving work efficiency and employee satisfaction.

[0347] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0348] Step 1:

[0349] The user wears the smart device and starts working. The smart device collects audio and video data in real time while the employee is working. The input is audio and video data during work, and the collected data is recorded as output.

[0350] Step 2:

[0351] The device converts the collected voice data into text data using Google Cloud Speech-to-Text. In this conversion process, the input is voice data and the output is text data. The voice data is transcribed.

[0352] Step 3:

[0353] The device performs emotion analysis on the collected video data using the Microsoft Azure Face API. It receives video data as input and obtains emotion parameters (happiness, sadness, anger, etc.) as output. The emotion analysis method identifies the employee's emotions from the video data.

[0354] Step 4:

[0355] The terminal sends the collected and converted text data and emotion data to the server. The input is text data and emotion data, and the data sent to the server is the output.

[0356] Step 5:

[0357] The server processes the received text data and emotional data using analytical means. The input is text data and emotional data, and analyzed skill and characteristic information is output. Generative AI performs data analysis using natural language processing technology.

[0358] Step 6:

[0359] Based on the analysis results, the generative AI will suggest appropriate transfers or project participation for employees. The input is the analysis results (skills, characteristics, and emotional data), and the output is a generated recommendation. An example of a specific prompt would be, "Analyze the emotions of employees at the logistics center and suggest an efficient process. Skills and emotions will be taken into consideration. Meeting content: Employee A has been very busy this month and reported that he had difficulty getting used to new work procedures, but that the work ultimately went smoothly. Emotion data: { "Happiness": 0.8, "Sadness": 0.1, "Anger": 0.1}."

[0360] Step 7:

[0361] The server notifies the generated proposal to the manager or person in charge of the relevant department. The proposal content is input and the notification is output. Notification is made via email or the internal communication system.

[0362] Step 8:

[0363] The manager then holds a one-on-one meeting with the employee based on the proposal and collects feedback on the results. The proposal is input and feedback data is output.

[0364] Step 9:

[0365] The device records the contents of the feedback meeting as audio data and converts it into text data using Google Cloud Speech-to-Text. The input is audio data and the output is text data.

[0366] Step 10:

[0367] The device performs emotion analysis on the video data of the feedback meeting using the Microsoft Azure Face API. The video data is input, and emotion parameters are obtained as output.

[0368] Step 11:

[0369] The server receives the feedback data and passes it to the generative AI, which takes text data and emotion data as input and outputs the analysis results.

[0370] Step 12:

[0371] Generative AI analyzes feedback and evaluates the appropriateness of proposals. The input is feedback data, and the output is an evaluation result. Based on this evaluation, new proposals and improvements are generated.

[0372] 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.

[0373] 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.

[0374] 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.

[0375] [Second embodiment]

[0376] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0377] 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.

[0378] 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).

[0379] 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.

[0380] 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.

[0381] 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).

[0382] 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. 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.

[0383] 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.

[0384] 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.

[0385] 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.

[0386] 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.

[0387] 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."

[0388] The present invention provides a system for efficiently managing and utilizing human resource skills within a company. Hereinafter, an embodiment of the present invention will be described in detail.

[0389] System Overview

[0390] This system collects, analyzes, and proposes employee skills and characteristics through regular one-on-one meetings between employees and generative AI. Specifically, it collects and analyzes the content of meetings with employees, proposes appropriate transfers and project participation, and finally collects and evaluates feedback.

[0391] Data collection

[0392] Once a month, users (employees) use company devices to hold one-on-one meetings with generative AI. During these meetings, the devices record the meeting content as audio and simultaneously convert the audio data into text data. This text data is also used as subtitle information for the meeting content. The collected data is sent from the devices to a server.

[0393] Data analysis

[0394] The server stores the received meeting content data in a dedicated database. The data is then passed to a generative AI analysis module. The generative AI uses natural language processing (NLP) to analyze the text data and extract important keywords and phrases. This allows employee skills and characteristics to be identified.

[0395] Suggestions and Notifications

[0396] Based on the analysis results, the server updates the employee skill set and characteristics database. The generative AI then uses this data to create appropriate employee transfer and project participation proposals. The proposals are then notified to managers and staff in the relevant departments via the server.

[0397] Feedback and Ratings

[0398] The person in charge will hold another one-on-one meeting with the employee based on the proposal and receive feedback on the proposal. This feedback information will again be sent from the device to the server and collected. The server will then pass the collected feedback to the generative AI and evaluate the appropriateness of the proposal.

[0399] Specific examples

[0400] For example, employee A belongs to the sales department and holds the following monthly one-on-one meeting. During the meeting, the user says, "This month, I focused particularly on negotiating with new clients, and I felt that my negotiation skills were one of my strengths." The device records this conversation and sends it to the server as text data.

[0401] The server passes the data to the generative AI, which analyzes the text data and extracts keywords such as "negotiation skills" and "new client," thereby identifying that employee A has strengths in negotiation skills. The server then updates the database for employee A, and the generative AI creates a proposal to transfer employee A to a new project and notifies the sales department manager. The manager discusses the proposal with employee A in the next one-on-one meeting and collects feedback. This feedback is again evaluated by the server and the generative AI to determine the appropriateness of the proposal.

[0402] In this way, the present invention can efficiently manage and utilize the skills and characteristics of employees, contributing to the growth and development of a company.

[0403] The processing flow will be explained below.

[0404] Step 1:

[0405] A user (employee) starts a one-on-one meeting with a generative AI using a company device. The user launches a dedicated application and presses the start button.

[0406] Step 2:

[0407] The device records the contents of the meeting as audio data in real time. At the same time, the audio data is converted into text data using natural language processing technology. The converted text data is also used as subtitle information for the meeting.

[0408] Step 3:

[0409] After the meeting ends, the device sends the recorded audio data and converted text data to the server, which then stores the received data in a dedicated database.

[0410] Step 4:

[0411] The server passes the stored text data to the generative AI's analysis module, where the generative AI uses natural language processing technology to analyze the text data.

[0412] Step 5:

[0413] Generative AI extracts important keywords and phrases from meeting content, for example, identifying keywords like "negotiation skills" and "new clients" and identifying employee skills and traits.

[0414] Step 6:

[0415] The server reflects the analysis results in the employee database and updates the employee's skill set and characteristics. In the case of employee A, a new skill data item, "Negotiation Skills: High," is added.

[0416] Step 7:

[0417] Based on the updated data, the generative AI generates proposals for appropriate employee transfers and project participation. For example, it creates a proposal to transfer Employee A to a large contract project in the sales department.

[0418] Step 8:

[0419] The server notifies the manager or person in charge of the relevant department of the proposal, and the notification is sent via email or internal messenger.

[0420] Step 9:

[0421] The user (person in charge) will hold another one-on-one meeting with the employee based on the proposal to discuss the proposal. The contents of this feedback meeting will also be recorded and converted into text.

[0422] Step 10:

[0423] The device sends the feedback meeting data to a server, which then passes it on to the generative AI, which analyzes the feedback and evaluates the appropriateness of the proposals.

[0424] Step 11:

[0425] The server stores the generative AI's evaluation results in a database and, if necessary, starts a new cycle with further suggestions and improvements.

[0426] This series of processes ensures that employee skills and characteristics are managed and utilized efficiently, improving the performance of the entire organization.

[0427] Example 1

[0428] 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."

[0429] Traditionally, the management and utilization of human resource skills within companies has been largely manual, making it difficult to efficiently collect and analyze data. In particular, there has been a lack of methods for accurately understanding employees' skills and characteristics and assigning them to appropriate tasks and projects based on that information. In addition, the process of collecting feedback and evaluating the appropriateness of proposals is cumbersome. This has limited the ability to maximize employee capabilities and promote corporate growth.

[0430] 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.

[0431] In this invention, the server includes information collection means for collecting the contents of meetings held between employees and the generative AI, data analysis means for analyzing the meeting content data collected from the information collection means, proposal generation means for proposing appropriate transfers or work participation for employees based on the employee skills and characteristics identified by the data analysis means, communication means for notifying relevant departments of the contents of the proposals made by the proposal generation means, opinion collection means for collecting feedback based on the contents of the notifications made by the notification means, and aptitude evaluation means for analyzing the feedback collected by the opinion collection means and evaluating the appropriateness of the contents of the proposals. This makes it possible to efficiently collect and analyze employee skills and characteristics, generate appropriate work proposals, and evaluate the feedback based on the proposals.

[0432] "Information collection means" refers to a device or system for collecting the contents of meetings held between employees and generative AI.

[0433] The "data analysis means" is a device or process for analyzing the conference content data collected from the information collection means.

[0434] The "proposal generating means" is a device or system for proposing appropriate transfers or work participation of employees based on the skills and characteristics of the employees identified by the data analysis means.

[0435] The "communication means" is a device or system for notifying the relevant departments of the contents of the proposal made by the proposal generating means.

[0436] The "opinion collection means" is a device or system for collecting feedback based on the content of the notification by the notification means.

[0437] The "suitability evaluation means" is a device or system for analyzing the feedback collected by the opinion collection means and evaluating the suitability of the proposal content.

[0438] "Generative AI" is an artificial intelligence system that uses natural language processing technology to analyze meeting content data and generate appropriate business proposals.

[0439] "Meeting content data" refers to information that records statements and exchanges made during meetings between employees and generative AI.

[0440] The present invention is a system for improving the efficiency of human resource skill management and utilization within a company. Specifically, it includes a process for analyzing data collected through one-on-one meetings between employees and generative AI, and proposing appropriate employee transfers and project participation. An embodiment of this system is described in detail below.

[0441] Data collection

[0442] Once a month, users (employees) use their company devices to hold one-on-one meetings with the generative AI. During these meetings, the devices use the following hardware and software:

[0443] Hardware: Microphones, recording devices

[0444] Software: Google Cloud Speech-to-Text

[0445] The device records the meeting contents as audio and converts the audio data into text data in real time using Google Cloud Speech-to-Text. This converted text data is also used as subtitle information for the meeting contents. The collected data is sent from the device to the server using HTTPS communication.

[0446] Data reception and storage

[0447] The server receives the text data of the conference contents sent and stores it in a dedicated database. This database uses MySQL, PostgreSQL, etc. The server performs transaction control to ensure data integrity and security.

[0448] Data analysis

[0449] The server passes the stored text data to a generative AI analysis module, which uses natural language processing (NLP) techniques such as OpenAI's GPT-4 to analyze the text data and extract key keywords and phrases that identify employee skills and traits.

[0450] Proposal creation

[0451] The server updates the employee skill set and characteristics database based on the results of the generative AI analysis. The generative AI then uses the updated data to create appropriate employee transfer and project participation proposals. These proposals are compiled into documents using natural language generation technology.

[0452] proposal notification

[0453] The server then notifies the relevant department managers and staff of the created proposals via email, Microsoft Teams, Slack, and other communication methods, including the data that formed the basis of the proposal and important keywords.

[0454] Feedback collection and evaluation

[0455] The person in charge holds another one-on-one meeting with the employee based on the proposal content, and enters the feedback obtained from the meeting into the device. The device then sends this feedback information to the server. The server stores the received feedback in a database and passes it on to the generative AI. The generative AI uses the feedback data to evaluate the appropriateness of the proposal content. Sentiment analysis technology and other techniques are used in the evaluation, and the results of this evaluation are reflected in the creation of the next proposal.

[0456] Specific examples

[0457] For example, employee A belongs to the sales department and holds the following monthly one-on-one meeting. During the meeting, the user says, "This month, I focused particularly on negotiating with new clients, and I felt that my negotiation skills were one of my strengths." The device records this conversation, converts it into text data using Google Cloud Speech-to-Text, and sends it to the server.

[0458] The server passes the data to a generative AI (e.g., OpenAI GPT-4), which analyzes the text data and extracts keywords such as "negotiation skills" and "new client." This identifies that employee A has strengths in negotiation skills. The server then updates the database for employee A, and the generative AI creates a proposal to transfer employee A to a new project and notifies the sales department manager. The manager discusses the proposal with employee A in the next one-on-one meeting and collects feedback. This feedback is again evaluated by the server and the generative AI to determine the appropriateness of the proposal.

[0459] Prompt Sentence Examples

[0460] "Employee A mentioned in this month's one-on-one meeting that he focused particularly on negotiating with new clients and felt that negotiation skills were one of his strengths. Based on this, please conduct an analysis of Employee A's skills and characteristics and create an appropriate project participation proposal."

[0461] In this way, the present invention can efficiently manage and utilize the skills and characteristics of employees, contributing to the growth and development of a company.

[0462] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0463] Step 1: Data collection

[0464] Users use company devices to hold regular one-on-one meetings with generative AI. When a meeting begins, the device records audio data through a microphone. This audio data becomes the input. The device then converts the audio data into text data in real time using Google Cloud Speech-to-Text. Here, the audio data is recognized as a string of characters, and data processing is performed to convert each utterance into text format. The converted text data becomes the output and is prepared for the next step.

[0465] Step 2: Send data

[0466] The terminal sends the generated text data to the server via HTTPS. This process uses encryption to ensure data security. The input is the converted text data, and the output is the secure receipt of the data by the server.

[0467] Step 3: Receiving and storing data

[0468] The server receives text data sent from the terminal. The input is text data sent via HTTPS communication, and the server stores the data in a dedicated database. Transaction control is used to maintain the integrity of the database during storage. The output is text data saved in the database.

[0469] Step 4: Data analysis

[0470] The server passes the text data stored in the database to the generative AI analysis module. The input is the text data retrieved from the database. The analysis module (e.g., OpenAI GPT-4) analyzes the data using natural language processing technology and extracts important keywords and phrases. This analysis identifies employee skills and characteristics. The output is the keywords resulting from the analysis and the identified skills and characteristics.

[0471] Step 5: Proposal Generation

[0472] The server updates the employee skill set and characteristics database based on the analysis results output by the generative AI. Using this skill set and characteristics data, the generative AI again creates appropriate transfer and project participation proposals. The input is the analysis results, and the output is the generated proposal.

[0473] Step 6: Proposal Notification

[0474] The server notifies the necessary managers and personnel of the generated proposals. The input is the generated proposal, and the output is a notification via email, Microsoft Teams, or Slack. This notification process also includes the data that formed the basis of the proposal and important keywords.

[0475] Step 7: Gather feedback

[0476] The person in charge holds another one-on-one meeting with the employee based on the proposal, and inputs the feedback obtained during the meeting into the terminal. The input is the feedback obtained during the meeting, and the terminal sends it back to the server. The output is the transmission of the feedback data to the server.

[0477] Step 8: Feedback evaluation

[0478] The server stores the received feedback in a database and passes it to the generative AI. The input is the feedback data, which the generative AI analyzes and evaluates the appropriateness of the proposal. Sentiment analysis technology and other techniques are used for the evaluation. The output is the evaluation result regarding the appropriateness of the proposal, which is reflected in the creation of the next proposal.

[0479] (Application example 1)

[0480] 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."

[0481] Modern companies are required to accurately understand the skills and characteristics of their personnel and propose appropriate transfers and project participation. In particular, in on-site work such as factories, workers' skills are directly linked to work efficiency and productivity, so proper skill management and rapid feedback are essential. However, in current systems, these processes are often carried out manually, which is time-consuming and labor-intensive. Furthermore, worker skill evaluation relies on subjective judgment, which can lead to inappropriate evaluations. A system that can solve these issues is needed.

[0482] 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.

[0483] In this invention, the server includes: a data collection means for collecting the contents of meetings held between employees and the generative AI; an analysis means for analyzing the meeting content data collected by the data collection means; a proposal means for proposing appropriate employee transfers or project participation based on the employee's skills and characteristics identified by the analysis means; a notification means for notifying relevant departments of the contents of the proposals made by the proposal means; a feedback collection means for collecting feedback based on the contents of the notifications made by the notification means; an evaluation means for analyzing the feedback collected by the feedback collection means and evaluating the appropriateness of the proposals; a means for collecting speech and work content during work using a recording device attached to an information processing device used by the worker; a conversion means for converting the collected speech data into text data and transmitting it to the generative AI server; and a proposal means for evaluating the worker's skills based on the text data generated by the conversion means and proposing appropriate reassignment to a work position. This makes it possible to efficiently and accurately grasp the worker's skills and characteristics and quickly propose appropriate transfers and project participation.

[0484] "Data collection means" refers to a means of collecting data such as speech during meetings and work between workers and generative AI, as well as the content of the work, using information processing devices and recording devices.

[0485] The "analysis means" is a means for analyzing the data collected by the data collection means and extracting important information and keywords.

[0486] The "suggestion means" is a means for proposing appropriate transfers or project participation based on the skills and characteristics of employees or workers identified by the analysis means.

[0487] The "notification means" is a means for notifying the relevant departments and managers of the contents of the proposal made by the proposal means.

[0488] The "feedback collection means" is a means for collecting feedback based on the content of the notification by the notification means.

[0489] The "evaluation means" is a means for analyzing the feedback collected by the feedback collection means and evaluating the appropriateness of the proposal content.

[0490] The "recording device" is an information processing device for recording the voices of workers and the details of their work.

[0491] The "conversion means" is a means for converting collected voice data into text data and sending it to the generative AI server.

[0492] "Generative AI" is artificial intelligence that analyzes collected text data and uses natural language processing technology to evaluate skills.

[0493] This invention is a system that efficiently manages the skills and characteristics of human resources within a company and proposes appropriate transfers and project participation. This system utilizes smart glasses and AI technology to automate the skill evaluation and feedback management of field workers.

[0494] System Overview

[0495] The system is configured as follows:

[0496] 1. Data collection methods:

[0497] Smart glasses are information processing devices used by workers that record their speech and the details of their work. Data is collected using a microphone and camera built into the smart glasses, allowing for real-time recording of the worker's work status and voice.

[0498] 2. Conversion method:

[0499] The voice data collected by the smart glasses is converted into text data using voice recognition software (e.g., the SpeechRecognition module). The converted text data is then sent to the generative AI server.

[0500] 3. Analysis method:

[0501] The generative AI server analyzes the collected text data and uses a generative AI model (e.g., OpenAI API) to extract important keywords and phrases from the text data using natural language processing technology and identify the skills of the workers.

[0502] 4. Proposal method:

[0503] Based on the analysis results, the generative AI server evaluates the worker's skill set and proposes appropriate transfers or project participation. These proposals are automated and notified to the worker and relevant department managers as appropriate.

[0504] 5. Means of notification:

[0505] The proposals are then sent to the relevant departments and managers via email or a dedicated application.

[0506] 6. Feedback Collection Methods:

[0507] After the worker performs the work in the new position based on the proposal, the results of the work and their impressions are collected as feedback. Voice data is collected again using smart glasses and converted into text data.

[0508] 7. Evaluation Methods:

[0509] The collected feedback data is reanalyzed to evaluate the appropriateness of the underlying proposals, and a generative AI model is used to derive improvements and new proposals from the feedback.

[0510] Specific examples

[0511] For example, suppose Worker A is installing new wiring and says, "I've learned how to install new wiring. I'm good at detailed work. I quickly discovered a problem with a specific part." The smart glasses will record this voice and convert it into text data.

[0512] The converted text is sent to the generative AI server as the following prompt:

[0513] Example prompt sentence:

[0514] Analyze the statements of the workers below, extract keywords, and evaluate their skill sets.

[0515] "I learned how to install new wiring. I'm good at detailed work. I quickly identified a problem with a specific component."

[0516] The generative AI analyzes this prompt and extracts keywords such as "wiring installation," "detailed work," and "detecting defects in specific components." It then evaluates that Worker A excels in these skills and proposes an appropriate new work position. This proposal is notified to the manager of the relevant department and ultimately fed back to Worker A. The feedback is again collected by the smart glasses and evaluated by the generative AI model. This makes it possible to optimize the proposal.

[0517] In this way, the present invention makes it possible to quickly and accurately evaluate the skills and characteristics of workers and efficiently propose appropriate transfers and project participation.

[0518] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0519] Step 1:

[0520] The user puts on the smart glasses and begins working. The smart glasses' built-in microphone and camera record audio and video while working. This allows the user's work status and comments to be collected in real time. The input is the audio and video of the work being done, and the output is the recorded data.

[0521] Step 2:

[0522] The device converts the collected voice data into text data. Voice recognition software (e.g., SpeechRecognition module) is used to convert the voice data into text information. The input is voice data, and the output is converted text data. This process results in the speech written in natural language.

[0523] Step 3:

[0524] The device sends the converted text data to the generative AI server. Transmission is via internet communication. The input is the text data, and the output is a notification to the generative AI server that data transmission is complete. This passes the text data to the server for analysis.

[0525] Step 4:

[0526] The server uses generative AI to analyze the received text data. Using a generative AI model (e.g., OpenAI's API), keywords and important phrases are extracted through analysis. The input is text data, and the output is the analyzed keywords and phrases. This process identifies the skills and characteristics of the worker.

[0527] Step 5:

[0528] The server creates proposals based on the analysis results. The proposals include new work positions or project participation that are suited to the worker's skills and characteristics. The input is the analyzed keywords and phrases, and the output is the proposals. The proposals are generated automatically.

[0529] Step 6:

[0530] The server notifies the relevant departments and administrators of the proposal contents. Notifications are sent via email or a dedicated application. The input is the proposal contents, and the output is a notification of notification completion, allowing the administrator to check the proposal.

[0531] Step 7:

[0532] The user performs a new task based on the suggestions. After completing the task, they record their impressions and any problems they have as feedback via voice. Data is collected again using smart glasses. The input is the user's voice feedback, and the output is the recorded feedback data.

[0533] Step 8:

[0534] The terminal converts the collected feedback voice data back into text data and sends it to the generative AI server using speech recognition software. The input is the feedback voice data, and the output is the converted feedback text data.

[0535] Step 9:

[0536] The server analyzes the collected feedback data and evaluates the appropriateness of the proposals. A generative AI model is used to derive improvements and new proposals from the feedback. The input is the feedback text data, and the output is the evaluation results and improvement proposals. This process optimizes the proposals for future use.

[0537] 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.

[0538] The present invention provides a system for efficiently managing and utilizing human resource skills and emotions within a company. Hereinafter, an embodiment of the present invention will be described in detail.

[0539] System Overview

[0540] This system collects, analyzes, and proposes employee skills, characteristics, and emotions through regular one-on-one meetings between employees and generative AI. Specifically, it collects the content of meetings with employees, analyzes their emotions using an emotion engine, proposes appropriate transfers or project participation, and finally collects and evaluates feedback.

[0541] Data collection

[0542] Once a month, users (employees) use their company devices to hold one-on-one meetings with the generative AI. The user launches a dedicated application and presses the start button for the meeting. The device then records the contents of the meeting as audio data in real time. At the same time, the audio data is converted into text data. This text data is also used as subtitle information for the meeting. The collected data is sent from the device to a server.

[0543] Emotion analysis

[0544] The server stores the received meeting content data in a dedicated database. The data is then passed to a generative AI analysis module, where an emotion engine is built in to recognize and extract user emotions from the meeting content data. For example, emotions such as joy, sadness, and anger are identified. The emotion engine analyzes emotions from voice tone and text content.

[0545] Data analysis

[0546] The generative AI comprehensively analyzes the emotion data provided by the emotion engine and the text data of meeting contents to identify employee skills and characteristics. Based on the extracted emotion and skill data, it creates proposals for appropriate employee job assignments and project participation.

[0547] Suggestions and Notifications

[0548] The server reflects the analysis results in the employee database, updating the employee's skill set and characteristics. The generative AI then takes emotional data into account and generates suitable transfer and project participation proposals for the employee. The proposals are then sent via the server to managers and staff in the relevant departments.

[0549] Feedback and Ratings

[0550] The person in charge holds another one-on-one meeting with the employee based on the proposal and collects feedback on the results. The contents of this feedback meeting are also recorded and converted into text. The device sends the feedback meeting data to the server, which then passes it on to the generative AI. The generative AI analyzes the feedback and evaluates the appropriateness of the proposal.

[0551] Specific examples

[0552] For example, employee B belongs to the development department and holds the following monthly one-on-one meeting. During the meeting, the user says, "This month I particularly struggled with learning a new technology, but I finally succeeded and I'm very happy." The device records this conversation and sends it to the server as text data. From this content, the emotion engine identifies changes in emotion from distress to joy.

[0553] The generative AI analyzes emotion data along with keywords related to "acquiring new technologies" and identifies that employee B has a high ability to acquire new technologies and feels a sense of accomplishment. The server then updates the database for employee B, and the generative AI proposes employee B's participation in a new project and notifies the development department manager. The manager then discusses the proposal with employee B in the next one-on-one meeting and collects feedback. This feedback is again evaluated by the server and the generative AI to determine the appropriateness of the proposal.

[0554] This series of processes enables efficient management and utilization of employee skills and emotions, contributing to the growth and development of the company.

[0555] The processing flow will be explained below.

[0556] Step 1:

[0557] A user (employee) starts a one-on-one meeting with a generative AI using a company device. The user launches a dedicated application and presses the start button.

[0558] Step 2:

[0559] The device records the contents of the meeting as audio data in real time. At the same time, the audio data is converted into text data using natural language processing technology. The converted text data is also used as subtitle information for the meeting.

[0560] Step 3:

[0561] After the meeting ends, the device sends the recorded audio data and converted text data to the server, which then stores the received data in a dedicated database.

[0562] Step 4:

[0563] The server passes the saved text and audio data to the generative AI analysis module, where the emotion engine analyzes the meeting content data to recognize the user's emotions and extracts emotional data.

[0564] Step 5:

[0565] The emotion engine analyzes the user's emotions from the meeting content based on voice tone and context, identifying emotions such as joy, sadness, and anger.

[0566] Step 6:

[0567] The generative AI comprehensively analyzes the emotional and text data provided by the emotion engine to identify employee skills and traits, including skill extraction based on text analysis and emotional state assessment based on emotion analysis.

[0568] Step 7:

[0569] The server reflects the analysis results in the employee database and updates the employee's skill set, characteristics, and emotional information. For example, for employee A, the data "Negotiation skills: High" and "Recent emotional state: Joy" are added.

[0570] Step 8:

[0571] Based on the updated database, the generative AI generates proposals for appropriate employee transfers and project participation. In doing so, it takes into account not only skill data but also emotional data when creating the proposals. For example, it might make a proposal such as, "Employee A should be transferred to a large contract project. As his emotional state has been stable recently, an environment with less mental stress would be suitable."

[0572] Step 9:

[0573] The server notifies managers and staff in the relevant departments of the generative AI's proposals, via email or internal messenger.

[0574] Step 10:

[0575] The user (person in charge) will hold a one-on-one meeting with the employee based on the proposal and collect feedback on the results. The contents of this feedback meeting will also be recorded and converted into text.

[0576] Step 11:

[0577] The device sends the feedback meeting data to a server, which then passes it on to the generative AI, which analyzes the feedback and evaluates the appropriateness of the proposals.

[0578] Step 12:

[0579] The server stores the results of the generative AI evaluation in a database and initiates a new cycle including further suggestions and improvements as needed, thereby enabling efficient management of employee skills and emotions, contributing to the growth and development of the company as a whole.

[0580] Example 2

[0581] 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."

[0582] Companies are seeking to efficiently manage and utilize the skills and emotions of their employees. Accurately understanding employees' emotions and skills and making appropriate transfer and project participation proposals based on that information is essential for corporate growth. However, traditional methods make it difficult to do this efficiently, and analyzing emotions and collecting and evaluating feedback, in particular, requires a great deal of time and effort.

[0583] 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.

[0584] In this invention, the server includes: a data collection means for collecting the contents of meetings held between employees and the generative AI; a conversion means for converting the conference audio data collected from the data collection means into text data; a transmission means for transmitting the text data and audio data to the server; an analysis means for analyzing the data; an emotion analysis means for analyzing the emotions of employees identified by the analysis means; a data analysis means for identifying the skills and characteristics of employees based on the emotion analysis means and the conference content text data; a proposal means for proposing appropriate transfers or project participation for employees based on the data analysis means; a notification means for notifying relevant departments of the contents of the proposals made by the proposal means; a feedback collection means for collecting feedback based on the contents of the notifications made by the notification means; and an evaluation means for analyzing the feedback collected by the feedback collection means and evaluating the appropriateness of the proposals. This enables efficient management of employees' emotions and skills and the proposal of appropriate transfers or project participation based on the results.

[0585] "Data collection means" refers to a means for collecting the contents of meetings held between employees and generative AI.

[0586] The "conversion means" is a means for converting collected conference voice data into text data.

[0587] The "transmission means" is a means for transmitting text data and voice data to the server.

[0588] "Analysis means" refers to means for analyzing collected data.

[0589] The "emotion analysis means" is a means for analyzing the emotions of the employees identified by the analysis means.

[0590] The "data analysis means" is a means for identifying the skills and characteristics of employees based on the emotion analysis means and the meeting content text data.

[0591] "Proposal means" refers to a means for proposing appropriate transfers or project participation of employees based on data analysis means.

[0592] The "notification means" is a means for notifying the relevant departments of the content of the proposal made by the proposal means.

[0593] The "feedback collection means" is a means for collecting feedback based on the notification content.

[0594] The "evaluation means" is a means for analyzing the feedback collected by the feedback collection means and evaluating the appropriateness of the proposal content.

[0595] The present invention is a system for efficiently managing and utilizing human resource skills and emotions within a company. An embodiment of the present invention will now be described in detail.

[0596] System Overview

[0597] This system collects employee skills, characteristics, and emotions through regular one-on-one meetings between employees and generative AI, and then analyzes and proposes the data. The system includes the following detailed processes:

[0598] Data collection

[0599] Once a month, users (employees) use their company's devices to hold one-on-one meetings with the generative AI. The user launches a dedicated application and presses the start button for the meeting. The device records the meeting content as audio data in real time. At the same time, the audio data is converted into text data. This text data is also used as subtitle information for the conversation. The collected data is sent from the device to a server.

[0600] Emotion analysis

[0601] The server stores the received meeting content data in a dedicated database. The data is then passed to a generative AI analysis module, where an emotion engine is built in to recognize and extract user emotions from the meeting content data. For example, emotions such as joy, sadness, and anger are identified. The emotion engine analyzes emotions from voice tone and text content.

[0602] Data analysis

[0603] The generative AI comprehensively analyzes the emotion data provided by the emotion engine and the text data of meeting contents to identify employee skills and characteristics. Based on the extracted emotion and skill data, it creates proposals for appropriate employee job assignments and project participation.

[0604] Suggestions and Notifications

[0605] The server reflects the analysis results in the employee database, updating the employee's skill set and characteristics. The generative AI then takes emotional data into account and generates suitable transfer and project participation proposals for the employee. The proposals are then sent via the server to managers and staff in the relevant departments.

[0606] Feedback and Ratings

[0607] The person in charge holds another one-on-one meeting with the employee based on the proposal and collects feedback on the results. The contents of this feedback meeting are also recorded and converted into text. The device sends the feedback meeting data to the server, which then passes it on to the generative AI. The generative AI analyzes the feedback and evaluates the appropriateness of the proposal.

[0608] Specific examples

[0609] For example, employee B belongs to the development department and holds the following monthly one-on-one meeting. During the meeting, the user says, "This month I particularly struggled with learning a new technology, but I finally succeeded and I'm very happy." The device records this conversation and sends it to the server as text data. From this content, the emotion engine identifies changes in emotion from distress to joy.

[0610] The generative AI analyzes emotion data along with keywords related to "acquiring new technologies" and identifies that employee B has a high ability to acquire new technologies and feels a sense of accomplishment. The server then updates the database for employee B, and the generative AI proposes employee B's participation in a new project and notifies the development department manager. The manager then discusses the proposal with employee B in the next one-on-one meeting and collects feedback. This feedback is again evaluated by the server and the generative AI to determine the appropriateness of the proposal.

[0611] Prompt Sentence Examples

[0612] Employee B, who works in the development department, said, "I struggled to learn new technology this month, but I finally succeeded and I'm very happy." Analyze this conversation to identify changes in the employee's emotions and skill characteristics.

[0613] The above is an embodiment of the present invention. This system enables efficient management and utilization of human resource skills and emotions within a company.

[0614] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0615] Step 1:

[0616] The user launches the dedicated application on the device and presses the "Start Meeting" button.

[0617] Input: User actions

[0618] Output: Start of meeting

[0619] Specific operation: The user launches the dedicated application and clicks the "Start Conference" button, which puts the device into conference recording mode.

[0620] Step 2:

[0621] The terminal records the contents of the meeting in real time and converts the voice data into text data using a voice recognition engine.

[0622] Input: Meeting audio

[0623] Output: Text data

[0624] How it works: The device records the audio of the meeting and converts the audio data into text data in real time using a speech recognition engine such as Google Cloud Speech-to-Text.

[0625] Step 3:

[0626] The terminal transmits the converted text data and the original voice data to the server.

[0627] Input: Text data and audio data

[0628] Output: Send data to the server

[0629] Specific operation: The device encrypts text data and voice data via the SSL / TLS protocol and sends it to the server.

[0630] Step 4:

[0631] The server stores the received data in a database and passes it on to the generative AI analysis module.

[0632] Input: Text data and audio data

[0633] Output: Storing in a database and passing data to analysis modules

[0634] Specific operation: The server stores the received data in a dedicated database and classifies it by user ID. The data is then passed to the generative AI analysis module.

[0635] Step 5:

[0636] The emotion engine analyzes the data and identifies the user's emotion.

[0637] Input: Text data and audio data

[0638] Output: Emotion data

[0639] What it does: An emotion engine (e.g., IBM Watson Tone Analyzer) analyzes the tone of text and speech to identify the user's emotions, such as joy, sadness, or anger.

[0640] Step 6:

[0641] Generative AI comprehensively analyzes emotional data and text data from meeting content to extract employee skills and characteristics.

[0642] Input: Emotion data and text data

[0643] Output: Skill data and attribute data

[0644] How it works: Generative AI integrates emotional and textual data to extract skills and characteristics, such as the speed of technological acquisition and the ability to adapt to challenges.

[0645] Step 7:

[0646] The server reflects the analysis results in the employee database, and the generative AI generates suggestions.

[0647] Input: Skill data and attribute data

[0648] Output: Proposal data

[0649] Specific operation: The server reflects skill data and characteristic data in the employee database, and the generative AI generates appropriate proposals for employee transfers and project participation.

[0650] Step 8:

[0651] The server notifies the manager or person in charge of the relevant department of the proposal.

[0652] Input: Proposal data

[0653] Output: Notification data

[0654] Specific operation: The server notifies the managers and staff of the relevant departments of the generated proposals via email or a dedicated notification system.

[0655] Step 9:

[0656] The person in charge will hold another one-on-one meeting with the employee to discuss the proposal and gather feedback.

[0657] Input: Proposal data

[0658] Output: Feedback data

[0659] Specific operations: The person in charge discusses the proposal with employees, records the audio of the feedback meeting, and converts it into text data.

[0660] Step 10:

[0661] The device sends the feedback meeting data to the server, and the generative AI evaluates it.

[0662] Input: Feedback data

[0663] Output: Evaluation data

[0664] Specific operation: The device sends the text and audio data of the feedback meeting to the server, which then passes the data to the generative AI. The generative AI analyzes the feedback data and evaluates the appropriateness of the proposal.

[0665] These are the processing steps of this system. At each step, data is collected, converted, analyzed, proposed, notified, and feedback is collected and evaluated, allowing for efficient management and utilization of employee skills and emotions.

[0666] (Application example 2)

[0667] 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."

[0668] It is extremely important to understand the skills and characteristics of employees within a company and to make appropriate work plans. However, it is difficult to conduct a comprehensive evaluation that includes employee emotions, which has made improving work efficiency and employee satisfaction a challenge. In addition, it is difficult to collect and analyze data accurately in real time using paper-based or simple digital tools, so a new system to solve these issues was needed.

[0669] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0670] In this invention, the server includes a data collection means for collecting the contents of meetings held between employees and the generative AI, an analysis means for analyzing the meeting content data collected by the data collection means, a proposal means for proposing appropriate employee transfers or project participation based on the employee skills, characteristics, and emotional data identified by the analysis means, a notification means for notifying relevant departments of the contents of the proposals made by the proposal means, a feedback collection means for collecting feedback based on the contents of the notifications made by the notification means, an evaluation means for analyzing the feedback collected by the feedback collection means and evaluating the appropriateness of the contents of the proposals, and an emotion analysis means for grasping employee emotions in real time via smart devices. This allows for a comprehensive evaluation of employee emotions, enabling improved work efficiency and employee satisfaction.

[0671] "Employee" refers to an employee working within a company.

[0672] "Generative AI" refers to the entire system that uses artificial intelligence technology to analyze data and generate proposals.

[0673] "Data collection means" refers to the devices and processes that collect the contents of the meeting in the form of audio, video, etc.

[0674] "Analysis means" refers to the device and its functions that analyze employee skills, characteristics, emotions, etc. based on collected data.

[0675] "Proposal means" refers to a device and its functions that generate proposals for employee transfers and project participation based on the analysis results.

[0676] "Notification means" refers to a device and its function that notifies the manager or person in charge of the relevant department of the content of the generated proposal.

[0677] "Feedback collection means" refers to a device and its functionality for organizing and recording feedback collected based on suggestions.

[0678] "Evaluation means" refers to a device and its functions that analyzes collected feedback and evaluates the appropriateness of suggestions.

[0679] "Emotion analysis means" refers to a device and its functions that analyzes employee emotions in real time using a smart device.

[0680] "Smart devices" refers to portable or wearable electronic devices with advanced information processing capabilities, such as smartphones, smart glasses, and head-mounted displays.

[0681] "Natural language processing technology" refers to the technology that processes, understands, generates, and analyzes human language using a computer.

[0682] The present invention provides a system for improving the work efficiency and satisfaction of employees in a logistics center. As an embodiment of the present invention, a system is described that collects and analyzes work content and emotional data in real time when employees perform their work using smart devices (such as smart glasses).

[0683] System Overview

[0684] Users (employees) wear smart devices (such as smart glasses) to carry out their daily work. The smart devices collect audio and video data in real time while they are working. The audio data is converted into text data, and emotions are analyzed from the video data.

[0685] Data collection

[0686] Smart devices capture employees' work activities in real time as audio and video data. This data is collected by a data collection tool. The audio data is converted into text data using Google Cloud Speech-to-Text, and the video data is subjected to emotion analysis using the Microsoft Azure Face API.

[0687] Emotion analysis

[0688] The server processes the collected audio and video data using analytical means. It performs emotion analysis using the Azure Face API and extracts emotional data. This emotional data is expressed as parameters such as "happiness," "sadness," and "anger."

[0689] Data analysis

[0690] Generative AI identifies employee skills and characteristics by comprehensively analyzing text and emotion data extracted from voice data. This process uses OpenAI's GPT model, which uses natural language processing technology to analyze meeting content data and recognize skills and characteristics.

[0691] Suggestions and Notifications

[0692] Based on the analysis results, the server uses generative AI to propose appropriate employee transfers and project participation. These proposals are then notified to managers and staff in the relevant departments. Notifications are sent via email or internal communication systems.

[0693] Feedback and Ratings

[0694] Based on the proposal, the manager will hold another one-on-one meeting with the employee and collect feedback on the results. This feedback data is also collected as voice data and converted into text data and emotion data. The server passes the feedback data to the generative AI and evaluates the appropriateness of the proposal.

[0695] Specific examples

[0696] For example, suppose Employee A is working at a logistics center, replenishing shelves with products. If Employee A reports, "I struggled at first with the new work procedures, but I was able to complete the work smoothly in the end," the smart device will record this conversation and send it to the server as text data. The emotion analysis means will then identify from this content that the employee is expressing great joy.

[0697] The generative AI analyzes emotional and text data, identifies that Employee A has mastered efficient work procedures, and suggests a similar approach next time. An example of a specific prompt would be: "Analyze the emotions of employees at the logistics center and suggest an efficient process. Consider skills and emotions. Meeting content: Employee A has been very busy this month and had difficulty getting used to new work procedures, but ultimately reported that the work went smoothly. Emotion data: {"Happiness": 0.8, "Sadness": 0.1, "Anger": 0.1}."

[0698] This series of processes allows for a comprehensive evaluation of employee emotions, improving work efficiency and employee satisfaction.

[0699] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0700] Step 1:

[0701] The user wears the smart device and starts working. The smart device collects audio and video data in real time while the employee is working. The input is audio and video data during work, and the collected data is recorded as output.

[0702] Step 2:

[0703] The device converts the collected voice data into text data using Google Cloud Speech-to-Text. In this conversion process, the input is voice data and the output is text data. The voice data is transcribed.

[0704] Step 3:

[0705] The device performs emotion analysis on the collected video data using the Microsoft Azure Face API. It receives video data as input and obtains emotion parameters (happiness, sadness, anger, etc.) as output. The emotion analysis method identifies the employee's emotions from the video data.

[0706] Step 4:

[0707] The terminal sends the collected and converted text data and emotion data to the server. The input is text data and emotion data, and the data sent to the server is the output.

[0708] Step 5:

[0709] The server processes the received text data and emotional data using analytical means. The input is text data and emotional data, and analyzed skill and characteristic information is output. Generative AI performs data analysis using natural language processing technology.

[0710] Step 6:

[0711] Based on the analysis results, the generative AI will suggest appropriate transfers or project participation for employees. The input is the analysis results (skills, characteristics, and emotional data), and the output is a generated recommendation. An example of a specific prompt would be, "Analyze the emotions of employees at the logistics center and suggest an efficient process. Skills and emotions will be taken into consideration. Meeting content: Employee A has been very busy this month and reported that he had difficulty getting used to new work procedures, but that the work ultimately went smoothly. Emotion data: { "Happiness": 0.8, "Sadness": 0.1, "Anger": 0.1}."

[0712] Step 7:

[0713] The server notifies the generated proposal to the manager or person in charge of the relevant department. The proposal content is input and the notification is output. Notification is made via email or the internal communication system.

[0714] Step 8:

[0715] The manager then holds a one-on-one meeting with the employee based on the proposal and collects feedback on the results. The proposal is input and feedback data is output.

[0716] Step 9:

[0717] The device records the contents of the feedback meeting as audio data and converts it into text data using Google Cloud Speech-to-Text. The input is audio data and the output is text data.

[0718] Step 10:

[0719] The device performs emotion analysis on the video data of the feedback meeting using the Microsoft Azure Face API. The video data is input, and emotion parameters are obtained as output.

[0720] Step 11:

[0721] The server receives the feedback data and passes it to the generative AI, which takes text data and emotion data as input and outputs the analysis results.

[0722] Step 12:

[0723] Generative AI analyzes feedback and evaluates the appropriateness of proposals. The input is feedback data, and the output is an evaluation result. Based on this evaluation, new proposals and improvements are generated.

[0724] 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.

[0725] 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.

[0726] 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.

[0727] [Third embodiment]

[0728] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0729] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0730] 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).

[0731] 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.

[0732] 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.

[0733] 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).

[0734] 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. 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.

[0735] 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.

[0736] 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.

[0737] 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.

[0738] 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.

[0739] 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."

[0740] The present invention provides a system for efficiently managing and utilizing human resource skills within a company. Hereinafter, an embodiment of the present invention will be described in detail.

[0741] System Overview

[0742] This system collects, analyzes, and proposes employee skills and characteristics through regular one-on-one meetings between employees and generative AI. Specifically, it collects and analyzes the content of meetings with employees, proposes appropriate transfers and project participation, and finally collects and evaluates feedback.

[0743] Data collection

[0744] Once a month, users (employees) use company devices to hold one-on-one meetings with generative AI. During these meetings, the devices record the meeting content as audio and simultaneously convert the audio data into text data. This text data is also used as subtitle information for the meeting content. The collected data is sent from the devices to a server.

[0745] Data analysis

[0746] The server stores the received meeting content data in a dedicated database. The data is then passed to a generative AI analysis module. The generative AI uses natural language processing (NLP) to analyze the text data and extract important keywords and phrases. This allows employee skills and characteristics to be identified.

[0747] Suggestions and Notifications

[0748] Based on the analysis results, the server updates the employee skill set and characteristics database. The generative AI then uses this data to create appropriate employee transfer and project participation proposals. The proposals are then notified to managers and staff in the relevant departments via the server.

[0749] Feedback and Ratings

[0750] The person in charge will hold another one-on-one meeting with the employee based on the proposal and receive feedback on the proposal. This feedback information will again be sent from the device to the server and collected. The server will then pass the collected feedback to the generative AI and evaluate the appropriateness of the proposal.

[0751] Specific examples

[0752] For example, employee A belongs to the sales department and holds the following monthly one-on-one meeting. During the meeting, the user says, "This month, I focused particularly on negotiating with new clients, and I felt that my negotiation skills were one of my strengths." The device records this conversation and sends it to the server as text data.

[0753] The server passes the data to the generative AI, which analyzes the text data and extracts keywords such as "negotiation skills" and "new client," thereby identifying that employee A has strengths in negotiation skills. The server then updates the database for employee A, and the generative AI creates a proposal to transfer employee A to a new project and notifies the sales department manager. The manager discusses the proposal with employee A in the next one-on-one meeting and collects feedback. This feedback is again evaluated by the server and the generative AI to determine the appropriateness of the proposal.

[0754] In this way, the present invention can efficiently manage and utilize the skills and characteristics of employees, contributing to the growth and development of a company.

[0755] The processing flow will be explained below.

[0756] Step 1:

[0757] A user (employee) starts a one-on-one meeting with a generative AI using a company device. The user launches a dedicated application and presses the start button.

[0758] Step 2:

[0759] The device records the contents of the meeting as audio data in real time. At the same time, the audio data is converted into text data using natural language processing technology. The converted text data is also used as subtitle information for the meeting.

[0760] Step 3:

[0761] After the meeting ends, the device sends the recorded audio data and converted text data to the server, which then stores the received data in a dedicated database.

[0762] Step 4:

[0763] The server passes the stored text data to the generative AI's analysis module, where the generative AI uses natural language processing technology to analyze the text data.

[0764] Step 5:

[0765] Generative AI extracts important keywords and phrases from meeting content, for example, identifying keywords like "negotiation skills" and "new clients" and identifying employee skills and traits.

[0766] Step 6:

[0767] The server reflects the analysis results in the employee database and updates the employee's skill set and characteristics. In the case of employee A, a new skill data item, "Negotiation Skills: High," is added.

[0768] Step 7:

[0769] Based on the updated data, the generative AI generates proposals for appropriate employee transfers and project participation. For example, it creates a proposal to transfer Employee A to a large contract project in the sales department.

[0770] Step 8:

[0771] The server notifies the manager or person in charge of the relevant department of the proposal, and the notification is sent via email or internal messenger.

[0772] Step 9:

[0773] The user (person in charge) will hold another one-on-one meeting with the employee based on the proposal to discuss the proposal. The contents of this feedback meeting will also be recorded and converted into text.

[0774] Step 10:

[0775] The device sends the feedback meeting data to a server, which then passes it on to the generative AI, which analyzes the feedback and evaluates the appropriateness of the proposals.

[0776] Step 11:

[0777] The server stores the generative AI's evaluation results in a database and, if necessary, starts a new cycle with further suggestions and improvements.

[0778] This series of processes ensures that employee skills and characteristics are managed and utilized efficiently, improving the performance of the entire organization.

[0779] Example 1

[0780] 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."

[0781] Traditionally, the management and utilization of human resource skills within companies has been largely manual, making it difficult to efficiently collect and analyze data. In particular, there has been a lack of methods for accurately understanding employees' skills and characteristics and assigning them to appropriate tasks and projects based on that information. In addition, the process of collecting feedback and evaluating the appropriateness of proposals is cumbersome. This has limited the ability to maximize employee capabilities and promote corporate growth.

[0782] 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.

[0783] In this invention, the server includes information collection means for collecting the contents of meetings held between employees and the generative AI, data analysis means for analyzing the meeting content data collected from the information collection means, proposal generation means for proposing appropriate transfers or work participation for employees based on the employee skills and characteristics identified by the data analysis means, communication means for notifying relevant departments of the contents of the proposals made by the proposal generation means, opinion collection means for collecting feedback based on the contents of the notifications made by the notification means, and aptitude evaluation means for analyzing the feedback collected by the opinion collection means and evaluating the appropriateness of the contents of the proposals. This makes it possible to efficiently collect and analyze employee skills and characteristics, generate appropriate work proposals, and evaluate the feedback based on the proposals.

[0784] "Information collection means" refers to a device or system for collecting the contents of meetings held between employees and generative AI.

[0785] The "data analysis means" is a device or process for analyzing the conference content data collected from the information collection means.

[0786] The "proposal generating means" is a device or system for proposing appropriate transfers or work participation of employees based on the skills and characteristics of the employees identified by the data analysis means.

[0787] The "communication means" is a device or system for notifying the relevant departments of the contents of the proposal made by the proposal generating means.

[0788] The "opinion collection means" is a device or system for collecting feedback based on the content of the notification by the notification means.

[0789] The "suitability evaluation means" is a device or system for analyzing the feedback collected by the opinion collection means and evaluating the suitability of the proposal content.

[0790] "Generative AI" is an artificial intelligence system that uses natural language processing technology to analyze meeting content data and generate appropriate business proposals.

[0791] "Meeting content data" refers to information that records statements and exchanges made during meetings between employees and generative AI.

[0792] The present invention is a system for improving the efficiency of human resource skill management and utilization within a company. Specifically, it includes a process for analyzing data collected through one-on-one meetings between employees and generative AI, and proposing appropriate employee transfers and project participation. An embodiment of this system is described in detail below.

[0793] Data collection

[0794] Once a month, users (employees) use their company devices to hold one-on-one meetings with the generative AI. During these meetings, the devices use the following hardware and software:

[0795] Hardware: Microphones, recording devices

[0796] Software: Google Cloud Speech-to-Text

[0797] The device records the meeting contents as audio and converts the audio data into text data in real time using Google Cloud Speech-to-Text. This converted text data is also used as subtitle information for the meeting contents. The collected data is sent from the device to the server using HTTPS communication.

[0798] Data reception and storage

[0799] The server receives the text data of the conference contents sent and stores it in a dedicated database. This database uses MySQL, PostgreSQL, etc. The server performs transaction control to ensure data integrity and security.

[0800] Data analysis

[0801] The server passes the stored text data to a generative AI analysis module, which uses natural language processing (NLP) techniques such as OpenAI's GPT-4 to analyze the text data and extract key keywords and phrases that identify employee skills and traits.

[0802] Proposal creation

[0803] The server updates the employee skill set and characteristics database based on the results of the generative AI analysis. The generative AI then uses the updated data to create appropriate employee transfer and project participation proposals. These proposals are compiled into documents using natural language generation technology.

[0804] proposal notification

[0805] The server then notifies the relevant department managers and staff of the created proposals via email, Microsoft Teams, Slack, and other communication methods, including the data that formed the basis of the proposal and important keywords.

[0806] Feedback collection and evaluation

[0807] The person in charge holds another one-on-one meeting with the employee based on the proposal content, and enters the feedback obtained from the meeting into the device. The device then sends this feedback information to the server. The server stores the received feedback in a database and passes it on to the generative AI. The generative AI uses the feedback data to evaluate the appropriateness of the proposal content. Sentiment analysis technology and other techniques are used in the evaluation, and the results of this evaluation are reflected in the creation of the next proposal.

[0808] Specific examples

[0809] For example, employee A belongs to the sales department and holds the following monthly one-on-one meeting. During the meeting, the user says, "This month, I focused particularly on negotiating with new clients, and I felt that my negotiation skills were one of my strengths." The device records this conversation, converts it into text data using Google Cloud Speech-to-Text, and sends it to the server.

[0810] The server passes the data to a generative AI (e.g., OpenAI GPT-4), which analyzes the text data and extracts keywords such as "negotiation skills" and "new client." This identifies that employee A has strengths in negotiation skills. The server then updates the database for employee A, and the generative AI creates a proposal to transfer employee A to a new project and notifies the sales department manager. The manager discusses the proposal with employee A in the next one-on-one meeting and collects feedback. This feedback is again evaluated by the server and the generative AI to determine the appropriateness of the proposal.

[0811] Prompt Sentence Examples

[0812] "Employee A mentioned in this month's one-on-one meeting that he focused particularly on negotiating with new clients and felt that negotiation skills were one of his strengths. Based on this, please conduct an analysis of Employee A's skills and characteristics and create an appropriate project participation proposal."

[0813] In this way, the present invention can efficiently manage and utilize the skills and characteristics of employees, contributing to the growth and development of a company.

[0814] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0815] Step 1: Data collection

[0816] Users use company devices to hold regular one-on-one meetings with generative AI. When a meeting begins, the device records audio data through a microphone. This audio data becomes the input. The device then converts the audio data into text data in real time using Google Cloud Speech-to-Text. Here, the audio data is recognized as a string of characters, and data processing is performed to convert each utterance into text format. The converted text data becomes the output and is prepared for the next step.

[0817] Step 2: Send data

[0818] The terminal sends the generated text data to the server via HTTPS. This process uses encryption to ensure data security. The input is the converted text data, and the output is the secure receipt of the data by the server.

[0819] Step 3: Receiving and storing data

[0820] The server receives text data sent from the terminal. The input is text data sent via HTTPS communication, and the server stores the data in a dedicated database. Transaction control is used to maintain the integrity of the database during storage. The output is text data saved in the database.

[0821] Step 4: Data analysis

[0822] The server passes the text data stored in the database to the generative AI analysis module. The input is the text data retrieved from the database. The analysis module (e.g., OpenAI GPT-4) analyzes the data using natural language processing technology and extracts important keywords and phrases. This analysis identifies employee skills and characteristics. The output is the keywords resulting from the analysis and the identified skills and characteristics.

[0823] Step 5: Proposal Generation

[0824] The server updates the employee skill set and characteristics database based on the analysis results output by the generative AI. Using this skill set and characteristics data, the generative AI again creates appropriate transfer and project participation proposals. The input is the analysis results, and the output is the generated proposal.

[0825] Step 6: Proposal Notification

[0826] The server notifies the necessary managers and personnel of the generated proposals. The input is the generated proposal, and the output is a notification via email, Microsoft Teams, or Slack. This notification process also includes the data that formed the basis of the proposal and important keywords.

[0827] Step 7: Gather feedback

[0828] The person in charge holds another one-on-one meeting with the employee based on the proposal, and inputs the feedback obtained during the meeting into the terminal. The input is the feedback obtained during the meeting, and the terminal sends it back to the server. The output is the transmission of the feedback data to the server.

[0829] Step 8: Feedback evaluation

[0830] The server stores the received feedback in a database and passes it to the generative AI. The input is the feedback data, which the generative AI analyzes and evaluates the appropriateness of the proposal. Sentiment analysis technology and other techniques are used for the evaluation. The output is the evaluation result regarding the appropriateness of the proposal, which is reflected in the creation of the next proposal.

[0831] (Application example 1)

[0832] 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."

[0833] Modern companies are required to accurately understand the skills and characteristics of their personnel and propose appropriate transfers and project participation. In particular, in on-site work such as factories, workers' skills are directly linked to work efficiency and productivity, so proper skill management and rapid feedback are essential. However, in current systems, these processes are often carried out manually, which is time-consuming and labor-intensive. Furthermore, worker skill evaluation relies on subjective judgment, which can lead to inappropriate evaluations. A system that can solve these issues is needed.

[0834] 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.

[0835] In this invention, the server includes: a data collection means for collecting the contents of meetings held between employees and the generative AI; an analysis means for analyzing the meeting content data collected by the data collection means; a proposal means for proposing appropriate employee transfers or project participation based on the employee's skills and characteristics identified by the analysis means; a notification means for notifying relevant departments of the contents of the proposals made by the proposal means; a feedback collection means for collecting feedback based on the contents of the notifications made by the notification means; an evaluation means for analyzing the feedback collected by the feedback collection means and evaluating the appropriateness of the proposals; a means for collecting speech and work content during work using a recording device attached to an information processing device used by the worker; a conversion means for converting the collected speech data into text data and transmitting it to the generative AI server; and a proposal means for evaluating the worker's skills based on the text data generated by the conversion means and proposing appropriate reassignment to a work position. This makes it possible to efficiently and accurately grasp the worker's skills and characteristics and quickly propose appropriate transfers and project participation.

[0836] "Data collection means" refers to a means of collecting data such as speech during meetings and work between workers and generative AI, as well as the content of the work, using information processing devices and recording devices.

[0837] The "analysis means" is a means for analyzing the data collected by the data collection means and extracting important information and keywords.

[0838] The "suggestion means" is a means for proposing appropriate transfers or project participation based on the skills and characteristics of employees or workers identified by the analysis means.

[0839] The "notification means" is a means for notifying the relevant departments and managers of the contents of the proposal made by the proposal means.

[0840] The "feedback collection means" is a means for collecting feedback based on the content of the notification by the notification means.

[0841] The "evaluation means" is a means for analyzing the feedback collected by the feedback collection means and evaluating the appropriateness of the proposal content.

[0842] The "recording device" is an information processing device for recording the voices of workers and the details of their work.

[0843] The "conversion means" is a means for converting collected voice data into text data and sending it to the generative AI server.

[0844] "Generative AI" is artificial intelligence that analyzes collected text data and uses natural language processing technology to evaluate skills.

[0845] This invention is a system that efficiently manages the skills and characteristics of human resources within a company and proposes appropriate transfers and project participation. This system utilizes smart glasses and AI technology to automate the skill evaluation and feedback management of field workers.

[0846] System Overview

[0847] The system is configured as follows:

[0848] 1. Data collection methods:

[0849] Smart glasses are information processing devices used by workers that record their speech and the details of their work. Data is collected using a microphone and camera built into the smart glasses, allowing for real-time recording of the worker's work status and voice.

[0850] 2. Conversion method:

[0851] The voice data collected by the smart glasses is converted into text data using voice recognition software (e.g., the SpeechRecognition module). The converted text data is then sent to the generative AI server.

[0852] 3. Analysis method:

[0853] The generative AI server analyzes the collected text data and uses a generative AI model (e.g., OpenAI API) to extract important keywords and phrases from the text data using natural language processing technology and identify the skills of the workers.

[0854] 4. Proposal method:

[0855] Based on the analysis results, the generative AI server evaluates the worker's skill set and proposes appropriate transfers or project participation. These proposals are automated and notified to the worker and relevant department managers as appropriate.

[0856] 5. Means of notification:

[0857] The proposals are then sent to the relevant departments and managers via email or a dedicated application.

[0858] 6. Feedback Collection Methods:

[0859] After the worker performs the work in the new position based on the proposal, the results of the work and their impressions are collected as feedback. Voice data is collected again using smart glasses and converted into text data.

[0860] 7. Evaluation Methods:

[0861] The collected feedback data is reanalyzed to evaluate the appropriateness of the underlying proposals, and a generative AI model is used to derive improvements and new proposals from the feedback.

[0862] Specific examples

[0863] For example, suppose Worker A is installing new wiring and says, "I've learned how to install new wiring. I'm good at detailed work. I quickly discovered a problem with a specific part." The smart glasses will record this voice and convert it into text data.

[0864] The converted text is sent to the generative AI server as the following prompt:

[0865] Example prompt sentence:

[0866] Analyze the statements of the workers below, extract keywords, and evaluate their skill sets.

[0867] "I learned how to install new wiring. I'm good at detailed work. I quickly identified a problem with a specific component."

[0868] The generative AI analyzes this prompt and extracts keywords such as "wiring installation," "detailed work," and "detecting defects in specific components." It then evaluates that Worker A excels in these skills and proposes an appropriate new work position. This proposal is notified to the manager of the relevant department and ultimately fed back to Worker A. The feedback is again collected by the smart glasses and evaluated by the generative AI model. This makes it possible to optimize the proposal.

[0869] In this way, the present invention makes it possible to quickly and accurately evaluate the skills and characteristics of workers and efficiently propose appropriate transfers and project participation.

[0870] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0871] Step 1:

[0872] The user puts on the smart glasses and begins working. The smart glasses' built-in microphone and camera record audio and video while working. This allows the user's work status and comments to be collected in real time. The input is the audio and video of the work being done, and the output is the recorded data.

[0873] Step 2:

[0874] The device converts the collected voice data into text data. Voice recognition software (e.g., SpeechRecognition module) is used to convert the voice data into text information. The input is voice data, and the output is converted text data. This process results in the speech written in natural language.

[0875] Step 3:

[0876] The device sends the converted text data to the generative AI server. Transmission is via internet communication. The input is the text data, and the output is a notification to the generative AI server that data transmission is complete. This passes the text data to the server for analysis.

[0877] Step 4:

[0878] The server uses generative AI to analyze the received text data. Using a generative AI model (e.g., OpenAI's API), keywords and important phrases are extracted through analysis. The input is text data, and the output is the analyzed keywords and phrases. This process identifies the skills and characteristics of the worker.

[0879] Step 5:

[0880] The server creates proposals based on the analysis results. The proposals include new work positions or project participation that are suited to the worker's skills and characteristics. The input is the analyzed keywords and phrases, and the output is the proposals. The proposals are generated automatically.

[0881] Step 6:

[0882] The server notifies the relevant departments and administrators of the proposal contents. Notifications are sent via email or a dedicated application. The input is the proposal contents, and the output is a notification of notification completion, allowing the administrator to check the proposal.

[0883] Step 7:

[0884] The user performs a new task based on the suggestions. After completing the task, they record their impressions and any problems they have as feedback via voice. Data is collected again using smart glasses. The input is the user's voice feedback, and the output is the recorded feedback data.

[0885] Step 8:

[0886] The terminal converts the collected feedback voice data back into text data and sends it to the generative AI server using speech recognition software. The input is the feedback voice data, and the output is the converted feedback text data.

[0887] Step 9:

[0888] The server analyzes the collected feedback data and evaluates the appropriateness of the proposals. A generative AI model is used to derive improvements and new proposals from the feedback. The input is the feedback text data, and the output is the evaluation results and improvement proposals. This process optimizes the proposals for future use.

[0889] 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.

[0890] The present invention provides a system for efficiently managing and utilizing human resource skills and emotions within a company. Hereinafter, an embodiment of the present invention will be described in detail.

[0891] System Overview

[0892] This system collects, analyzes, and proposes employee skills, characteristics, and emotions through regular one-on-one meetings between employees and generative AI. Specifically, it collects the content of meetings with employees, analyzes their emotions using an emotion engine, proposes appropriate transfers or project participation, and finally collects and evaluates feedback.

[0893] Data collection

[0894] Once a month, users (employees) use their company devices to hold one-on-one meetings with the generative AI. The user launches a dedicated application and presses the start button for the meeting. The device then records the contents of the meeting as audio data in real time. At the same time, the audio data is converted into text data. This text data is also used as subtitle information for the meeting. The collected data is sent from the device to a server.

[0895] Emotion analysis

[0896] The server stores the received meeting content data in a dedicated database. The data is then passed to a generative AI analysis module, where an emotion engine is built in to recognize and extract user emotions from the meeting content data. For example, emotions such as joy, sadness, and anger are identified. The emotion engine analyzes emotions from voice tone and text content.

[0897] Data analysis

[0898] The generative AI comprehensively analyzes the emotion data provided by the emotion engine and the text data of meeting contents to identify employee skills and characteristics. Based on the extracted emotion and skill data, it creates proposals for appropriate employee job assignments and project participation.

[0899] Suggestions and Notifications

[0900] The server reflects the analysis results in the employee database, updating the employee's skill set and characteristics. The generative AI then takes emotional data into account and generates suitable transfer and project participation proposals for the employee. The proposals are then sent via the server to managers and staff in the relevant departments.

[0901] Feedback and Ratings

[0902] The person in charge holds another one-on-one meeting with the employee based on the proposal and collects feedback on the results. The contents of this feedback meeting are also recorded and converted into text. The device sends the feedback meeting data to the server, which then passes it on to the generative AI. The generative AI analyzes the feedback and evaluates the appropriateness of the proposal.

[0903] Specific examples

[0904] For example, employee B belongs to the development department and holds the following monthly one-on-one meeting. During the meeting, the user says, "This month I particularly struggled with learning a new technology, but I finally succeeded and I'm very happy." The device records this conversation and sends it to the server as text data. From this content, the emotion engine identifies changes in emotion from distress to joy.

[0905] The generative AI analyzes emotion data along with keywords related to "acquiring new technologies" and identifies that employee B has a high ability to acquire new technologies and feels a sense of accomplishment. The server then updates the database for employee B, and the generative AI proposes employee B's participation in a new project and notifies the development department manager. The manager then discusses the proposal with employee B in the next one-on-one meeting and collects feedback. This feedback is again evaluated by the server and the generative AI to determine the appropriateness of the proposal.

[0906] This series of processes enables efficient management and utilization of employee skills and emotions, contributing to the growth and development of the company.

[0907] The processing flow will be explained below.

[0908] Step 1:

[0909] A user (employee) starts a one-on-one meeting with a generative AI using a company device. The user launches a dedicated application and presses the start button.

[0910] Step 2:

[0911] The device records the contents of the meeting as audio data in real time. At the same time, the audio data is converted into text data using natural language processing technology. The converted text data is also used as subtitle information for the meeting.

[0912] Step 3:

[0913] After the meeting ends, the device sends the recorded audio data and converted text data to the server, which then stores the received data in a dedicated database.

[0914] Step 4:

[0915] The server passes the saved text and audio data to the generative AI analysis module, where the emotion engine analyzes the meeting content data to recognize the user's emotions and extracts emotional data.

[0916] Step 5:

[0917] The emotion engine analyzes the user's emotions from the meeting content based on voice tone and context, identifying emotions such as joy, sadness, and anger.

[0918] Step 6:

[0919] The generative AI comprehensively analyzes the emotional and text data provided by the emotion engine to identify employee skills and traits, including skill extraction based on text analysis and emotional state assessment based on emotion analysis.

[0920] Step 7:

[0921] The server reflects the analysis results in the employee database and updates the employee's skill set, characteristics, and emotional information. For example, for employee A, the data "Negotiation skills: High" and "Recent emotional state: Joy" are added.

[0922] Step 8:

[0923] Based on the updated database, the generative AI generates proposals for appropriate employee transfers and project participation. In doing so, it takes into account not only skill data but also emotional data when creating the proposals. For example, it might make a proposal such as, "Employee A should be transferred to a large contract project. As his emotional state has been stable recently, an environment with less mental stress would be suitable."

[0924] Step 9:

[0925] The server notifies managers and staff in the relevant departments of the generative AI's proposals, via email or internal messenger.

[0926] Step 10:

[0927] The user (person in charge) will hold a one-on-one meeting with the employee based on the proposal and collect feedback on the results. The contents of this feedback meeting will also be recorded and converted into text.

[0928] Step 11:

[0929] The device sends the feedback meeting data to a server, which then passes it on to the generative AI, which analyzes the feedback and evaluates the appropriateness of the proposals.

[0930] Step 12:

[0931] The server stores the results of the generative AI evaluation in a database and initiates a new cycle including further suggestions and improvements as needed, thereby enabling efficient management of employee skills and emotions, contributing to the growth and development of the company as a whole.

[0932] Example 2

[0933] 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."

[0934] Companies are seeking to efficiently manage and utilize the skills and emotions of their employees. Accurately understanding employees' emotions and skills and making appropriate transfer and project participation proposals based on that information is essential for corporate growth. However, traditional methods make it difficult to do this efficiently, and analyzing emotions and collecting and evaluating feedback, in particular, requires a great deal of time and effort.

[0935] 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.

[0936] In this invention, the server includes: a data collection means for collecting the contents of meetings held between employees and the generative AI; a conversion means for converting the conference audio data collected from the data collection means into text data; a transmission means for transmitting the text data and audio data to the server; an analysis means for analyzing the data; an emotion analysis means for analyzing the emotions of employees identified by the analysis means; a data analysis means for identifying the skills and characteristics of employees based on the emotion analysis means and the conference content text data; a proposal means for proposing appropriate transfers or project participation for employees based on the data analysis means; a notification means for notifying relevant departments of the contents of the proposals made by the proposal means; a feedback collection means for collecting feedback based on the contents of the notifications made by the notification means; and an evaluation means for analyzing the feedback collected by the feedback collection means and evaluating the appropriateness of the proposals. This enables efficient management of employees' emotions and skills and the proposal of appropriate transfers or project participation based on the results.

[0937] "Data collection means" refers to a means for collecting the contents of meetings held between employees and generative AI.

[0938] The "conversion means" is a means for converting collected conference voice data into text data.

[0939] The "transmission means" is a means for transmitting text data and voice data to the server.

[0940] "Analysis means" refers to means for analyzing collected data.

[0941] The "emotion analysis means" is a means for analyzing the emotions of the employees identified by the analysis means.

[0942] The "data analysis means" is a means for identifying the skills and characteristics of employees based on the emotion analysis means and the meeting content text data.

[0943] "Proposal means" refers to a means for proposing appropriate transfers or project participation of employees based on data analysis means.

[0944] The "notification means" is a means for notifying the relevant departments of the content of the proposal made by the proposal means.

[0945] The "feedback collection means" is a means for collecting feedback based on the notification content.

[0946] The "evaluation means" is a means for analyzing the feedback collected by the feedback collection means and evaluating the appropriateness of the proposal content.

[0947] The present invention is a system for efficiently managing and utilizing human resource skills and emotions within a company. An embodiment of the present invention will now be described in detail.

[0948] System Overview

[0949] This system collects employee skills, characteristics, and emotions through regular one-on-one meetings between employees and generative AI, and then analyzes and proposes the data. The system includes the following detailed processes:

[0950] Data collection

[0951] Once a month, users (employees) use their company's devices to hold one-on-one meetings with the generative AI. The user launches a dedicated application and presses the start button for the meeting. The device records the meeting content as audio data in real time. At the same time, the audio data is converted into text data. This text data is also used as subtitle information for the conversation. The collected data is sent from the device to a server.

[0952] Emotion analysis

[0953] The server stores the received meeting content data in a dedicated database. The data is then passed to a generative AI analysis module, where an emotion engine is built in to recognize and extract user emotions from the meeting content data. For example, emotions such as joy, sadness, and anger are identified. The emotion engine analyzes emotions from voice tone and text content.

[0954] Data analysis

[0955] The generative AI comprehensively analyzes the emotion data provided by the emotion engine and the text data of meeting contents to identify employee skills and characteristics. Based on the extracted emotion and skill data, it creates proposals for appropriate employee job assignments and project participation.

[0956] Suggestions and Notifications

[0957] The server reflects the analysis results in the employee database, updating the employee's skill set and characteristics. The generative AI then takes emotional data into account and generates suitable transfer and project participation proposals for the employee. The proposals are then sent via the server to managers and staff in the relevant departments.

[0958] Feedback and Ratings

[0959] The person in charge holds another one-on-one meeting with the employee based on the proposal and collects feedback on the results. The contents of this feedback meeting are also recorded and converted into text. The device sends the feedback meeting data to the server, which then passes it on to the generative AI. The generative AI analyzes the feedback and evaluates the appropriateness of the proposal.

[0960] Specific examples

[0961] For example, employee B belongs to the development department and holds the following monthly one-on-one meeting. During the meeting, the user says, "This month I particularly struggled with learning a new technology, but I finally succeeded and I'm very happy." The device records this conversation and sends it to the server as text data. From this content, the emotion engine identifies changes in emotion from distress to joy.

[0962] The generative AI analyzes emotion data along with keywords related to "acquiring new technologies" and identifies that employee B has a high ability to acquire new technologies and feels a sense of accomplishment. The server then updates the database for employee B, and the generative AI proposes employee B's participation in a new project and notifies the development department manager. The manager then discusses the proposal with employee B in the next one-on-one meeting and collects feedback. This feedback is again evaluated by the server and the generative AI to determine the appropriateness of the proposal.

[0963] Prompt Sentence Examples

[0964] Employee B, who works in the development department, said, "I struggled to learn new technology this month, but I finally succeeded and I'm very happy." Analyze this conversation to identify changes in the employee's emotions and skill characteristics.

[0965] The above is an embodiment of the present invention. This system enables efficient management and utilization of human resource skills and emotions within a company.

[0966] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0967] Step 1:

[0968] The user launches the dedicated application on the device and presses the "Start Meeting" button.

[0969] Input: User actions

[0970] Output: Start of meeting

[0971] Specific operation: The user launches the dedicated application and clicks the "Start Conference" button, which puts the device into conference recording mode.

[0972] Step 2:

[0973] The terminal records the contents of the meeting in real time and converts the voice data into text data using a voice recognition engine.

[0974] Input: Meeting audio

[0975] Output: Text data

[0976] How it works: The device records the audio of the meeting and converts the audio data into text data in real time using a speech recognition engine such as Google Cloud Speech-to-Text.

[0977] Step 3:

[0978] The terminal transmits the converted text data and the original voice data to the server.

[0979] Input: Text data and audio data

[0980] Output: Send data to the server

[0981] Specific operation: The device encrypts text data and voice data via the SSL / TLS protocol and sends it to the server.

[0982] Step 4:

[0983] The server stores the received data in a database and passes it on to the generative AI analysis module.

[0984] Input: Text data and audio data

[0985] Output: Storing in a database and passing data to analysis modules

[0986] Specific operation: The server stores the received data in a dedicated database and classifies it by user ID. The data is then passed to the generative AI analysis module.

[0987] Step 5:

[0988] The emotion engine analyzes the data and identifies the user's emotion.

[0989] Input: Text data and audio data

[0990] Output: Emotion data

[0991] What it does: An emotion engine (e.g., IBM Watson Tone Analyzer) analyzes the tone of text and speech to identify the user's emotions, such as joy, sadness, or anger.

[0992] Step 6:

[0993] Generative AI comprehensively analyzes emotional data and text data from meeting content to extract employee skills and characteristics.

[0994] Input: Emotion data and text data

[0995] Output: Skill data and attribute data

[0996] How it works: Generative AI integrates emotional and textual data to extract skills and characteristics, such as the speed of technological acquisition and the ability to adapt to challenges.

[0997] Step 7:

[0998] The server reflects the analysis results in the employee database, and the generative AI generates suggestions.

[0999] Input: Skill data and attribute data

[1000] Output: Proposal data

[1001] Specific operation: The server reflects skill data and characteristic data in the employee database, and the generative AI generates appropriate proposals for employee transfers and project participation.

[1002] Step 8:

[1003] The server notifies the manager or person in charge of the relevant department of the proposal.

[1004] Input: Proposal data

[1005] Output: Notification data

[1006] Specific operation: The server notifies the managers and staff of the relevant departments of the generated proposals via email or a dedicated notification system.

[1007] Step 9:

[1008] The person in charge will hold another one-on-one meeting with the employee to discuss the proposal and gather feedback.

[1009] Input: Proposal data

[1010] Output: Feedback data

[1011] Specific operations: The person in charge discusses the proposal with employees, records the audio of the feedback meeting, and converts it into text data.

[1012] Step 10:

[1013] The device sends the feedback meeting data to the server, and the generative AI evaluates it.

[1014] Input: Feedback data

[1015] Output: Evaluation data

[1016] Specific operation: The device sends the text and audio data of the feedback meeting to the server, which then passes the data to the generative AI. The generative AI analyzes the feedback data and evaluates the appropriateness of the proposal.

[1017] These are the processing steps of this system. At each step, data is collected, converted, analyzed, proposed, notified, and feedback is collected and evaluated, allowing for efficient management and utilization of employee skills and emotions.

[1018] (Application example 2)

[1019] 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."

[1020] It is extremely important to understand the skills and characteristics of employees within a company and to make appropriate work plans. However, it is difficult to conduct a comprehensive evaluation that includes employee emotions, which has made improving work efficiency and employee satisfaction a challenge. In addition, it is difficult to collect and analyze data accurately in real time using paper-based or simple digital tools, so a new system to solve these issues was needed.

[1021] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1022] In this invention, the server includes a data collection means for collecting the contents of meetings held between employees and the generative AI, an analysis means for analyzing the meeting content data collected by the data collection means, a proposal means for proposing appropriate employee transfers or project participation based on the employee skills, characteristics, and emotional data identified by the analysis means, a notification means for notifying relevant departments of the contents of the proposals made by the proposal means, a feedback collection means for collecting feedback based on the contents of the notifications made by the notification means, an evaluation means for analyzing the feedback collected by the feedback collection means and evaluating the appropriateness of the contents of the proposals, and an emotion analysis means for grasping employee emotions in real time via smart devices. This allows for a comprehensive evaluation of employee emotions, enabling improved work efficiency and employee satisfaction.

[1023] "Employee" refers to an employee working within a company.

[1024] "Generative AI" refers to the entire system that uses artificial intelligence technology to analyze data and generate proposals.

[1025] "Data collection means" refers to the devices and processes that collect the contents of the meeting in the form of audio, video, etc.

[1026] "Analysis means" refers to the device and its functions that analyze employee skills, characteristics, emotions, etc. based on collected data.

[1027] "Proposal means" refers to a device and its functions that generate proposals for employee transfers and project participation based on the analysis results.

[1028] "Notification means" refers to a device and its function that notifies the manager or person in charge of the relevant department of the content of the generated proposal.

[1029] "Feedback collection means" refers to a device and its functionality for organizing and recording feedback collected based on suggestions.

[1030] "Evaluation means" refers to a device and its functions that analyzes collected feedback and evaluates the appropriateness of suggestions.

[1031] "Emotion analysis means" refers to a device and its functions that analyzes employee emotions in real time using a smart device.

[1032] "Smart devices" refers to portable or wearable electronic devices with advanced information processing capabilities, such as smartphones, smart glasses, and head-mounted displays.

[1033] "Natural language processing technology" refers to the technology that processes, understands, generates, and analyzes human language using a computer.

[1034] The present invention provides a system for improving the work efficiency and satisfaction of employees in a logistics center. As an embodiment of the present invention, a system is described that collects and analyzes work content and emotional data in real time when employees perform their work using smart devices (such as smart glasses).

[1035] System Overview

[1036] Users (employees) wear smart devices (such as smart glasses) to carry out their daily work. The smart devices collect audio and video data in real time while they are working. The audio data is converted into text data, and emotions are analyzed from the video data.

[1037] Data collection

[1038] Smart devices capture employees' work activities in real time as audio and video data. This data is collected by a data collection tool. The audio data is converted into text data using Google Cloud Speech-to-Text, and the video data is subjected to emotion analysis using the Microsoft Azure Face API.

[1039] Emotion analysis

[1040] The server processes the collected audio and video data using analytical means. It performs emotion analysis using the Azure Face API and extracts emotional data. This emotional data is expressed as parameters such as "happiness," "sadness," and "anger."

[1041] Data analysis

[1042] Generative AI identifies employee skills and characteristics by comprehensively analyzing text and emotion data extracted from voice data. This process uses OpenAI's GPT model, which uses natural language processing technology to analyze meeting content data and recognize skills and characteristics.

[1043] Suggestions and Notifications

[1044] Based on the analysis results, the server uses generative AI to propose appropriate employee transfers and project participation. These proposals are then notified to managers and staff in the relevant departments. Notifications are sent via email or internal communication systems.

[1045] Feedback and Ratings

[1046] Based on the proposal, the manager will hold another one-on-one meeting with the employee and collect feedback on the results. This feedback data is also collected as voice data and converted into text data and emotion data. The server passes the feedback data to the generative AI and evaluates the appropriateness of the proposal.

[1047] Specific examples

[1048] For example, suppose Employee A is working at a logistics center, replenishing shelves with products. If Employee A reports, "I struggled at first with the new work procedures, but I was able to complete the work smoothly in the end," the smart device will record this conversation and send it to the server as text data. The emotion analysis means will then identify from this content that the employee is expressing great joy.

[1049] The generative AI analyzes emotional and text data, identifies that Employee A has mastered efficient work procedures, and suggests a similar approach next time. An example of a specific prompt would be: "Analyze the emotions of employees at the logistics center and suggest an efficient process. Consider skills and emotions. Meeting content: Employee A has been very busy this month and had difficulty getting used to new work procedures, but ultimately reported that the work went smoothly. Emotion data: {"Happiness": 0.8, "Sadness": 0.1, "Anger": 0.1}."

[1050] This series of processes allows for a comprehensive evaluation of employee emotions, improving work efficiency and employee satisfaction.

[1051] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1052] Step 1:

[1053] The user wears the smart device and starts working. The smart device collects audio and video data in real time while the employee is working. The input is audio and video data during work, and the collected data is recorded as output.

[1054] Step 2:

[1055] The device converts the collected voice data into text data using Google Cloud Speech-to-Text. In this conversion process, the input is voice data and the output is text data. The voice data is transcribed.

[1056] Step 3:

[1057] The device performs emotion analysis on the collected video data using the Microsoft Azure Face API. It receives video data as input and obtains emotion parameters (happiness, sadness, anger, etc.) as output. The emotion analysis method identifies the employee's emotions from the video data.

[1058] Step 4:

[1059] The terminal sends the collected and converted text data and emotion data to the server. The input is text data and emotion data, and the data sent to the server is the output.

[1060] Step 5:

[1061] The server processes the received text data and emotional data using analytical means. The input is text data and emotional data, and analyzed skill and characteristic information is output. Generative AI performs data analysis using natural language processing technology.

[1062] Step 6:

[1063] Based on the analysis results, the generative AI will suggest appropriate transfers or project participation for employees. The input is the analysis results (skills, characteristics, and emotional data), and the output is a generated recommendation. An example of a specific prompt would be, "Analyze the emotions of employees at the logistics center and suggest an efficient process. Skills and emotions will be taken into consideration. Meeting content: Employee A has been very busy this month and reported that he had difficulty getting used to new work procedures, but that the work ultimately went smoothly. Emotion data: { "Happiness": 0.8, "Sadness": 0.1, "Anger": 0.1}."

[1064] Step 7:

[1065] The server notifies the generated proposal to the manager or person in charge of the relevant department. The proposal content is input and the notification is output. Notification is made via email or the internal communication system.

[1066] Step 8:

[1067] The manager then holds a one-on-one meeting with the employee based on the proposal and collects feedback on the results. The proposal is input and feedback data is output.

[1068] Step 9:

[1069] The device records the contents of the feedback meeting as audio data and converts it into text data using Google Cloud Speech-to-Text. The input is audio data and the output is text data.

[1070] Step 10:

[1071] The device performs emotion analysis on the video data of the feedback meeting using the Microsoft Azure Face API. The video data is input, and emotion parameters are obtained as output.

[1072] Step 11:

[1073] The server receives the feedback data and passes it to the generative AI, which takes text data and emotion data as input and outputs the analysis results.

[1074] Step 12:

[1075] Generative AI analyzes feedback and evaluates the appropriateness of proposals. The input is feedback data, and the output is an evaluation result. Based on this evaluation, new proposals and improvements are generated.

[1076] 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.

[1077] 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.

[1078] 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.

[1079] [Fourth embodiment]

[1080] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1081] 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.

[1082] 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).

[1083] 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.

[1084] 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.

[1085] 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).

[1086] 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. 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.

[1087] 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.

[1088] 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.

[1089] 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.

[1090] 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.

[1091] 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.

[1092] 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."

[1093] The present invention provides a system for efficiently managing and utilizing human resource skills within a company. Hereinafter, an embodiment of the present invention will be described in detail.

[1094] System Overview

[1095] This system collects, analyzes, and proposes employee skills and characteristics through regular one-on-one meetings between employees and generative AI. Specifically, it collects and analyzes the content of meetings with employees, proposes appropriate transfers and project participation, and finally collects and evaluates feedback.

[1096] Data collection

[1097] Once a month, users (employees) use company devices to hold one-on-one meetings with generative AI. During these meetings, the devices record the meeting content as audio and simultaneously convert the audio data into text data. This text data is also used as subtitle information for the meeting content. The collected data is sent from the devices to a server.

[1098] Data analysis

[1099] The server stores the received meeting content data in a dedicated database. The data is then passed to a generative AI analysis module. The generative AI uses natural language processing (NLP) to analyze the text data and extract important keywords and phrases. This allows employee skills and characteristics to be identified.

[1100] Suggestions and Notifications

[1101] Based on the analysis results, the server updates the employee skill set and characteristics database. The generative AI then uses this data to create appropriate employee transfer and project participation proposals. The proposals are then notified to managers and staff in the relevant departments via the server.

[1102] Feedback and Ratings

[1103] The person in charge will hold another one-on-one meeting with the employee based on the proposal and receive feedback on the proposal. This feedback information will again be sent from the device to the server and collected. The server will then pass the collected feedback to the generative AI and evaluate the appropriateness of the proposal.

[1104] Specific examples

[1105] For example, employee A belongs to the sales department and holds the following monthly one-on-one meeting. During the meeting, the user says, "This month, I focused particularly on negotiating with new clients, and I felt that my negotiation skills were one of my strengths." The device records this conversation and sends it to the server as text data.

[1106] The server passes the data to the generative AI, which analyzes the text data and extracts keywords such as "negotiation skills" and "new client," thereby identifying that employee A has strengths in negotiation skills. The server then updates the database for employee A, and the generative AI creates a proposal to transfer employee A to a new project and notifies the sales department manager. The manager discusses the proposal with employee A in the next one-on-one meeting and collects feedback. This feedback is again evaluated by the server and the generative AI to determine the appropriateness of the proposal.

[1107] In this way, the present invention can efficiently manage and utilize the skills and characteristics of employees, contributing to the growth and development of a company.

[1108] The processing flow will be explained below.

[1109] Step 1:

[1110] A user (employee) starts a one-on-one meeting with a generative AI using a company device. The user launches a dedicated application and presses the start button.

[1111] Step 2:

[1112] The device records the contents of the meeting as audio data in real time. At the same time, the audio data is converted into text data using natural language processing technology. The converted text data is also used as subtitle information for the meeting.

[1113] Step 3:

[1114] After the meeting ends, the device sends the recorded audio data and converted text data to the server, which then stores the received data in a dedicated database.

[1115] Step 4:

[1116] The server passes the stored text data to the generative AI's analysis module, where the generative AI uses natural language processing technology to analyze the text data.

[1117] Step 5:

[1118] Generative AI extracts important keywords and phrases from meeting content, for example, identifying keywords like "negotiation skills" and "new clients" and identifying employee skills and traits.

[1119] Step 6:

[1120] The server reflects the analysis results in the employee database and updates the employee's skill set and characteristics. In the case of employee A, a new skill data item, "Negotiation Skills: High," is added.

[1121] Step 7:

[1122] Based on the updated data, the generative AI generates proposals for appropriate employee transfers and project participation. For example, it creates a proposal to transfer Employee A to a large contract project in the sales department.

[1123] Step 8:

[1124] The server notifies the manager or person in charge of the relevant department of the proposal, and the notification is sent via email or internal messenger.

[1125] Step 9:

[1126] The user (person in charge) will hold another one-on-one meeting with the employee based on the proposal to discuss the proposal. The contents of this feedback meeting will also be recorded and converted into text.

[1127] Step 10:

[1128] The device sends the feedback meeting data to a server, which then passes it on to the generative AI, which analyzes the feedback and evaluates the appropriateness of the proposals.

[1129] Step 11:

[1130] The server stores the generative AI's evaluation results in a database and, if necessary, starts a new cycle with further suggestions and improvements.

[1131] This series of processes ensures that employee skills and characteristics are managed and utilized efficiently, improving the performance of the entire organization.

[1132] Example 1

[1133] 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."

[1134] Traditionally, the management and utilization of human resource skills within companies has been largely manual, making it difficult to efficiently collect and analyze data. In particular, there has been a lack of methods for accurately understanding employees' skills and characteristics and assigning them to appropriate tasks and projects based on that information. In addition, the process of collecting feedback and evaluating the appropriateness of proposals is cumbersome. This has limited the ability to maximize employee capabilities and promote corporate growth.

[1135] 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.

[1136] In this invention, the server includes information collection means for collecting the contents of meetings held between employees and the generative AI, data analysis means for analyzing the meeting content data collected from the information collection means, proposal generation means for proposing appropriate transfers or work participation for employees based on the employee skills and characteristics identified by the data analysis means, communication means for notifying relevant departments of the contents of the proposals made by the proposal generation means, opinion collection means for collecting feedback based on the contents of the notifications made by the notification means, and aptitude evaluation means for analyzing the feedback collected by the opinion collection means and evaluating the appropriateness of the contents of the proposals. This makes it possible to efficiently collect and analyze employee skills and characteristics, generate appropriate work proposals, and evaluate the feedback based on the proposals.

[1137] "Information collection means" refers to a device or system for collecting the contents of meetings held between employees and generative AI.

[1138] The "data analysis means" is a device or process for analyzing the conference content data collected from the information collection means.

[1139] The "proposal generating means" is a device or system for proposing appropriate transfers or work participation of employees based on the skills and characteristics of the employees identified by the data analysis means.

[1140] The "communication means" is a device or system for notifying the relevant departments of the contents of the proposal made by the proposal generating means.

[1141] The "opinion collection means" is a device or system for collecting feedback based on the content of the notification by the notification means.

[1142] The "suitability evaluation means" is a device or system for analyzing the feedback collected by the opinion collection means and evaluating the suitability of the proposal content.

[1143] "Generative AI" is an artificial intelligence system that uses natural language processing technology to analyze meeting content data and generate appropriate business proposals.

[1144] "Meeting content data" refers to information that records statements and exchanges made during meetings between employees and generative AI.

[1145] The present invention is a system for improving the efficiency of human resource skill management and utilization within a company. Specifically, it includes a process for analyzing data collected through one-on-one meetings between employees and generative AI, and proposing appropriate employee transfers and project participation. An embodiment of this system is described in detail below.

[1146] Data collection

[1147] Once a month, users (employees) use their company devices to hold one-on-one meetings with the generative AI. During these meetings, the devices use the following hardware and software:

[1148] Hardware: Microphones, recording devices

[1149] Software: Google Cloud Speech-to-Text

[1150] The device records the meeting contents as audio and converts the audio data into text data in real time using Google Cloud Speech-to-Text. This converted text data is also used as subtitle information for the meeting contents. The collected data is sent from the device to the server using HTTPS communication.

[1151] Data reception and storage

[1152] The server receives the text data of the conference contents sent and stores it in a dedicated database. This database uses MySQL, PostgreSQL, etc. The server performs transaction control to ensure data integrity and security.

[1153] Data analysis

[1154] The server passes the stored text data to a generative AI analysis module, which uses natural language processing (NLP) techniques such as OpenAI's GPT-4 to analyze the text data and extract key keywords and phrases that identify employee skills and traits.

[1155] Proposal creation

[1156] The server updates the employee skill set and characteristics database based on the results of the generative AI analysis. The generative AI then uses the updated data to create appropriate employee transfer and project participation proposals. These proposals are compiled into documents using natural language generation technology.

[1157] proposal notification

[1158] The server then notifies the relevant department managers and staff of the created proposals via email, Microsoft Teams, Slack, and other communication methods, including the data that formed the basis of the proposal and important keywords.

[1159] Feedback collection and evaluation

[1160] The person in charge holds another one-on-one meeting with the employee based on the proposal content, and enters the feedback obtained from the meeting into the device. The device then sends this feedback information to the server. The server stores the received feedback in a database and passes it on to the generative AI. The generative AI uses the feedback data to evaluate the appropriateness of the proposal content. Sentiment analysis technology and other techniques are used in the evaluation, and the results of this evaluation are reflected in the creation of the next proposal.

[1161] Specific examples

[1162] For example, employee A belongs to the sales department and holds the following monthly one-on-one meeting. During the meeting, the user says, "This month, I focused particularly on negotiating with new clients, and I felt that my negotiation skills were one of my strengths." The device records this conversation, converts it into text data using Google Cloud Speech-to-Text, and sends it to the server.

[1163] The server passes the data to a generative AI (e.g., OpenAI GPT-4), which analyzes the text data and extracts keywords such as "negotiation skills" and "new client." This identifies that employee A has strengths in negotiation skills. The server then updates the database for employee A, and the generative AI creates a proposal to transfer employee A to a new project and notifies the sales department manager. The manager discusses the proposal with employee A in the next one-on-one meeting and collects feedback. This feedback is again evaluated by the server and the generative AI to determine the appropriateness of the proposal.

[1164] Prompt Sentence Examples

[1165] "Employee A mentioned in this month's one-on-one meeting that he focused particularly on negotiating with new clients and felt that negotiation skills were one of his strengths. Based on this, please conduct an analysis of Employee A's skills and characteristics and create an appropriate project participation proposal."

[1166] In this way, the present invention can efficiently manage and utilize the skills and characteristics of employees, contributing to the growth and development of a company.

[1167] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1168] Step 1: Data collection

[1169] Users use company devices to hold regular one-on-one meetings with generative AI. When a meeting begins, the device records audio data through a microphone. This audio data becomes the input. The device then converts the audio data into text data in real time using Google Cloud Speech-to-Text. Here, the audio data is recognized as a string of characters, and data processing is performed to convert each utterance into text format. The converted text data becomes the output and is prepared for the next step.

[1170] Step 2: Send data

[1171] The terminal sends the generated text data to the server via HTTPS. This process uses encryption to ensure data security. The input is the converted text data, and the output is the secure receipt of the data by the server.

[1172] Step 3: Receiving and storing data

[1173] The server receives text data sent from the terminal. The input is text data sent via HTTPS communication, and the server stores the data in a dedicated database. Transaction control is used to maintain the integrity of the database during storage. The output is text data saved in the database.

[1174] Step 4: Data analysis

[1175] The server passes the text data stored in the database to the generative AI analysis module. The input is the text data retrieved from the database. The analysis module (e.g., OpenAI GPT-4) analyzes the data using natural language processing technology and extracts important keywords and phrases. This analysis identifies employee skills and characteristics. The output is the keywords resulting from the analysis and the identified skills and characteristics.

[1176] Step 5: Proposal Generation

[1177] The server updates the employee skill set and characteristics database based on the analysis results output by the generative AI. Using this skill set and characteristics data, the generative AI again creates appropriate transfer and project participation proposals. The input is the analysis results, and the output is the generated proposal.

[1178] Step 6: Proposal Notification

[1179] The server notifies the necessary managers and personnel of the generated proposals. The input is the generated proposal, and the output is a notification via email, Microsoft Teams, or Slack. This notification process also includes the data that formed the basis of the proposal and important keywords.

[1180] Step 7: Gather feedback

[1181] The person in charge holds another one-on-one meeting with the employee based on the proposal, and inputs the feedback obtained during the meeting into the terminal. The input is the feedback obtained during the meeting, and the terminal sends it back to the server. The output is the transmission of the feedback data to the server.

[1182] Step 8: Feedback evaluation

[1183] The server stores the received feedback in a database and passes it to the generative AI. The input is the feedback data, which the generative AI analyzes and evaluates the appropriateness of the proposal. Sentiment analysis technology and other techniques are used for the evaluation. The output is the evaluation result regarding the appropriateness of the proposal, which is reflected in the creation of the next proposal.

[1184] (Application example 1)

[1185] 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."

[1186] Modern companies are required to accurately understand the skills and characteristics of their personnel and propose appropriate transfers and project participation. In particular, in on-site work such as factories, workers' skills are directly linked to work efficiency and productivity, so proper skill management and rapid feedback are essential. However, in current systems, these processes are often carried out manually, which is time-consuming and labor-intensive. Furthermore, worker skill evaluation relies on subjective judgment, which can lead to inappropriate evaluations. A system that can solve these issues is needed.

[1187] 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.

[1188] In this invention, the server includes: a data collection means for collecting the contents of meetings held between employees and the generative AI; an analysis means for analyzing the meeting content data collected by the data collection means; a proposal means for proposing appropriate employee transfers or project participation based on the employee's skills and characteristics identified by the analysis means; a notification means for notifying relevant departments of the contents of the proposals made by the proposal means; a feedback collection means for collecting feedback based on the contents of the notifications made by the notification means; an evaluation means for analyzing the feedback collected by the feedback collection means and evaluating the appropriateness of the proposals; a means for collecting speech and work content during work using a recording device attached to an information processing device used by the worker; a conversion means for converting the collected speech data into text data and transmitting it to the generative AI server; and a proposal means for evaluating the worker's skills based on the text data generated by the conversion means and proposing appropriate reassignment to a work position. This makes it possible to efficiently and accurately grasp the worker's skills and characteristics and quickly propose appropriate transfers and project participation.

[1189] "Data collection means" refers to a means of collecting data such as speech during meetings and work between workers and generative AI, as well as the content of the work, using information processing devices and recording devices.

[1190] The "analysis means" is a means for analyzing the data collected by the data collection means and extracting important information and keywords.

[1191] The "suggestion means" is a means for proposing appropriate transfers or project participation based on the skills and characteristics of employees or workers identified by the analysis means.

[1192] The "notification means" is a means for notifying the relevant departments and managers of the contents of the proposal made by the proposal means.

[1193] The "feedback collection means" is a means for collecting feedback based on the content of the notification by the notification means.

[1194] The "evaluation means" is a means for analyzing the feedback collected by the feedback collection means and evaluating the appropriateness of the proposal content.

[1195] The "recording device" is an information processing device for recording the voices of workers and the details of their work.

[1196] The "conversion means" is a means for converting collected voice data into text data and sending it to the generative AI server.

[1197] "Generative AI" is artificial intelligence that analyzes collected text data and uses natural language processing technology to evaluate skills.

[1198] This invention is a system that efficiently manages the skills and characteristics of human resources within a company and proposes appropriate transfers and project participation. This system utilizes smart glasses and AI technology to automate the skill evaluation and feedback management of field workers.

[1199] System Overview

[1200] The system is configured as follows:

[1201] 1. Data collection methods:

[1202] Smart glasses are information processing devices used by workers that record their speech and the details of their work. Data is collected using a microphone and camera built into the smart glasses, allowing for real-time recording of the worker's work status and voice.

[1203] 2. Conversion method:

[1204] The voice data collected by the smart glasses is converted into text data using voice recognition software (e.g., the SpeechRecognition module). The converted text data is then sent to the generative AI server.

[1205] 3. Analysis method:

[1206] The generative AI server analyzes the collected text data and uses a generative AI model (e.g., OpenAI API) to extract important keywords and phrases from the text data using natural language processing technology and identify the skills of the workers.

[1207] 4. Proposal method:

[1208] Based on the analysis results, the generative AI server evaluates the worker's skill set and proposes appropriate transfers or project participation. These proposals are automated and notified to the worker and relevant department managers as appropriate.

[1209] 5. Means of notification:

[1210] The proposals are then sent to the relevant departments and managers via email or a dedicated application.

[1211] 6. Feedback Collection Methods:

[1212] After the worker performs the work in the new position based on the proposal, the results of the work and their impressions are collected as feedback. Voice data is collected again using smart glasses and converted into text data.

[1213] 7. Evaluation Methods:

[1214] The collected feedback data is reanalyzed to evaluate the appropriateness of the underlying proposals, and a generative AI model is used to derive improvements and new proposals from the feedback.

[1215] Specific examples

[1216] For example, suppose Worker A is installing new wiring and says, "I've learned how to install new wiring. I'm good at detailed work. I quickly discovered a problem with a specific part." The smart glasses will record this voice and convert it into text data.

[1217] The converted text is sent to the generative AI server as the following prompt:

[1218] Example prompt sentence:

[1219] Analyze the statements of the workers below, extract keywords, and evaluate their skill sets.

[1220] "I learned how to install new wiring. I'm good at detailed work. I quickly identified a problem with a specific component."

[1221] The generative AI analyzes this prompt and extracts keywords such as "wiring installation," "detailed work," and "detecting defects in specific components." It then evaluates that Worker A excels in these skills and proposes an appropriate new work position. This proposal is notified to the manager of the relevant department and ultimately fed back to Worker A. The feedback is again collected by the smart glasses and evaluated by the generative AI model. This makes it possible to optimize the proposal.

[1222] In this way, the present invention makes it possible to quickly and accurately evaluate the skills and characteristics of workers and efficiently propose appropriate transfers and project participation.

[1223] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1224] Step 1:

[1225] The user puts on the smart glasses and begins working. The smart glasses' built-in microphone and camera record audio and video while working. This allows the user's work status and comments to be collected in real time. The input is the audio and video of the work being done, and the output is the recorded data.

[1226] Step 2:

[1227] The device converts the collected voice data into text data. Voice recognition software (e.g., SpeechRecognition module) is used to convert the voice data into text information. The input is voice data, and the output is converted text data. This process results in the speech written in natural language.

[1228] Step 3:

[1229] The device sends the converted text data to the generative AI server. Transmission is via internet communication. The input is the text data, and the output is a notification to the generative AI server that data transmission is complete. This passes the text data to the server for analysis.

[1230] Step 4:

[1231] The server uses generative AI to analyze the received text data. Using a generative AI model (e.g., OpenAI's API), keywords and important phrases are extracted through analysis. The input is text data, and the output is the analyzed keywords and phrases. This process identifies the skills and characteristics of the worker.

[1232] Step 5:

[1233] The server creates proposals based on the analysis results. The proposals include new work positions or project participation that are suited to the worker's skills and characteristics. The input is the analyzed keywords and phrases, and the output is the proposals. The proposals are generated automatically.

[1234] Step 6:

[1235] The server notifies the relevant departments and administrators of the proposal contents. Notifications are sent via email or a dedicated application. The input is the proposal contents, and the output is a notification of notification completion, allowing the administrator to check the proposal.

[1236] Step 7:

[1237] The user performs a new task based on the suggestions. After completing the task, they record their impressions and any problems they have as feedback via voice. Data is collected again using smart glasses. The input is the user's voice feedback, and the output is the recorded feedback data.

[1238] Step 8:

[1239] The terminal converts the collected feedback voice data back into text data and sends it to the generative AI server using speech recognition software. The input is the feedback voice data, and the output is the converted feedback text data.

[1240] Step 9:

[1241] The server analyzes the collected feedback data and evaluates the appropriateness of the proposals. A generative AI model is used to derive improvements and new proposals from the feedback. The input is the feedback text data, and the output is the evaluation results and improvement proposals. This process optimizes the proposals for future use.

[1242] 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.

[1243] The present invention provides a system for efficiently managing and utilizing human resource skills and emotions within a company. Hereinafter, an embodiment of the present invention will be described in detail.

[1244] System Overview

[1245] This system collects, analyzes, and proposes employee skills, characteristics, and emotions through regular one-on-one meetings between employees and generative AI. Specifically, it collects the content of meetings with employees, analyzes their emotions using an emotion engine, proposes appropriate transfers or project participation, and finally collects and evaluates feedback.

[1246] Data collection

[1247] Once a month, users (employees) use their company devices to hold one-on-one meetings with the generative AI. The user launches a dedicated application and presses the start button for the meeting. The device then records the contents of the meeting as audio data in real time. At the same time, the audio data is converted into text data. This text data is also used as subtitle information for the meeting. The collected data is sent from the device to a server.

[1248] Emotion analysis

[1249] The server stores the received meeting content data in a dedicated database. The data is then passed to a generative AI analysis module, where an emotion engine is built in to recognize and extract user emotions from the meeting content data. For example, emotions such as joy, sadness, and anger are identified. The emotion engine analyzes emotions from voice tone and text content.

[1250] Data analysis

[1251] The generative AI comprehensively analyzes the emotion data provided by the emotion engine and the text data of meeting contents to identify employee skills and characteristics. Based on the extracted emotion and skill data, it creates proposals for appropriate employee job assignments and project participation.

[1252] Suggestions and Notifications

[1253] The server reflects the analysis results in the employee database, updating the employee's skill set and characteristics. The generative AI then takes emotional data into account and generates suitable transfer and project participation proposals for the employee. The proposals are then sent via the server to managers and staff in the relevant departments.

[1254] Feedback and Ratings

[1255] The person in charge holds another one-on-one meeting with the employee based on the proposal and collects feedback on the results. The contents of this feedback meeting are also recorded and converted into text. The device sends the feedback meeting data to the server, which then passes it on to the generative AI. The generative AI analyzes the feedback and evaluates the appropriateness of the proposal.

[1256] Specific examples

[1257] For example, employee B belongs to the development department and holds the following monthly one-on-one meeting. During the meeting, the user says, "This month I particularly struggled with learning a new technology, but I finally succeeded and I'm very happy." The device records this conversation and sends it to the server as text data. From this content, the emotion engine identifies changes in emotion from distress to joy.

[1258] The generative AI analyzes emotion data along with keywords related to "acquiring new technologies" and identifies that employee B has a high ability to acquire new technologies and feels a sense of accomplishment. The server then updates the database for employee B, and the generative AI proposes employee B's participation in a new project and notifies the development department manager. The manager then discusses the proposal with employee B in the next one-on-one meeting and collects feedback. This feedback is again evaluated by the server and the generative AI to determine the appropriateness of the proposal.

[1259] This series of processes enables efficient management and utilization of employee skills and emotions, contributing to the growth and development of the company.

[1260] The processing flow will be explained below.

[1261] Step 1:

[1262] A user (employee) starts a one-on-one meeting with a generative AI using a company device. The user launches a dedicated application and presses the start button.

[1263] Step 2:

[1264] The device records the contents of the meeting as audio data in real time. At the same time, the audio data is converted into text data using natural language processing technology. The converted text data is also used as subtitle information for the meeting.

[1265] Step 3:

[1266] After the meeting ends, the device sends the recorded audio data and converted text data to the server, which then stores the received data in a dedicated database.

[1267] Step 4:

[1268] The server passes the saved text and audio data to the generative AI analysis module, where the emotion engine analyzes the meeting content data to recognize the user's emotions and extracts emotional data.

[1269] Step 5:

[1270] The emotion engine analyzes the user's emotions from the meeting content based on voice tone and context, identifying emotions such as joy, sadness, and anger.

[1271] Step 6:

[1272] The generative AI comprehensively analyzes the emotional and text data provided by the emotion engine to identify employee skills and traits, including skill extraction based on text analysis and emotional state assessment based on emotion analysis.

[1273] Step 7:

[1274] The server reflects the analysis results in the employee database and updates the employee's skill set, characteristics, and emotional information. For example, for employee A, the data "Negotiation skills: High" and "Recent emotional state: Joy" are added.

[1275] Step 8:

[1276] Based on the updated database, the generative AI generates proposals for appropriate employee transfers and project participation. In doing so, it takes into account not only skill data but also emotional data when creating the proposals. For example, it might make a proposal such as, "Employee A should be transferred to a large contract project. As his emotional state has been stable recently, an environment with less mental stress would be suitable."

[1277] Step 9:

[1278] The server notifies managers and staff in the relevant departments of the generative AI's proposals, via email or internal messenger.

[1279] Step 10:

[1280] The user (person in charge) will hold a one-on-one meeting with the employee based on the proposal and collect feedback on the results. The contents of this feedback meeting will also be recorded and converted into text.

[1281] Step 11:

[1282] The device sends the feedback meeting data to a server, which then passes it on to the generative AI, which analyzes the feedback and evaluates the appropriateness of the proposals.

[1283] Step 12:

[1284] The server stores the results of the generative AI evaluation in a database and initiates a new cycle including further suggestions and improvements as needed, thereby enabling efficient management of employee skills and emotions, contributing to the growth and development of the company as a whole.

[1285] Example 2

[1286] 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."

[1287] Companies are seeking to efficiently manage and utilize the skills and emotions of their employees. Accurately understanding employees' emotions and skills and making appropriate transfer and project participation proposals based on that information is essential for corporate growth. However, traditional methods make it difficult to do this efficiently, and analyzing emotions and collecting and evaluating feedback, in particular, requires a great deal of time and effort.

[1288] 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.

[1289] In this invention, the server includes: a data collection means for collecting the contents of meetings held between employees and the generative AI; a conversion means for converting the conference audio data collected from the data collection means into text data; a transmission means for transmitting the text data and audio data to the server; an analysis means for analyzing the data; an emotion analysis means for analyzing the emotions of employees identified by the analysis means; a data analysis means for identifying the skills and characteristics of employees based on the emotion analysis means and the conference content text data; a proposal means for proposing appropriate transfers or project participation for employees based on the data analysis means; a notification means for notifying relevant departments of the contents of the proposals made by the proposal means; a feedback collection means for collecting feedback based on the contents of the notifications made by the notification means; and an evaluation means for analyzing the feedback collected by the feedback collection means and evaluating the appropriateness of the proposals. This enables efficient management of employees' emotions and skills and the proposal of appropriate transfers or project participation based on the results.

[1290] "Data collection means" refers to a means for collecting the contents of meetings held between employees and generative AI.

[1291] The "conversion means" is a means for converting collected conference voice data into text data.

[1292] The "transmission means" is a means for transmitting text data and voice data to the server.

[1293] "Analysis means" refers to means for analyzing collected data.

[1294] The "emotion analysis means" is a means for analyzing the emotions of the employees identified by the analysis means.

[1295] The "data analysis means" is a means for identifying the skills and characteristics of employees based on the emotion analysis means and the meeting content text data.

[1296] "Proposal means" refers to a means for proposing appropriate transfers or project participation of employees based on data analysis means.

[1297] The "notification means" is a means for notifying the relevant departments of the content of the proposal made by the proposal means.

[1298] The "feedback collection means" is a means for collecting feedback based on the notification content.

[1299] The "evaluation means" is a means for analyzing the feedback collected by the feedback collection means and evaluating the appropriateness of the proposal content.

[1300] The present invention is a system for efficiently managing and utilizing human resource skills and emotions within a company. An embodiment of the present invention will now be described in detail.

[1301] System Overview

[1302] This system collects employee skills, characteristics, and emotions through regular one-on-one meetings between employees and generative AI, and then analyzes and proposes the data. The system includes the following detailed processes:

[1303] Data collection

[1304] Once a month, users (employees) use their company's devices to hold one-on-one meetings with the generative AI. The user launches a dedicated application and presses the start button for the meeting. The device records the meeting content as audio data in real time. At the same time, the audio data is converted into text data. This text data is also used as subtitle information for the conversation. The collected data is sent from the device to a server.

[1305] Emotion analysis

[1306] The server stores the received meeting content data in a dedicated database. The data is then passed to a generative AI analysis module, where an emotion engine is built in to recognize and extract user emotions from the meeting content data. For example, emotions such as joy, sadness, and anger are identified. The emotion engine analyzes emotions from voice tone and text content.

[1307] Data analysis

[1308] The generative AI comprehensively analyzes the emotion data provided by the emotion engine and the text data of meeting contents to identify employee skills and characteristics. Based on the extracted emotion and skill data, it creates proposals for appropriate employee job assignments and project participation.

[1309] Suggestions and Notifications

[1310] The server reflects the analysis results in the employee database, updating the employee's skill set and characteristics. The generative AI then takes emotional data into account and generates suitable transfer and project participation proposals for the employee. The proposals are then sent via the server to managers and staff in the relevant departments.

[1311] Feedback and Ratings

[1312] The person in charge holds another one-on-one meeting with the employee based on the proposal and collects feedback on the results. The contents of this feedback meeting are also recorded and converted into text. The device sends the feedback meeting data to the server, which then passes it on to the generative AI. The generative AI analyzes the feedback and evaluates the appropriateness of the proposal.

[1313] Specific examples

[1314] For example, employee B belongs to the development department and holds the following monthly one-on-one meeting. During the meeting, the user says, "This month I particularly struggled with learning a new technology, but I finally succeeded and I'm very happy." The device records this conversation and sends it to the server as text data. From this content, the emotion engine identifies changes in emotion from distress to joy.

[1315] The generative AI analyzes emotion data along with keywords related to "acquiring new technologies" and identifies that employee B has a high ability to acquire new technologies and feels a sense of accomplishment. The server then updates the database for employee B, and the generative AI proposes employee B's participation in a new project and notifies the development department manager. The manager then discusses the proposal with employee B in the next one-on-one meeting and collects feedback. This feedback is again evaluated by the server and the generative AI to determine the appropriateness of the proposal.

[1316] Prompt Sentence Examples

[1317] Employee B, who works in the development department, said, "I struggled to learn new technology this month, but I finally succeeded and I'm very happy." Analyze this conversation to identify changes in the employee's emotions and skill characteristics.

[1318] The above is an embodiment of the present invention. This system enables efficient management and utilization of human resource skills and emotions within a company.

[1319] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1320] Step 1:

[1321] The user launches the dedicated application on the device and presses the "Start Meeting" button.

[1322] Input: User actions

[1323] Output: Start of meeting

[1324] Specific operation: The user launches the dedicated application and clicks the "Start Conference" button, which puts the device into conference recording mode.

[1325] Step 2:

[1326] The terminal records the contents of the meeting in real time and converts the voice data into text data using a voice recognition engine.

[1327] Input: Meeting audio

[1328] Output: Text data

[1329] How it works: The device records the audio of the meeting and converts the audio data into text data in real time using a speech recognition engine such as Google Cloud Speech-to-Text.

[1330] Step 3:

[1331] The terminal transmits the converted text data and the original voice data to the server.

[1332] Input: Text data and audio data

[1333] Output: Send data to the server

[1334] Specific operation: The device encrypts text data and voice data via the SSL / TLS protocol and sends it to the server.

[1335] Step 4:

[1336] The server stores the received data in a database and passes it on to the generative AI analysis module.

[1337] Input: Text data and audio data

[1338] Output: Storing in a database and passing data to analysis modules

[1339] Specific operation: The server stores the received data in a dedicated database and classifies it by user ID. The data is then passed to the generative AI analysis module.

[1340] Step 5:

[1341] The emotion engine analyzes the data and identifies the user's emotion.

[1342] Input: Text data and audio data

[1343] Output: Emotion data

[1344] What it does: An emotion engine (e.g., IBM Watson Tone Analyzer) analyzes the tone of text and speech to identify the user's emotions, such as joy, sadness, or anger.

[1345] Step 6:

[1346] Generative AI comprehensively analyzes emotional data and text data from meeting content to extract employee skills and characteristics.

[1347] Input: Emotion data and text data

[1348] Output: Skill data and attribute data

[1349] How it works: Generative AI integrates emotional and textual data to extract skills and characteristics, such as the speed of technological acquisition and the ability to adapt to challenges.

[1350] Step 7:

[1351] The server reflects the analysis results in the employee database, and the generative AI generates suggestions.

[1352] Input: Skill data and attribute data

[1353] Output: Proposal data

[1354] Specific operation: The server reflects skill data and characteristic data in the employee database, and the generative AI generates appropriate proposals for employee transfers and project participation.

[1355] Step 8:

[1356] The server notifies the manager or person in charge of the relevant department of the proposal.

[1357] Input: Proposal data

[1358] Output: Notification data

[1359] Specific operation: The server notifies the managers and staff of the relevant departments of the generated proposals via email or a dedicated notification system.

[1360] Step 9:

[1361] The person in charge will hold another one-on-one meeting with the employee to discuss the proposal and gather feedback.

[1362] Input: Proposal data

[1363] Output: Feedback data

[1364] Specific operations: The person in charge discusses the proposal with employees, records the audio of the feedback meeting, and converts it into text data.

[1365] Step 10:

[1366] The device sends the feedback meeting data to the server, and the generative AI evaluates it.

[1367] Input: Feedback data

[1368] Output: Evaluation data

[1369] Specific operation: The device sends the text and audio data of the feedback meeting to the server, which then passes the data to the generative AI. The generative AI analyzes the feedback data and evaluates the appropriateness of the proposal.

[1370] These are the processing steps of this system. At each step, data is collected, converted, analyzed, proposed, notified, and feedback is collected and evaluated, allowing for efficient management and utilization of employee skills and emotions.

[1371] (Application example 2)

[1372] 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."

[1373] It is extremely important to understand the skills and characteristics of employees within a company and to make appropriate work plans. However, it is difficult to conduct a comprehensive evaluation that includes employee emotions, which has made improving work efficiency and employee satisfaction a challenge. In addition, it is difficult to collect and analyze data accurately in real time using paper-based or simple digital tools, so a new system to solve these issues was needed.

[1374] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1375] In this invention, the server includes a data collection means for collecting the contents of meetings held between employees and the generative AI, an analysis means for analyzing the meeting content data collected by the data collection means, a proposal means for proposing appropriate employee transfers or project participation based on the employee skills, characteristics, and emotional data identified by the analysis means, a notification means for notifying relevant departments of the contents of the proposals made by the proposal means, a feedback collection means for collecting feedback based on the contents of the notifications made by the notification means, an evaluation means for analyzing the feedback collected by the feedback collection means and evaluating the appropriateness of the contents of the proposals, and an emotion analysis means for grasping employee emotions in real time via smart devices. This allows for a comprehensive evaluation of employee emotions, enabling improved work efficiency and employee satisfaction.

[1376] "Employee" refers to an employee working within a company.

[1377] "Generative AI" refers to the entire system that uses artificial intelligence technology to analyze data and generate proposals.

[1378] "Data collection means" refers to the devices and processes that collect the contents of the meeting in the form of audio, video, etc.

[1379] "Analysis means" refers to the device and its functions that analyze employee skills, characteristics, emotions, etc. based on collected data.

[1380] "Proposal means" refers to a device and its functions that generate proposals for employee transfers and project participation based on the analysis results.

[1381] "Notification means" refers to a device and its function that notifies the manager or person in charge of the relevant department of the content of the generated proposal.

[1382] "Feedback collection means" refers to a device and its functionality for organizing and recording feedback collected based on suggestions.

[1383] "Evaluation means" refers to a device and its functions that analyzes collected feedback and evaluates the appropriateness of suggestions.

[1384] "Emotion analysis means" refers to a device and its functions that analyzes employee emotions in real time using a smart device.

[1385] "Smart devices" refers to portable or wearable electronic devices with advanced information processing capabilities, such as smartphones, smart glasses, and head-mounted displays.

[1386] "Natural language processing technology" refers to the technology that processes, understands, generates, and analyzes human language using a computer.

[1387] The present invention provides a system for improving the work efficiency and satisfaction of employees in a logistics center. As an embodiment of the present invention, a system is described that collects and analyzes work content and emotional data in real time when employees perform their work using smart devices (such as smart glasses).

[1388] System Overview

[1389] Users (employees) wear smart devices (such as smart glasses) to carry out their daily work. The smart devices collect audio and video data in real time while they are working. The audio data is converted into text data, and emotions are analyzed from the video data.

[1390] Data collection

[1391] Smart devices capture employees' work activities in real time as audio and video data. This data is collected by a data collection tool. The audio data is converted into text data using Google Cloud Speech-to-Text, and the video data is subjected to emotion analysis using the Microsoft Azure Face API.

[1392] Emotion analysis

[1393] The server processes the collected audio and video data using analytical means. It performs emotion analysis using the Azure Face API and extracts emotional data. This emotional data is expressed as parameters such as "happiness," "sadness," and "anger."

[1394] Data analysis

[1395] Generative AI identifies employee skills and characteristics by comprehensively analyzing text and emotion data extracted from voice data. This process uses OpenAI's GPT model, which uses natural language processing technology to analyze meeting content data and recognize skills and characteristics.

[1396] Suggestions and Notifications

[1397] Based on the analysis results, the server uses generative AI to propose appropriate employee transfers and project participation. These proposals are then notified to managers and staff in the relevant departments. Notifications are sent via email or internal communication systems.

[1398] Feedback and Ratings

[1399] Based on the proposal, the manager will hold another one-on-one meeting with the employee and collect feedback on the results. This feedback data is also collected as voice data and converted into text data and emotion data. The server passes the feedback data to the generative AI and evaluates the appropriateness of the proposal.

[1400] Specific examples

[1401] For example, suppose Employee A is working at a logistics center, replenishing shelves with products. If Employee A reports, "I struggled at first with the new work procedures, but I was able to complete the work smoothly in the end," the smart device will record this conversation and send it to the server as text data. The emotion analysis means will then identify from this content that the employee is expressing great joy.

[1402] The generative AI analyzes emotional and text data, identifies that Employee A has mastered efficient work procedures, and suggests a similar approach next time. An example of a specific prompt would be: "Analyze the emotions of employees at the logistics center and suggest an efficient process. Consider skills and emotions. Meeting content: Employee A has been very busy this month and had difficulty getting used to new work procedures, but ultimately reported that the work went smoothly. Emotion data: {"Happiness": 0.8, "Sadness": 0.1, "Anger": 0.1}."

[1403] This series of processes allows for a comprehensive evaluation of employee emotions, improving work efficiency and employee satisfaction.

[1404] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1405] Step 1:

[1406] The user wears the smart device and starts working. The smart device collects audio and video data in real time while the employee is working. The input is audio and video data during work, and the collected data is recorded as output.

[1407] Step 2:

[1408] The device converts the collected voice data into text data using Google Cloud Speech-to-Text. In this conversion process, the input is voice data and the output is text data. The voice data is transcribed.

[1409] Step 3:

[1410] The device performs emotion analysis on the collected video data using the Microsoft Azure Face API. It receives video data as input and obtains emotion parameters (happiness, sadness, anger, etc.) as output. The emotion analysis method identifies the employee's emotions from the video data.

[1411] Step 4:

[1412] The terminal sends the collected and converted text data and emotion data to the server. The input is text data and emotion data, and the data sent to the server is the output.

[1413] Step 5:

[1414] The server processes the received text data and emotional data using analytical means. The input is text data and emotional data, and analyzed skill and characteristic information is output. Generative AI performs data analysis using natural language processing technology.

[1415] Step 6:

[1416] Based on the analysis results, the generative AI will suggest appropriate transfers or project participation for employees. The input is the analysis results (skills, characteristics, and emotional data), and the output is a generated recommendation. An example of a specific prompt would be, "Analyze the emotions of employees at the logistics center and suggest an efficient process. Skills and emotions will be taken into consideration. Meeting content: Employee A has been very busy this month and reported that he had difficulty getting used to new work procedures, but that the work ultimately went smoothly. Emotion data: { "Happiness": 0.8, "Sadness": 0.1, "Anger": 0.1}."

[1417] Step 7:

[1418] The server notifies the generated proposal to the manager or person in charge of the relevant department. The proposal content is input and the notification is output. Notification is made via email or the internal communication system.

[1419] Step 8:

[1420] The manager then holds a one-on-one meeting with the employee based on the proposal and collects feedback on the results. The proposal is input and feedback data is output.

[1421] Step 9:

[1422] The device records the contents of the feedback meeting as audio data and converts it into text data using Google Cloud Speech-to-Text. The input is audio data and the output is text data.

[1423] Step 10:

[1424] The device performs emotion analysis on the video data of the feedback meeting using the Microsoft Azure Face API. The video data is input, and emotion parameters are obtained as output.

[1425] Step 11:

[1426] The server receives the feedback data and passes it to the generative AI, which takes text data and emotion data as input and outputs the analysis results.

[1427] Step 12:

[1428] Generative AI analyzes feedback and evaluates the appropriateness of proposals. The input is feedback data, and the output is an evaluation result. Based on this evaluation, new proposals and improvements are generated.

[1429] 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.

[1430] 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.

[1431] 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.

[1432] 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.

[1433] 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.

[1434] 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.

[1435] 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).

[1436] 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.

[1437] 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."

[1438] 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.

[1439] 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).

[1440] 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.

[1441] 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.

[1442] 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.

[1443] 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.

[1444] 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.

[1445] 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.

[1446] 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.

[1447] 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.

[1448] 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.

[1449] 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.

[1450] The following is further disclosed regarding the above embodiment.

[1451] (Claim 1)

[1452] A data collection method for collecting the contents of meetings between employees and generative AI;

[1453] analysis means for analyzing the conference content data collected from the data collection means;

[1454] a proposal means for proposing appropriate transfers or project participation of employees based on the skills and characteristics of the employees identified by the analysis means;

[1455] a notification means for notifying relevant departments of the content of the proposal made by the proposal means;

[1456] a feedback collection means for collecting feedback based on the content of the notification by the notification means;

[1457] evaluation means for analyzing the feedback collected by the feedback collection means and evaluating the appropriateness of the proposal content;

[1458] A system including:

[1459] (Claim 2)

[1460] The system of claim 1, wherein the generative AI analyzes meeting content data using natural language processing technology.

[1461] (Claim 3)

[1462] 2. The system according to claim 1, further comprising a conversion means for recording the conference content data as audio data and converting the audio data into text data.

[1463] "Example 1"

[1464] (Claim 1)

[1465] An information gathering means for collecting the contents of meetings held between employees and generative AI;

[1466] data analysis means for analyzing the conference content data collected from the information collection means;

[1467] a proposal generation means for proposing appropriate transfers or work participation of employees based on the skills and characteristics of the employees identified by the data analysis means;

[1468] a communication means for notifying relevant departments of the content of the proposal made by the proposal generating means;

[1469] an opinion collection means for collecting feedback based on the content of the notification by the notification means;

[1470] an appropriateness evaluation means for analyzing the feedback collected by the opinion collection means and evaluating the appropriateness of the proposal content;

[1471] A system including:

[1472] (Claim 2)

[1473] The system of claim 1, wherein the generative AI analyzes meeting content data using natural language processing technology.

[1474] (Claim 3)

[1475] 2. The system according to claim 1, further comprising a data conversion means for recording the conference content data as audio data and converting the audio data into text data.

[1476] "Application Example 1"

[1477] (Claim 1)

[1478] A data collection method for collecting the contents of meetings between employees and generative AI;

[1479] analysis means for analyzing the conference content data collected from the data collection means;

[1480] a proposal means for proposing appropriate transfers or project participation of employees based on the skills and characteristics of the employees identified by the analysis means;

[1481] a notification means for notifying relevant departments of the content of the proposal made by the proposal means;

[1482] a feedback collection means for collecting feedback based on the content of the notification by the notification means;

[1483] evaluation means for analyzing the feedback collected by the feedback collection means and evaluating the appropriateness of the proposal content;

[1484] a means for collecting utterances and work contents during work by utilizing a recording device attached to an information processing device used by the worker;

[1485] A conversion means for converting the collected voice data into text data and transmitting it to a generative AI server;

[1486] a suggestion means for evaluating the skills of the workers from the text data generated by the conversion means and suggesting a reassignment to an appropriate work position;

[1487] A system including:

[1488] (Claim 2)

[1489] The system of claim 1, wherein the generative AI analyzes meeting content data using natural language processing technology.

[1490] (Claim 3)

[1491] 2. The system according to claim 1, further comprising a conversion means for recording the conference content data as audio data and converting the audio data into text data.

[1492] "Example 2: Combining Emotion Engines"

[1493] (Claim 1)

[1494] A data collection method for collecting the contents of meetings between employees and generative AI;

[1495] a conversion means for converting the conference voice data collected from the data collection means into text data;

[1496] a transmitting means for transmitting the text data and the voice data to a server;

[1497] analysis means for analyzing the data;

[1498] emotion analysis means for analyzing the emotions of employees identified by the analysis means;

[1499] a data analysis means for identifying the skills and characteristics of employees based on the emotion analysis means and the meeting content text data;

[1500] a proposal means for proposing appropriate transfers or project participation of employees based on the data analysis means;

[1501] a notification means for notifying relevant departments of the content of the proposal made by the proposal means;

[1502] a feedback collection means for collecting feedback based on the content of the notification by the notification means;

[1503] evaluation means for analyzing the feedback collected by the feedback collection means and evaluating the appropriateness of the proposal content;

[1504] A system including:

[1505] (Claim 2)

[1506] The system according to claim 1, wherein the generative AI analyzes the meeting content data using natural language processing technology and speech analysis technology.

[1507] (Claim 3)

[1508] 2. The system according to claim 1, further comprising a conversion means for recording the conference content data as audio data and converting the audio data into text data.

[1509] "Application example 2 when combining emotion engines"

[1510] (Claim 1)

[1511] A data collection method for collecting the contents of meetings between employees and generative AI;

[1512] analysis means for analyzing the conference content data collected from the data collection means;

[1513] a proposal means for proposing appropriate transfers or project participation of employees based on the skills, characteristics and emotional data of the employees identified by the analysis means;

[1514] a notification means for notifying relevant departments of the content of the proposal made by the proposal means;

[1515] a feedback collection means for collecting feedback based on the content of the notification by the notification means;

[1516] evaluation means for analyzing the feedback collected by the feedback collection means and evaluating the appropriateness of the proposal content;

[1517] Sentiment analysis tools to grasp employee emotions in real time through smart devices,

[1518] A system including:

[1519] (Claim 2)

[1520] The system of claim 1, wherein the generative AI analyzes meeting content data using natural language processing technology and sentiment analysis technology.

[1521] (Claim 3)

[1522] 2. The system according to claim 1, further comprising a conversion means for recording the meeting content data and the emotion data of the employees at that time as voice data, and converting the voice data into text data and emotion data. [Explanation of symbols]

[1523] 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 data collection method for collecting the contents of meetings between employees and generative AI; analysis means for analyzing the conference content data collected from the data collection means; a proposal means for proposing appropriate transfers or project participation of employees based on the skills and characteristics of the employees identified by the analysis means; a notification means for notifying relevant departments of the content of the proposal made by the proposal means; a feedback collection means for collecting feedback based on the content of the notification by the notification means; evaluation means for analyzing the feedback collected by the feedback collection means and evaluating the appropriateness of the proposal content; A system including:

2. The system according to claim 1, wherein the generative AI analyzes the meeting content data using natural language processing technology.

3. 2. The system according to claim 1, further comprising a conversion means for recording the conference content data as voice data and converting the voice data into text data.

Images