System

Abstract

A system is provided.SOLUTION: A system comprising: means for recording operation data of a user during work; means for collecting message data of the user; means for analyzing the recorded operation data and the collected message data and evaluating productivity, creativity, business contribution, and cooperativeness of the user; and means for visualizing an evaluation result.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In corporate personnel evaluations, personal preferences and relationships are often emphasized over performance, which can lead to the problem of "friendly personnel" practices that can lead to poor performance. Furthermore, there are many cases where the evaluator's emotional bias influences the evaluation, resulting in an inappropriate evaluation of true ability. Under these circumstances, it is difficult to improve company-wide productivity or establish a fair evaluation system, so there is a need to eliminate emotional bias and achieve fair and multifaceted evaluations. [Means for solving the problem]

[0005] The present invention provides a system that records user operation data and collects message data during work, analyzes the data, and evaluates users' productivity, creativity, business contribution, and cooperativeness from multiple perspectives. Specifically, the system includes a means for encrypting the recorded operation data, transmitting it to a server, and storing it, and a means for analyzing the collected message data using a natural language processing algorithm to evaluate cooperativeness. This system eliminates emotional bias and enables fair and multifaceted evaluation, thereby establishing a meritocratic personnel evaluation system for companies.

[0006] "User work activity data" refers to data about a user's digital activities, such as the computer applications they use, the files they access, the web pages they browse, and the documents they create or edit while performing their work.

[0007] "Message data" refers to data related to the content, time of sending, and recipient of messages sent or received by users using internal chat tools, email, etc.

[0008] "Productivity" is an index that measures the quantity and quality of work that a user accomplishes within a certain period of time, and specifically includes the number of tasks completed and work efficiency.

[0009] "Creativity" refers to an indicator that measures a user's ability to propose new ideas and solutions and contribute to problem solving and value creation.

[0010] "Business contribution" refers to an index that measures the extent to which the projects or business activities in which a user participated have influenced the profits and progress of the business.

[0011] "Cooperativeness" refers to an index that measures the degree to which a user cooperates with other members to carry out tasks and contributes to teamwork and support activities.

[0012] "Encryption" refers to a technology that converts data using a specific algorithm to protect it from unauthorized access.

[0013] "Server" refers to a computer system within a network that receives, stores, and analyzes data sent from user terminals.

[0014] "Natural language processing algorithms" refer to computer programs and technologies that analyze text data, extract meaning, and perform processes such as sentiment analysis and topic modeling.

[0015] The "evaluation score" is a numerical value obtained as a result of the analysis, and refers to an index for comprehensively measuring a user's productivity, creativity, business contribution, and cooperativeness. [Brief explanation of the drawings]

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

[0017] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

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

[0020] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0021] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

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

[0026] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0033] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

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

[0037] The system of the present invention collects and analyzes operation data and message data of users during their work, and evaluates the users' productivity, creativity, business contribution, and cooperativeness from various angles. Detailed embodiments of the system are described below.

[0038] Explanation of program processing

[0039] In the system of the present invention, the following processing is performed.

[0040] Data collection

[0041] 1. Collecting Operational Data

[0042] The device monitors the user's work activities and records data in real time, such as applications running, files accessed, web pages browsed, and documents created or edited.

[0043] The terminal collects this operational data at regular intervals, compresses it, and sends it to the server in encrypted form.

[0044] 2. Message Data Collection

[0045] The device records the content, time of sending, and recipient of messages sent and received via the user's internal chat tool, email, etc.

[0046] The device preprocesses the collected message data (text cleaning, tokenization, etc.) and periodically sends it to the server.

[0047] Data storage and management

[0048] 3. Data storage

[0049] The server receives operation data and message data sent from the terminal in real time and stores them in a secure database.

[0050] The server performs regular backups to ensure data consistency and integrity, and restores data when necessary.

[0051] Data analysis

[0052] 4. Analysis of Operational Data

[0053] The server analyzes the recorded operation data and calculates productivity indicators for each user (e.g., number of tasks processed, work time, work efficiency).

[0054] The server evaluates the contribution of each project and calculates the impact on the project's profits and progress.

[0055] 5. Message Data Analysis

[0056] The server analyzes the message data using natural language processing algorithms and evaluates the level of cooperation, including analyzing the sentiment of the message content.

[0057] The server performs sentiment analysis to identify positive and negative communications and calculates an agreeableness score.

[0058] Evaluation and visualization

[0059] 6. Calculation of evaluation score

[0060] The server combines the above-mentioned productivity, creativity, business contribution, and cooperativeness indicators to generate an overall evaluation score for each user.

[0061] The server visualizes the evaluation results based on this score as graphs and charts and displays them on a dashboard.

[0062] 7. Providing Feedback

[0063] The user logs in to the dashboard and checks the evaluation results.

[0064] The server displays feedback to the user and provides feedback on areas for improvement and strengths based on the evaluation results.

[0065] Specific examples

[0066] For example, if employee A is working on multiple projects:

[0067] The device records in detail employee A's daily working hours, files handled, applications used, etc.

[0068] The device collects messages exchanged with other members through the company's internal chat tool, preprocesses them, and then sends them to the server.

[0069] The server analyzes this data and calculates employee A's productivity (e.g., number of tasks completed per day), business contribution (e.g., impact on project progress), and cooperation (e.g., percentage of positive messages).

[0070] Based on these analysis results, the server generates an overall evaluation score for employee A and displays it on the dashboard.

[0071] User Employee A accesses the dashboard to review his or her own evaluation and receive feedback on strengths and areas for improvement.

[0072] In this way, the system of the present invention eliminates emotional bias and realizes fair and multifaceted evaluation based on data.

[0073] The processing flow will be explained below.

[0074] Step 1:

[0075] The device monitors user operations in real time while working and records each operation event (launching an application, accessing a file, browsing a web page, creating or editing a document, etc.).

[0076] Step 2:

[0077] The device collects the recorded operation data at regular intervals and compresses it to reduce the data volume. The compressed operation data is temporarily stored in the device.

[0078] Step 3:

[0079] The device encrypts the compressed operation data and sends it to the server after ensuring security. Transmission is performed during off-peak hours to minimize network load.

[0080] Step 4:

[0081] The device also collects data from users' internal chat tools and emails, and preprocesses it, including metadata such as message content, sending time, and recipients. Preprocessing includes text cleaning and tokenization.

[0082] Step 5:

[0083] The terminal compresses and encrypts the preprocessed message data and transmits it to the server in the same manner as the operation data.

[0084] Step 6:

[0085] The server receives operation data and message data sent from the device in real time and stores them in a secure database. The stored data undergoes a backup process to ensure data consistency and integrity.

[0086] Step 7:

[0087] The server analyzes the saved operation data and calculates productivity indicators for each user, including the number of tasks completed, work time, and work efficiency.

[0088] Step 8:

[0089] The server evaluates the contribution of each project by calculating the user's operation data and the impact on the progress and profits of the project.

[0090] Step 9:

[0091] The server analyzes the message data using natural language processing algorithms, which perform sentiment analysis of the text, distinguish between positive and negative communication, and calculate an agreeableness score.

[0092] Step 10:

[0093] The server combines each user's productivity, creativity, business contribution, and cooperativeness indicators to generate an overall evaluation score.

[0094] Step 11:

[0095] The server visualizes the generated rating scores and displays them on a dashboard as graphs and charts, allowing users to check their own ratings.

[0096] Step 12:

[0097] Users access a dashboard to view their assessment results and feedback, which includes strengths and areas for improvement based on the assessment results.

[0098] This series of processing steps eliminates emotional bias and enables a multifaceted and fair evaluation.

[0099] Example 1

[0100] 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."

[0101] With conventional systems, it was easy for emotional bias to creep in when evaluating users' work efficiency and cooperation, making it difficult to make objective, data-based evaluations. Furthermore, there was also the issue of delays in evaluation results because operation data and message data were not collected and analyzed in real time. Furthermore, when providing evaluation results to users, there was also the issue of a lack of specific feedback on areas for improvement and strengths.

[0102] 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.

[0103] In this invention, the server includes means for recording user operation data during work in real time and compressing and encrypting it at regular intervals before transmitting it, means for preprocessing message data and periodically transmitting it, means for generating an evaluation score for each user and displaying it on a dashboard, and means for providing the user with feedback on areas for improvement and strengths. This enables fair and multifaceted evaluation based on data and makes it possible to provide the user with specific areas for improvement and strengths in real time.

[0104] "User operation data" refers to data such as the applications a user uses to perform their work, the files they access, the web pages they browse, and the documents they create and edit.

[0105] "Message data" refers to data related to the content, time of sending, and recipient of messages sent and received by users via internal chat tools, email, etc.

[0106] "Analysis" refers to the processing and analysis of recorded or collected data to extract and evaluate specific indicators or patterns.

[0107] "Productivity" refers to indicators such as the number of tasks, workload, and work efficiency completed by a user within a certain period of time.

[0108] "Creativity" refers to the ability of users to propose new ideas and come up with original solutions while performing their work.

[0109] "Business contribution" refers to an indicator that evaluates the impact that the projects and tasks a user is responsible for have on the profits and progress of the entire organization.

[0110] "Collaboration" is an indicator that evaluates how effectively a user can cooperate with other members in internal communications and build positive relationships.

[0111] "Means for visualizing evaluation results" refers to means for displaying the user evaluation results obtained by analysis in a visual format such as a graph or chart.

[0112] "Means for recording data in real time" refers to means for instantly recording information each time a user performs an operation.

[0113] "Means for compressing and encrypting and transmitting" refers to means for compressing and encrypting collected data for the purpose of reducing its size and protecting its security, and transmitting it to a server via a network.

[0114] "Means for preprocessing and sending" refers to means for periodically sending collected message data to a server after preprocessing it, such as cleaning and tokenizing it, into a format suitable for analysis.

[0115] The "means for generating an evaluation score" refers to a means for integrating various indicators such as productivity, creativity, business contribution, and cooperativeness to calculate an overall evaluation score for each user.

[0116] "Means for displaying on a dashboard" refers to means for displaying the evaluation score and feedback information on a dashboard that can be accessed by the user.

[0117] "Means for providing feedback on areas for improvement and strengths" refers to means for analyzing specific areas for improvement and strengths based on the user's evaluation results and providing them to the user.

[0118] The system of the present invention collects and analyzes operation data and message data of users during their work, and evaluates the users' productivity, creativity, business contribution, and cooperativeness from various angles. Detailed embodiments of the system are described below.

[0119] Data collection

[0120] Operational Data Collection

[0121] The device monitors user activity 24 / 7, recording in real time which applications are running, which files are accessed, which web pages are browsed, and which documents are created or edited.

[0122] The terminal compresses the collected operation data every hour and sends it to the server in encrypted form, using encryption technologies such as SSL / TLS to protect the data.

[0123] Message Data Collection

[0124] The device monitors the user's internal chat tools and emails, recording the content of messages sent and received, the time of sending, and the recipients.

[0125] The device preprocesses message data (such as text cleaning and tokenization) once a day before sending it to the server. This preprocessing is done using Python's NLTK and SpaCy libraries.

[0126] Data storage and management

[0127] Data storage

[0128] The server stores the received operation data and message data in a high-speed database (e.g., PostgreSQL or MongoDB) in real time, and performs transaction management to maintain data consistency.

[0129] The server performs regular database backups to prevent data loss, and the backup data is also stored in cloud storage such as AWS S3.

[0130] Data analysis

[0131] Analysis of operational data

[0132] The server uses machine learning algorithms to analyze the operation data and calculate productivity metrics for each user, using libraries such as Scikit-learn and TensorFlow.

[0133] The server then evaluates the user's contribution to each project and calculates the impact on the project's profits and progress, using multivariate analysis and clustering techniques.

[0134] Parsing message data

[0135] The server analyzes message data using natural language processing (NLP) algorithms, including sentiment analysis, leveraging models such as BERT and GPT-3.

[0136] The server distinguishes between positive and negative communication from the message content and calculates an agreeableness score.

[0137] Evaluation and visualization

[0138] Calculation of evaluation score

[0139] The server aggregates the productivity, creativity, business contribution, and collaboration metrics to generate an overall evaluation score for each user, which is then displayed as graphs and charts using visualization libraries such as D3.js and Chart.js.

[0140] The server updates the evaluation results in real time and displays them on a dashboard, which uses visualization tools such as Kibana and Grafana.

[0141] Providing Feedback

[0142] Providing Feedback

[0143] Users can log in to their account and check the results of their evaluations on the dashboard, where they can see not only the overall evaluation score but also detailed feedback on each indicator.

[0144] The server provides users with feedback on areas for improvement and strengths based on the evaluation results, and proposes specific action plans, including goal setting and progress management tools.

[0145] Specific examples

[0146] For example, let's say employee A is working on multiple projects.

[0147] The terminal records employee A's daily operation data (such as applications used and files accessed) in real time and sends it to the server every hour.

[0148] The terminal collects messages sent and received by employee A via internal chat tools and email, preprocesses them once a day, and then sends them to the server.

[0149] The server analyzes employee A's productivity (e.g., number of tasks completed per day) based on the operation data and evaluates his / her contribution to each project.

[0150] The server uses NLP algorithms to perform sentiment analysis of the message data and calculates an agreeableness score.

[0151] Based on these analysis results, the server generates an overall evaluation score for employee A and displays it on the dashboard.

[0152] User Employee A accesses the dashboard to review his or her own evaluation and receive feedback on strengths and areas for improvement.

[0153] Prompt Sentence Examples

[0154] Below are examples of prompt sentences to be input to the generative AI model based on specific examples.

[0155] Explain how to analyze Employee A's number of tasks completed per day, productivity score, and contribution per project and display them on a dashboard.

[0156] Please tell us more about the algorithm that analyzes the sentiment of chat messages and calculates the agreeableness score.

[0157] Explain how you can use interaction and message data to assess user creativity.

[0158] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0159] Step 1: Collect data

[0160] Operational Data Collection

[0161] The terminal records operational data in real time, such as the launch history of applications used by the user when performing work, files accessed, web pages browsed, and documents created and edited.

[0162] The input of the terminal is the user's operation events (e.g., clicks, keystrokes), and the output is the log data in which these events are recorded.

[0163] The device periodically compresses and encrypts the operational data before sending it to the server, using encryption technologies such as SSL / TLS to protect the data.

[0164] Message Data Collection

[0165] The device records the content, time of sending, and recipient of messages sent and received via the user's internal chat tool or email.

[0166] The input to the terminal is events such as sending and receiving emails from an internal chat tool, and the output is log data in which these message data are recorded.

[0167] The device preprocesses the collected message data (such as text cleaning and tokenization) and periodically sends it to the server. Preprocessing is performed using Python's NLTK and SpaCy libraries.

[0168] Step 2: Store and manage your data

[0169] Data storage

[0170] The server receives the operation data and message data sent from the terminal and stores them in a database (e.g., PostgreSQL or MongoDB) in real time.

[0171] The input of the server is encrypted operational and message data, and the output is data stored in a database.

[0172] The server performs transaction management to enhance data consistency and integrity. In addition, it periodically backs up the database and stores it in cloud storage (e.g., AWS S3).

[0173] Step 3: Data analysis

[0174] Analysis of operational data

[0175] The server uses machine learning algorithms to analyze the operation data and calculate productivity indicators for each user (e.g., number of tasks completed, work time, and work efficiency).

[0176] The input of the server is the operational data stored in the database, and the output is the analysis results including productivity indicators.

[0177] The server uses libraries such as Scikit-learn and TensorFlow to extract and analyze patterns and trends in the operational data.

[0178] Parsing message data

[0179] The server analyzes the message data using natural language processing (NLP) algorithms and performs sentiment analysis.

[0180] The server's input is message data stored in a database, and its output is analysis results such as cooperativeness scores.

[0181] The server utilizes generative AI models such as BERT and GPT-3 to perform sentiment analysis of message content and identify positive and negative communication.

[0182] Step 4: Evaluate and visualize

[0183] Calculation of evaluation score

[0184] The server integrates the productivity, creativity, business contribution, and cooperativeness indicators to generate an overall evaluation score for each user.

[0185] The input to the server is the analysis results of the operation data and message data, and the output is a comprehensive evaluation score.

[0186] The server uses visualization libraries such as D3.js and Chart.js to display the evaluation results as graphs and charts.

[0187] Step 5: Provide feedback

[0188] Providing Feedback

[0189] Users can log in to their dashboard with their account and check the evaluation results.

[0190] The input of the dashboard is the evaluation scores and feedback information sent from the server, and the output is the visualization data displayed to the user.

[0191] The server provides users with feedback on areas for improvement and strengths based on the evaluation results, and proposes specific action plans, including goal setting and progress management tools.

[0192] (Application example 1)

[0193] 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."

[0194] In recent years, factories have been required to collect and analyze employee operation data and message data in order to improve work efficiency and productivity. However, to evaluate employee activities from multiple angles, it is necessary to collect data in real time and analyze it with high accuracy. In conventional systems, the collection and analysis of operation data and message data are separated, and evaluation criteria are limited, making it difficult to evaluate overall productivity and cooperativeness. The present invention aims to solve these problems and provide a system that comprehensively and fairly evaluates the productivity, cooperativeness, creativity, and business contribution of factory workers.

[0195] 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.

[0196] In this invention, the server includes a means for analyzing the recorded operation data and collected message data to evaluate the user's productivity, creativity, business contribution, and cooperativeness, a means for visualizing the evaluation results, and a means for supporting the creation of prompt sentences to be input to the generative AI model, thereby enabling the evaluation of work efficiency and cooperativeness in factories.

[0197] "Operational data" refers to the series of work procedures and operations performed by a user during work, including, specifically, running applications, accessed files, viewed web pages, and created / edited documents.

[0198] "Message data" is text data that includes information such as the content, transmission time, and recipient of messages sent and received by users via in-house chat tools, e-mail, etc.

[0199] "Productivity" is an index that indicates the quantity and quality of tasks and deliverables that a user has completed within a certain period of time, and is used to evaluate the user's work efficiency and ability to perform work.

[0200] "Creativity" is an index that evaluates a user's ability to come up with new ideas and projects and to apply them to actual work.

[0201] "Business contribution" is an index that evaluates how much a user's business activities have affected the profits of the entire organization and the progress of a project.

[0202] "Cooperativeness" is an index that evaluates how smoothly a user communicates with other members and how much they contribute to achieving the team's goals.

[0203] "Visualization" refers to displaying the evaluation results in a visual format such as a graph or chart, allowing users to intuitively understand them.

[0204] "Real-time" refers to data collection or processing occurring immediately without delay, meaning that user actions and operations are immediately reflected in the system.

[0205] "Generative AI models" refer to algorithms or models that use artificial intelligence technology to analyze user behavioral data and provide evaluations and feedback.

[0206] A "prompt sentence" is a text sentence that contains input data for a generative AI model, and contains information that serves as instructions for the AI ​​to perform appropriate analysis and evaluation.

[0207] The system of the present invention collects and analyzes operation data and message data of workers during their work in a factory, and evaluates their productivity and cooperation. Specific embodiments will be described below.

[0208] Data collection methods

[0209] First, the device (in this case, smart glasses) collects the worker's operation data. This data includes eye movements during work, setup procedures, details of repair work, and the status of the work environment. The smart glasses use built-in cameras and sensors to monitor and record this data in real time, and then periodically send it to a server in a consolidated form.

[0210] Message data is collected by using the voice recognition function of the smart glasses to recognize verbal instructions and reports given by workers and record them as text data. This text data is then periodically sent to a server after undergoing preprocessing (such as text cleaning and tokenization).

[0211] Data Storage and Management

[0212] The server then receives the operation and message data sent from the device in real time and stores it in a secure database. To ensure data consistency and integrity, the server performs regular backups and restores the data when necessary.

[0213] Data Analysis Methods

[0214] The server analyzes the recorded operation data and calculates productivity indicators for each user (e.g., number of tasks completed, working time, work efficiency). Furthermore, it evaluates the contribution of each project and calculates the impact on the project's profits and progress.

[0215] Message data is analyzed using natural language processing algorithms, which evaluates cooperation by analyzing the sentiment of the message content. Sentiment analysis distinguishes between positive and negative communication and calculates a cooperation score.

[0216] Evaluation and visualization

[0217] The server combines the above indicators of productivity, creativity, business contribution, and cooperativeness to generate an overall evaluation score for each user. Based on this score, the evaluation results are visualized as graphs and charts and displayed on a dashboard. Users can log in to the dashboard to check their evaluation results and receive feedback based on them.

[0218] Specific examples

[0219] For example, if a factory worker is assembling a product:

[0220] The smart glasses record workers' eye movements and work procedures in detail.

[0221] Verbal instructions and reports given by workers are collected using a voice recognition function and converted into text data.

[0222] The server receives and analyzes this data in real time and evaluates it based on work efficiency and cooperation.

[0223] The evaluation results and feedback are displayed in real time on the smart glasses display.

[0224] Examples of prompt statements

[0225] Enter the following prompt for the generative AI model:

[0226] Operation data: A worker is assembling product A. Part number 123 is being assembled, and eye movement is normal and there are no problems with the work procedure.

[0227] Message data: Assembly complete.

[0228] The above is an embodiment of the present invention, which makes it possible to comprehensively evaluate work efficiency and cooperation in a factory and provide feedback for improvement.

[0229] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0230] Step 1:

[0231] The terminal collects the worker's operation data. The input is real-time data such as eye movements and work procedures collected by the smart glasses using cameras and sensors. This data is temporarily stored on the terminal. The output is compressed and encrypted operation data.

[0232] Step 2:

[0233] The terminal collects message data from workers. The input is verbal instructions and reports from workers obtained using a voice recognition function. The voice data is converted into text data, which is preprocessed (text cleaning and tokenization) and temporarily stored. The output is the preprocessed text data.

[0234] Step 3:

[0235] The terminal periodically collects operation data and message data and sends them to the server. The input is the data collected and preprocessed in steps 1 and 2. The data is sent to the server in real time. The output is the data sent to the server in real time.

[0236] Step 4:

[0237] The server stores the data it receives in a database. The input is the operation data and message data sent from the terminal. This data is securely stored in the database and is backed up regularly to ensure consistency and completeness. The output is the data securely stored in the database.

[0238] Step 5:

[0239] The server analyzes the operation data. The input is the saved operation data, and by analyzing this data, it calculates productivity indicators for each user (e.g., number of tasks completed, work time, work efficiency, etc.). The output is the productivity indicators for each user.

[0240] Step 6:

[0241] The server analyzes the message data using a natural language processing algorithm. The input is the stored message data. This data is used to analyze the message content and sentiment, and calculate an agreeableness score. The output is an agreeableness score.

[0242] Step 7:

[0243] The server combines the productivity index and cooperativeness score to generate an overall evaluation score for each user. The inputs are the productivity index and cooperativeness score obtained in steps 5 and 6. These are combined to calculate the overall evaluation score. The output is the overall evaluation score.

[0244] Step 8:

[0245] The server visualizes the overall evaluation score and displays it on a dashboard. The input is the overall evaluation score calculated in step 7. This is visually represented as a graph or chart and displayed on the dashboard so that the user can check it. The output is a dashboard showing the evaluation results.

[0246] Step 9:

[0247] The server assists in creating prompt sentences to be input to the generated AI model. The input is operation data and message data. Based on this, a prompt sentence is generated and input to the AI ​​model. As a specific example, the following prompt sentence is generated: "Operation data: Worker is assembling product A. Part number 123 is assembled, eye movement is normal, no problems with the work procedure. Message data: Assembly completed." The output is the generated prompt sentence.

[0248] 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.

[0249] The system of the present invention evaluates users' productivity, creativity, business contribution, and cooperativeness by collecting and analyzing operation data and message data during user work. Furthermore, by combining it with an emotion engine that recognizes users' emotions, the accuracy of the evaluation and the quality of the feedback are improved.

[0250] Explanation of program processing

[0251] In the system of the present invention, the following processing is performed.

[0252] Data collection

[0253] 1. Collecting Operational Data

[0254] The device monitors the user's work activities in real time and records each operation event (launching an application, accessing a file, browsing a web page, creating or editing a document, etc.).

[0255] The terminal collects this operational data at regular intervals, compresses it, and sends it to the server in encrypted form.

[0256] 2. Message Data Collection

[0257] The device records the content, time of sending, and recipient of messages sent and received via the user's internal chat tool, email, etc.

[0258] The device preprocesses the collected message data (text cleaning, tokenization, etc.) and periodically sends it to the server.

[0259] Data storage and management

[0260] 3. Data storage

[0261] The server receives the operation data and message data sent from the terminal in real time and stores them in a secure database.

[0262] The server performs regular backups to ensure data consistency and integrity, and restores data when necessary.

[0263] Data analysis

[0264] 4. Analysis of Operational Data

[0265] The server analyzes the recorded operation data and calculates productivity indicators for each user (e.g., number of tasks processed, work time, work efficiency).

[0266] The server evaluates the contribution of each project and calculates the impact on the project's profits and progress.

[0267] 5. Message Data Analysis

[0268] The server analyzes the message data using natural language processing algorithms, including analyzing the sentiment of the text, to extract data to assess the user's agreeableness.

[0269] 6. Use of Emotion Engine

[0270] The server uses an emotion engine to recognize the user's emotions from the user's message data and operation data during work.

[0271] The emotion engine identifies positive and negative emotions and calculates emotional indicators such as agreeableness and stress level.

[0272] Evaluation and visualization

[0273] 7. Calculation of evaluation score

[0274] The server integrates the data on productivity, creativity, business contribution, cooperativeness, and emotional indicators mentioned above to generate an overall evaluation score for each user.

[0275] The server visualizes the evaluation results based on this score as graphs and charts and displays them on a dashboard.

[0276] 8. Providing Feedback

[0277] Users access a dashboard to view their assessment results along with feedback based on sentiment analysis, including areas for improvement in stress management and team communication.

[0278] Specific examples

[0279] For example, if Employee A handles multiple tasks during work and simultaneously communicates with team members using an internal chat tool:

[0280] The terminal sequentially records detailed operation data while employee A is working and periodically transmits it to the server.

[0281] The terminal preprocesses the contents of the internal chat messages and sends them to the server.

[0282] The server analyzes the operation data and calculates employee A's productivity index.

[0283] The server analyzes the message data using natural language processing algorithms to evaluate cooperation and quality of communication.

[0284] The server uses an emotion engine to analyze employee A's emotional state from the message content and operation data, and generates an emotion index.

[0285] The server aggregates all the data and displays an overall rating score and sentiment-based feedback on a dashboard.

[0286] User Employee A accesses the dashboard to check his / her own evaluation and feedback and understand the areas for improvement that need to be made.

[0287] In this way, the system of the present invention combines emotion engines to achieve fair and multifaceted evaluation that takes into account the user's emotional state.

[0288] The processing flow will be explained below.

[0289] Step 1:

[0290] The device monitors user operations in real time while working and records each operation event (launching an application, accessing a file, browsing a web page, creating or editing a document, etc.).

[0291] Step 2:

[0292] The device collects the recorded operation data at regular intervals and compresses it to reduce the data volume. The compressed operation data is temporarily stored on the device.

[0293] Step 3:

[0294] The device encrypts the compressed operation data and sends it to the server after ensuring security. Transmission is performed during off-peak hours to minimize network load.

[0295] Step 4:

[0296] The device collects data from users' internal chat tools and emails, and preprocesses it, including metadata such as message content, sending time, and recipients. Preprocessing includes text cleaning and tokenization.

[0297] Step 5:

[0298] The terminal compresses and encrypts the preprocessed message data and transmits it to the server in the same manner as the operation data.

[0299] Step 6:

[0300] The server receives operation data and message data sent from the device in real time and stores them in a secure database. The stored data undergoes a backup process to ensure data consistency and integrity.

[0301] Step 7:

[0302] The server analyzes the recorded operation data and calculates productivity indicators for each user (e.g., number of tasks completed, work time, work efficiency). Statistical analysis of the data and machine learning algorithms are used for the analysis.

[0303] Step 8:

[0304] The server calculates the user's operational data and their impact on the progress and profits of the project to assess their contribution to each project, taking into account the number of tasks completed and the quality of deliverables related to a particular project.

[0305] Step 9:

[0306] The server analyzes the message data using natural language processing algorithms, including text cleansing, tokenization, and grammar analysis, to classify the sentiment of the message.

[0307] Step 10:

[0308] The server uses a sentiment engine to analyze the text extracted from the message data and calculate a positive, negative, or neutral sentiment score, as well as analyze long-term sentiment trends.

[0309] Step 11:

[0310] The server reflects the emotion score obtained by the emotion engine in the evaluation of the user's agreeableness, comparing the frequency of positive messages with the frequency of negative messages, and updates the user's agreeableness score.

[0311] Step 12:

[0312] The server then combines the data on productivity, creativity, business contribution, collaboration, and emotional indicators obtained above to generate an overall evaluation score for each user, calculated based on a weighted combination of each indicator.

[0313] Step 13:

[0314] The server generates graphs and charts to visually display the overall evaluation score, and displays them on the dashboard, allowing users to check their own evaluation results at a glance.

[0315] Step 14:

[0316] Users access a dashboard to view their assessment results, which includes personalized feedback along with their assessment scores, allowing users to recognize strengths and areas for improvement.

[0317] Step 15:

[0318] The server continuously collects and analyzes data and periodically updates the evaluation results, allowing users to be evaluated on their work performance in real time and provide appropriate feedback.

[0319] By combining this flow with an emotion engine, the system of the present invention achieves a multifaceted and fair evaluation that reflects the user's emotional state.

[0320] Example 2

[0321] 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."

[0322] In modern work environments, there is a demand for accurate evaluation of users' productivity, cooperativeness, and even their emotional state. However, conventional systems only collect general operation data and message data, making it difficult to perform detailed evaluations that take into account the user's emotional state. Furthermore, there are insufficient means to visualize the results of user evaluations in an intuitive manner. This results in a lack of effective feedback and prevents work improvements.

[0323] 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.

[0324] In this invention, the server includes means for recording user operation data during work, means for collecting user message data, means for analyzing the recorded operation data and the collected message data to evaluate the user's productivity, creativity, business contribution, and cooperativeness, means for recognizing the user's emotions and reflecting them in the evaluation results, and means for visualizing the evaluation results. This enables fair and multifaceted evaluation that takes the user's emotional state into consideration, and makes it possible to intuitively visualize the results and provide effective feedback.

[0325] "User operation data during work" refers to information about a series of operations that occur when a user performs work (launching and using applications, accessing files, viewing web pages, creating and editing documents, etc.).

[0326] "Message data" refers to text messages sent and received by users using internal chat tools or email, as well as related metadata such as the time of sending and recipient information.

[0327] "Productivity" refers to an index for evaluating the results a user has achieved in work within a certain period of time, the amount of tasks processed, and the efficiency of the time required for these tasks.

[0328] "Creativity" refers to an index used to evaluate users' ability to propose and implement new ideas, improvements, and original solutions.

[0329] "Business contribution" refers to an index used to evaluate the degree of contribution a user has made to a specific project or to the overall business.

[0330] "Collaboration" refers to an index used to evaluate a user's ability to smoothly communicate and cooperate with their team and other members.

[0331] "Means for recognizing emotions and reflecting them in the evaluation results" refers to algorithms and processes that recognize the user's emotional state (positive or negative emotions, etc.) from message data and operational data during work, and reflect that emotional information in the evaluation results.

[0332] "Means for visualizing evaluation results" refers to means for providing evaluation results such as user productivity, creativity, business contribution, cooperativeness, and emotional state in the form of visual displays such as graphs, charts, and dashboards.

[0333] "Natural language processing algorithm" refers to a set of processes and techniques that enable computer programs to understand, analyze, and process human natural language.

[0334] The system of the present invention evaluates users' productivity, creativity, business contribution, and cooperativeness by collecting and analyzing operation data and message data during user work. In addition, by combining it with an emotion engine that recognizes users' emotions, the accuracy of the evaluation and the quality of the feedback are improved.

[0335] The system uses the following hardware and software.

[0336] Hardware

[0337] Terminal: A device that collects user operation data and message data.

[0338] Server: A central control device that receives, stores, and analyzes data.

[0339] Emotion Engine: A specific device for recognizing a user's emotional state

[0340] software

[0341] Data collection program: Runs on the terminal and collects operation data and message data.

[0342] Encryption and compression programs: Encrypt and compress data

[0343] Natural Language Processing (NLP) algorithms: Analyze message data and extract agreeableness and emotional state

[0344] Data analysis program: Analyzes operational data to measure productivity, creativity, and business contribution

[0345] Visualization program: Visually displays evaluation results in graphs and charts

[0346] Data collection

[0347] The device monitors users' work activities in real time and records each operation event (e.g., launching an application, accessing a file, viewing a web page, creating or editing a document). The device also records the content, time of sending, and recipient of messages sent and received via internal chat tools and email. The recorded data is compressed, encrypted, and sent to a server at regular intervals.

[0348] Data storage and management

[0349] The server receives the operational and message data sent by the devices and stores it in a secure database that is regularly backed up and can be restored if necessary.

[0350] Data analysis

[0351] The server analyzes the recorded operation data and calculates productivity indicators for each user (number of tasks completed, work time, work efficiency). It also evaluates contribution to each project and measures the impact on the entire project. Message data is analyzed using a natural language processing algorithm to evaluate cooperation and emotional state. The results of this analysis are input into an emotion engine to identify the user's emotional state (e.g., positive, negative).

[0352] Evaluation and visualization

[0353] The server integrates the analysis results and generates an overall evaluation score based on the user's productivity, creativity, business contribution, collaborative ability, and emotional state. The evaluation results are displayed on a dashboard as graphs and charts to visualize them. Users access the dashboard and check the feedback provided along with the evaluation results. This feedback includes areas for improvement in stress management and team communication.

[0354] Specific examples

[0355] For example, if Employee A handles multiple tasks while simultaneously communicating with team members using an internal chat tool, the device will record detailed operational data of Employee A during work and periodically send it to the server. The content of the internal chat messages will also be preprocessed and sent to the server. The server will analyze this data and evaluate Employee A's productivity index, cooperativeness, and emotional state. Finally, the overall evaluation score and feedback will be displayed on a dashboard that Employee A can access and check.

[0356] For example, the following prompt sentence is fed into the generative AI model:

[0357] "Please generate a performance evaluation report for the last month. Specifically, please include feedback on work efficiency and productivity from operation data, collaboration from message data, and emotion indicators from the emotion engine."

[0358] This prompt is designed to generate a detailed and comprehensive performance evaluation report.

[0359] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0360] Step 1:

[0361] Operational Data Collection

[0362] The terminal monitors the user's work operations in real time and captures user operation events (launching applications, accessing files, viewing web pages, creating and editing documents, etc.) as input.

[0363] Specifically, the terminal generates a log file and records each operation with a timestamp.

[0364] As an output, the data of these operation events is temporarily stored.

[0365] Step 2:

[0366] Sending and storing operational data

[0367] The terminal collects the operation data at regular intervals and compresses and encrypts the operation event data temporarily stored as input.

[0368] Specifically, the terminal applies a data compression algorithm and then an encryption algorithm.

[0369] The compressed and encrypted data is output and sent to the server.

[0370] The server extracts the received data and stores it in a secure database.

[0371] Step 3:

[0372] Message Data Collection

[0373] The device collects message data from the user's internal chat tool and email, and takes as input the text message and its metadata (such as the time of sending and the recipient).

[0374] Specifically, the device preprocesses the message data (cleaning the text, tokenizing it) and converts it into a format that is easy to analyze.

[0375] As output, it generates preprocessed message data and sends it to the server.

[0376] Step 4:

[0377] Sending and storing message data

[0378] The terminal periodically transmits the pre-processed message data to the server.

[0379] The server extracts the received data and stores it in a secure database.

[0380] The output is the message data stored on the server.

[0381] Step 5:

[0382] Analysis of operational data

[0383] The server takes operational data from the operational database as input and applies data analysis algorithms.

[0384] Specific operations include calculating the number of tasks processed per unit time, average work time, and frequency of each operation.

[0385] As output, productivity indicators for each user (e.g., number of tasks completed, work time, work efficiency) are generated.

[0386] Step 6:

[0387] Parsing message data

[0388] The server takes message data from a message database as input and applies natural language processing algorithms.

[0389] Specifically, the system performs sentiment analysis on the text, extracts positive and negative expressions, and uses them to evaluate cooperation.

[0390] As output, it produces an agreement index and emotional state extracted from the message data.

[0391] Step 7:

[0392] Using the Emotion Engine

[0393] The server provides message data and operation data as input to the emotion engine to recognize the emotional state.

[0394] Specifically, the emotion engine distinguishes between positive and negative emotions and calculates emotional indicators such as stress level and cooperativeness.

[0395] As output, it generates the emotional state identification result and the emotional index.

[0396] Step 8:

[0397] Calculation and visualization of evaluation scores

[0398] The server integrates the productivity index, cooperativeness index, and emotional index to calculate an overall evaluation score.

[0399] Specifically, each indicator is weighted, an integrated calculation is performed, and the data is converted into a visually easy-to-understand format.

[0400] As output, an overall evaluation score and graphs and charts of the evaluation results are generated and displayed on a dashboard.

[0401] Step 9:

[0402] Providing feedback

[0403] Users access the dashboard to view their assessment results and feedback.

[0404] Specifically, the user views the evaluation results and receives specific advice on areas for improvement such as stress management and team communication.

[0405] As an output, information is provided for the user to determine self-improvement actions.

[0406] In this way, specific operations are performed at each processing step, and final evaluation and feedback are provided through data processing and calculations based on the input data.

[0407] (Application example 2)

[0408] 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."

[0409] Collaborative robots (cobots) are becoming increasingly common in modern factories, but there is a lack of accurate ways to monitor and evaluate their productivity and cooperation. Furthermore, there is no established method for utilizing generative AI models to optimize robot behavior. This makes efficient production management and appropriate feedback difficult.

[0410] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for recording operation data of a user during work; means for collecting user message data; means for analyzing the recorded operation data and collected message data and evaluating the user's productivity, creativity, business contribution, and cooperativeness; means for visualizing the evaluation results; means for collecting operation data and communication data of operating devices in a factory and analyzing the productivity and cooperativeness of a collaborative robot; and means for inputting the analysis results into a generative AI model and generating prompt sentences that optimize the operation of the collaborative robot. This makes it possible to accurately monitor, evaluate, and optimize the productivity and cooperativeness of a collaborative robot.

[0411] "User's operation data during work" is information about all operations generated when a user performs work.

[0412] "Message data" refers to information about the content, time of sending, and recipient of messages sent or received by users inside or outside the company.

[0413] "Productivity" is an index that quantifies the efficiency and effectiveness of a user's work.

[0414] "Creativity" is the ability of users to generate new ideas and solutions in their work.

[0415] "Business contribution" is an index that shows how much a user's work contributes to the goals and profits of the entire organization.

[0416] "Collaborative ability" is the ability to show how effectively a user can cooperate with other members.

[0417] "Evaluation results" are the results and data obtained by evaluating productivity, creativity, business contribution, and cooperation.

[0418] "Visualization" is the process of presenting evaluation results and data in visual formats such as graphs and charts.

[0419] "Operation data of operating equipment in the factory" is detailed information about the operation of equipment and robots used in the factory.

[0420] "Communication data" refers to information about all communications, such as voice commands and visual signals, that take place within the factory.

[0421] A "generative AI model" is an artificial intelligence model that analyzes the current situation based on collected data and generates instructions and prompts to achieve optimal behavior.

[0422] A "prompt sentence" is an instruction sentence created by a generative AI model based on the analysis results to optimize the behavior of a collaborative robot.

[0423] This invention is a system that collects operation data and message data from users during work, analyzes this data to evaluate their productivity, creativity, business contribution, and cooperativeness, and visualizes the evaluation results. It also collects operation data and communication data from operating devices in factories, analyzes the productivity and cooperativeness of collaborative robots (cobots), and generates prompts that achieve optimal operation based on a generative AI model.

[0424] Program processing explanation

[0425] The server uses a means for recording user operation data during work to monitor and record in real time operation events (e.g., application startup, file access, document creation / editing, etc.) in the user's work as a log. It also uses a means for collecting message data to acquire message data sent and received by users inside and outside the company, and preprocesses this (text cleaning, tokenization, etc.) in preparation for analysis.

[0426] The server encrypts operational and message data before transmitting and storing it in a secure database, ensuring data consistency and integrity, while also performing regular backups and restoring data as needed.

[0427] The data is analyzed using machine learning algorithms (e.g., Scikit-learn) and natural language processing algorithms (e.g., NLTK or spaCy), and productivity indicators (e.g., number of tasks completed, work time, and work efficiency) are calculated from the recorded operation data. Message data is also used to evaluate the user's cooperativeness, and an emotion engine is used to calculate emotion indicators. The obtained data is integrated to calculate an overall evaluation score, which is then displayed as graphs or charts using a visualization tool.

[0428] In addition, the system collects operational and communication data from cobots in factories, analyzes this data to evaluate the cobots' productivity and cooperation, and inputs the analysis results into a generative AI model to generate prompts and optimize the cobots' behavior.

[0429] Specific examples

[0430] For example, consider a situation where collaborative robot A receives instructions from a human worker via voice commands when performing the task of picking up a part and placing it in a designated location in a factory. At this time, the server collects all of robot A's operation logs and communication data and stores them in a database. Using machine learning algorithms and natural language processing algorithms, robot A's productivity and cooperativeness are analyzed, and based on the results, a generative AI model generates prompt sentences to optimize robot A's behavior.

[0431] An example of the prompt statement it generates is:

[0432] Cobot A reports the current task progress. Retrieve the latest number of completed tasks and working time from the operation log to calculate the productivity index. Furthermore, analyze the voice commands received from the latest message log to evaluate the cooperativeness index.

[0433] In this way, the system of the present invention is able to accurately monitor, evaluate, and optimize the productivity and cooperation of users and collaborative robots.

[0434] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0435] Step 1:

[0436] The terminal collects operational data of the user in real time while he or she is working. Specifically, it monitors operational events such as application launches, file accesses, and document creation and editing, and records each event in log format. The input is the user's operational events, and the output is the recorded operation log. This data is compressed and encrypted at regular intervals and sent to the server.

[0437] Step 2:

[0438] The device collects the user's message data. Specifically, it records the content, sending time, and recipient of messages sent and received via internal chat tools, email, etc. The collected data is preprocessed (text cleaning, tokenization, etc.) and periodically sent to the server. The input is the user's message data, and the output is the preprocessed message data.

[0439] Step 3:

[0440] The server stores the received operational and message data in a secure database. The database has a means of maintaining consistency and integrity, and is backed up regularly. The input is the encrypted operational and message data, and the output is the stored data.

[0441] Step 4:

[0442] The server analyzes the recorded operation data. Specifically, it uses a machine learning algorithm (e.g., Scikit-learn) to calculate productivity indicators (e.g., number of tasks processed, work time, and work efficiency). The input is the stored operation data, and the output is the calculated productivity indicators.

[0443] Step 5:

[0444] The server analyzes the message data using a natural language processing algorithm (e.g., NLTK or spaCy) to calculate agreeableness and sentiment indexes. It uses a sentiment engine to identify positive and negative sentiments and evaluate agreeableness and stress levels. The input is the preprocessed message data, and the output is agreeableness and sentiment indexes.

[0445] Step 6:

[0446] The server aggregates all data and generates an overall evaluation score for each user. This score is calculated based on productivity, creativity, business contribution, cooperativeness, and emotional indicators. The inputs are productivity indicators, cooperativeness data, and emotional data, and the output is the overall evaluation score.

[0447] Step 7:

[0448] The server displays the evaluation results using a visualization tool. Specifically, productivity, collaboration, emotional indicators, and overall evaluation scores are visually displayed in graph and chart format on a dashboard. The input is the overall evaluation score and related data, and the output is the visualized evaluation results.

[0449] Step 8:

[0450] The terminal collects operation and communication data of collaborative robots in a factory. Specifically, it records each robot operation event (e.g., picking up and placing parts, movement path, machine operation) as a log. It also collects instructions from human workers and communications with other robots. The input is the collaborative robot's operation events and communication data, and the output is the recorded operation and communication data.

[0451] Step 9:

[0452] The server analyzes the operation data and communication data of the collaborative robots. From the analyzed data, it calculates indicators to evaluate the robots' productivity and cooperativeness. The input is the collected operation data and communication data, and the output is the evaluation indicators.

[0453] Step 10:

[0454] The server inputs the analysis results using the generative AI model and generates prompt sentences to optimize the behavior of the collaborative robot. The inputs are the evaluation index and the generative AI model, and the output is the optimized prompt sentence.

[0455] Specific prompt examples:

[0456] Cobot A reports the current task progress. Retrieve the latest number of completed tasks and working time from the operation log to calculate the productivity index. Furthermore, analyze the voice commands received from the latest message log to evaluate the cooperativeness index.

[0457] In this way, by going through each processing step, a system is realized that accurately monitors and evaluates the productivity and cooperation of the user and the collaborative robot.

[0458] 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.

[0459] 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.

[0460] 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.

[0461] [Second embodiment]

[0462] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0463] 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.

[0464] 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).

[0465] 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.

[0466] 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.

[0467] 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).

[0468] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0469] 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.

[0470] 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.

[0471] 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.

[0472] 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.

[0473] 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."

[0474] The system of the present invention collects and analyzes operation data and message data of users during their work, and evaluates the users' productivity, creativity, business contribution, and cooperativeness from various angles. Detailed embodiments of the system are described below.

[0475] Explanation of program processing

[0476] In the system of the present invention, the following processing is performed.

[0477] Data collection

[0478] 1. Collecting Operational Data

[0479] The device monitors the user's work activities and records data in real time, such as applications running, files accessed, web pages browsed, and documents created or edited.

[0480] The terminal collects this operational data at regular intervals, compresses it, and sends it to the server in encrypted form.

[0481] 2. Message Data Collection

[0482] The device records the content, time of sending, and recipient of messages sent and received via the user's internal chat tool, email, etc.

[0483] The device preprocesses the collected message data (text cleaning, tokenization, etc.) and periodically sends it to the server.

[0484] Data storage and management

[0485] 3. Data storage

[0486] The server receives operation data and message data sent from the terminal in real time and stores them in a secure database.

[0487] The server performs regular backups to ensure data consistency and integrity, and restores data when necessary.

[0488] Data analysis

[0489] 4. Analysis of Operational Data

[0490] The server analyzes the recorded operation data and calculates productivity indicators for each user (e.g., number of tasks processed, work time, work efficiency).

[0491] The server evaluates the contribution of each project and calculates the impact on the project's profits and progress.

[0492] 5. Message Data Analysis

[0493] The server analyzes the message data using natural language processing algorithms and evaluates the level of cooperation, including analyzing the sentiment of the message content.

[0494] The server performs sentiment analysis to identify positive and negative communications and calculates an agreeableness score.

[0495] Evaluation and visualization

[0496] 6. Calculation of evaluation score

[0497] The server combines the above-mentioned productivity, creativity, business contribution, and cooperativeness indicators to generate an overall evaluation score for each user.

[0498] The server visualizes the evaluation results based on this score as graphs and charts and displays them on a dashboard.

[0499] 7. Providing Feedback

[0500] The user logs in to the dashboard and checks the evaluation results.

[0501] The server displays feedback to the user and provides feedback on areas for improvement and strengths based on the evaluation results.

[0502] Specific examples

[0503] For example, if employee A is working on multiple projects:

[0504] The device records in detail employee A's daily working hours, files handled, applications used, etc.

[0505] The device collects messages exchanged with other members through the company's internal chat tool, preprocesses them, and then sends them to the server.

[0506] The server analyzes this data and calculates employee A's productivity (e.g., number of tasks completed per day), business contribution (e.g., impact on project progress), and cooperation (e.g., percentage of positive messages).

[0507] Based on these analysis results, the server generates an overall evaluation score for employee A and displays it on the dashboard.

[0508] User Employee A accesses the dashboard to review his or her own evaluation and receive feedback on strengths and areas for improvement.

[0509] In this way, the system of the present invention eliminates emotional bias and realizes fair and multifaceted evaluation based on data.

[0510] The processing flow will be explained below.

[0511] Step 1:

[0512] The device monitors user operations in real time while working and records each operation event (launching an application, accessing a file, browsing a web page, creating or editing a document, etc.).

[0513] Step 2:

[0514] The device collects the recorded operation data at regular intervals and compresses it to reduce the data volume. The compressed operation data is temporarily stored in the device.

[0515] Step 3:

[0516] The device encrypts the compressed operation data and sends it to the server after ensuring security. Transmission is performed during off-peak hours to minimize network load.

[0517] Step 4:

[0518] The device also collects data from users' internal chat tools and emails, and preprocesses it, including metadata such as message content, sending time, and recipients. Preprocessing includes text cleaning and tokenization.

[0519] Step 5:

[0520] The terminal compresses and encrypts the preprocessed message data and transmits it to the server in the same manner as the operation data.

[0521] Step 6:

[0522] The server receives operation data and message data sent from the device in real time and stores them in a secure database. The stored data undergoes a backup process to ensure data consistency and integrity.

[0523] Step 7:

[0524] The server analyzes the saved operation data and calculates productivity indicators for each user, including the number of tasks completed, work time, and work efficiency.

[0525] Step 8:

[0526] The server evaluates the contribution of each project by calculating the user's operation data and the impact on the progress and profits of the project.

[0527] Step 9:

[0528] The server analyzes the message data using natural language processing algorithms, which perform sentiment analysis of the text, distinguish between positive and negative communication, and calculate an agreeableness score.

[0529] Step 10:

[0530] The server combines each user's productivity, creativity, business contribution, and cooperativeness indicators to generate an overall evaluation score.

[0531] Step 11:

[0532] The server visualizes the generated rating scores and displays them on a dashboard as graphs and charts, allowing users to check their own ratings.

[0533] Step 12:

[0534] Users access a dashboard to view their assessment results and feedback, which includes strengths and areas for improvement based on the assessment results.

[0535] This series of processing steps eliminates emotional bias and enables a multifaceted and fair evaluation.

[0536] Example 1

[0537] 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."

[0538] With conventional systems, it was easy for emotional bias to creep in when evaluating users' work efficiency and cooperation, making it difficult to make objective, data-based evaluations. Furthermore, there was also the issue of delays in evaluation results because operation data and message data were not collected and analyzed in real time. Furthermore, there was also the issue of a lack of specific feedback on areas for improvement and strengths when providing evaluation results to users.

[0539] 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.

[0540] In this invention, the server includes means for recording user operation data during work in real time and compressing and encrypting it at regular intervals before transmitting it, means for preprocessing message data and periodically transmitting it, means for generating an evaluation score for each user and displaying it on a dashboard, and means for providing the user with feedback on areas for improvement and strengths. This enables fair and multifaceted evaluation based on data and makes it possible to provide the user with specific areas for improvement and strengths in real time.

[0541] "User operation data" refers to data such as the applications a user uses to perform their work, the files they access, the web pages they browse, and the documents they create and edit.

[0542] "Message data" refers to data related to the content, time of sending, and recipient of messages sent and received by users via internal chat tools, email, etc.

[0543] "Analysis" refers to the processing and analysis of recorded or collected data to extract and evaluate specific indicators or patterns.

[0544] "Productivity" refers to indicators such as the number of tasks, workload, and work efficiency completed by a user within a certain period of time.

[0545] "Creativity" refers to the ability of users to propose new ideas and come up with original solutions while performing their work.

[0546] "Business contribution" refers to an indicator that evaluates the impact that the projects and tasks a user is responsible for have on the profits and progress of the entire organization.

[0547] "Collaboration" is an indicator that evaluates how effectively a user can cooperate with other members in internal communications and build positive relationships.

[0548] "Means for visualizing evaluation results" refers to means for displaying the user evaluation results obtained by analysis in a visual format such as a graph or chart.

[0549] "Means for recording data in real time" refers to means for instantly recording information each time a user performs an operation.

[0550] "Means for compressing and encrypting and transmitting" refers to means for compressing and encrypting collected data for the purpose of reducing its size and protecting its security, and transmitting it to a server via a network.

[0551] "Means for preprocessing and sending" refers to means for periodically sending collected message data to a server after preprocessing it, such as cleaning and tokenizing it, into a format suitable for analysis.

[0552] The "means for generating an evaluation score" refers to a means for integrating various indicators such as productivity, creativity, business contribution, and cooperativeness to calculate an overall evaluation score for each user.

[0553] "Means for displaying on a dashboard" refers to means for displaying the evaluation score and feedback information on a dashboard that can be accessed by the user.

[0554] "Means for providing feedback on areas for improvement and strengths" refers to means for analyzing specific areas for improvement and strengths based on the user's evaluation results and providing them to the user.

[0555] The system of the present invention collects and analyzes operation data and message data of users during their work, and evaluates the users' productivity, creativity, business contribution, and cooperativeness from various angles. Detailed embodiments of the system are described below.

[0556] Data collection

[0557] Operational Data Collection

[0558] The device monitors user activity 24 / 7, recording in real time which applications are running, which files are accessed, which web pages are browsed, and which documents are created or edited.

[0559] The terminal compresses the collected operation data every hour and sends it to the server in encrypted form, using encryption technologies such as SSL / TLS to protect the data.

[0560] Message Data Collection

[0561] The device monitors the user's internal chat tools and emails, recording the content of messages sent and received, the time of sending, and the recipients.

[0562] The device preprocesses message data (such as text cleaning and tokenization) once a day before sending it to the server. This preprocessing is done using Python's NLTK and SpaCy libraries.

[0563] Data storage and management

[0564] Data storage

[0565] The server stores the received operation data and message data in a high-speed database (e.g., PostgreSQL or MongoDB) in real time, and performs transaction management to maintain data consistency.

[0566] The server performs regular database backups to prevent data loss, and the backup data is also stored in cloud storage such as AWS S3.

[0567] Data analysis

[0568] Analysis of operational data

[0569] The server uses machine learning algorithms to analyze the operation data and calculate productivity metrics for each user, using libraries such as Scikit-learn and TensorFlow.

[0570] The server then evaluates the user's contribution to each project and calculates the impact on the project's profits and progress, using multivariate analysis and clustering techniques.

[0571] Parsing message data

[0572] The server analyzes message data using natural language processing (NLP) algorithms, including sentiment analysis, leveraging models such as BERT and GPT-3.

[0573] The server distinguishes between positive and negative communication from the message content and calculates an agreeableness score.

[0574] Evaluation and visualization

[0575] Calculation of evaluation score

[0576] The server aggregates the productivity, creativity, business contribution, and collaboration metrics to generate an overall evaluation score for each user, which is then displayed as graphs and charts using visualization libraries such as D3.js and Chart.js.

[0577] The server updates the evaluation results in real time and displays them on a dashboard, which uses visualization tools such as Kibana and Grafana.

[0578] Providing feedback

[0579] Providing feedback

[0580] Users can log in to their account and check the results of their evaluations on the dashboard, where they can see not only the overall evaluation score but also detailed feedback on each indicator.

[0581] The server provides users with feedback on areas for improvement and strengths based on the evaluation results, and proposes specific action plans, including goal setting and progress management tools.

[0582] Specific examples

[0583] For example, let's say employee A is working on multiple projects.

[0584] The terminal records employee A's daily operation data (such as applications used and files accessed) in real time and sends it to the server every hour.

[0585] The terminal collects messages sent and received by employee A via internal chat tools and email, preprocesses them once a day, and then sends them to the server.

[0586] The server analyzes employee A's productivity (e.g., number of tasks completed per day) based on the operation data and evaluates his / her contribution to each project.

[0587] The server uses NLP algorithms to perform sentiment analysis of the message data and calculates an agreeableness score.

[0588] Based on these analysis results, the server generates an overall evaluation score for employee A and displays it on the dashboard.

[0589] User Employee A accesses the dashboard to review his or her own evaluation and receive feedback on strengths and areas for improvement.

[0590] Prompt Sentence Examples

[0591] Below are examples of prompt sentences to be input to the generative AI model based on specific examples.

[0592] Explain how to analyze Employee A's number of tasks completed per day, productivity score, and contribution per project and display them on a dashboard.

[0593] Please tell us more about the algorithm that analyzes the sentiment of chat messages and calculates the agreeableness score.

[0594] Explain how you can use interaction and message data to assess user creativity.

[0595] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0596] Step 1: Collect data

[0597] Operational Data Collection

[0598] The terminal records operational data in real time, such as the launch history of applications used by the user when performing work, files accessed, web pages browsed, and documents created and edited.

[0599] The input of the terminal is the user's operation events (e.g., clicks, keystrokes), and the output is the log data in which these events are recorded.

[0600] The device periodically compresses and encrypts the operational data before sending it to the server, using encryption technologies such as SSL / TLS to protect the data.

[0601] Message Data Collection

[0602] The device records the content, time of sending, and recipient of messages sent and received via the user's internal chat tool or email.

[0603] The input to the terminal is events such as sending and receiving emails from an internal chat tool, and the output is log data in which these message data are recorded.

[0604] The device preprocesses the collected message data (such as text cleaning and tokenization) and periodically sends it to the server. Preprocessing is performed using Python's NLTK and SpaCy libraries.

[0605] Step 2: Store and manage your data

[0606] Data storage

[0607] The server receives the operation data and message data sent from the terminal and stores them in a database (e.g., PostgreSQL or MongoDB) in real time.

[0608] The input of the server is encrypted operational and message data, and the output is data stored in a database.

[0609] The server performs transaction management to enhance data consistency and integrity. In addition, it periodically backs up the database and stores it in cloud storage (e.g., AWS S3).

[0610] Step 3: Data analysis

[0611] Analysis of operational data

[0612] The server uses machine learning algorithms to analyze the operation data and calculate productivity indicators for each user (e.g., number of tasks completed, work time, and work efficiency).

[0613] The input of the server is the operational data stored in the database, and the output is the analysis results including productivity indicators.

[0614] The server uses libraries such as Scikit-learn and TensorFlow to extract and analyze patterns and trends in the operational data.

[0615] Parsing message data

[0616] The server analyzes the message data using natural language processing (NLP) algorithms and performs sentiment analysis.

[0617] The server's input is message data stored in a database, and its output is analysis results such as cooperativeness scores.

[0618] The server utilizes generative AI models such as BERT and GPT-3 to perform sentiment analysis of message content and identify positive and negative communication.

[0619] Step 4: Evaluate and visualize

[0620] Calculation of evaluation score

[0621] The server integrates the productivity, creativity, business contribution, and cooperativeness indicators to generate an overall evaluation score for each user.

[0622] The input to the server is the analysis results of the operation data and message data, and the output is a comprehensive evaluation score.

[0623] The server uses visualization libraries such as D3.js and Chart.js to display the evaluation results as graphs and charts.

[0624] Step 5: Provide feedback

[0625] Providing feedback

[0626] Users can log in to their dashboard with their account and check the evaluation results.

[0627] The input of the dashboard is the evaluation scores and feedback information sent from the server, and the output is the visualization data displayed to the user.

[0628] The server provides users with feedback on areas for improvement and strengths based on the evaluation results, and proposes specific action plans, including goal setting and progress management tools.

[0629] (Application example 1)

[0630] 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."

[0631] In recent years, factories have been required to collect and analyze employee operation data and message data in order to improve work efficiency and productivity. However, to evaluate employee activities from multiple angles, it is necessary to collect data in real time and analyze it with high accuracy. In conventional systems, the collection and analysis of operation data and message data are separated, and evaluation criteria are limited, making it difficult to evaluate overall productivity and cooperativeness. The present invention aims to solve these problems and provide a system that comprehensively and fairly evaluates the productivity, cooperativeness, creativity, and business contribution of factory workers.

[0632] 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.

[0633] In this invention, the server includes a means for analyzing the recorded operation data and collected message data to evaluate the user's productivity, creativity, business contribution, and cooperativeness, a means for visualizing the evaluation results, and a means for supporting the creation of prompt sentences to be input to the generative AI model, thereby enabling the evaluation of work efficiency and cooperativeness in factories.

[0634] "Operational data" refers to the series of work procedures and operations performed by a user during work, including, specifically, running applications, accessed files, viewed web pages, and created / edited documents.

[0635] "Message data" is text data that includes information such as the content, transmission time, and recipient of messages sent and received by users via in-house chat tools, e-mail, etc.

[0636] "Productivity" is an index that indicates the quantity and quality of tasks and deliverables that a user has completed within a certain period of time, and is used to evaluate the user's work efficiency and ability to perform work.

[0637] "Creativity" is an index that evaluates a user's ability to come up with new ideas and projects and to apply them to actual work.

[0638] "Business contribution" is an index that evaluates how much a user's business activities have affected the profits of the entire organization and the progress of a project.

[0639] "Cooperativeness" is an index that evaluates how smoothly a user communicates with other members and how much they contribute to achieving the team's goals.

[0640] "Visualization" refers to displaying the evaluation results in a visual format such as a graph or chart, allowing users to intuitively understand them.

[0641] "Real-time" refers to data collection or processing occurring immediately without delay, meaning that user actions and operations are immediately reflected in the system.

[0642] "Generative AI models" refer to algorithms or models that use artificial intelligence technology to analyze user behavioral data and provide evaluations and feedback.

[0643] A "prompt sentence" is a text sentence that contains input data for a generative AI model, and contains information that serves as instructions for the AI ​​to perform appropriate analysis and evaluation.

[0644] The system of the present invention collects and analyzes operation data and message data of workers during their work in a factory, and evaluates their productivity and cooperation. Specific embodiments will be described below.

[0645] Data collection methods

[0646] First, the device (in this case, smart glasses) collects the worker's operation data. This data includes eye movements during work, setup procedures, details of repair work, and the status of the work environment. The smart glasses use built-in cameras and sensors to monitor and record this data in real time, and then periodically send it to a server in a consolidated form.

[0647] Message data is collected by using the voice recognition function of the smart glasses to recognize verbal instructions and reports given by workers and record them as text data. This text data is then periodically sent to a server after undergoing preprocessing (such as text cleaning and tokenization).

[0648] Data Storage and Management

[0649] The server then receives the operation and message data sent from the device in real time and stores it in a secure database. To ensure data consistency and integrity, the server performs regular backups and restores the data when necessary.

[0650] Data Analysis Methods

[0651] The server analyzes the recorded operation data and calculates productivity indicators for each user (e.g., number of tasks completed, working time, work efficiency). Furthermore, it evaluates the contribution of each project and calculates the impact on the project's profits and progress.

[0652] Message data is analyzed using natural language processing algorithms, which evaluates cooperation by analyzing the sentiment of the message content. Sentiment analysis distinguishes between positive and negative communication and calculates a cooperation score.

[0653] Evaluation and visualization

[0654] The server combines the above indicators of productivity, creativity, business contribution, and cooperativeness to generate an overall evaluation score for each user. Based on this score, the evaluation results are visualized as graphs and charts and displayed on a dashboard. Users can log in to the dashboard to check their evaluation results and receive feedback based on them.

[0655] Specific examples

[0656] For example, if a factory worker is assembling a product:

[0657] The smart glasses record workers' eye movements and work procedures in detail.

[0658] Verbal instructions and reports given by workers are collected using a voice recognition function and converted into text data.

[0659] The server receives and analyzes this data in real time and evaluates it based on work efficiency and cooperation.

[0660] The evaluation results and feedback are displayed in real time on the smart glasses display.

[0661] Examples of prompt statements

[0662] Enter the following prompt for the generative AI model:

[0663] Operation data: A worker is assembling product A. Part number 123 is being assembled, and eye movement is normal and there are no problems with the work procedure.

[0664] Message data: Assembly complete.

[0665] The above is an embodiment of the present invention, which makes it possible to comprehensively evaluate work efficiency and cooperation in a factory and provide feedback for improvement.

[0666] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0667] Step 1:

[0668] The terminal collects the worker's operation data. The input is real-time data such as eye movements and work procedures collected by the smart glasses using cameras and sensors. This data is temporarily stored on the terminal. The output is compressed and encrypted operation data.

[0669] Step 2:

[0670] The terminal collects message data from workers. The input is verbal instructions and reports from workers obtained using a voice recognition function. The voice data is converted into text data, which is preprocessed (text cleaning and tokenization) and temporarily stored. The output is the preprocessed text data.

[0671] Step 3:

[0672] The terminal periodically collects operation data and message data and sends them to the server. The input is the data collected and preprocessed in steps 1 and 2. The data is sent to the server in real time. The output is the data sent to the server in real time.

[0673] Step 4:

[0674] The server stores the data it receives in a database. The input is the operation data and message data sent from the terminal. This data is securely stored in the database and is backed up regularly to ensure consistency and completeness. The output is the data securely stored in the database.

[0675] Step 5:

[0676] The server analyzes the operation data. The input is the saved operation data, and by analyzing this data, it calculates productivity indicators for each user (e.g., number of tasks completed, work time, work efficiency, etc.). The output is the productivity indicators for each user.

[0677] Step 6:

[0678] The server analyzes the message data using a natural language processing algorithm. The input is the stored message data. This data is used to analyze the message content and sentiment, and calculate an agreeableness score. The output is an agreeableness score.

[0679] Step 7:

[0680] The server combines the productivity index and cooperativeness score to generate an overall evaluation score for each user. The inputs are the productivity index and cooperativeness score obtained in steps 5 and 6. These are combined to calculate the overall evaluation score. The output is the overall evaluation score.

[0681] Step 8:

[0682] The server visualizes the overall evaluation score and displays it on a dashboard. The input is the overall evaluation score calculated in step 7. This is visually represented as a graph or chart and displayed on the dashboard so that the user can check it. The output is a dashboard showing the evaluation results.

[0683] Step 9:

[0684] The server assists in creating prompt sentences to be input to the generated AI model. The input is operation data and message data. Based on this, a prompt sentence is generated and input to the AI ​​model. As a specific example, the following prompt sentence is generated: "Operation data: Worker is assembling product A. Part number 123 is assembled, eye movement is normal, no problems with the work procedure. Message data: Assembly completed." The output is the generated prompt sentence.

[0685] 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.

[0686] The system of the present invention evaluates users' productivity, creativity, business contribution, and cooperativeness by collecting and analyzing operation data and message data during user work. Furthermore, by combining it with an emotion engine that recognizes users' emotions, the accuracy of the evaluation and the quality of the feedback are improved.

[0687] Explanation of program processing

[0688] In the system of the present invention, the following processing is performed.

[0689] Data collection

[0690] 1. Collecting Operational Data

[0691] The device monitors the user's work activities in real time and records each operation event (launching an application, accessing a file, browsing a web page, creating or editing a document, etc.).

[0692] The terminal collects this operational data at regular intervals, compresses it, and sends it to the server in encrypted form.

[0693] 2. Message Data Collection

[0694] The device records the content, time of sending, and recipient of messages sent and received via the user's internal chat tool, email, etc.

[0695] The device preprocesses the collected message data (text cleaning, tokenization, etc.) and periodically sends it to the server.

[0696] Data storage and management

[0697] 3. Data storage

[0698] The server receives the operation data and message data sent from the terminal in real time and stores them in a secure database.

[0699] The server performs regular backups to ensure data consistency and integrity, and restores data when necessary.

[0700] Data analysis

[0701] 4. Analysis of Operational Data

[0702] The server analyzes the recorded operation data and calculates productivity indicators for each user (e.g., number of tasks processed, work time, work efficiency).

[0703] The server evaluates the contribution of each project and calculates the impact on the project's profits and progress.

[0704] 5. Message Data Analysis

[0705] The server analyzes the message data using natural language processing algorithms, including analyzing the sentiment of the text, to extract data to assess the user's agreeableness.

[0706] 6. Use of Emotion Engine

[0707] The server uses an emotion engine to recognize the user's emotions from the user's message data and operation data during work.

[0708] The emotion engine identifies positive and negative emotions and calculates emotional indicators such as agreeableness and stress level.

[0709] Evaluation and visualization

[0710] 7. Calculation of evaluation score

[0711] The server integrates the data on productivity, creativity, business contribution, cooperativeness, and emotional indicators mentioned above to generate an overall evaluation score for each user.

[0712] The server visualizes the evaluation results based on this score as graphs and charts and displays them on a dashboard.

[0713] 8. Providing Feedback

[0714] Users access a dashboard to view their evaluation results along with feedback based on sentiment analysis, including areas for improvement in stress management and team communication.

[0715] Specific examples

[0716] For example, if Employee A handles multiple tasks during work and simultaneously communicates with team members using an internal chat tool:

[0717] The terminal sequentially records detailed operation data while employee A is working and periodically transmits it to the server.

[0718] The terminal preprocesses the contents of the internal chat messages and sends them to the server.

[0719] The server analyzes the operation data and calculates employee A's productivity index.

[0720] The server analyzes the message data using natural language processing algorithms to evaluate cooperation and quality of communication.

[0721] The server uses an emotion engine to analyze employee A's emotional state from the message content and operation data, and generates an emotion index.

[0722] The server aggregates all the data and displays an overall rating score and sentiment-based feedback on a dashboard.

[0723] User Employee A accesses the dashboard to check his / her own evaluation and feedback and understand the areas for improvement that need to be made.

[0724] In this way, the system of the present invention combines emotion engines to achieve a fair and multifaceted evaluation that takes into account the user's emotional state.

[0725] The processing flow will be explained below.

[0726] Step 1:

[0727] The device monitors user operations in real time while working and records each operation event (launching an application, accessing a file, browsing a web page, creating or editing a document, etc.).

[0728] Step 2:

[0729] The device collects the recorded operation data at regular intervals and compresses it to reduce the data volume. The compressed operation data is temporarily stored on the device.

[0730] Step 3:

[0731] The device encrypts the compressed operation data and sends it to the server after ensuring security. Transmission is performed during off-peak hours to minimize network load.

[0732] Step 4:

[0733] The device collects data from users' internal chat tools and emails, and preprocesses it, including metadata such as message content, sending time, and recipients. Preprocessing includes text cleaning and tokenization.

[0734] Step 5:

[0735] The terminal compresses and encrypts the preprocessed message data and transmits it to the server in the same manner as the operation data.

[0736] Step 6:

[0737] The server receives operation data and message data sent from the device in real time and stores them in a secure database. The stored data undergoes a backup process to ensure data consistency and integrity.

[0738] Step 7:

[0739] The server analyzes the recorded operation data and calculates productivity indicators for each user (e.g., number of tasks completed, work time, work efficiency). Statistical analysis of the data and machine learning algorithms are used for the analysis.

[0740] Step 8:

[0741] The server calculates the user's operational data and their impact on the progress and profits of the project to assess their contribution to each project, taking into account the number of tasks completed and the quality of deliverables related to a particular project.

[0742] Step 9:

[0743] The server analyzes the message data using natural language processing algorithms, including text cleansing, tokenization, and grammar analysis, to classify the sentiment of the message.

[0744] Step 10:

[0745] The server uses a sentiment engine to analyze the text extracted from the message data and calculate a positive, negative, or neutral sentiment score, as well as analyze long-term sentiment trends.

[0746] Step 11:

[0747] The server reflects the emotion score obtained by the emotion engine in the evaluation of the user's agreeableness, comparing the frequency of positive messages with the frequency of negative messages, and updates the user's agreeableness score.

[0748] Step 12:

[0749] The server then combines the data on productivity, creativity, business contribution, collaboration, and emotional indicators obtained above to generate an overall evaluation score for each user, calculated based on a weighted combination of each indicator.

[0750] Step 13:

[0751] The server generates graphs and charts to visually display the overall evaluation score, and displays them on the dashboard, allowing users to check their own evaluation results at a glance.

[0752] Step 14:

[0753] Users access a dashboard to view their assessment results, which includes personalized feedback along with their assessment scores, allowing users to recognize strengths and areas for improvement.

[0754] Step 15:

[0755] The server continuously collects and analyzes data and periodically updates the evaluation results, allowing users to be evaluated on their work performance in real time and provide appropriate feedback.

[0756] By combining this flow with an emotion engine, the system of the present invention achieves a multifaceted and fair evaluation that reflects the user's emotional state.

[0757] Example 2

[0758] 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."

[0759] In modern work environments, there is a demand for accurate evaluation of users' productivity, cooperativeness, and even their emotional state. However, conventional systems only collect general operation data and message data, making it difficult to perform detailed evaluations that take into account the user's emotional state. Furthermore, there are insufficient means to visualize the results of user evaluations in an intuitive manner. This results in a lack of effective feedback and prevents work improvements.

[0760] 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.

[0761] In this invention, the server includes a means for recording user operation data during work, a means for collecting user message data, a means for analyzing the recorded operation data and the collected message data to evaluate the user's productivity, creativity, business contribution, and cooperativeness, a means for recognizing the user's emotions and reflecting them in the evaluation results, and a means for visualizing the evaluation results. This enables a fair and multifaceted evaluation that takes the user's emotional state into consideration, and makes it possible to visualize the results in an intuitive manner and provide effective feedback.

[0762] "User operation data during work" refers to information about a series of operations that occur when a user performs work (launching and using applications, accessing files, viewing web pages, creating and editing documents, etc.).

[0763] "Message data" refers to text messages sent and received by users using internal chat tools or email, as well as related metadata such as the time of sending and recipient information.

[0764] "Productivity" refers to an index for evaluating the results a user has achieved in work within a certain period of time, the amount of tasks processed, and the efficiency of the time required for these tasks.

[0765] "Creativity" refers to an index used to evaluate users' ability to propose and implement new ideas, improvements, and original solutions.

[0766] "Business contribution" refers to an index used to evaluate the degree of contribution a user has made to a specific project or to the overall business.

[0767] "Collaboration" refers to an index used to evaluate a user's ability to smoothly communicate and cooperate with their team and other members.

[0768] "Means for recognizing emotions and reflecting them in the evaluation results" refers to algorithms and processes that recognize the user's emotional state (positive or negative emotions, etc.) from message data and operational data during work, and reflect that emotional information in the evaluation results.

[0769] "Means for visualizing evaluation results" refers to means for providing evaluation results such as user productivity, creativity, business contribution, cooperativeness, and emotional state in the form of visual displays such as graphs, charts, and dashboards.

[0770] "Natural language processing algorithm" refers to a set of processes and techniques that enable computer programs to understand, analyze, and process human natural language.

[0771] The system of the present invention evaluates users' productivity, creativity, business contribution, and cooperativeness by collecting and analyzing operation data and message data during user work. In addition, by combining it with an emotion engine that recognizes users' emotions, the accuracy of the evaluation and the quality of the feedback are improved.

[0772] The system uses the following hardware and software.

[0773] Hardware

[0774] Terminal: A device that collects user operation data and message data.

[0775] Server: A central control device that receives, stores, and analyzes data.

[0776] Emotion Engine: A specific device for recognizing a user's emotional state

[0777] software

[0778] Data collection program: Runs on the terminal and collects operation data and message data.

[0779] Encryption and compression programs: Encrypt and compress data

[0780] Natural Language Processing (NLP) algorithms: Analyze message data and extract agreeableness and emotional state

[0781] Data analysis program: Analyzes operational data to measure productivity, creativity, and business contribution

[0782] Visualization program: Visually displays evaluation results in graphs and charts

[0783] Data collection

[0784] The device monitors users' work activities in real time and records each operation event (e.g., launching an application, accessing a file, viewing a web page, creating or editing a document). The device also records the content, time of sending, and recipient of messages sent and received via internal chat tools and email. The recorded data is compressed, encrypted, and sent to a server at regular intervals.

[0785] Data storage and management

[0786] The server receives the operational and message data sent by the devices and stores it in a secure database that is regularly backed up and can be restored if necessary.

[0787] Data analysis

[0788] The server analyzes the recorded operation data and calculates productivity indicators for each user (number of tasks completed, work time, work efficiency). It also evaluates contribution to each project and measures the impact on the entire project. Message data is analyzed using a natural language processing algorithm to evaluate cooperation and emotional state. The results of this analysis are input into an emotion engine to identify the user's emotional state (e.g., positive, negative).

[0789] Evaluation and visualization

[0790] The server integrates the analysis results and generates an overall evaluation score based on the user's productivity, creativity, business contribution, collaborative ability, and emotional state. The evaluation results are displayed on a dashboard as graphs and charts to visualize them. Users access the dashboard and check the feedback provided along with the evaluation results. This feedback includes areas for improvement in stress management and team communication.

[0791] Specific examples

[0792] For example, if Employee A handles multiple tasks while simultaneously communicating with team members using an internal chat tool, the device will record detailed operational data of Employee A during work and periodically send it to the server. The content of the internal chat messages will also be preprocessed and sent to the server. The server will analyze this data and evaluate Employee A's productivity index, cooperativeness, and emotional state. Finally, the overall evaluation score and feedback will be displayed on a dashboard that Employee A can access and check.

[0793] For example, the following prompt sentence is fed into the generative AI model:

[0794] "Please generate a performance evaluation report for the last month. Specifically, please include feedback on work efficiency and productivity from operation data, collaboration from message data, and emotion indicators from the emotion engine."

[0795] This prompt is designed to generate a detailed and comprehensive performance evaluation report.

[0796] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0797] Step 1:

[0798] Operational Data Collection

[0799] The device monitors the user's work operations in real time and captures user operation events (launching applications, accessing files, viewing web pages, creating and editing documents, etc.) as input.

[0800] Specifically, the terminal generates a log file and records each operation with a timestamp.

[0801] As an output, the data of these operation events is temporarily stored.

[0802] Step 2:

[0803] Sending and storing operational data

[0804] The terminal collects the operation data at regular intervals and compresses and encrypts the operation event data temporarily stored as input.

[0805] Specifically, the terminal applies a data compression algorithm and then an encryption algorithm.

[0806] The compressed and encrypted data is output and sent to the server.

[0807] The server extracts the received data and stores it in a secure database.

[0808] Step 3:

[0809] Message Data Collection

[0810] The device collects message data from the user's internal chat tool and email, and takes as input the text message and its metadata (such as the time of sending and the recipient).

[0811] Specifically, the device preprocesses the message data (cleaning the text, tokenizing it) and converts it into a format that is easy to analyze.

[0812] As output, it generates preprocessed message data and sends it to the server.

[0813] Step 4:

[0814] Sending and storing message data

[0815] The terminal periodically transmits the pre-processed message data to the server.

[0816] The server extracts the received data and stores it in a secure database.

[0817] The output is the message data stored on the server.

[0818] Step 5:

[0819] Analysis of operational data

[0820] The server takes operational data from the operational database as input and applies data analysis algorithms.

[0821] Specific operations include calculating the number of tasks processed per unit time, average work time, and frequency of each operation.

[0822] As output, productivity indicators for each user (e.g., number of tasks completed, work time, work efficiency) are generated.

[0823] Step 6:

[0824] Parsing message data

[0825] The server takes message data from a message database as input and applies natural language processing algorithms.

[0826] Specifically, the system performs sentiment analysis on the text, extracts positive and negative expressions, and uses them to evaluate cooperation.

[0827] As output, it produces an agreement index and emotional state extracted from the message data.

[0828] Step 7:

[0829] Using the Emotion Engine

[0830] The server provides message data and operation data as input to the emotion engine to recognize the emotional state.

[0831] Specifically, the emotion engine distinguishes between positive and negative emotions and calculates emotional indicators such as stress level and cooperativeness.

[0832] As output, it generates the emotional state identification result and the emotional index.

[0833] Step 8:

[0834] Calculation and visualization of evaluation scores

[0835] The server integrates the productivity index, cooperativeness index, and emotional index to calculate an overall evaluation score.

[0836] Specifically, each indicator is weighted, an integrated calculation is performed, and the data is converted into a visually easy-to-understand format.

[0837] As output, an overall evaluation score and graphs and charts of the evaluation results are generated and displayed on a dashboard.

[0838] Step 9:

[0839] Providing feedback

[0840] Users access the dashboard to view their assessment results and feedback.

[0841] Specifically, the user views the evaluation results and receives specific advice on areas for improvement such as stress management and team communication.

[0842] As an output, information is provided for the user to determine self-improvement actions.

[0843] In this way, specific operations are performed at each processing step, and final evaluation and feedback are provided through data processing and calculations based on the input data.

[0844] (Application example 2)

[0845] 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."

[0846] Collaborative robots (cobots) are becoming increasingly common in modern factories, but there is a lack of accurate ways to monitor and evaluate their productivity and cooperation. Furthermore, there is no established method for utilizing generative AI models to optimize robot behavior. This makes efficient production management and appropriate feedback difficult.

[0847] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for recording operation data of a user during work; means for collecting user message data; means for analyzing the recorded operation data and collected message data and evaluating the user's productivity, creativity, business contribution, and cooperativeness; means for visualizing the evaluation results; means for collecting operation data and communication data of operating devices in a factory and analyzing the productivity and cooperativeness of a collaborative robot; and means for inputting the analysis results into a generative AI model and generating prompt sentences that optimize the operation of the collaborative robot. This makes it possible to accurately monitor, evaluate, and optimize the productivity and cooperativeness of a collaborative robot.

[0848] "User's operation data during work" is information about all operations generated when a user performs work.

[0849] "Message data" refers to information about the content, time of sending, and recipient of messages sent or received by users inside or outside the company.

[0850] "Productivity" is an index that quantifies the efficiency and effectiveness of a user's work.

[0851] "Creativity" is the ability of users to generate new ideas and solutions in their work.

[0852] "Business contribution" is an index that shows how much a user's work contributes to the goals and profits of the entire organization.

[0853] "Collaborative ability" is the ability to show how effectively a user can cooperate with other members.

[0854] "Evaluation results" are the results and data obtained by evaluating productivity, creativity, business contribution, and cooperation.

[0855] "Visualization" is the process of presenting evaluation results and data in visual formats such as graphs and charts.

[0856] "Operation data of operating equipment in the factory" is detailed information about the operation of equipment and robots used in the factory.

[0857] "Communication data" refers to information about all communications, such as voice commands and visual signals, that take place within the factory.

[0858] A "generative AI model" is an artificial intelligence model that analyzes the current situation based on collected data and generates instructions and prompts to achieve optimal behavior.

[0859] A "prompt sentence" is an instruction sentence created by a generative AI model based on the analysis results to optimize the behavior of a collaborative robot.

[0860] This invention is a system that collects operation data and message data from users during work, analyzes this data to evaluate their productivity, creativity, business contribution, and cooperativeness, and visualizes the evaluation results. It also collects operation data and communication data from operating devices in factories, analyzes the productivity and cooperativeness of collaborative robots (cobots), and generates prompts that achieve optimal operation based on a generative AI model.

[0861] Program processing explanation

[0862] The server uses a means for recording user operation data during work to monitor and record in real time operation events (e.g., application startup, file access, document creation / editing, etc.) in the user's work as a log. It also uses a means for collecting message data to acquire message data sent and received by users inside and outside the company, and preprocesses this (text cleaning, tokenization, etc.) in preparation for analysis.

[0863] The server encrypts operational and message data before transmitting and storing it in a secure database, ensuring data consistency and integrity, while also performing regular backups and restoring data as needed.

[0864] The data is analyzed using machine learning algorithms (e.g., Scikit-learn) and natural language processing algorithms (e.g., NLTK or spaCy), and productivity indicators (e.g., number of tasks completed, work time, and work efficiency) are calculated from the recorded operation data. Message data is also used to evaluate the user's cooperativeness, and an emotion engine is used to calculate emotion indicators. The obtained data is integrated to calculate an overall evaluation score, which is then displayed as graphs or charts using a visualization tool.

[0865] In addition, the system collects operational and communication data from cobots in factories, analyzes this data to evaluate the cobots' productivity and cooperation, and inputs the analysis results into a generative AI model to generate prompts and optimize the cobots' behavior.

[0866] Specific examples

[0867] For example, consider a situation where collaborative robot A receives instructions from a human worker via voice commands when performing the task of picking up a part and placing it in a designated location in a factory. At this time, the server collects all of robot A's operation logs and communication data and stores them in a database. Using machine learning algorithms and natural language processing algorithms, robot A's productivity and cooperativeness are analyzed, and based on the results, a generative AI model generates prompt sentences to optimize robot A's behavior.

[0868] An example of the prompt statement it generates is:

[0869] Cobot A reports the current task progress. Retrieve the latest number of completed tasks and working time from the operation log to calculate the productivity index. Furthermore, analyze the voice commands received from the latest message log to evaluate the cooperativeness index.

[0870] In this way, the system of the present invention is able to accurately monitor, evaluate, and optimize the productivity and cooperation of users and collaborative robots.

[0871] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0872] Step 1:

[0873] The terminal collects operational data of the user in real time while he or she is working. Specifically, it monitors operational events such as application launches, file accesses, and document creation and editing, and records each event in log format. The input is the user's operational events, and the output is the recorded operation log. This data is compressed and encrypted at regular intervals and sent to the server.

[0874] Step 2:

[0875] The device collects the user's message data. Specifically, it records the content, sending time, and recipient of messages sent and received via internal chat tools, email, etc. The collected data is preprocessed (text cleaning, tokenization, etc.) and periodically sent to the server. The input is the user's message data, and the output is the preprocessed message data.

[0876] Step 3:

[0877] The server stores the received operational and message data in a secure database. The database has a means of maintaining consistency and integrity, and is backed up regularly. The input is the encrypted operational and message data, and the output is the stored data.

[0878] Step 4:

[0879] The server analyzes the recorded operation data. Specifically, it uses a machine learning algorithm (e.g., Scikit-learn) to calculate productivity indicators (e.g., number of tasks processed, work time, and work efficiency). The input is the stored operation data, and the output is the calculated productivity indicators.

[0880] Step 5:

[0881] The server analyzes the message data using a natural language processing algorithm (e.g., NLTK or spaCy) to calculate agreeableness and sentiment indexes. It uses a sentiment engine to identify positive and negative sentiments and evaluate agreeableness and stress levels. The input is the preprocessed message data, and the output is agreeableness and sentiment indexes.

[0882] Step 6:

[0883] The server aggregates all data and generates an overall evaluation score for each user. This score is calculated based on productivity, creativity, business contribution, cooperativeness, and emotional indicators. The inputs are productivity indicators, cooperativeness data, and emotional data, and the output is the overall evaluation score.

[0884] Step 7:

[0885] The server displays the evaluation results using a visualization tool. Specifically, productivity, collaboration, emotional indicators, and overall evaluation scores are visually displayed in graph and chart format on a dashboard. The input is the overall evaluation score and related data, and the output is the visualized evaluation results.

[0886] Step 8:

[0887] The terminal collects operation and communication data of collaborative robots in a factory. Specifically, it records each robot operation event (e.g., picking up and placing parts, movement path, machine operation) as a log. It also collects instructions from human workers and communications with other robots. The input is the collaborative robot's operation events and communication data, and the output is the recorded operation and communication data.

[0888] Step 9:

[0889] The server analyzes the operation data and communication data of the collaborative robots. From the analyzed data, it calculates indicators to evaluate the robots' productivity and cooperativeness. The input is the collected operation data and communication data, and the output is the evaluation indicators.

[0890] Step 10:

[0891] The server inputs the analysis results using the generative AI model and generates prompt sentences to optimize the behavior of the collaborative robot. The inputs are the evaluation index and the generative AI model, and the output is the optimized prompt sentence.

[0892] Specific prompt examples:

[0893] Cobot A reports the current task progress. Retrieve the latest number of completed tasks and working time from the operation log to calculate the productivity index. Furthermore, analyze the voice commands received from the latest message log to evaluate the cooperativeness index.

[0894] In this way, by going through each processing step, a system is realized that accurately monitors and evaluates the productivity and cooperation of the user and the collaborative robot.

[0895] 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.

[0896] 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.

[0897] 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.

[0898] [Third embodiment]

[0899] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0900] 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.

[0901] 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).

[0902] 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.

[0903] 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.

[0904] 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).

[0905] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0906] 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.

[0907] 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.

[0908] 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.

[0909] 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.

[0910] 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."

[0911] The system of the present invention collects and analyzes operation data and message data of users during their work, and evaluates the users' productivity, creativity, business contribution, and cooperativeness from various angles. Detailed embodiments of the system are described below.

[0912] Explanation of program processing

[0913] In the system of the present invention, the following processing is performed.

[0914] Data collection

[0915] 1. Collecting Operational Data

[0916] The device monitors the user's work activities and records data in real time, such as applications running, files accessed, web pages browsed, and documents created or edited.

[0917] The terminal collects this operational data at regular intervals, compresses it, and sends it to the server in encrypted form.

[0918] 2. Message Data Collection

[0919] The device records the content, time of sending, and recipient of messages sent and received via the user's internal chat tool, email, etc.

[0920] The device preprocesses the collected message data (text cleaning, tokenization, etc.) and periodically sends it to the server.

[0921] Data storage and management

[0922] 3. Data storage

[0923] The server receives operation data and message data sent from the terminal in real time and stores them in a secure database.

[0924] The server performs regular backups to ensure data consistency and integrity, and restores data when necessary.

[0925] Data analysis

[0926] 4. Analysis of Operational Data

[0927] The server analyzes the recorded operation data and calculates productivity indicators for each user (e.g., number of tasks processed, work time, work efficiency).

[0928] The server evaluates the contribution of each project and calculates the impact on the project's profits and progress.

[0929] 5. Message Data Analysis

[0930] The server analyzes the message data using natural language processing algorithms and evaluates the level of cooperation, including analyzing the sentiment of the message content.

[0931] The server performs sentiment analysis to identify positive and negative communications and calculates an agreeableness score.

[0932] Evaluation and visualization

[0933] 6. Calculation of evaluation score

[0934] The server combines the above-mentioned productivity, creativity, business contribution, and cooperativeness indicators to generate an overall evaluation score for each user.

[0935] The server visualizes the evaluation results based on this score as graphs and charts and displays them on a dashboard.

[0936] 7. Providing Feedback

[0937] The user logs in to the dashboard and checks the evaluation results.

[0938] The server displays feedback to the user and provides feedback on areas for improvement and strengths based on the evaluation results.

[0939] Specific examples

[0940] For example, if employee A is working on multiple projects:

[0941] The device records in detail employee A's daily working hours, files handled, applications used, etc.

[0942] The device collects messages exchanged with other members through the company's internal chat tool, preprocesses them, and then sends them to the server.

[0943] The server analyzes this data and calculates employee A's productivity (e.g., number of tasks completed per day), business contribution (e.g., impact on project progress), and cooperation (e.g., percentage of positive messages).

[0944] Based on these analysis results, the server generates an overall evaluation score for employee A and displays it on the dashboard.

[0945] User Employee A accesses the dashboard to review his or her own evaluation and receive feedback on strengths and areas for improvement.

[0946] In this way, the system of the present invention eliminates emotional bias and realizes fair and multifaceted evaluation based on data.

[0947] The processing flow will be explained below.

[0948] Step 1:

[0949] The device monitors user operations in real time while working and records each operation event (launching an application, accessing a file, browsing a web page, creating or editing a document, etc.).

[0950] Step 2:

[0951] The device collects the recorded operation data at regular intervals and compresses it to reduce the data volume. The compressed operation data is temporarily stored in the device.

[0952] Step 3:

[0953] The device encrypts the compressed operation data and sends it to the server after ensuring security. Transmission is performed during off-peak hours to minimize network load.

[0954] Step 4:

[0955] The device also collects data from users' internal chat tools and emails, and preprocesses it, including metadata such as message content, sending time, and recipients. Preprocessing includes text cleaning and tokenization.

[0956] Step 5:

[0957] The terminal compresses and encrypts the preprocessed message data and transmits it to the server in the same manner as the operation data.

[0958] Step 6:

[0959] The server receives operation data and message data sent from the device in real time and stores them in a secure database. The stored data undergoes a backup process to ensure data consistency and integrity.

[0960] Step 7:

[0961] The server analyzes the saved operation data and calculates productivity indicators for each user, including the number of tasks completed, work time, and work efficiency.

[0962] Step 8:

[0963] The server evaluates the contribution of each project by calculating the user's operation data and the impact on the progress and profits of the project.

[0964] Step 9:

[0965] The server analyzes the message data using natural language processing algorithms, which perform sentiment analysis of the text, distinguish between positive and negative communication, and calculate an agreeableness score.

[0966] Step 10:

[0967] The server combines each user's productivity, creativity, business contribution, and cooperativeness indicators to generate an overall evaluation score.

[0968] Step 11:

[0969] The server visualizes the generated rating scores and displays them on a dashboard as graphs and charts, allowing users to check their own ratings.

[0970] Step 12:

[0971] Users access a dashboard to view their assessment results and feedback, which includes strengths and areas for improvement based on the assessment results.

[0972] This series of processing steps eliminates emotional bias and enables a multifaceted and fair evaluation.

[0973] Example 1

[0974] 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."

[0975] With conventional systems, it was easy for emotional bias to creep in when evaluating users' work efficiency and cooperation, making it difficult to make objective, data-based evaluations. Furthermore, there was also the issue of delays in evaluation results because operation data and message data were not collected and analyzed in real time. Furthermore, when providing evaluation results to users, there was also the issue of a lack of specific feedback on areas for improvement and strengths.

[0976] 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.

[0977] In this invention, the server includes means for recording user operation data during work in real time and compressing and encrypting it at regular intervals before transmitting it, means for preprocessing message data and periodically transmitting it, means for generating an evaluation score for each user and displaying it on a dashboard, and means for providing the user with feedback on areas for improvement and strengths. This enables fair and multifaceted evaluation based on data and makes it possible to provide the user with specific areas for improvement and strengths in real time.

[0978] "User operation data" refers to data such as the applications a user uses to perform their work, the files they access, the web pages they browse, and the documents they create and edit.

[0979] "Message data" refers to data related to the content, time of sending, and recipient of messages sent and received by users via internal chat tools, email, etc.

[0980] "Analysis" refers to the processing and analysis of recorded or collected data to extract and evaluate specific indicators or patterns.

[0981] "Productivity" refers to indicators such as the number of tasks, workload, and work efficiency completed by a user within a certain period of time.

[0982] "Creativity" refers to the ability of users to propose new ideas and come up with original solutions while performing their work.

[0983] "Business contribution" refers to an indicator that evaluates the impact that the projects and tasks a user is responsible for have on the profits and progress of the entire organization.

[0984] "Collaboration" is an indicator that evaluates how effectively a user can cooperate with other members in internal communications and build positive relationships.

[0985] "Means for visualizing evaluation results" refers to means for displaying the user evaluation results obtained by analysis in a visual format such as a graph or chart.

[0986] "Means for recording data in real time" refers to means for instantly recording information each time a user performs an operation.

[0987] "Means for compressing and encrypting and transmitting" refers to means for compressing and encrypting collected data for the purpose of reducing its size and protecting its security, and transmitting it to a server via a network.

[0988] "Means for preprocessing and sending" refers to means for periodically sending collected message data to a server after preprocessing it, such as cleaning and tokenizing it, into a format suitable for analysis.

[0989] The "means for generating an evaluation score" refers to a means for integrating various indicators such as productivity, creativity, business contribution, and cooperativeness to calculate an overall evaluation score for each user.

[0990] "Means for displaying on a dashboard" refers to means for displaying the evaluation score and feedback information on a dashboard that can be accessed by the user.

[0991] "Means for providing feedback on areas for improvement and strengths" refers to means for analyzing specific areas for improvement and strengths based on the user's evaluation results and providing them to the user.

[0992] The system of the present invention collects and analyzes operation data and message data of users during their work, and evaluates the users' productivity, creativity, business contribution, and cooperativeness from various angles. Detailed embodiments of the system are described below.

[0993] Data collection

[0994] Operational Data Collection

[0995] The device monitors user activity 24 / 7, recording in real time which applications are running, which files are accessed, which web pages are browsed, and which documents are created or edited.

[0996] The terminal compresses the collected operation data every hour and sends it to the server in encrypted form, using encryption technologies such as SSL / TLS to protect the data.

[0997] Message Data Collection

[0998] The device monitors the user's internal chat tools and emails, recording the content of messages sent and received, the time of sending, and the recipients.

[0999] The device preprocesses message data (such as text cleaning and tokenization) once a day before sending it to the server. This preprocessing is done using Python's NLTK and SpaCy libraries.

[1000] Data storage and management

[1001] Data storage

[1002] The server stores the received operation data and message data in a high-speed database (e.g., PostgreSQL or MongoDB) in real time, and performs transaction management to maintain data consistency.

[1003] The server performs regular database backups to prevent data loss, and the backup data is also stored in cloud storage such as AWS S3.

[1004] Data analysis

[1005] Analysis of operational data

[1006] The server uses machine learning algorithms to analyze the operation data and calculate productivity metrics for each user, using libraries such as Scikit-learn and TensorFlow.

[1007] The server then evaluates the user's contribution to each project and calculates the impact on the project's profits and progress, using multivariate analysis and clustering techniques.

[1008] Parsing message data

[1009] The server analyzes message data using natural language processing (NLP) algorithms, including sentiment analysis, leveraging models such as BERT and GPT-3.

[1010] The server distinguishes between positive and negative communication from the message content and calculates an agreeableness score.

[1011] Evaluation and visualization

[1012] Calculation of evaluation score

[1013] The server aggregates the productivity, creativity, business contribution, and collaboration metrics to generate an overall evaluation score for each user, which is then displayed as graphs and charts using visualization libraries such as D3.js and Chart.js.

[1014] The server updates the evaluation results in real time and displays them on a dashboard, which uses visualization tools such as Kibana and Grafana.

[1015] Providing Feedback

[1016] Providing Feedback

[1017] Users can log in to their account and check the results of their evaluations on the dashboard, where they can see not only the overall evaluation score but also detailed feedback on each indicator.

[1018] The server provides users with feedback on areas for improvement and strengths based on the evaluation results, and proposes specific action plans, including goal setting and progress management tools.

[1019] Specific examples

[1020] For example, let's say employee A is working on multiple projects.

[1021] The terminal records employee A's daily operation data (such as applications used and files accessed) in real time and sends it to the server every hour.

[1022] The terminal collects messages sent and received by employee A via internal chat tools and email, preprocesses them once a day, and then sends them to the server.

[1023] The server analyzes employee A's productivity (e.g., number of tasks completed per day) based on the operation data and evaluates his / her contribution to each project.

[1024] The server uses NLP algorithms to perform sentiment analysis of the message data and calculates an agreeableness score.

[1025] Based on these analysis results, the server generates an overall evaluation score for employee A and displays it on the dashboard.

[1026] User Employee A accesses the dashboard to review his or her own evaluation and receive feedback on strengths and areas for improvement.

[1027] Prompt Sentence Examples

[1028] Below are examples of prompt sentences to be input to the generative AI model based on specific examples.

[1029] Explain how to analyze Employee A's number of tasks completed per day, productivity score, and contribution per project and display them on a dashboard.

[1030] Please tell us more about the algorithm that analyzes the sentiment of chat messages and calculates the agreeableness score.

[1031] Explain how you can use interaction and message data to assess user creativity.

[1032] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1033] Step 1: Collect data

[1034] Operational Data Collection

[1035] The terminal records operational data in real time, such as the launch history of applications used by the user when performing work, files accessed, web pages browsed, and documents created and edited.

[1036] The input of the terminal is the user's operation events (e.g., clicks, keystrokes), and the output is the log data in which these events are recorded.

[1037] The device periodically compresses and encrypts the operational data before sending it to the server, using encryption technologies such as SSL / TLS to protect the data.

[1038] Message Data Collection

[1039] The device records the content, time of sending, and recipient of messages sent and received via the user's internal chat tool or email.

[1040] The input to the terminal is events such as sending and receiving emails from an internal chat tool, and the output is log data in which these message data are recorded.

[1041] The device preprocesses the collected message data (such as text cleaning and tokenization) and periodically sends it to the server. Preprocessing is performed using Python's NLTK and SpaCy libraries.

[1042] Step 2: Store and manage your data

[1043] Data storage

[1044] The server receives the operation data and message data sent from the terminal and stores them in a database (e.g., PostgreSQL or MongoDB) in real time.

[1045] The input of the server is encrypted operational and message data, and the output is data stored in a database.

[1046] The server performs transaction management to enhance data consistency and integrity. In addition, it periodically backs up the database and stores it in cloud storage (e.g., AWS S3).

[1047] Step 3: Data analysis

[1048] Analysis of operational data

[1049] The server uses machine learning algorithms to analyze the operation data and calculate productivity indicators for each user (e.g., number of tasks completed, work time, and work efficiency).

[1050] The input of the server is the operational data stored in the database, and the output is the analysis results including productivity indicators.

[1051] The server uses libraries such as Scikit-learn and TensorFlow to extract and analyze patterns and trends in the operational data.

[1052] Parsing message data

[1053] The server analyzes the message data using natural language processing (NLP) algorithms and performs sentiment analysis.

[1054] The server's input is message data stored in a database, and its output is analysis results such as cooperativeness scores.

[1055] The server utilizes generative AI models such as BERT and GPT-3 to perform sentiment analysis of message content and identify positive and negative communication.

[1056] Step 4: Evaluate and visualize

[1057] Calculation of evaluation score

[1058] The server integrates the productivity, creativity, business contribution, and cooperativeness indicators to generate an overall evaluation score for each user.

[1059] The input to the server is the analysis results of the operation data and message data, and the output is a comprehensive evaluation score.

[1060] The server uses visualization libraries such as D3.js and Chart.js to display the evaluation results as graphs and charts.

[1061] Step 5: Provide feedback

[1062] Providing Feedback

[1063] Users can log in to their dashboard with their account and check the evaluation results.

[1064] The input of the dashboard is the evaluation scores and feedback information sent from the server, and the output is the visualization data displayed to the user.

[1065] The server provides users with feedback on areas for improvement and strengths based on the evaluation results, and proposes specific action plans, including goal setting and progress management tools.

[1066] (Application example 1)

[1067] 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."

[1068] In recent years, factories have been required to collect and analyze employee operation data and message data in order to improve work efficiency and productivity. However, to evaluate employee activities from multiple angles, it is necessary to collect data in real time and analyze it with high accuracy. In conventional systems, the collection and analysis of operation data and message data are separated, and evaluation criteria are limited, making it difficult to evaluate overall productivity and cooperativeness. The present invention aims to solve these problems and provide a system that comprehensively and fairly evaluates the productivity, cooperativeness, creativity, and business contribution of factory workers.

[1069] 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.

[1070] In this invention, the server includes a means for analyzing the recorded operation data and collected message data to evaluate the user's productivity, creativity, business contribution, and cooperativeness, a means for visualizing the evaluation results, and a means for supporting the creation of prompt sentences to be input to the generative AI model, thereby enabling the evaluation of work efficiency and cooperativeness in factories.

[1071] "Operational data" refers to the series of work procedures and operations performed by a user during work, including, specifically, running applications, accessed files, viewed web pages, and created / edited documents.

[1072] "Message data" is text data that includes information such as the content, transmission time, and recipient of messages sent and received by users via in-house chat tools, e-mail, etc.

[1073] "Productivity" is an index that indicates the quantity and quality of tasks and deliverables that a user has completed within a certain period of time, and is used to evaluate the user's work efficiency and ability to perform work.

[1074] "Creativity" is an index that evaluates a user's ability to come up with new ideas and projects and to apply them to actual work.

[1075] "Business contribution" is an index that evaluates how much a user's business activities have affected the profits of the entire organization and the progress of a project.

[1076] "Cooperativeness" is an index that evaluates how smoothly a user communicates with other members and how much they contribute to achieving the team's goals.

[1077] "Visualization" refers to displaying the evaluation results in a visual format such as a graph or chart, allowing users to intuitively understand them.

[1078] "Real-time" refers to data collection or processing occurring immediately without delay, meaning that user actions and operations are immediately reflected in the system.

[1079] "Generative AI models" refer to algorithms or models that use artificial intelligence technology to analyze user behavioral data and provide evaluations and feedback.

[1080] A "prompt sentence" is a text sentence that contains input data for a generative AI model, and contains information that serves as instructions for the AI ​​to perform appropriate analysis and evaluation.

[1081] The system of the present invention collects and analyzes operation data and message data of workers during their work in a factory, and evaluates their productivity and cooperation. Specific embodiments will be described below.

[1082] Data collection methods

[1083] First, the device (in this case, smart glasses) collects the worker's operation data. This data includes eye movements during work, setup procedures, details of repair work, and the status of the work environment. The smart glasses use built-in cameras and sensors to monitor and record this data in real time, and then periodically send it to a server in a consolidated form.

[1084] Message data is collected by using the voice recognition function of the smart glasses to recognize verbal instructions and reports given by workers and record them as text data. This text data is then periodically sent to a server after undergoing preprocessing (such as text cleaning and tokenization).

[1085] Data Storage and Management

[1086] The server then receives the operation and message data sent from the device in real time and stores it in a secure database. To ensure data consistency and integrity, the server performs regular backups and restores the data when necessary.

[1087] Data Analysis Methods

[1088] The server analyzes the recorded operation data and calculates productivity indicators for each user (e.g., number of tasks completed, working time, work efficiency). Furthermore, it evaluates the contribution of each project and calculates the impact on the project's profits and progress.

[1089] Message data is analyzed using natural language processing algorithms, which evaluates cooperation by analyzing the sentiment of the message content. Sentiment analysis distinguishes between positive and negative communication and calculates a cooperation score.

[1090] Evaluation and visualization

[1091] The server combines the above indicators of productivity, creativity, business contribution, and cooperativeness to generate an overall evaluation score for each user. Based on this score, the evaluation results are visualized as graphs and charts and displayed on a dashboard. Users can log in to the dashboard to check their evaluation results and receive feedback based on them.

[1092] Specific examples

[1093] For example, if a factory worker is assembling a product:

[1094] The smart glasses record workers' eye movements and work procedures in detail.

[1095] Verbal instructions and reports given by workers are collected using a voice recognition function and converted into text data.

[1096] The server receives and analyzes this data in real time and evaluates it based on work efficiency and cooperation.

[1097] The evaluation results and feedback are displayed in real time on the smart glasses display.

[1098] Examples of prompt statements

[1099] Enter the following prompt for the generative AI model:

[1100] Operation data: A worker is assembling product A. Part number 123 is being assembled, and eye movement is normal and there are no problems with the work procedure.

[1101] Message data: Assembly complete.

[1102] The above is an embodiment of the present invention, which makes it possible to comprehensively evaluate work efficiency and cooperation in a factory and provide feedback for improvement.

[1103] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1104] Step 1:

[1105] The terminal collects the worker's operation data. The input is real-time data such as eye movements and work procedures collected by the smart glasses using cameras and sensors. This data is temporarily stored on the terminal. The output is compressed and encrypted operation data.

[1106] Step 2:

[1107] The terminal collects message data from workers. The input is verbal instructions and reports from workers obtained using a voice recognition function. The voice data is converted into text data, which is preprocessed (text cleaning and tokenization) and temporarily stored. The output is the preprocessed text data.

[1108] Step 3:

[1109] The terminal periodically collects operation data and message data and sends them to the server. The input is the data collected and preprocessed in steps 1 and 2. The data is sent to the server in real time. The output is the data sent to the server in real time.

[1110] Step 4:

[1111] The server stores the data it receives in a database. The input is the operation data and message data sent from the terminal. This data is securely stored in the database and is backed up regularly to ensure consistency and completeness. The output is the data securely stored in the database.

[1112] Step 5:

[1113] The server analyzes the operation data. The input is the saved operation data, and by analyzing this data, it calculates productivity indicators for each user (e.g., number of tasks completed, work time, work efficiency, etc.). The output is the productivity indicators for each user.

[1114] Step 6:

[1115] The server analyzes the message data using a natural language processing algorithm. The input is the stored message data. This data is used to analyze the message content and sentiment, and calculate an agreeableness score. The output is an agreeableness score.

[1116] Step 7:

[1117] The server combines the productivity index and cooperativeness score to generate an overall evaluation score for each user. The inputs are the productivity index and cooperativeness score obtained in steps 5 and 6. These are combined to calculate the overall evaluation score. The output is the overall evaluation score.

[1118] Step 8:

[1119] The server visualizes the overall evaluation score and displays it on a dashboard. The input is the overall evaluation score calculated in step 7. This is visually represented as a graph or chart and displayed on the dashboard so that the user can check it. The output is a dashboard showing the evaluation results.

[1120] Step 9:

[1121] The server assists in creating prompt sentences to be input to the generated AI model. The input is operation data and message data. Based on this, a prompt sentence is generated and input to the AI ​​model. As a specific example, the following prompt sentence is generated: "Operation data: Worker is assembling product A. Part number 123 is assembled, eye movement is normal, no problems with the work procedure. Message data: Assembly completed." The output is the generated prompt sentence.

[1122] 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.

[1123] The system of the present invention evaluates users' productivity, creativity, business contribution, and cooperativeness by collecting and analyzing operation data and message data during user work. Furthermore, by combining it with an emotion engine that recognizes users' emotions, the accuracy of the evaluation and the quality of the feedback are improved.

[1124] Explanation of program processing

[1125] In the system of the present invention, the following processing is performed.

[1126] Data collection

[1127] 1. Collecting Operational Data

[1128] The device monitors the user's work activities in real time and records each operation event (launching an application, accessing a file, browsing a web page, creating or editing a document, etc.).

[1129] The terminal collects this operational data at regular intervals, compresses it, and sends it to the server in encrypted form.

[1130] 2. Message Data Collection

[1131] The device records the content, time of sending, and recipient of messages sent and received via the user's internal chat tool, email, etc.

[1132] The device preprocesses the collected message data (text cleaning, tokenization, etc.) and periodically sends it to the server.

[1133] Data storage and management

[1134] 3. Data storage

[1135] The server receives the operation data and message data sent from the terminal in real time and stores them in a secure database.

[1136] The server performs regular backups to ensure data consistency and integrity, and restores data when necessary.

[1137] Data analysis

[1138] 4. Analysis of Operational Data

[1139] The server analyzes the recorded operation data and calculates productivity indicators for each user (e.g., number of tasks processed, work time, work efficiency).

[1140] The server evaluates the contribution of each project and calculates the impact on the project's profits and progress.

[1141] 5. Message Data Analysis

[1142] The server analyzes the message data using natural language processing algorithms, including analyzing the sentiment of the text, to extract data to assess the user's agreeableness.

[1143] 6. Use of Emotion Engine

[1144] The server uses an emotion engine to recognize the user's emotions from the user's message data and operation data during work.

[1145] The emotion engine identifies positive and negative emotions and calculates emotional indicators such as agreeableness and stress level.

[1146] Evaluation and visualization

[1147] 7. Calculation of evaluation score

[1148] The server integrates the data on productivity, creativity, business contribution, cooperativeness, and emotional indicators mentioned above to generate an overall evaluation score for each user.

[1149] The server visualizes the evaluation results based on this score as graphs and charts and displays them on a dashboard.

[1150] 8. Providing Feedback

[1151] Users access a dashboard to view their evaluation results along with feedback based on sentiment analysis, including areas for improvement in stress management and team communication.

[1152] Specific examples

[1153] For example, if Employee A handles multiple tasks during work and simultaneously communicates with team members using an internal chat tool:

[1154] The terminal sequentially records detailed operation data while employee A is working and periodically transmits it to the server.

[1155] The terminal preprocesses the contents of the internal chat messages and sends them to the server.

[1156] The server analyzes the operation data and calculates employee A's productivity index.

[1157] The server analyzes the message data using natural language processing algorithms to evaluate cooperation and quality of communication.

[1158] The server uses an emotion engine to analyze employee A's emotional state from the message content and operation data, and generates an emotion index.

[1159] The server aggregates all the data and displays an overall rating score and sentiment-based feedback on a dashboard.

[1160] User Employee A accesses the dashboard to check his / her own evaluation and feedback and understand the areas for improvement that need to be made.

[1161] In this way, the system of the present invention combines emotion engines to achieve fair and multifaceted evaluation that takes into account the user's emotional state.

[1162] The processing flow will be explained below.

[1163] Step 1:

[1164] The device monitors user operations in real time while working and records each operation event (launching an application, accessing a file, browsing a web page, creating or editing a document, etc.).

[1165] Step 2:

[1166] The device collects the recorded operation data at regular intervals and compresses it to reduce the data volume. The compressed operation data is temporarily stored on the device.

[1167] Step 3:

[1168] The device encrypts the compressed operation data and sends it to the server after ensuring security. Transmission is performed during off-peak hours to minimize network load.

[1169] Step 4:

[1170] The device collects data from users' internal chat tools and emails, and preprocesses it, including metadata such as message content, sending time, and recipients. Preprocessing includes text cleaning and tokenization.

[1171] Step 5:

[1172] The terminal compresses and encrypts the preprocessed message data and transmits it to the server in the same manner as the operation data.

[1173] Step 6:

[1174] The server receives operation data and message data sent from the device in real time and stores them in a secure database. The stored data undergoes a backup process to ensure data consistency and integrity.

[1175] Step 7:

[1176] The server analyzes the recorded operation data and calculates productivity indicators for each user (e.g., number of tasks completed, work time, work efficiency). Statistical analysis of the data and machine learning algorithms are used for the analysis.

[1177] Step 8:

[1178] The server calculates the user's operational data and their impact on the progress and profits of the project to assess their contribution to each project, taking into account the number of tasks completed and the quality of deliverables related to a particular project.

[1179] Step 9:

[1180] The server analyzes the message data using natural language processing algorithms, including text cleansing, tokenization, and grammar analysis, to classify the sentiment of the message.

[1181] Step 10:

[1182] The server uses a sentiment engine to analyze the text extracted from the message data and calculate a positive, negative, or neutral sentiment score, as well as analyze long-term sentiment trends.

[1183] Step 11:

[1184] The server reflects the emotion score obtained by the emotion engine in the evaluation of the user's agreeableness, comparing the frequency of positive messages with the frequency of negative messages, and updates the user's agreeableness score.

[1185] Step 12:

[1186] The server then combines the data on productivity, creativity, business contribution, collaboration, and emotional indicators obtained above to generate an overall evaluation score for each user, calculated based on a weighted combination of each indicator.

[1187] Step 13:

[1188] The server generates graphs and charts to visually display the overall evaluation score, and displays them on the dashboard, allowing users to check their own evaluation results at a glance.

[1189] Step 14:

[1190] Users access a dashboard to view their assessment results, which includes personalized feedback along with their assessment scores, allowing users to recognize strengths and areas for improvement.

[1191] Step 15:

[1192] The server continuously collects and analyzes data and periodically updates the evaluation results, allowing users to be evaluated on their work performance in real time and provide appropriate feedback.

[1193] By combining this flow with an emotion engine, the system of the present invention achieves a multifaceted and fair evaluation that reflects the user's emotional state.

[1194] Example 2

[1195] 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."

[1196] In modern work environments, there is a demand for accurate evaluation of users' productivity, cooperativeness, and even their emotional state. However, conventional systems only collect general operation data and message data, making it difficult to perform detailed evaluations that take into account the user's emotional state. Furthermore, there are insufficient means to visualize the results of user evaluations in an intuitive manner. This results in a lack of effective feedback and prevents work improvements.

[1197] 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.

[1198] In this invention, the server includes means for recording user operation data during work, means for collecting user message data, means for analyzing the recorded operation data and the collected message data to evaluate the user's productivity, creativity, business contribution, and cooperativeness, means for recognizing the user's emotions and reflecting them in the evaluation results, and means for visualizing the evaluation results. This enables fair and multifaceted evaluation that takes the user's emotional state into consideration, and makes it possible to intuitively visualize the results and provide effective feedback.

[1199] "User operation data during work" refers to information about a series of operations that occur when a user performs work (launching and using applications, accessing files, viewing web pages, creating and editing documents, etc.).

[1200] "Message data" refers to text messages sent and received by users using internal chat tools or email, as well as related metadata such as the time of sending and recipient information.

[1201] "Productivity" refers to an index for evaluating the results a user has achieved in work within a certain period of time, the amount of tasks processed, and the efficiency of the time required for these tasks.

[1202] "Creativity" refers to an index used to evaluate users' ability to propose and implement new ideas, improvements, and original solutions.

[1203] "Business contribution" refers to an index used to evaluate the degree of contribution a user has made to a specific project or to the overall business.

[1204] "Collaboration" refers to an index used to evaluate a user's ability to smoothly communicate and cooperate with their team and other members.

[1205] "Means for recognizing emotions and reflecting them in the evaluation results" refers to algorithms and processes that recognize the user's emotional state (positive or negative emotions, etc.) from message data and operational data during work, and reflect that emotional information in the evaluation results.

[1206] "Means for visualizing evaluation results" refers to means for providing evaluation results such as user productivity, creativity, business contribution, cooperativeness, and emotional state in the form of visual displays such as graphs, charts, and dashboards.

[1207] "Natural language processing algorithm" refers to a set of processes and techniques that enable computer programs to understand, analyze, and process human natural language.

[1208] The system of the present invention evaluates users' productivity, creativity, business contribution, and cooperativeness by collecting and analyzing operation data and message data during user work. In addition, by combining it with an emotion engine that recognizes users' emotions, the accuracy of the evaluation and the quality of the feedback are improved.

[1209] The system uses the following hardware and software.

[1210] Hardware

[1211] Terminal: A device that collects user operation data and message data.

[1212] Server: A central control device that receives, stores, and analyzes data.

[1213] Emotion Engine: A specific device for recognizing a user's emotional state

[1214] software

[1215] Data collection program: Runs on the terminal and collects operation data and message data.

[1216] Encryption and compression programs: Encrypt and compress data

[1217] Natural Language Processing (NLP) algorithms: Analyze message data and extract agreeableness and emotional state

[1218] Data analysis program: Analyzes operational data to measure productivity, creativity, and business contribution

[1219] Visualization program: Visually displays evaluation results in graphs and charts

[1220] Data collection

[1221] The device monitors users' work activities in real time and records each operation event (e.g., launching an application, accessing a file, viewing a web page, creating or editing a document). The device also records the content, time of sending, and recipient of messages sent and received via internal chat tools and email. The recorded data is compressed, encrypted, and sent to a server at regular intervals.

[1222] Data storage and management

[1223] The server receives the operational and message data sent by the devices and stores it in a secure database that is regularly backed up and can be restored if necessary.

[1224] Data analysis

[1225] The server analyzes the recorded operation data and calculates productivity indicators for each user (number of tasks completed, work time, work efficiency). It also evaluates contribution to each project and measures the impact on the entire project. Message data is analyzed using a natural language processing algorithm to evaluate cooperation and emotional state. The results of this analysis are input into an emotion engine to identify the user's emotional state (e.g., positive, negative).

[1226] Evaluation and visualization

[1227] The server integrates the analysis results and generates an overall evaluation score based on the user's productivity, creativity, business contribution, collaborative ability, and emotional state. The evaluation results are displayed on a dashboard as graphs and charts to visualize them. Users access the dashboard and check the feedback provided along with the evaluation results. This feedback includes areas for improvement in stress management and team communication.

[1228] Specific examples

[1229] For example, if Employee A handles multiple tasks while simultaneously communicating with team members using an internal chat tool, the device will record detailed operational data of Employee A during work and periodically send it to the server. The content of the internal chat messages will also be preprocessed and sent to the server. The server will analyze this data and evaluate Employee A's productivity index, cooperativeness, and emotional state. Finally, the overall evaluation score and feedback will be displayed on a dashboard that Employee A can access and check.

[1230] For example, the following prompt sentence is fed into the generative AI model:

[1231] "Please generate a performance evaluation report for the last month. Specifically, please include feedback on work efficiency and productivity from operation data, collaboration from message data, and emotion indicators from the emotion engine."

[1232] This prompt is designed to generate a detailed and comprehensive performance evaluation report.

[1233] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1234] Step 1:

[1235] Operational Data Collection

[1236] The device monitors the user's work operations in real time and captures user operation events (launching applications, accessing files, viewing web pages, creating and editing documents, etc.) as input.

[1237] Specifically, the terminal generates a log file and records each operation with a timestamp.

[1238] As an output, the data of these operation events is temporarily stored.

[1239] Step 2:

[1240] Sending and storing operational data

[1241] The terminal collects the operation data at regular intervals and compresses and encrypts the operation event data temporarily stored as input.

[1242] Specifically, the terminal applies a data compression algorithm and then an encryption algorithm.

[1243] The compressed and encrypted data is output and sent to the server.

[1244] The server extracts the received data and stores it in a secure database.

[1245] Step 3:

[1246] Message Data Collection

[1247] The device collects message data from the user's internal chat tool and email, and takes as input the text message and its metadata (such as the time of sending and the recipient).

[1248] Specifically, the device preprocesses the message data (cleaning the text, tokenizing it) and converts it into a format that is easy to analyze.

[1249] As output, it generates preprocessed message data and sends it to the server.

[1250] Step 4:

[1251] Sending and storing message data

[1252] The terminal periodically transmits the pre-processed message data to the server.

[1253] The server extracts the received data and stores it in a secure database.

[1254] The output is the message data stored on the server.

[1255] Step 5:

[1256] Analysis of operational data

[1257] The server takes operational data from the operational database as input and applies data analysis algorithms.

[1258] Specific operations include calculating the number of tasks processed per unit time, average work time, and frequency of each operation.

[1259] As output, productivity indicators for each user (e.g., number of tasks completed, work time, work efficiency) are generated.

[1260] Step 6:

[1261] Parsing message data

[1262] The server takes message data from a message database as input and applies natural language processing algorithms.

[1263] Specifically, the system performs sentiment analysis on the text, extracts positive and negative expressions, and uses them to evaluate cooperation.

[1264] As output, it produces an agreement index and emotional state extracted from the message data.

[1265] Step 7:

[1266] Using the Emotion Engine

[1267] The server provides message data and operation data as input to the emotion engine to recognize the emotional state.

[1268] Specifically, the emotion engine distinguishes between positive and negative emotions and calculates emotional indicators such as stress level and cooperativeness.

[1269] As output, it generates the emotional state identification result and the emotional index.

[1270] Step 8:

[1271] Calculation and visualization of evaluation scores

[1272] The server integrates the productivity index, cooperativeness index, and emotional index to calculate an overall evaluation score.

[1273] Specifically, each indicator is weighted, an integrated calculation is performed, and the data is converted into a visually easy-to-understand format.

[1274] As output, an overall evaluation score and graphs and charts of the evaluation results are generated and displayed on a dashboard.

[1275] Step 9:

[1276] Providing feedback

[1277] Users access the dashboard to view their assessment results and feedback.

[1278] Specifically, the user views the evaluation results and receives specific advice on areas for improvement such as stress management and team communication.

[1279] As an output, information is provided for the user to determine self-improvement actions.

[1280] In this way, specific operations are performed at each processing step, and final evaluation and feedback are provided through data processing and calculations based on the input data.

[1281] (Application example 2)

[1282] 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."

[1283] Collaborative robots (cobots) are becoming increasingly common in modern factories, but there is a lack of accurate ways to monitor and evaluate their productivity and cooperation. Furthermore, there is no established method for utilizing generative AI models to optimize robot behavior. This makes efficient production management and appropriate feedback difficult.

[1284] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for recording operation data of a user during work; means for collecting user message data; means for analyzing the recorded operation data and collected message data and evaluating the user's productivity, creativity, business contribution, and cooperativeness; means for visualizing the evaluation results; means for collecting operation data and communication data of operating devices in a factory and analyzing the productivity and cooperativeness of a collaborative robot; and means for inputting the analysis results into a generative AI model and generating prompt sentences that optimize the operation of the collaborative robot. This makes it possible to accurately monitor, evaluate, and optimize the productivity and cooperativeness of a collaborative robot.

[1285] "User's operation data during work" is information about all operations generated when a user performs work.

[1286] "Message data" refers to information about the content, time of sending, and recipient of messages sent or received by users inside or outside the company.

[1287] "Productivity" is an index that quantifies the efficiency and effectiveness of a user's work.

[1288] "Creativity" is the ability of users to generate new ideas and solutions in their work.

[1289] "Business contribution" is an index that shows how much a user's work contributes to the goals and profits of the entire organization.

[1290] "Collaborative ability" is the ability to show how effectively a user can cooperate with other members.

[1291] "Evaluation results" are the results and data obtained by evaluating productivity, creativity, business contribution, and cooperation.

[1292] "Visualization" is the process of presenting evaluation results and data in visual formats such as graphs and charts.

[1293] "Operation data of operating equipment in the factory" is detailed information about the operation of equipment and robots used in the factory.

[1294] "Communication data" refers to information about all communications, such as voice commands and visual signals, that take place within the factory.

[1295] A "generative AI model" is an artificial intelligence model that analyzes the current situation based on collected data and generates instructions and prompts to achieve optimal behavior.

[1296] A "prompt sentence" is an instruction sentence created by a generative AI model based on the analysis results to optimize the behavior of a collaborative robot.

[1297] This invention is a system that collects operation data and message data from users during work, analyzes this data to evaluate their productivity, creativity, business contribution, and cooperativeness, and visualizes the evaluation results. It also collects operation data and communication data from operating devices in factories, analyzes the productivity and cooperativeness of collaborative robots (cobots), and generates prompts that achieve optimal operation based on a generative AI model.

[1298] Program processing explanation

[1299] The server uses a means for recording user operation data during work to monitor and record in real time operation events (e.g., application startup, file access, document creation / editing, etc.) in the user's work as a log. It also uses a means for collecting message data to acquire message data sent and received by users inside and outside the company, and preprocesses this (text cleaning, tokenization, etc.) in preparation for analysis.

[1300] The server encrypts operational and message data before transmitting and storing it in a secure database, ensuring data consistency and integrity, while also performing regular backups and restoring data as needed.

[1301] The data is analyzed using machine learning algorithms (e.g., Scikit-learn) and natural language processing algorithms (e.g., NLTK or spaCy), and productivity indicators (e.g., number of tasks completed, work time, and work efficiency) are calculated from the recorded operation data. Message data is also used to evaluate the user's cooperativeness, and an emotion engine is used to calculate emotion indicators. The obtained data is integrated to calculate an overall evaluation score, which is then displayed as graphs or charts using a visualization tool.

[1302] In addition, the system collects operational and communication data from cobots in factories, analyzes this data to evaluate the cobots' productivity and cooperation, and inputs the analysis results into a generative AI model to generate prompts and optimize the cobots' behavior.

[1303] Specific examples

[1304] For example, consider a situation where collaborative robot A receives instructions from a human worker via voice commands when performing the task of picking up a part and placing it in a designated location in a factory. At this time, the server collects all of robot A's operation logs and communication data and stores them in a database. Using machine learning algorithms and natural language processing algorithms, robot A's productivity and cooperativeness are analyzed, and based on the results, a generative AI model generates prompt sentences to optimize robot A's behavior.

[1305] An example of the prompt statement it generates is:

[1306] Cobot A reports the current task progress. Retrieve the latest number of completed tasks and working time from the operation log to calculate the productivity index. Furthermore, analyze the voice commands received from the latest message log to evaluate the cooperativeness index.

[1307] In this way, the system of the present invention is able to accurately monitor, evaluate, and optimize the productivity and cooperation of users and collaborative robots.

[1308] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1309] Step 1:

[1310] The terminal collects operational data of the user in real time while he or she is working. Specifically, it monitors operational events such as application launches, file accesses, and document creation and editing, and records each event in log format. The input is the user's operational events, and the output is the recorded operation log. This data is compressed and encrypted at regular intervals and sent to the server.

[1311] Step 2:

[1312] The device collects the user's message data. Specifically, it records the content, sending time, and recipient of messages sent and received via internal chat tools, email, etc. The collected data is preprocessed (text cleaning, tokenization, etc.) and periodically sent to the server. The input is the user's message data, and the output is the preprocessed message data.

[1313] Step 3:

[1314] The server stores the received operational and message data in a secure database. The database has a means of maintaining consistency and integrity, and is backed up regularly. The input is the encrypted operational and message data, and the output is the stored data.

[1315] Step 4:

[1316] The server analyzes the recorded operation data. Specifically, it uses a machine learning algorithm (e.g., Scikit-learn) to calculate productivity indicators (e.g., number of tasks processed, work time, and work efficiency). The input is the stored operation data, and the output is the calculated productivity indicators.

[1317] Step 5:

[1318] The server analyzes the message data using a natural language processing algorithm (e.g., NLTK or spaCy) to calculate agreeableness and sentiment indexes. It uses a sentiment engine to identify positive and negative sentiments and evaluate agreeableness and stress levels. The input is the preprocessed message data, and the output is agreeableness and sentiment indexes.

[1319] Step 6:

[1320] The server aggregates all data and generates an overall evaluation score for each user. This score is calculated based on productivity, creativity, business contribution, cooperativeness, and emotional indicators. The inputs are productivity indicators, cooperativeness data, and emotional data, and the output is the overall evaluation score.

[1321] Step 7:

[1322] The server displays the evaluation results using a visualization tool. Specifically, productivity, collaboration, emotional indicators, and overall evaluation scores are visually displayed in graph and chart format on a dashboard. The input is the overall evaluation score and related data, and the output is the visualized evaluation results.

[1323] Step 8:

[1324] The terminal collects operation and communication data of collaborative robots in a factory. Specifically, it records each robot operation event (e.g., picking up and placing parts, movement path, machine operation) as a log. It also collects instructions from human workers and communications with other robots. The input is the collaborative robot's operation events and communication data, and the output is the recorded operation and communication data.

[1325] Step 9:

[1326] The server analyzes the operation data and communication data of the collaborative robots. From the analyzed data, it calculates indicators to evaluate the robots' productivity and cooperativeness. The input is the collected operation data and communication data, and the output is the evaluation indicators.

[1327] Step 10:

[1328] The server inputs the analysis results using the generative AI model and generates prompt sentences to optimize the behavior of the collaborative robot. The inputs are the evaluation index and the generative AI model, and the output is the optimized prompt sentence.

[1329] Specific prompt examples:

[1330] Cobot A reports the current task progress. Retrieve the latest number of completed tasks and working time from the operation log to calculate the productivity index. Furthermore, analyze the voice commands received from the latest message log to evaluate the cooperativeness index.

[1331] In this way, by going through each processing step, a system is realized that accurately monitors and evaluates the productivity and cooperation of the user and the collaborative robot.

[1332] 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.

[1333] 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.

[1334] 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.

[1335] [Fourth embodiment]

[1336] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1337] 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.

[1338] 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).

[1339] 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.

[1340] 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.

[1341] 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).

[1342] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1343] 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.

[1344] 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.

[1345] 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.

[1346] 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.

[1347] 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.

[1348] 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."

[1349] The system of the present invention collects and analyzes operation data and message data of users during their work, and evaluates the users' productivity, creativity, business contribution, and cooperativeness from various angles. Detailed embodiments of the system are described below.

[1350] Explanation of program processing

[1351] In the system of the present invention, the following processing is performed.

[1352] Data collection

[1353] 1. Collecting Operational Data

[1354] The device monitors the user's work activities and records data in real time, such as applications running, files accessed, web pages browsed, and documents created or edited.

[1355] The terminal collects this operational data at regular intervals, compresses it, and sends it to the server in encrypted form.

[1356] 2. Message Data Collection

[1357] The device records the content, time of sending, and recipient of messages sent and received via the user's internal chat tool, email, etc.

[1358] The device preprocesses the collected message data (text cleaning, tokenization, etc.) and periodically sends it to the server.

[1359] Data storage and management

[1360] 3. Data storage

[1361] The server receives operation data and message data sent from the terminal in real time and stores them in a secure database.

[1362] The server performs regular backups to ensure data consistency and integrity, and restores data when necessary.

[1363] Data analysis

[1364] 4. Analysis of Operational Data

[1365] The server analyzes the recorded operation data and calculates productivity indicators for each user (e.g., number of tasks processed, work time, work efficiency).

[1366] The server evaluates the contribution of each project and calculates the impact on the project's profits and progress.

[1367] 5. Message Data Analysis

[1368] The server analyzes the message data using natural language processing algorithms and evaluates the level of cooperation, including analyzing the sentiment of the message content.

[1369] The server performs sentiment analysis to identify positive and negative communications and calculates an agreeableness score.

[1370] Evaluation and visualization

[1371] 6. Calculation of evaluation score

[1372] The server combines the above-mentioned productivity, creativity, business contribution, and cooperativeness indicators to generate an overall evaluation score for each user.

[1373] The server visualizes the evaluation results based on this score as graphs and charts and displays them on a dashboard.

[1374] 7. Providing Feedback

[1375] The user logs in to the dashboard and checks the evaluation results.

[1376] The server displays feedback to the user and provides feedback on areas for improvement and strengths based on the evaluation results.

[1377] Specific examples

[1378] For example, if employee A is working on multiple projects:

[1379] The device records in detail employee A's daily working hours, files handled, applications used, etc.

[1380] The device collects messages exchanged with other members through the company's internal chat tool, preprocesses them, and then sends them to the server.

[1381] The server analyzes this data and calculates employee A's productivity (e.g., number of tasks completed per day), business contribution (e.g., impact on project progress), and cooperation (e.g., percentage of positive messages).

[1382] Based on these analysis results, the server generates an overall evaluation score for employee A and displays it on the dashboard.

[1383] User Employee A accesses the dashboard to review his or her own evaluation and receive feedback on strengths and areas for improvement.

[1384] In this way, the system of the present invention eliminates emotional bias and realizes fair and multifaceted evaluation based on data.

[1385] The processing flow will be explained below.

[1386] Step 1:

[1387] The device monitors user operations in real time while working and records each operation event (launching an application, accessing a file, browsing a web page, creating or editing a document, etc.).

[1388] Step 2:

[1389] The device collects the recorded operation data at regular intervals and compresses it to reduce the data volume. The compressed operation data is temporarily stored in the device.

[1390] Step 3:

[1391] The device encrypts the compressed operation data and sends it to the server after ensuring security. Transmission is performed during off-peak hours to minimize network load.

[1392] Step 4:

[1393] The device also collects data from users' internal chat tools and emails, and preprocesses it, including metadata such as message content, sending time, and recipients. Preprocessing includes text cleaning and tokenization.

[1394] Step 5:

[1395] The terminal compresses and encrypts the preprocessed message data and transmits it to the server in the same manner as the operation data.

[1396] Step 6:

[1397] The server receives operation data and message data sent from the device in real time and stores them in a secure database. The stored data undergoes a backup process to ensure data consistency and integrity.

[1398] Step 7:

[1399] The server analyzes the saved operation data and calculates productivity indicators for each user, including the number of tasks completed, work time, and work efficiency.

[1400] Step 8:

[1401] The server evaluates the contribution of each project by calculating the user's operation data and the impact on the progress and profits of the project.

[1402] Step 9:

[1403] The server analyzes the message data using natural language processing algorithms, which perform sentiment analysis of the text, distinguish between positive and negative communication, and calculate an agreeableness score.

[1404] Step 10:

[1405] The server combines each user's productivity, creativity, business contribution, and cooperativeness indicators to generate an overall evaluation score.

[1406] Step 11:

[1407] The server visualizes the generated rating scores and displays them on a dashboard as graphs and charts, allowing users to check their own ratings.

[1408] Step 12:

[1409] Users access a dashboard to view their assessment results and feedback, which includes strengths and areas for improvement based on the assessment results.

[1410] This series of processing steps eliminates emotional bias and enables a multifaceted and fair evaluation.

[1411] Example 1

[1412] 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."

[1413] With conventional systems, it was easy for emotional bias to creep in when evaluating users' work efficiency and cooperation, making it difficult to make objective, data-based evaluations. Furthermore, there was also the issue of delays in evaluation results because operation data and message data were not collected and analyzed in real time. Furthermore, when providing evaluation results to users, there was also the issue of a lack of specific feedback on areas for improvement and strengths.

[1414] 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.

[1415] In this invention, the server includes means for recording user operation data during work in real time and compressing and encrypting it at regular intervals before transmitting it, means for preprocessing message data and periodically transmitting it, means for generating an evaluation score for each user and displaying it on a dashboard, and means for providing the user with feedback on areas for improvement and strengths. This enables fair and multifaceted evaluation based on data and makes it possible to provide the user with specific areas for improvement and strengths in real time.

[1416] "User operation data" refers to data such as the applications a user uses to perform their work, the files they access, the web pages they browse, and the documents they create and edit.

[1417] "Message data" refers to data related to the content, time of sending, and recipient of messages sent and received by users via internal chat tools, email, etc.

[1418] "Analysis" refers to the processing and analysis of recorded or collected data to extract and evaluate specific indicators or patterns.

[1419] "Productivity" refers to indicators such as the number of tasks, workload, and work efficiency completed by a user within a certain period of time.

[1420] "Creativity" refers to the ability of users to propose new ideas and come up with original solutions while performing their work.

[1421] "Business contribution" refers to an indicator that evaluates the impact that the projects and tasks a user is responsible for have on the profits and progress of the entire organization.

[1422] "Collaboration" is an indicator that evaluates how effectively a user can cooperate with other members in internal communications and build positive relationships.

[1423] "Means for visualizing evaluation results" refers to means for displaying the user evaluation results obtained by analysis in a visual format such as a graph or chart.

[1424] "Means for recording data in real time" refers to means for instantly recording information each time a user performs an operation.

[1425] "Means for compressing and encrypting and transmitting" refers to means for compressing and encrypting collected data for the purpose of reducing its size and protecting its security, and transmitting it to a server via a network.

[1426] "Means for preprocessing and sending" refers to means for periodically sending collected message data to a server after preprocessing it, such as cleaning and tokenizing it, into a format suitable for analysis.

[1427] The "means for generating an evaluation score" refers to a means for integrating various indicators such as productivity, creativity, business contribution, and cooperativeness to calculate an overall evaluation score for each user.

[1428] "Means for displaying on a dashboard" refers to means for displaying the evaluation score and feedback information on a dashboard that can be accessed by the user.

[1429] "Means for providing feedback on areas for improvement and strengths" refers to means for analyzing specific areas for improvement and strengths based on the user's evaluation results and providing them to the user.

[1430] The system of the present invention collects and analyzes operation data and message data of users during their work, and evaluates the users' productivity, creativity, business contribution, and cooperativeness from various angles. Detailed embodiments of the system are described below.

[1431] Data collection

[1432] Operational Data Collection

[1433] The device monitors user activity 24 / 7, recording in real time which applications are running, which files are accessed, which web pages are browsed, and which documents are created or edited.

[1434] The terminal compresses the collected operation data every hour and sends it to the server in encrypted form, using encryption technologies such as SSL / TLS to protect the data.

[1435] Message Data Collection

[1436] The device monitors the user's internal chat tools and emails, recording the content of messages sent and received, the time of sending, and the recipients.

[1437] The device preprocesses message data (such as text cleaning and tokenization) once a day before sending it to the server. This preprocessing is done using Python's NLTK and SpaCy libraries.

[1438] Data storage and management

[1439] Data storage

[1440] The server stores the received operation data and message data in a high-speed database (e.g., PostgreSQL or MongoDB) in real time, and performs transaction management to maintain data consistency.

[1441] The server performs regular database backups to prevent data loss, and the backup data is also stored in cloud storage such as AWS S3.

[1442] Data analysis

[1443] Analysis of operational data

[1444] The server uses machine learning algorithms to analyze the operation data and calculate productivity metrics for each user, using libraries such as Scikit-learn and TensorFlow.

[1445] The server then evaluates the user's contribution to each project and calculates the impact on the project's profits and progress, using multivariate analysis and clustering techniques.

[1446] Parsing message data

[1447] The server analyzes message data using natural language processing (NLP) algorithms, including sentiment analysis, leveraging models such as BERT and GPT-3.

[1448] The server distinguishes between positive and negative communication from the message content and calculates an agreeableness score.

[1449] Evaluation and visualization

[1450] Calculation of evaluation score

[1451] The server aggregates the productivity, creativity, business contribution, and collaboration metrics to generate an overall evaluation score for each user, which is then displayed as graphs and charts using visualization libraries such as D3.js and Chart.js.

[1452] The server updates the evaluation results in real time and displays them on a dashboard, which uses visualization tools such as Kibana and Grafana.

[1453] Providing Feedback

[1454] Providing Feedback

[1455] Users can log in to their account and check the results of their evaluations on the dashboard, where they can see not only the overall evaluation score but also detailed feedback on each indicator.

[1456] The server provides users with feedback on areas for improvement and strengths based on the evaluation results, and proposes specific action plans, including goal setting and progress management tools.

[1457] Specific examples

[1458] For example, let's say employee A is working on multiple projects.

[1459] The terminal records employee A's daily operation data (such as applications used and files accessed) in real time and sends it to the server every hour.

[1460] The terminal collects messages sent and received by employee A via internal chat tools and email, preprocesses them once a day, and then sends them to the server.

[1461] The server analyzes employee A's productivity (e.g., number of tasks completed per day) based on the operation data and evaluates his / her contribution to each project.

[1462] The server uses NLP algorithms to perform sentiment analysis of the message data and calculates an agreeableness score.

[1463] Based on these analysis results, the server generates an overall evaluation score for employee A and displays it on the dashboard.

[1464] User Employee A accesses the dashboard to review his or her own evaluation and receive feedback on strengths and areas for improvement.

[1465] Prompt Sentence Examples

[1466] Below are examples of prompt sentences to be input to the generative AI model based on specific examples.

[1467] Explain how to analyze Employee A's number of tasks completed per day, productivity score, and contribution per project and display them on a dashboard.

[1468] Please tell us more about the algorithm that analyzes the sentiment of chat messages and calculates the agreeableness score.

[1469] Explain how you can use interaction and message data to assess user creativity.

[1470] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1471] Step 1: Collect data

[1472] Operational Data Collection

[1473] The terminal records operational data in real time, such as the launch history of applications used by the user when performing work, files accessed, web pages browsed, and documents created and edited.

[1474] The input of the terminal is the user's operation events (e.g., clicks, keystrokes), and the output is the log data in which these events are recorded.

[1475] The device periodically compresses and encrypts the operational data before sending it to the server, using encryption technologies such as SSL / TLS to protect the data.

[1476] Message Data Collection

[1477] The device records the content, time of sending, and recipient of messages sent and received via the user's internal chat tool or email.

[1478] The input to the terminal is events such as sending and receiving emails from an internal chat tool, and the output is log data in which these message data are recorded.

[1479] The device preprocesses the collected message data (such as text cleaning and tokenization) and periodically sends it to the server. Preprocessing is performed using Python's NLTK and SpaCy libraries.

[1480] Step 2: Store and manage your data

[1481] Data storage

[1482] The server receives the operation data and message data sent from the terminal and stores them in a database (e.g., PostgreSQL or MongoDB) in real time.

[1483] The input of the server is encrypted operational and message data, and the output is data stored in a database.

[1484] The server performs transaction management to enhance data consistency and integrity. In addition, it periodically backs up the database and stores it in cloud storage (e.g., AWS S3).

[1485] Step 3: Data analysis

[1486] Analysis of operational data

[1487] The server uses machine learning algorithms to analyze the operation data and calculate productivity indicators for each user (e.g., number of tasks completed, work time, and work efficiency).

[1488] The input of the server is the operational data stored in the database, and the output is the analysis results including productivity indicators.

[1489] The server uses libraries such as Scikit-learn and TensorFlow to extract and analyze patterns and trends in the operational data.

[1490] Parsing message data

[1491] The server analyzes the message data using natural language processing (NLP) algorithms and performs sentiment analysis.

[1492] The server's input is message data stored in a database, and its output is analysis results such as cooperativeness scores.

[1493] The server utilizes generative AI models such as BERT and GPT-3 to perform sentiment analysis of message content and identify positive and negative communication.

[1494] Step 4: Evaluate and visualize

[1495] Calculation of evaluation score

[1496] The server integrates the productivity, creativity, business contribution, and cooperativeness indicators to generate an overall evaluation score for each user.

[1497] The input to the server is the analysis results of the operation data and message data, and the output is a comprehensive evaluation score.

[1498] The server uses visualization libraries such as D3.js and Chart.js to display the evaluation results as graphs and charts.

[1499] Step 5: Provide feedback

[1500] Providing feedback

[1501] Users can log in to their dashboard with their account and check the evaluation results.

[1502] The input of the dashboard is the evaluation scores and feedback information sent from the server, and the output is the visualization data displayed to the user.

[1503] The server provides users with feedback on areas for improvement and strengths based on the evaluation results, and proposes specific action plans, including goal setting and progress management tools.

[1504] (Application example 1)

[1505] 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."

[1506] In recent years, factories have been required to collect and analyze employee operation data and message data in order to improve work efficiency and productivity. However, to evaluate employee activities from multiple angles, it is necessary to collect data in real time and analyze it with high accuracy. In conventional systems, the collection and analysis of operation data and message data are separated, and evaluation criteria are limited, making it difficult to evaluate overall productivity and cooperativeness. The present invention aims to solve these problems and provide a system that comprehensively and fairly evaluates the productivity, cooperativeness, creativity, and business contribution of factory workers.

[1507] 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.

[1508] In this invention, the server includes a means for analyzing the recorded operation data and collected message data to evaluate the user's productivity, creativity, business contribution, and cooperativeness, a means for visualizing the evaluation results, and a means for supporting the creation of prompt sentences to be input to the generative AI model, thereby enabling the evaluation of work efficiency and cooperativeness in factories.

[1509] "Operational data" refers to the series of work procedures and operations performed by a user during work, including, specifically, running applications, accessed files, viewed web pages, and created / edited documents.

[1510] "Message data" is text data that includes information such as the content, transmission time, and recipient of messages sent and received by users via in-house chat tools, e-mail, etc.

[1511] "Productivity" is an index that indicates the quantity and quality of tasks and deliverables that a user has completed within a certain period of time, and is used to evaluate the user's work efficiency and ability to perform work.

[1512] "Creativity" is an index that evaluates a user's ability to come up with new ideas and projects and to apply them to actual work.

[1513] "Business contribution" is an index that evaluates how much a user's business activities have affected the profits of the entire organization and the progress of a project.

[1514] "Cooperativeness" is an index that evaluates how smoothly a user communicates with other members and how much they contribute to achieving the team's goals.

[1515] "Visualization" refers to displaying the evaluation results in a visual format such as a graph or chart, allowing users to intuitively understand them.

[1516] "Real-time" refers to data collection or processing occurring immediately without delay, meaning that user actions and operations are immediately reflected in the system.

[1517] "Generative AI models" refer to algorithms or models that use artificial intelligence technology to analyze user behavioral data and provide evaluations and feedback.

[1518] A "prompt sentence" is a text sentence that contains input data for a generative AI model, and contains information that serves as instructions for the AI ​​to perform appropriate analysis and evaluation.

[1519] The system of the present invention collects and analyzes operation data and message data of workers during their work in a factory, and evaluates their productivity and cooperation. Specific embodiments will be described below.

[1520] Data collection methods

[1521] First, the device (in this case, smart glasses) collects the worker's operation data. This data includes eye movements during work, setup procedures, details of repair work, and the status of the work environment. The smart glasses use built-in cameras and sensors to monitor and record this data in real time, and then periodically send it to a server in a consolidated form.

[1522] Message data is collected by using the voice recognition function of the smart glasses to recognize verbal instructions and reports given by workers and record them as text data. This text data is then periodically sent to a server after undergoing preprocessing (such as text cleaning and tokenization).

[1523] Data Storage and Management

[1524] The server then receives the operation and message data sent from the device in real time and stores it in a secure database. To ensure data consistency and integrity, the server performs regular backups and restores the data when necessary.

[1525] Data Analysis Methods

[1526] The server analyzes the recorded operation data and calculates productivity indicators for each user (e.g., number of tasks completed, working time, work efficiency). Furthermore, it evaluates the contribution of each project and calculates the impact on the project's profits and progress.

[1527] Message data is analyzed using natural language processing algorithms, which evaluates cooperation by analyzing the sentiment of the message content. Sentiment analysis distinguishes between positive and negative communication and calculates a cooperation score.

[1528] Evaluation and visualization

[1529] The server combines the above indicators of productivity, creativity, business contribution, and cooperativeness to generate an overall evaluation score for each user. Based on this score, the evaluation results are visualized as graphs and charts and displayed on a dashboard. Users can log in to the dashboard to check their evaluation results and receive feedback based on them.

[1530] Specific examples

[1531] For example, if a factory worker is assembling a product:

[1532] The smart glasses record workers' eye movements and work procedures in detail.

[1533] Verbal instructions and reports given by workers are collected using a voice recognition function and converted into text data.

[1534] The server receives and analyzes this data in real time and evaluates it based on work efficiency and cooperation.

[1535] The evaluation results and feedback are displayed in real time on the smart glasses display.

[1536] Examples of prompt statements

[1537] Enter the following prompt for the generative AI model:

[1538] Operation data: A worker is assembling product A. Part number 123 is being assembled, and eye movement is normal and there are no problems with the work procedure.

[1539] Message data: Assembly complete.

[1540] The above is an embodiment of the present invention, which makes it possible to comprehensively evaluate work efficiency and cooperation in a factory and provide feedback for improvement.

[1541] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1542] Step 1:

[1543] The terminal collects the worker's operation data. The input is real-time data such as eye movements and work procedures collected by the smart glasses using cameras and sensors. This data is temporarily stored on the device. The output is compressed and encrypted operation data.

[1544] Step 2:

[1545] The terminal collects message data from workers. The input is verbal instructions and reports from workers obtained using a voice recognition function. The voice data is converted into text data, which is preprocessed (text cleaning and tokenization) and temporarily stored. The output is the preprocessed text data.

[1546] Step 3:

[1547] The terminal periodically collects operation data and message data and sends them to the server. The input is the data collected and preprocessed in steps 1 and 2. The data is sent to the server in real time. The output is the data sent to the server in real time.

[1548] Step 4:

[1549] The server stores the data it receives in a database. The input is the operation data and message data sent from the terminal. This data is securely stored in the database and is backed up regularly to ensure consistency and completeness. The output is the data securely stored in the database.

[1550] Step 5:

[1551] The server analyzes the operation data. The input is the saved operation data, and by analyzing this data, it calculates productivity indicators for each user (e.g., number of tasks completed, work time, work efficiency, etc.). The output is the productivity indicators for each user.

[1552] Step 6:

[1553] The server analyzes the message data using a natural language processing algorithm. The input is the stored message data. This data is used to analyze the message content and sentiment, and calculate an agreeableness score. The output is an agreeableness score.

[1554] Step 7:

[1555] The server combines the productivity index and cooperativeness score to generate an overall evaluation score for each user. The inputs are the productivity index and cooperativeness score obtained in steps 5 and 6. These are combined to calculate the overall evaluation score. The output is the overall evaluation score.

[1556] Step 8:

[1557] The server visualizes the overall evaluation score and displays it on a dashboard. The input is the overall evaluation score calculated in step 7. This is visually represented as a graph or chart and displayed on the dashboard so that the user can check it. The output is a dashboard showing the evaluation results.

[1558] Step 9:

[1559] The server assists in creating prompt sentences to be input to the generated AI model. The input is operation data and message data. Based on this, a prompt sentence is generated and input to the AI ​​model. As a specific example, the following prompt sentence is generated: "Operation data: Worker is assembling product A. Part number 123 is assembled, eye movement is normal, no problems with the work procedure. Message data: Assembly completed." The output is the generated prompt sentence.

[1560] 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.

[1561] The system of the present invention evaluates users' productivity, creativity, business contribution, and cooperativeness by collecting and analyzing operation data and message data during user work. Furthermore, by combining it with an emotion engine that recognizes users' emotions, the accuracy of the evaluation and the quality of the feedback are improved.

[1562] Explanation of program processing

[1563] In the system of the present invention, the following processing is performed.

[1564] Data collection

[1565] 1. Collecting Operational Data

[1566] The device monitors the user's work activities in real time and records each operation event (launching an application, accessing a file, browsing a web page, creating or editing a document, etc.).

[1567] The terminal collects this operational data at regular intervals, compresses it, and sends it to the server in encrypted form.

[1568] 2. Message Data Collection

[1569] The device records the content, time of sending, and recipient of messages sent and received via the user's internal chat tool, email, etc.

[1570] The device preprocesses the collected message data (text cleaning, tokenization, etc.) and periodically sends it to the server.

[1571] Data storage and management

[1572] 3. Data storage

[1573] The server receives the operation data and message data sent from the terminal in real time and stores them in a secure database.

[1574] The server performs regular backups to ensure data consistency and integrity, and restores data when necessary.

[1575] Data analysis

[1576] 4. Analysis of Operational Data

[1577] The server analyzes the recorded operation data and calculates productivity indicators for each user (e.g., number of tasks processed, work time, work efficiency).

[1578] The server evaluates the contribution of each project and calculates the impact on the project's profits and progress.

[1579] 5. Message Data Analysis

[1580] The server analyzes the message data using natural language processing algorithms, including analyzing the sentiment of the text, to extract data to assess the user's agreeableness.

[1581] 6. Use of Emotion Engine

[1582] The server uses an emotion engine to recognize the user's emotions from the user's message data and operation data during work.

[1583] The emotion engine identifies positive and negative emotions and calculates emotional indicators such as agreeableness and stress level.

[1584] Evaluation and visualization

[1585] 7. Calculation of evaluation score

[1586] The server integrates the data on productivity, creativity, business contribution, cooperativeness, and emotional indicators mentioned above to generate an overall evaluation score for each user.

[1587] The server visualizes the evaluation results based on this score as graphs and charts and displays them on a dashboard.

[1588] 8. Providing Feedback

[1589] Users access a dashboard to view their assessment results along with feedback based on sentiment analysis, including areas for improvement in stress management and team communication.

[1590] Specific examples

[1591] For example, if Employee A handles multiple tasks during work and simultaneously communicates with team members using an internal chat tool:

[1592] The terminal sequentially records detailed operation data while employee A is working and periodically transmits it to the server.

[1593] The terminal preprocesses the contents of the internal chat messages and sends them to the server.

[1594] The server analyzes the operation data and calculates employee A's productivity index.

[1595] The server analyzes the message data using natural language processing algorithms to evaluate cooperation and quality of communication.

[1596] The server uses an emotion engine to analyze employee A's emotional state from the message content and operation data, and generates an emotion index.

[1597] The server aggregates all the data and displays an overall rating score and sentiment-based feedback on a dashboard.

[1598] User Employee A accesses the dashboard to check his / her own evaluation and feedback and understand the areas for improvement that need to be made.

[1599] In this way, the system of the present invention combines emotion engines to achieve fair and multifaceted evaluation that takes into account the user's emotional state.

[1600] The processing flow will be explained below.

[1601] Step 1:

[1602] The device monitors user operations in real time while working and records each operation event (launching an application, accessing a file, browsing a web page, creating or editing a document, etc.).

[1603] Step 2:

[1604] The device collects the recorded operation data at regular intervals and compresses it to reduce the data volume. The compressed operation data is temporarily stored on the device.

[1605] Step 3:

[1606] The device encrypts the compressed operation data and sends it to the server after ensuring security. Transmission is performed during off-peak hours to minimize network load.

[1607] Step 4:

[1608] The device collects data from users' internal chat tools and emails, and preprocesses it, including metadata such as message content, sending time, and recipients. Preprocessing includes text cleaning and tokenization.

[1609] Step 5:

[1610] The terminal compresses and encrypts the preprocessed message data and transmits it to the server in the same manner as the operation data.

[1611] Step 6:

[1612] The server receives operation data and message data sent from the device in real time and stores them in a secure database. The stored data undergoes a backup process to ensure data consistency and integrity.

[1613] Step 7:

[1614] The server analyzes the recorded operation data and calculates productivity indicators for each user (e.g., number of tasks completed, work time, work efficiency). Statistical analysis of the data and machine learning algorithms are used for the analysis.

[1615] Step 8:

[1616] The server calculates the user's operational data and their impact on the progress and profits of the project to assess their contribution to each project, taking into account the number of tasks completed and the quality of deliverables related to a particular project.

[1617] Step 9:

[1618] The server analyzes the message data using natural language processing algorithms, including text cleansing, tokenization, and grammar analysis, to classify the sentiment of the message.

[1619] Step 10:

[1620] The server uses a sentiment engine to analyze the text extracted from the message data and calculate a positive, negative, or neutral sentiment score, as well as analyze long-term sentiment trends.

[1621] Step 11:

[1622] The server reflects the emotion score obtained by the emotion engine in the evaluation of the user's agreeableness, comparing the frequency of positive messages with the frequency of negative messages, and updates the user's agreeableness score.

[1623] Step 12:

[1624] The server then combines the data on productivity, creativity, business contribution, collaboration, and emotional indicators obtained above to generate an overall evaluation score for each user, calculated based on a weighted combination of each indicator.

[1625] Step 13:

[1626] The server generates graphs and charts to visually display the overall evaluation score, and displays them on the dashboard, allowing users to check their own evaluation results at a glance.

[1627] Step 14:

[1628] Users access a dashboard to view their assessment results, which includes personalized feedback along with their assessment scores, allowing users to recognize strengths and areas for improvement.

[1629] Step 15:

[1630] The server continuously collects and analyzes data and periodically updates the evaluation results, allowing users to be evaluated on their work performance in real time and provide appropriate feedback.

[1631] By combining this flow with an emotion engine, the system of the present invention achieves a multifaceted and fair evaluation that reflects the user's emotional state.

[1632] Example 2

[1633] 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."

[1634] In modern work environments, there is a demand for accurate evaluation of users' productivity, cooperativeness, and even their emotional state. However, conventional systems only collect general operation data and message data, making it difficult to perform detailed evaluations that take into account the user's emotional state. Furthermore, there are insufficient means to visualize the results of user evaluations in an intuitive manner. This results in a lack of effective feedback and prevents work improvements.

[1635] 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.

[1636] In this invention, the server includes a means for recording user operation data during work, a means for collecting user message data, a means for analyzing the recorded operation data and the collected message data to evaluate the user's productivity, creativity, business contribution, and cooperativeness, a means for recognizing the user's emotions and reflecting them in the evaluation results, and a means for visualizing the evaluation results. This enables a fair and multifaceted evaluation that takes the user's emotional state into consideration, and makes it possible to visualize the results in an intuitive manner and provide effective feedback.

[1637] "User operation data during work" refers to information about a series of operations that occur when a user performs work (launching and using applications, accessing files, viewing web pages, creating and editing documents, etc.).

[1638] "Message data" refers to text messages sent and received by users using internal chat tools or email, as well as related metadata such as the time of sending and recipient information.

[1639] "Productivity" refers to an index for evaluating the results a user has achieved in work within a certain period of time, the amount of tasks processed, and the efficiency of the time required for these tasks.

[1640] "Creativity" refers to an index used to evaluate users' ability to propose and implement new ideas, improvements, and original solutions.

[1641] "Business contribution" refers to an index used to evaluate the degree of contribution a user has made to a specific project or to the overall business.

[1642] "Collaboration" refers to an index used to evaluate a user's ability to smoothly communicate and cooperate with their team and other members.

[1643] "Means for recognizing emotions and reflecting them in the evaluation results" refers to algorithms and processes that recognize the user's emotional state (positive or negative emotions, etc.) from message data and operational data during work, and reflect that emotional information in the evaluation results.

[1644] "Means for visualizing evaluation results" refers to means for providing evaluation results such as user productivity, creativity, business contribution, cooperativeness, and emotional state in the form of visual displays such as graphs, charts, and dashboards.

[1645] "Natural language processing algorithm" refers to a set of processes and techniques that enable computer programs to understand, analyze, and process human natural language.

[1646] The system of the present invention evaluates users' productivity, creativity, business contribution, and cooperativeness by collecting and analyzing operation data and message data during user work. In addition, by combining it with an emotion engine that recognizes users' emotions, the accuracy of the evaluation and the quality of the feedback are improved.

[1647] The system uses the following hardware and software.

[1648] Hardware

[1649] Terminal: A device that collects user operation data and message data.

[1650] Server: A central control device that receives, stores, and analyzes data.

[1651] Emotion Engine: A specific device for recognizing a user's emotional state

[1652] software

[1653] Data collection program: Runs on the terminal and collects operation data and message data.

[1654] Encryption and compression programs: Encrypt and compress data

[1655] Natural Language Processing (NLP) algorithms: Analyze message data and extract agreeableness and emotional state

[1656] Data analysis program: Analyzes operational data to measure productivity, creativity, and business contribution

[1657] Visualization program: Visually displays evaluation results in graphs and charts

[1658] Data collection

[1659] The device monitors users' work activities in real time and records each operation event (e.g., launching an application, accessing a file, viewing a web page, creating or editing a document). The device also records the content, time of sending, and recipient of messages sent and received via internal chat tools and email. The recorded data is compressed, encrypted, and sent to a server at regular intervals.

[1660] Data storage and management

[1661] The server receives the operational and message data sent by the devices and stores it in a secure database that is regularly backed up and can be restored if necessary.

[1662] Data analysis

[1663] The server analyzes the recorded operation data and calculates productivity indicators for each user (number of tasks completed, work time, work efficiency). It also evaluates contribution to each project and measures the impact on the entire project. Message data is analyzed using a natural language processing algorithm to evaluate cooperation and emotional state. The results of this analysis are input into an emotion engine to identify the user's emotional state (e.g., positive, negative).

[1664] Evaluation and visualization

[1665] The server integrates the analysis results and generates an overall evaluation score based on the user's productivity, creativity, business contribution, collaborative ability, and emotional state. The evaluation results are displayed on a dashboard as graphs and charts to visualize them. Users access the dashboard and check the feedback provided along with the evaluation results. This feedback includes areas for improvement in stress management and team communication.

[1666] Specific examples

[1667] For example, if Employee A handles multiple tasks while simultaneously communicating with team members using an internal chat tool, the device will record detailed operational data of Employee A during work and periodically send it to the server. The content of the internal chat messages will also be preprocessed and sent to the server. The server will analyze this data and evaluate Employee A's productivity index, cooperativeness, and emotional state. Finally, the overall evaluation score and feedback will be displayed on a dashboard that Employee A can access and check.

[1668] For example, the following prompt sentence is fed into the generative AI model:

[1669] "Please generate a performance evaluation report for the last month. Specifically, please include feedback on work efficiency and productivity from operation data, collaboration from message data, and emotion indicators from the emotion engine."

[1670] This prompt is designed to generate a detailed and comprehensive performance evaluation report.

[1671] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1672] Step 1:

[1673] Operational Data Collection

[1674] The terminal monitors the user's work operations in real time and captures user operation events (launching applications, accessing files, viewing web pages, creating and editing documents, etc.) as input.

[1675] Specifically, the terminal generates a log file and records each operation with a timestamp.

[1676] As an output, the data of these operation events is temporarily stored.

[1677] Step 2:

[1678] Sending and storing operational data

[1679] The terminal collects the operation data at regular intervals and compresses and encrypts the operation event data temporarily stored as input.

[1680] Specifically, the terminal applies a data compression algorithm and then an encryption algorithm.

[1681] The compressed and encrypted data is output and sent to the server.

[1682] The server extracts the received data and stores it in a secure database.

[1683] Step 3:

[1684] Message Data Collection

[1685] The device collects message data from the user's internal chat tool and email, and takes as input the text message and its metadata (such as the time of sending and the recipient).

[1686] Specifically, the device preprocesses the message data (cleaning the text, tokenizing it) and converts it into a format that is easy to analyze.

[1687] As output, it generates preprocessed message data and sends it to the server.

[1688] Step 4:

[1689] Sending and storing message data

[1690] The terminal periodically transmits the pre-processed message data to the server.

[1691] The server extracts the received data and stores it in a secure database.

[1692] The output is the message data stored on the server.

[1693] Step 5:

[1694] Analysis of operational data

[1695] The server takes operational data from the operational database as input and applies data analysis algorithms.

[1696] Specific operations include calculating the number of tasks processed per unit time, average work time, and frequency of each operation.

[1697] As output, productivity indicators for each user (e.g., number of tasks completed, work time, work efficiency) are generated.

[1698] Step 6:

[1699] Parsing message data

[1700] The server takes message data from a message database as input and applies natural language processing algorithms.

[1701] Specifically, the system performs sentiment analysis on the text, extracts positive and negative expressions, and uses them to evaluate cooperation.

[1702] As output, it produces an agreement index and emotional state extracted from the message data.

[1703] Step 7:

[1704] Using the Emotion Engine

[1705] The server provides message data and operation data as input to the emotion engine to recognize the emotional state.

[1706] Specifically, the emotion engine distinguishes between positive and negative emotions and calculates emotional indicators such as stress level and cooperativeness.

[1707] As output, it generates the emotional state identification result and the emotional index.

[1708] Step 8:

[1709] Calculation and visualization of evaluation scores

[1710] The server integrates the productivity index, cooperativeness index, and emotional index to calculate an overall evaluation score.

[1711] Specifically, each indicator is weighted, an integrated calculation is performed, and the data is converted into a visually easy-to-understand format.

[1712] As output, an overall evaluation score and graphs and charts of the evaluation results are generated and displayed on a dashboard.

[1713] Step 9:

[1714] Providing feedback

[1715] Users access the dashboard to view their assessment results and feedback.

[1716] Specifically, the user views the evaluation results and receives specific advice on areas for improvement such as stress management and team communication.

[1717] As an output, information is provided for the user to determine self-improvement actions.

[1718] In this way, specific operations are performed at each processing step, and final evaluation and feedback are provided through data processing and calculations based on the input data.

[1719] (Application example 2)

[1720] 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."

[1721] Collaborative robots (cobots) are becoming increasingly common in modern factories, but there is a lack of accurate ways to monitor and evaluate their productivity and cooperation. Furthermore, there is no established method for utilizing generative AI models to optimize robot behavior. This makes efficient production management and appropriate feedback difficult.

[1722] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for recording operation data of a user during work; means for collecting user message data; means for analyzing the recorded operation data and collected message data and evaluating the user's productivity, creativity, business contribution, and cooperativeness; means for visualizing the evaluation results; means for collecting operation data and communication data of operating devices in a factory and analyzing the productivity and cooperativeness of a collaborative robot; and means for inputting the analysis results into a generative AI model and generating prompt sentences that optimize the operation of the collaborative robot. This makes it possible to accurately monitor, evaluate, and optimize the productivity and cooperativeness of a collaborative robot.

[1723] "User's operation data during work" is information about all operations generated when a user performs work.

[1724] "Message data" refers to information about the content, time of sending, and recipient of messages sent or received by users inside or outside the company.

[1725] "Productivity" is an index that quantifies the efficiency and effectiveness of a user's work.

[1726] "Creativity" is the ability of users to generate new ideas and solutions in their work.

[1727] "Business contribution" is an index that shows how much a user's work contributes to the goals and profits of the entire organization.

[1728] "Collaborative ability" is the ability to show how effectively a user can cooperate with other members.

[1729] "Evaluation results" are the results and data obtained by evaluating productivity, creativity, business contribution, and cooperation.

[1730] "Visualization" is the process of presenting evaluation results and data in visual formats such as graphs and charts.

[1731] "Operation data of operating equipment in the factory" is detailed information about the operation of equipment and robots used in the factory.

[1732] "Communication data" refers to information about all communications, such as voice commands and visual signals, that take place within the factory.

[1733] A "generative AI model" is an artificial intelligence model that analyzes the current situation based on collected data and generates instructions and prompts to achieve optimal behavior.

[1734] A "prompt sentence" is an instruction sentence created by a generative AI model based on the analysis results to optimize the behavior of a collaborative robot.

[1735] This invention is a system that collects operation data and message data from users during work, analyzes this data to evaluate their productivity, creativity, business contribution, and cooperativeness, and visualizes the evaluation results. It also collects operation data and communication data from operating devices in factories, analyzes the productivity and cooperativeness of collaborative robots (cobots), and generates prompts that achieve optimal operation based on a generative AI model.

[1736] Program processing explanation

[1737] The server uses a means for recording user operation data during work to monitor and record in real time operation events (e.g., application startup, file access, document creation / editing, etc.) in the user's work as a log. It also uses a means for collecting message data to acquire message data sent and received by users inside and outside the company, and preprocesses this (text cleaning, tokenization, etc.) in preparation for analysis.

[1738] The server encrypts operational and message data before transmitting and storing it in a secure database, ensuring data consistency and integrity, while also performing regular backups and restoring data as needed.

[1739] The data is analyzed using machine learning algorithms (e.g., Scikit-learn) and natural language processing algorithms (e.g., NLTK or spaCy), and productivity indicators (e.g., number of tasks completed, work time, and work efficiency) are calculated from the recorded operation data. Message data is also used to evaluate the user's cooperativeness, and an emotion engine is used to calculate emotion indicators. The obtained data is integrated to calculate an overall evaluation score, which is then displayed as graphs or charts using a visualization tool.

[1740] In addition, the system collects operational and communication data from cobots in factories, analyzes this data to evaluate the cobots' productivity and cooperation, and inputs the analysis results into a generative AI model to generate prompts and optimize the cobots' behavior.

[1741] Specific examples

[1742] For example, consider a situation where collaborative robot A receives instructions from a human worker via voice commands when performing the task of picking up a part and placing it in a designated location in a factory. At this time, the server collects all of robot A's operation logs and communication data and stores them in a database. Using machine learning algorithms and natural language processing algorithms, robot A's productivity and cooperativeness are analyzed, and based on the results, a generative AI model generates prompt sentences to optimize robot A's behavior.

[1743] An example of the prompt statement it generates is:

[1744] Cobot A reports the current task progress. Retrieve the latest number of completed tasks and working time from the operation log to calculate the productivity index. Furthermore, analyze the voice commands received from the latest message log to evaluate the cooperativeness index.

[1745] In this way, the system of the present invention is able to accurately monitor, evaluate, and optimize the productivity and cooperation of users and collaborative robots.

[1746] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1747] Step 1:

[1748] The terminal collects operational data of the user in real time while he or she is working. Specifically, it monitors operational events such as application launches, file accesses, and document creation and editing, and records each event in log format. The input is the user's operational events, and the output is the recorded operation log. This data is compressed and encrypted at regular intervals and sent to the server.

[1749] Step 2:

[1750] The device collects the user's message data. Specifically, it records the content, sending time, and recipient of messages sent and received via internal chat tools, email, etc. The collected data is preprocessed (text cleaning, tokenization, etc.) and periodically sent to the server. The input is the user's message data, and the output is the preprocessed message data.

[1751] Step 3:

[1752] The server stores the received operational and message data in a secure database. The database has a means of maintaining consistency and integrity, and is backed up regularly. The input is the encrypted operational and message data, and the output is the stored data.

[1753] Step 4:

[1754] The server analyzes the recorded operation data. Specifically, it uses a machine learning algorithm (e.g., Scikit-learn) to calculate productivity indicators (e.g., number of tasks processed, work time, and work efficiency). The input is the stored operation data, and the output is the calculated productivity indicators.

[1755] Step 5:

[1756] The server analyzes the message data using a natural language processing algorithm (e.g., NLTK or spaCy) to calculate agreeableness and sentiment indexes. It uses a sentiment engine to identify positive and negative sentiments and evaluate agreeableness and stress levels. The input is the preprocessed message data, and the output is agreeableness and sentiment indexes.

[1757] Step 6:

[1758] The server aggregates all data and generates an overall evaluation score for each user. This score is calculated based on productivity, creativity, business contribution, cooperativeness, and emotional indicators. The inputs are productivity indicators, cooperativeness data, and emotional data, and the output is the overall evaluation score.

[1759] Step 7:

[1760] The server displays the evaluation results using a visualization tool. Specifically, productivity, collaboration, emotional indicators, and overall evaluation scores are visually displayed in graph and chart format on a dashboard. The input is the overall evaluation score and related data, and the output is the visualized evaluation results.

[1761] Step 8:

[1762] The terminal collects operation and communication data from collaborative robots in the factory. Specifically, it records each robot operation event (e.g., part pickup and placement, movement path, machine operation) as a log. It also collects instructions from human workers and communications with other robots. The input is the collaborative robot's operation events and communication data, and the output is the recorded operation and communication data.

[1763] Step 9:

[1764] The server analyzes the operation data and communication data of the collaborative robots. From the analyzed data, it calculates indicators to evaluate the robots' productivity and cooperativeness. The input is the collected operation data and communication data, and the output is the evaluation indicators.

[1765] Step 10:

[1766] The server inputs the analysis results using the generative AI model and generates prompt sentences to optimize the behavior of the collaborative robot. The inputs are the evaluation index and the generative AI model, and the output is the optimized prompt sentence.

[1767] Specific prompt examples:

[1768] Cobot A reports the current task progress. Retrieve the latest number of completed tasks and working time from the operation log to calculate the productivity index. Furthermore, analyze the voice commands received from the latest message log to evaluate the cooperativeness index.

[1769] In this way, by going through each processing step, a system is realized that accurately monitors and evaluates the productivity and cooperation of the user and the collaborative robot.

[1770] 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.

[1771] 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.

[1772] 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.

[1773] 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.

[1774] 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.

[1775] 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.

[1776] 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).

[1777] 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.

[1778] 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."

[1779] 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.

[1780] 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).

[1781] 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.

[1782] 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.

[1783] 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.

[1784] 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.

[1785] 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.

[1786] 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.

[1787] 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.

[1788] 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.

[1789] 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.

[1790] 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.

[1791] The following is further disclosed regarding the above embodiment.

[1792] (Claim 1)

[1793] A means for recording operation data during a user's work;

[1794] means for collecting user message data;

[1795] A means for analyzing the recorded operation data and the collected message data to evaluate the user's productivity, creativity, business contribution, and cooperativeness;

[1796] A means for visualizing the evaluation results;

[1797] A system including:

[1798] (Claim 2)

[1799] 2. The system according to claim 1, further comprising means for encrypting the recorded operation data, transmitting the encrypted data to a server, and storing the encrypted data.

[1800] (Claim 3)

[1801] 10. The system of claim 1, further comprising means for analyzing the collected message data with a natural language processing algorithm to evaluate the user's cooperativeness.

[1802] "Example 1"

[1803] (Claim 1)

[1804] A means for recording operation data during a user's work;

[1805] means for collecting user message data;

[1806] A means for analyzing the recorded operation data and the collected message data to evaluate the user's productivity, creativity, business contribution, and cooperativeness;

[1807] A means for visualizing the evaluation results;

[1808] A means for recording operation data in real time, compressing and encrypting it at regular intervals, and transmitting it;

[1809] means for preprocessing and periodically transmitting message data;

[1810] a means for generating and displaying a per-user rating score on a dashboard;

[1811] A means to provide feedback to users on areas for improvement and strengths, and

[1812] A system including:

[1813] (Claim 2)

[1814] 2. The system according to claim 1, further comprising means for encrypting the recorded operation data, transmitting the encrypted data to a server, and storing the encrypted data.

[1815] (Claim 3)

[1816] 10. The system of claim 1, further comprising means for analyzing the collected message data with a natural language processing algorithm to evaluate the user's cooperativeness.

[1817] "Application Example 1"

[1818] (Claim 1)

[1819] A means for recording operation data during a user's work;

[1820] means for collecting user message data;

[1821] A means for analyzing the recorded operation data and the collected message data to evaluate the user's productivity, creativity, business contribution, and cooperativeness;

[1822] A means for visualizing the evaluation results;

[1823] means for transmitting operational data to a server in real time;

[1824] means for preprocessing message data and recording content, time, and destination;

[1825] A means for the server to analyze the operation data and calculate productivity indicators such as work efficiency and work accuracy;

[1826] A server analyzes message data and evaluates the level of cooperation and quality of communication.

[1827] A means for assisting in the creation of prompt sentences to be input to the generative AI model;

[1828] A system including:

[1829] (Claim 2)

[1830] 2. The system according to claim 1, further comprising means for encrypting the recorded operation data, transmitting the encrypted data to a server, and storing the encrypted data.

[1831] (Claim 3)

[1832] 10. The system of claim 1, further comprising means for analyzing the collected message data with a natural language processing algorithm to evaluate the user's cooperativeness.

[1833] "Example 2: Combining Emotion Engines"

[1834] (Claim 1)

[1835] A means for recording operation data during a user's work;

[1836] means for collecting user message data;

[1837] A means for analyzing the recorded operation data and the collected message data to evaluate the user's productivity, creativity, business contribution, and cooperativeness;

[1838] A means for recognizing a user's emotion and reflecting it in the evaluation result;

[1839] A means for visualizing the evaluation results;

[1840] A system including:

[1841] (Claim 2)

[1842] 2. The system according to claim 1, further comprising means for compressing the recorded operation data at regular intervals, transmitting the data to a server in an encrypted format, and storing the data therein.

[1843] (Claim 3)

[1844] 10. The system of claim 1, further comprising means for analyzing the collected message data with a natural language processing algorithm to assess agreeableness and emotional state.

[1845] "Application example 2 when combining emotion engines"

[1846] (Claim 1)

[1847] A means for recording operation data during a user's work;

[1848] means for collecting user message data;

[1849] A means for analyzing the recorded operation data and the collected message data to evaluate the user's productivity, creativity, business contribution and cooperativeness;

[1850] A means for visualizing the evaluation results;

[1851] A means for collecting operation data and communication data of operating devices in a factory and analyzing the productivity and cooperation...

Claims

1. A means for recording operation data during a user's work; means for collecting user message data; A means for analyzing the recorded operation data and the collected message data to evaluate the user's productivity, creativity, business contribution, and cooperativeness; A means for visualizing the evaluation results; A system including:

2. 2. The system according to claim 1, further comprising means for encrypting the recorded operation data, transmitting the encrypted data to a server, and storing the encrypted data.

3. 2. The system of claim 1, further comprising means for analyzing the collected message data with a natural language processing algorithm to evaluate the user's cooperativeness.

Images