System

Abstract

A system is provided.SOLUTION: The system includes a means for collecting job data of each employee, a means for analyzing the collected job data and evaluating the job performance of the employee based on an evaluation index, a means for calculating an evaluation score for each employee based on the evaluation result, and a means for generating and notifying a detailed report of the evaluation score and evaluation contents.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 conventional employee evaluation systems, evaluations are often subjective by superiors, which can lead to unfairness, such as those who appeal more favorably, resulting in problems such as a decline in employee motivation and dissatisfaction with the evaluation. Furthermore, because the evaluation criteria are not clear, employees often do not feel satisfied with the evaluation results. There is a need to solve this problem. [Means for solving the problem]

[0005] This invention is an employee evaluation system that includes a means for collecting work data for each employee, a means for analyzing the collected work data and evaluating the work performance of employees based on evaluation indicators, a means for calculating an evaluation score for each employee based on the evaluation results, and a means for generating and notifying a detailed report of the evaluation score and evaluation content.The system also includes a means for analyzing the collected work data using natural language processing and machine learning techniques to determine the importance and contribution of work, and a means for using accuracy, efficiency, and creativity of work as evaluation criteria and setting evaluation weights based on these, thereby enabling fair and impartial employee evaluation.

[0006] "Business data" refers to all information related to the work that employees perform on a daily basis, including comments made in meetings, project progress, document creation, email content, etc.

[0007] "Means of collection" refers to devices and software used to acquire each employee's work data in real time or periodically and store it in the system.

[0008] "Means of analysis" refers to the algorithms and technologies used to process collected business data and interpret it as meaningful information, including natural language processing (NLP) and machine learning technologies.

[0009] "Evaluation indicators" refer to the standards or indicators used to objectively evaluate an employee's work performance, such as accuracy, efficiency, and creativity.

[0010] "Means of evaluation" refers to algorithms and technologies for quantifying employees' work performance based on evaluation indicators and expressing it as an evaluation score.

[0011] An "evaluation score" is a numerical value that comprehensively represents an employee's work performance and is calculated based on collected work data and evaluation indicators.

[0012] "Means for generating reports" refers to software or technology used to document and provide assessment scores and details to employees and supervisors.

[0013] "Means of notification" refers to technologies such as email systems and portal sites that transmit generated reports to relevant parties at the appropriate time. [Brief explanation of the drawings]

[0014] [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

[0015] 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.

[0016] First, the terms used in the following description will be explained.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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."

[0035] As a form for implementing the invention, this system performs a series of processes: collects work data for each employee, analyzes the collected data, evaluates work performance based on evaluation indicators, calculates an evaluation score for each employee based on the results, and generates and notifies a detailed report of the evaluation content.

[0036] Explanation of program processing

[0037] Business data collection

[0038] The server collects in real time audio data and comments from meetings attended by employees, email content, data from project management tools, etc. For example, audio data and operation logs are sent to the server via the microphones and logs of devices (PCs and smartphones) used during meetings.

[0039] Data analysis and evaluation

[0040] The server analyzes the collected data using natural language processing (NLP) and machine learning technologies. Specifically, it converts the audio data from meetings into text and analyzes the content and context of what is being said. It also analyzes email content and project progress data in the same way, categorizing each person's contribution to the task and their importance as evaluation indicators. In this process, it assigns scores based on fixed evaluation criteria (such as accuracy, efficiency, and creativity of the task).

[0041] Calculation of evaluation score

[0042] The server calculates an evaluation score for each employee based on the analysis results. For example, if an employee speaks in a meeting and their comments contribute significantly to the progress of a project, that comment will be given a high score. Other factors that contribute to the score include the number of completed project tasks and the efficiency of email exchanges.

[0043] Report generation and notification

[0044] The server generates an evaluation report for each employee based on the calculated evaluation score and detailed evaluation content. This report includes detailed evaluations and feedback for each task, as well as areas for improvement for the employee. The generated report is notified to relevant parties by email and is also uploaded to an employee-only portal site.

[0045] Specific examples

[0046] For example, suppose employee A has achieved results in an important project. All comments made in meetings using devices (PCs or smartphones) and task completion data recorded in the project management tool are collected on a server. The collected voice data is converted into text and analyzed using natural language processing. If it turns out that these comments made in the meeting contributed significantly to the success of the project, employee A's evaluation score will be high.

[0047] If Employee B proposes a new idea for improving work efficiency by email and the proposal has a positive impact on the company as a whole, the server analyzes the email content and reflects it in the evaluation score.Finally, the server generates an evaluation report for Employees A and B and notifies the HR department and their superiors.This report includes specific evaluation details as well as areas for improvement and additional feedback.

[0048] As described above, the present invention ensures transparency and fairness in evaluations by collecting detailed and fair employee work data and conducting multifaceted evaluations.

[0049] The processing flow will be explained below.

[0050] Step 1: Collect business data

[0051] The devices collect data on the daily work of each employee. For example, speech during meetings is recorded through a microphone, and work-related email data sent and received from the email server is also collected. The collected data is sent to the server in real time.

[0052] Step 2: Save your data

[0053] The server temporarily stores the business data received from the terminal in a buffer, then transfers it to the database and stores it in the appropriate format. This storage process is necessary to prevent data loss and facilitate subsequent analysis.

[0054] Step 3: Preprocessing the data

[0055] The server preprocesses the stored data: voice data is converted to text using a speech recognition engine; email data is processed using natural language processing (NLP) techniques to extract important keywords and phrases; and project management data is extracted to identify the progress and completion status of each task.

[0056] Step 4: Analyze the evaluation metrics

[0057] The server then analyzes the preprocessed data according to evaluation criteria. For example, it analyzes the context of comments made in meetings and evaluates how much those comments contributed to the progress of the project. Other evaluation criteria include the quality of submitted ideas and documents, the content of emails, and the speed of responses.

[0058] Step 5: Scoring and evaluation

[0059] The server calculates an evaluation score for each employee based on the analysis results. For example, it sets evaluation weights for each job based on evaluation criteria such as accuracy, efficiency, and creativity, and calculates an overall score. This score is saved in a database and used to generate reports, which will be described later.

[0060] Step 6: Generate reports

[0061] The server generates an evaluation report for each employee based on the evaluation score and detailed evaluation content. This report includes the evaluation content of each job, a score breakdown, areas for improvement, and feedback. The generated report is prepared in a format suitable for the HR department or supervisor.

[0062] Step 7: Notification and Delivery

[0063] The server notifies the automatically generated evaluation report to the user (supervisor or HR department) by email, and also uploads the report to an employee-only portal site so that employees can check their own evaluations at any time.

[0064] This is the specific process flow of an employee evaluation system that utilizes AI. This enables fair and impartial evaluations, which improves employee motivation and provides evaluations that employees can be satisfied with.

[0065] Example 1

[0066] 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."

[0067] When evaluating employee performance, traditional evaluation systems tend to rely on subjective judgment and often lack fairness and transparency. Furthermore, because they only collect a portion of work data, it is difficult to accurately evaluate an employee's overall performance. Furthermore, the lack of feedback on evaluation results means that they are unable to provide guidance for employee growth or work improvement.

[0068] 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.

[0069] In this invention, the server includes means for collecting employee work data in real time, means for appropriately structuring the collected work data and converting it into an analyzable format, means for analyzing the preprocessed data using natural language processing and machine learning techniques, means for calculating an evaluation score for each employee based on the analysis results, and means for generating and notifying a report based on the evaluation score and detailed evaluation content. This enables detailed and fair evaluation of employee work performance, ensuring transparency and fairness.

[0070] "Business data" refers to information about the work that employees perform on a daily basis, including audio data from meetings, statements, email content, and data from project management tools.

[0071] "Real-time" refers to data being collected or processed immediately as it is generated, with little or no time delay.

[0072] "Structuring" refers to organizing and converting raw data into a table format, database format, or other format that makes it easier to analyze and process.

[0073] "Natural language processing (NLP)" is a technology that uses computers to analyze human language, and includes topic modeling and sentiment analysis of text data.

[0074] "Machine learning" is a technology that allows computers to use data to learn patterns and automatically perform tasks such as prediction and classification.

[0075] An "evaluation score" is a numerical representation of an employee's work performance, calculated based on specific evaluation criteria.

[0076] A "report" refers to a document or electronic data that compiles information such as evaluation scores, detailed evaluation content, feedback, and areas for improvement.

[0077] "Notification" refers to informing relevant parties of the evaluation results and reports, and includes means such as email or uploading to a portal site.

[0078] "Automatic speech recognition (ASR)" is a technology that converts voice data into text data.

[0079] "Topic modeling" is a technology that automatically extracts hidden topics (themes) from large amounts of text data.

[0080] "Sentiment analysis" is a technique that analyzes emotions and opinions within text data and determines whether they are positive, negative, or neutral.

[0081] "Accuracy" is an evaluation criterion that indicates how error-free a task is being performed.

[0082] "Efficiency" is an evaluation criterion that indicates how efficiently work is being carried out.

[0083] "Creativity" is a measure of the ability to provide new ideas and innovative solutions in the workplace.

[0084] The following description is provided as an embodiment of the present invention: The system is realized through the cooperation of a server, a terminal, and a user, each of which plays a specific role.

[0085] Business data collection

[0086] The server collects employees' work data in real time. Specifically, meeting audio data, comments, email content, and project management tool data are automatically sent to the server from the devices used by employees (PCs and smartphones). For example, what an employee says during an online meeting is collected as audio data using the device's microphone and immediately sent to the server.

[0087] Data Preprocessing

[0088] The server structures the collected business data and converts it into an analyzable format. Voice data is converted into text using automatic speech recognition (ASR) technology, and email content is tokenized. Data obtained from project management tools is also converted into a unified format, allowing for centralized management and easier analysis.

[0089] Analyzing the data

[0090] The server then analyzes the preprocessed data using natural language processing (NLP) and machine learning techniques. Specifically, it performs topic modeling and sentiment analysis on the text data to analyze the content and context of comments. For example, it determines the extent to which comments made during a meeting contribute to the progress of a project. In this process, it classifies the data based on evaluation criteria such as work accuracy, efficiency, and creativity, and generates a score.

[0091] Calculation of evaluation score

[0092] The server calculates an evaluation score for each employee based on the results of the data analysis. For example, if an employee's comments in a meeting significantly contribute to the progress of a project, a high score will be given based on the analysis of the content of those comments. The score also reflects the number of tasks completed in the project management tool and the efficiency of email exchanges.

[0093] Report generation and notification

[0094] The server generates an evaluation report for each employee based on the evaluation score and detailed evaluation content. This report includes specific evaluation details, feedback, and areas for improvement. The generated report is notified to the terminal by email and is also uploaded to an employee-only portal site.

[0095] Examples of concrete examples and prompts

[0096] For example, if employee A participates in a Zoom meeting and makes an important comment during the meeting, the device (PC or smartphone) collects the audio data and sends it to the server. The server then converts this audio data into text using automatic speech recognition technology and analyzes it using natural language processing. If the analysis determines that employee A's comments contributed to the project's success, a high evaluation score is calculated. Similarly, if employee B proposes a new idea for improving work efficiency via email and the content of that proposal has a positive impact on the entire company, the server analyzes the content of that email and reflects it in the evaluation score. Finally, the server generates an evaluation report, notifies the human resources department and superiors via email, and uploads it to a dedicated portal site.

[0097] An example of a prompt sentence might be:

[0098] "Please tell me a specific method for converting what Employee A said during a Zoom meeting into text, analyzing the context, and evaluating his / her contribution to the project."

[0099] "Employee B proposed an idea for improving work efficiency via email. Please explain in detail how the contents of this email can be automatically analyzed and reflected in the evaluation score."

[0100] The above explanation shows how this system collects, pre-processes, analyzes, evaluates, and generates reports to provide a detailed and fair evaluation of employees' work performance, ensuring transparency and fairness and promoting employee growth.

[0101] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0102] Step 1:

[0103] The server collects employee work data in real time.

[0104] Input: Voice data, email data, project management tool data, etc. sent from devices used by employees

[0105] Specific operation: The device (PC or smartphone) captures audio data during the meeting through a microphone and sends it to the server. It also captures task completion information from the project management tool and email content as appropriate and sends them to the server.

[0106] Output: Business data aggregated on the server

[0107] Step 2:

[0108] The server preprocesses and structures the collected business data.

[0109] Input: Raw data collected on the server (voice data, email data, project management tool data, etc.)

[0110] Specific operation: Voice data is converted to text data using automatic speech recognition (ASR), email content is structured by a tokenization server, and data from project management tools is also converted into a unified format.

[0111] Output: Structured data

[0112] Step 3:

[0113] The server analyzes the structured data using natural language processing (NLP) and machine learning techniques.

[0114] Input: Preprocessed structured data (text data, email data, project management data, etc.)

[0115] Specific operations: Topic modeling and sentiment analysis are performed on text data to analyze its context and content, and the data is then classified and scored based on evaluation criteria for operational accuracy, efficiency, and creativity.

[0116] Output: Scored evaluation data

[0117] Step 4:

[0118] The server calculates an evaluation score for each employee based on the results of the data analysis.

[0119] Input: Scored assessment data

[0120] Specific operation: Comprehensively evaluate individual evaluations (for example, contributions made in meetings, number of completed tasks, etc.) and calculate an overall evaluation score for each employee.

[0121] Output: Evaluation score for each employee

[0122] Step 5:

[0123] The server generates and notifies an evaluation report based on the evaluation score and detailed evaluation content.

[0124] Input: Evaluation score and detailed evaluation content for each employee

[0125] Specific operation: A report is generated based on the evaluation results. This report includes detailed evaluations, feedback, and areas for improvement for each task. The generated report is notified by email and also uploaded to the employee-only portal site.

[0126] Output: Notified evaluation report

[0127] By following the above steps, the system can provide a detailed and fair evaluation of employees' work performance, ensuring transparency and fairness.

[0128] (Application example 1)

[0129] 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."

[0130] It is necessary to collect and analyze not only employee work data but also activity data from the work machines in the factory and conduct comprehensive evaluations to improve production efficiency and ensure transparency and fairness in evaluations. It is also considered necessary to take measures to consistently monitor and evaluate the performance of employees and work machines.

[0131] 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.

[0132] In this invention, the server includes means for collecting work data for each employee and activity data for each work machine, means for analyzing the collected work data and activity data and evaluating the performance of employees and work machines based on evaluation indices, means for calculating evaluation scores for each employee and work machine based on the evaluation results, and means for generating and notifying detailed reports of the evaluation scores and evaluation contents. This makes it possible to comprehensively evaluate and improve the performance of employees and work machines, and to increase production efficiency and the transparency and fairness of evaluations.

[0133] "Business data" refers to information related to the work performed by employees, including meeting audio, statements, email content, project management tool data, and the like.

[0134] "Work machines" are automated machines and robots used to carry out production work in factories.

[0135] "Activity data" refers to data related to the activity of a machine, such as the work performed by the machine, its operating status, the occurrence of errors, and the results of quality checks.

[0136] The "server" is an information processing device that collects and analyzes data, calculates evaluation scores, and generates and notifies reports.

[0137] "Evaluation indicators" are standards or criteria for evaluating business and work performance, including accuracy, efficiency, creativity, etc.

[0138] "Natural language processing" is a technology that converts text data into a form that is easy for computers to understand and analyze, and analyzes the content and context.

[0139] "Machine learning technology" is a technology that allows computers to learn from data and perform analysis, predictions, classification, etc.

[0140] An "evaluation score" is a numerical value calculated based on the evaluation index, and represents the performance of an employee and a work machine.

[0141] A "detailed report" is a report that includes the evaluation score and details of the evaluation, and is notified to employees and managers.

[0142] The present invention provides a system for unifying employee and machine performance evaluation. The system operates in the following manner.

[0143] First, the server collects each employee's work data and work machine activity data. Work data includes audio data and comments from meetings attended by employees, email content, and data from project management tools, all of which are collected via the microphones and logs of devices (such as PCs and smartphones). Work machine activity data includes work content, operating status, error occurrence status, quality check results, etc.

[0144] The server then analyzes the collected data using natural language processing (NLP) and machine learning techniques, including:

[0145] For natural language processing, SpaCy is used to convert audio data into text and then analyze the content and context.

[0146] For machine learning technology, Scikit-learn and Tensorflow (TENSORFLOW (registered trademark)) are used to input collected data into a learning model and perform analysis based on evaluation indicators.

[0147] Based on the analysis results, the server calculates an evaluation score for each employee and work machine. The evaluation score is determined based on the accuracy, efficiency, and creativity of the work and tasks. For example, if an employee's comments in a meeting contribute significantly to the progress of a project, the comments will receive a high score. Similarly, if a work machine performs production tasks efficiently and detects errors early, its activities will receive a high score.

[0148] Finally, the server generates a report based on the evaluation score and detailed evaluation content. This report includes detailed evaluations of each task and work, feedback, and areas for improvement. The generated report is notified by email and also uploaded to a dedicated portal site.

[0149] For example, at the end of each day in a factory, robots automatically send their activity logs to a server, which then analyzes the logs and evaluates the robot's performance. An evaluation report is sent to the manager via email, highlighting areas for improvement and strengths of the robot. Employee comments made during project meetings and ideas for improving work efficiency proposed via email are also evaluated.

[0150] Example prompt sentence:

[0151] "Design a system to analyze the robot's activity log and evaluate its work performance. The log will include records of the work performed, error detection, and quality checks. Include a process to calculate the evaluation score and generate a report to notify the user."

[0152] The main components of the invention are a server equipped with a data collection device, a data analysis device, an evaluation score calculation device, a report generation device and a notification means, which enables integrated management and evaluation of the performance of employees and work machines in factory and office environments.

[0153] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0154] Step 1:

[0155] The server collects each employee's work data and work machine activity data. Specifically, it collects meeting audio data, comments, email content, and project management tool data in real time through the microphones and logs of terminals (PCs and smartphones). It also collects data such as operating status, error occurrences, and quality check results from the sensors and loggers of the work machines. The input is data from the terminals and work machines, and the output is the collected work data and activity data.

[0156] Step 2:

[0157] The server analyzes the collected business data and activity data using natural language processing (NLP) and machine learning technologies. First, it uses speech recognition technology (e.g., Google® Speech-to-Text API) to convert the voice data into text. Then, it uses SpaCy to perform content analysis on the text data. The activity data of the work machines is input into a learning model using Scikit-learn or TensorFlow, which classifies and analyzes the data. The input is the collected data, and the output is the data analysis results.

[0158] Step 3:

[0159] The server calculates an evaluation score for each employee and work machine based on the analysis results. Evaluation indicators include the accuracy, efficiency, and creativity of work and tasks. Scores for each indicator are calculated from the analysis results, and an evaluation score is generated by combining these. Specifically, the evaluation criteria include how much each employee's comments in meetings or the content of their emails contribute to the progress of the project, and how early the work machine detects errors. The input is the data analysis results, and the output is the evaluation score.

[0160] Step 4:

[0161] The server generates a detailed report of the evaluation score and the evaluation content. The report includes detailed evaluations and feedback for each task and operation, as well as points for improvement. Specifically, it describes the breakdown of scores for each indicator and how each is reflected in the overall evaluation. The input is the evaluation score and analysis results, and the output is the evaluation report.

[0162] Step 5:

[0163] The server notifies the relevant parties of the generated evaluation report by sending an email or uploading it to a dedicated portal site. The user can check the report via the email or portal site where the notification was received and get feedback. The input is the evaluation report, and the output is a notification message.

[0164] This series of processes enables comprehensive evaluation of the performance of employees and work machines, improving production efficiency and transparency and fairness of evaluations.

[0165] 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.

[0166] The following describes an embodiment of the present invention. The present invention is a system that collects work data of each employee, analyzes the collected data, and evaluates work performance based on evaluation indicators, and further combines it with an emotion engine that recognizes the user's emotions.

[0167] Explanation of program processing

[0168] Business data collection

[0169] The device collects in real time audio spoken during meetings, work-related emails, data from project management tools, etc. For example, audio data recorded with a microphone during a meeting and email data extracted from the email server are all sent to the server.

[0170] Data analysis

[0171] The server converts the voice data into text using a speech recognition engine and analyzes it using natural language processing (NLP). Email data and project management data are also analyzed in the same way, and the importance and contribution of work are classified as evaluation indicators. An emotion engine is also built in, and the user's emotions are analyzed from the voice and text data. This emotion data is used to evaluate the motivation and stress levels of employees when performing their work.

[0172] Emotion Engine Operation

[0173] The emotion engine analyzes voice tone and text writing to identify emotions such as joy, anger, sadness, and surprise. Features such as volume, speed, and intonation are extracted from voice data, while keywords and context are analyzed from text data. For example, if a person speaks passionately during a meeting, they will be evaluated as "highly motivated," while if the content of an email is calm, they will be evaluated as "low stress."

[0174] Calculation of evaluation score

[0175] The server calculates an employee's evaluation score by combining the work evaluation indicators and emotional data. If the work data is highly evaluated and the emotion engine analysis identifies high motivation, the employee's score will be high. Evaluation criteria include work accuracy, efficiency, and creativity, and evaluation weights are set based on these.

[0176] Report generation and notification

[0177] The server generates an evaluation report for each employee based on the evaluation score, detailed evaluation content, and sentiment analysis results. The report includes the evaluation content of each task, a breakdown of the score, feedback based on sentiment data, and areas for improvement. The generated report is automatically sent by email to the person in charge in the relevant department and also uploaded to an employee-only portal site.

[0178] Specific examples

[0179] For example, suppose employee A actively speaks up during a project meeting, and his or her comments contribute significantly to the progress of the project. At that time, the device records the voice data and sends it to the server. The server converts the voice data into text and analyzes the content of the comments using natural language processing technology.

[0180] Furthermore, the emotion engine recognizes high motivation from the tone and content of Employee A's comments. This data is reflected in the evaluation indicators, and the final evaluation score is calculated.

[0181] The evaluation report for Employee A clearly shows his high motivation and contribution to his work, and his supervisor can provide accurate feedback based on the report. In this way, a fair and impartial evaluation is achieved.

[0182] The above is a specific embodiment of an employee evaluation system that combines an emotion engine. This system enables comprehensive evaluation that takes into account not only an employee's work performance but also their emotional state.

[0183] The processing flow will be explained below.

[0184] Step 1: Collect business data

[0185] The devices collect data on employees' daily work. For example, speech during meetings is recorded through a microphone, and work-related email data is obtained from the email server. Data from project management tools is also collected periodically. This data is sent to the server in real time.

[0186] Step 2: Preprocessing the data

[0187] The server converts voice data received from the device into text data using a voice recognition engine, and also converts email data and project management data into a format that can be analyzed directly and stored in a database.

[0188] Step 3: Extracting emotion data

[0189] The server then uses an emotion engine to analyze the user's emotions from the converted text data. Features such as volume, speed, and intonation are extracted from the voice data, while specific keywords and context are analyzed to identify emotions from the text data. For example, if the speech is passionate, the analysis result is stored in the database as "high motivation."

[0190] Step 4: Analyze business data

[0191] The server analyzes text data and project management data using natural language processing (NLP) technology, classifying the contribution and importance of work as evaluation indicators. For example, it analyzes how comments made during a meeting contributed to the progress of a project, and stores the results in a database.

[0192] Step 5: Calculating the evaluation score

[0193] The server calculates an evaluation score for each employee by combining the analyzed work data and emotional data. Evaluation weights are set based on evaluation criteria such as work accuracy, efficiency, and creativity, and the emotional data is also taken into account when calculating the score. For example, if an employee's work contribution is high and their emotional data is "highly motivated," the employee's evaluation score will be high.

[0194] Step 6: Generate reports

[0195] The server generates an evaluation report for each employee based on the evaluation score and detailed evaluation content. The report includes the evaluation content of each task, a breakdown of the score, feedback based on emotional data, and areas for improvement. The generated report is saved in a database.

[0196] Step 7: Notification and Delivery

[0197] The server notifies the automatically generated evaluation report to the user (supervisor or HR department) by email, and also uploads the report to an employee-only portal site so that employees can check their own evaluations at any time.

[0198] Step 8: Managing Feedback

[0199] Users can review the evaluation report and add feedback as needed. This feedback is also saved on the server and reflected in the next evaluation. Through this process, fair and impartial employee evaluations are achieved.

[0200] Example 2

[0201] 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."

[0202] When evaluating employee performance, conventional systems only consider work data, making it difficult to properly reflect employees' emotional state and motivation. Furthermore, there are insufficient methods for efficiently and automatically processing collected data to provide fair and impartial evaluations. This results in one-sided evaluations, which makes it difficult to fully evaluate employees' true contributions and motivation.

[0203] 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.

[0204] In this invention, the server includes means for analyzing each employee's work data using natural language processing and emotion analysis technology, and evaluating the employee's work performance based on work evaluation indicators and emotion data, means for calculating an evaluation score for each employee by combining the evaluation indicators and emotion data, and means for generating a detailed report of the evaluation score and evaluation content and notifying related departments and employees. This makes it possible to analyze and evaluate the work data and emotion data in an integrated manner, and to comprehensively evaluate the employee's work performance and emotions.

[0205] "Employee business data" refers to all data generated by or related to an employee's daily work, including, for example, audio recordings, work-related emails, and data from project management tools.

[0206] "Natural language processing" is a technology that enables computers to understand, analyze, and generate natural human language, and is a technology that can analyze text data and audio data to extract meaning.

[0207] "Emotion analysis technology" is a technology that identifies and analyzes human emotions from voice and text data, and evaluates emotional states by analyzing volume, intonation, keywords, and context.

[0208] "Evaluation indicators" are standards for evaluating an employee's work performance and contribution, and specifically include accuracy, efficiency, creativity, and emotional aspects of work.

[0209] An "evaluation score" is a numerical value calculated based on evaluation indicators, and is used to comprehensively evaluate an employee's work performance and emotional state.

[0210] A "detailed report" is a document that summarizes the evaluation score, evaluation content, and sentiment analysis results, and is used to communicate the evaluation results to employees and related departments.

[0211] "Speech recognition technology" is a technology that converts voice data into text data, and is a technology that can analyze voice data and accurately convert what is spoken into text.

[0212] "Machine learning technology" is a technology in which a computer learns patterns from data and makes predictions and judgments based on those patterns, and is used to analyze and evaluate business data.

[0213] "Emotional data" is data obtained using emotion analysis technology, and indicates employees' emotional state, motivation, stress level, etc.

[0214] The following describes in detail the mode for carrying out this invention. This system uses major hardware and software to collect and analyze employee work data and emotional data, and calculate and notify an evaluation score. The procedure is explained below.

[0215] Business data collection

[0216] The device collects various business data in real time, such as the audio of employees' speech during meetings, work-related emails, and data from project management tools. Specifically, audio recordings are made using a microphone during meetings, and emails are extracted using an email client. This data is then immediately sent to the server.

[0217] Converting audio data to text

[0218] The server converts the received audio data into text using the Google Speech-to-Text API, and during this process, it also performs pre-processing such as cleaning and noise removal.

[0219] Data analysis

[0220] The server uses natural language processing (NLP) technology to analyze text data (voice data converted to text and email data) and data obtained from project management tools. Specific NLP technologies include the Python NLTK library and SpaCy. For example, the server evaluates the contribution and importance of employees' comments and sets appropriate evaluation indicators.

[0221] Emotional Data Analysis

[0222] The server uses emotion analysis technology (for example, IBM Watson (registered trademark) Natural Language Understanding) to analyze employee emotions from voice and text data. Feature quantities such as volume, intonation, and speed are extracted from voice data, and keywords and context are analyzed from text data. For example, an employee may be assessed as "highly motivated" based on passionate comments made during a meeting, or as "low stress" based on calm email content.

[0223] Calculation of evaluation score

[0224] The server combines work evaluation indicators and emotional data to calculate an evaluation score for each employee. This evaluation uses evaluation criteria such as accuracy, efficiency, and creativity, each of which is weighted. For example, if an employee's work is highly accurate and the emotional analysis results indicate high motivation, the employee's evaluation score will be high.

[0225] Report generation and notification

[0226] The server generates an evaluation report for each employee based on the calculated evaluation score and detailed evaluation content. This report includes the evaluation content of each job, a breakdown of the score, the results of sentiment analysis, feedback, and areas for improvement. The generated report is sent by email to the person in charge in the relevant department and also uploaded to an employee-only portal site.

[0227] Specific examples

[0228] For example, suppose Employee A actively speaks up during a project meeting, and his or her comments contribute significantly to the progress of the project. At that time, the device records the voice data and sends it to the server in real time. The server converts the received voice data into text and analyzes the content of the comments using NLP technology. Furthermore, the emotion engine recognizes Employee A's high motivation from the tone and content of his or her comments, and this data is reflected in the evaluation indicators.

[0229] Example prompts to input to the generative AI model

[0230] "Employee A actively spoke up during the project meeting, and his comments contributed greatly to the progress of the project. Please explain in detail the data collected, the analysis method, the specific operation of the emotion engine, how the evaluation score was calculated, and the contents of the generated report."

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

[0232] Step 1:

[0233] Business data collection

[0234] The device collects real-time data such as employee speech during meetings, work-related emails, and data from project management tools. For example, it can record audio using a conference microphone and extract work-related emails from an email client.

[0235] Input: Meeting audio data, email data, project management tool data

[0236] Output: Send collected data (audio file, email data file, project data file) to the server.

[0237] Step 2:

[0238] Converting audio data to text

[0239] The server converts the received audio data into text using the Google Speech-to-Text API, which also cleans and removes noise from the audio data.

[0240] Input: Audio file

[0241] Output: Text data (audio file converted to text)

[0242] Step 3:

[0243] Data analysis

[0244] The server analyzes text data, email data, and project management data using natural language processing (NLP) technology. Specifically, it uses Python's NLTK library and SpaCy to analyze the text data and classify it into evaluation indicators such as the importance and contribution of tasks.

[0245] Input: Text data, email data, project data

[0246] Output: Data with business performance indicators

[0247] Step 4:

[0248] Emotional Data Analysis

[0249] The server uses emotion analysis technology (e.g., IBM Watson Natural Language Understanding) to analyze emotions from voice and text data. Specifically, it extracts volume, speed, and intonation from voice data, and analyzes keywords and context from text data to assess the employee's emotional state.

[0250] Input: Text data, speech analysis data

[0251] Output: Emotion analysis results (emotional state evaluation data)

[0252] Step 5:

[0253] Calculation of evaluation score

[0254] The server combines performance metrics and emotional data to calculate an employee evaluation score, which includes criteria such as accuracy, efficiency, and creativity, each of which is weighted.

[0255] Input: Data with business evaluation indicators, sentiment analysis results

[0256] Output: Evaluation score

[0257] Step 6:

[0258] Report generation and notification

[0259] The server generates an evaluation report for each employee based on the evaluation score and detailed evaluation content. This report includes the evaluation content of each task, a breakdown of the score, the results of sentiment analysis, feedback and areas for improvement, etc. The generated report is sent by email to the person in charge in the relevant department and also uploaded to the employee-only portal site.

[0260] Input: Evaluation score, detailed evaluation content (job evaluation, emotional data)

[0261] Output: Evaluation report (email and upload to portal site)

[0262] (Application example 2)

[0263] 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."

[0264] Conventional employee evaluation systems only evaluate employees' work performance, making it difficult to provide a comprehensive evaluation that reflects their actual emotions and motivation levels. Furthermore, there is a lack of means to grasp the quality of customer service in physical stores in real time and provide appropriate feedback. To address these issues, there is a need for a system that comprehensively evaluates employees' work performance and emotions.

[0265] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting work data of each employee, means for analyzing the collected work data and evaluating the work performance of the employee based on the evaluation index, means for calculating an evaluation score for each employee based on the evaluation results, means for generating and notifying a detailed report of the evaluation score and evaluation content, means for using a wearable device to collect voice data during customer interactions, and means for analyzing the collected voice data using natural language processing and an emotion engine to evaluate the emotional tone and work performance of the employee. This enables real-time evaluation and feedback of employees in physical stores.

[0266] "Each employee's business data" refers to all data generated when an employee performs their work, such as audio spoken during business meetings, work-related emails, and data from project management tools.

[0267] "Natural language processing" is a technology that allows computers to understand and process human language, and involves tasks such as analyzing sentences and recognizing emotions.

[0268] An "emotion engine" refers to a system that includes algorithms that analyze voice tone and text content to identify specific emotions.

[0269] A "wearable device" is an electronic device that can be worn on the body and is equipped with a microphone and sensors for collecting voice data.

[0270] "Evaluation indicators" are specific standards or measures used to evaluate an employee's work performance, and include accuracy, efficiency, creativity, etc.

[0271] An "evaluation score" is numerical data calculated based on evaluation indicators, and quantitatively indicates an employee's work performance and emotional state.

[0272] A "report" is a document containing an evaluation score, detailed evaluation content, and feedback, which is communicated to employees and managers.

[0273] An embodiment of this invention is a comprehensive evaluation system that collects employee work data, evaluates work performance based on evaluation indicators, and also considers employee motivation and stress levels in combination with an emotion engine. Specifically, it includes a series of processes: collecting voice data using a wearable device, analyzing the data using natural language processing (NLP), evaluating emotions using the emotion engine, and generating and notifying reports of the evaluation results.

[0274] Program Description

[0275] Audio data collection

[0276] The server uses wearable devices (e.g., smart glasses or smartphones) as terminals to collect voice data in real time during customer interactions, thereby recording the content and tone of the employee's dialogue.

[0277] Analysis of audio data

[0278] The server converts the collected voice data into text using a speech recognition engine and analyzes it using natural language processing (NLP) technology. Specifically, it converts voice to text using Python's speech_recognition library and uses Hugging Face's transformers library to use daigo / bert-base-japanese-sentiment, a sentiment analysis model specifically for Japanese.

[0279] Emotion Engine Operation

[0280] The server calculates an emotion score from the analyzed text data using an emotion engine, for example, the textblob library, to analyze the polarity (positive or negative) and subjectivity of the text data and evaluate the employee's emotional state.

[0281] Calculation of evaluation score

[0282] The server combines the work evaluation indicators and emotional data to calculate an employee evaluation score, which is calculated based on the emotion score, polarity score, and subjectivity score, and uses the results to comprehensively evaluate the employee's work performance and emotional state.

[0283] Report generation and notification

[0284] The server generates an evaluation report for each employee based on the evaluation score, detailed evaluation content, and sentiment analysis results. The generated report is automatically sent by email to the relevant department and also uploaded to an employee-only portal site.

[0285] Specific examples

[0286] For example, if a staff member is engaging in friendly and enthusiastic conversation while interacting with a customer, the voice data will be collected and analyzed by the smart glasses. Based on the analysis results, the staff member's evaluation score will be increased, and the results will be generated as a report and notified to the manager. In this way, real-time evaluation and feedback of employees in physical stores will be possible.

[0287] Prompt Sentence Examples

[0288] "Evaluate your sentiment and performance score based on the following text: 'Hey customer, what do you think of this product? It's very popular and we think you'll be pleased with it.'"

[0289] This invention enables the evaluation of the work performance of employees in physical stores in a fair and efficient manner in real time, thereby enabling the provision of high-quality customer service.

[0290] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0291] Step 1:

[0292] The terminal collects voice data in real time when employees interact with customers via wearable devices (smart glasses or smartphones). The input is the voice of the conversation with the customer, and the output is the collected voice data. This voice data is sent to the server.

[0293] Step 2:

[0294] The server converts the collected voice data into text using a voice recognition engine. The input is voice data and the output is text data. This process uses the Python speech_recognition library.

[0295] Step 3:

[0296] The server analyzes the text data using natural language processing (NLP) and calculates a sentiment score using an emotion engine. The input is text data, and the output is the sentiment score and the analyzed text data. This analysis is performed using the daigo / bert-base-japanese-sentiment model from the transformers library.

[0297] Step 4:

[0298] The server analyzes the polarity (positive or negative) and subjectivity of the text data based on the output of the emotion engine. The input is the analyzed text data, and the output is the polarity score and the subjectivity score. This process uses the textblob library.

[0299] Step 5:

[0300] The server calculates an employee evaluation score by combining the work evaluation indicators and emotional data. The inputs are the emotional score, polarity score, and subjectivity score, and the output is a comprehensive evaluation score. This allows for a comprehensive evaluation of the employee's work performance and emotional state.

[0301] Step 6:

[0302] The server generates an evaluation report for each employee based on the evaluation score, detailed evaluation content, and sentiment analysis results. The input is the overall evaluation score and analysis results, and the output is the evaluation report.

[0303] Step 7:

[0304] The server automatically sends the generated evaluation report to the relevant department by email and also uploads it to the employee-only portal site.The input is the evaluation report and the output is the delivered report.

[0305] In this way, through a series of processes from collecting voice data to analyzing, evaluating, and notifying, this system makes it possible to comprehensively evaluate employees' work performance and emotional state and provide feedback in real time.

[0306] 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.

[0307] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0308] 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.

[0309] [Second embodiment]

[0310] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0311] 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.

[0312] 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).

[0313] 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.

[0314] 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.

[0315] 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).

[0316] 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.

[0317] 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.

[0318] 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.

[0319] 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.

[0320] 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.

[0321] 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."

[0322] As a form for implementing the invention, this system performs a series of processes: collects work data for each employee, analyzes the collected data, evaluates work performance based on evaluation indicators, calculates an evaluation score for each employee based on the results, and generates and notifies a detailed report of the evaluation content.

[0323] Explanation of program processing

[0324] Business data collection

[0325] The server collects in real time audio data and comments from meetings attended by employees, email content, data from project management tools, etc. For example, audio data and operation logs are sent to the server via the microphones and logs of devices (PCs and smartphones) used during meetings.

[0326] Data analysis and evaluation

[0327] The server analyzes the collected data using natural language processing (NLP) and machine learning technologies. Specifically, it converts the audio data from meetings into text and analyzes the content and context of what is being said. It also analyzes email content and project progress data in the same way, categorizing each person's contribution to the task and their importance as evaluation indicators. In this process, it assigns scores based on fixed evaluation criteria (such as accuracy, efficiency, and creativity of the task).

[0328] Calculation of evaluation score

[0329] The server calculates an evaluation score for each employee based on the analysis results. For example, if an employee speaks in a meeting and their comments contribute significantly to the progress of a project, that comment will be given a high score. Other factors that contribute to the score include the number of completed project tasks and the efficiency of email exchanges.

[0330] Report generation and notification

[0331] The server generates an evaluation report for each employee based on the calculated evaluation score and detailed evaluation content. This report includes detailed evaluations and feedback for each task, as well as areas for improvement for the employee. The generated report is notified to relevant parties by email and is also uploaded to an employee-only portal site.

[0332] Specific examples

[0333] For example, suppose employee A has achieved results in an important project. All comments made in meetings using devices (PCs or smartphones) and task completion data recorded in the project management tool are collected on a server. The collected voice data is converted into text and analyzed using natural language processing. If it turns out that these comments made in the meeting contributed significantly to the success of the project, employee A's evaluation score will be high.

[0334] If Employee B proposes a new idea for improving work efficiency by email and the proposal has a positive impact on the company as a whole, the server analyzes the email content and reflects it in the evaluation score.Finally, the server generates an evaluation report for Employees A and B and notifies the HR department and their superiors.This report includes specific evaluation details as well as areas for improvement and additional feedback.

[0335] As described above, the present invention ensures transparency and fairness in evaluations by collecting detailed and fair employee work data and conducting multifaceted evaluations.

[0336] The processing flow will be explained below.

[0337] Step 1: Collect business data

[0338] The devices collect data on the daily work of each employee. For example, speech during meetings is recorded through a microphone, and work-related email data sent and received from the email server is also collected. The collected data is sent to the server in real time.

[0339] Step 2: Save your data

[0340] The server temporarily stores the business data received from the terminal in a buffer, then transfers it to the database and stores it in the appropriate format. This storage process is necessary to prevent data loss and facilitate subsequent analysis.

[0341] Step 3: Preprocessing the data

[0342] The server preprocesses the stored data: voice data is converted to text using a speech recognition engine; email data is processed using natural language processing (NLP) techniques to extract important keywords and phrases; and project management data is extracted to identify the progress and completion status of each task.

[0343] Step 4: Analyze the evaluation metrics

[0344] The server then analyzes the preprocessed data according to evaluation criteria. For example, it analyzes the context of comments made in meetings and evaluates how much those comments contributed to the progress of the project. Other evaluation criteria include the quality of submitted ideas and documents, the content of emails, and the speed of responses.

[0345] Step 5: Scoring and evaluation

[0346] The server calculates an evaluation score for each employee based on the analysis results. For example, it sets evaluation weights for each job based on evaluation criteria such as accuracy, efficiency, and creativity, and calculates an overall score. This score is saved in a database and used to generate reports, which will be described later.

[0347] Step 6: Generate reports

[0348] The server generates an evaluation report for each employee based on the evaluation score and detailed evaluation content. This report includes the evaluation content of each job, a score breakdown, areas for improvement, and feedback. The generated report is prepared in a format suitable for the HR department or supervisor.

[0349] Step 7: Notification and Delivery

[0350] The server notifies the automatically generated evaluation report to the user (supervisor or HR department) by email, and also uploads the report to an employee-only portal site so that employees can check their own evaluations at any time.

[0351] This is the specific process flow of an employee evaluation system that utilizes AI. This enables fair and impartial evaluations, which improves employee motivation and provides evaluations that employees can be satisfied with.

[0352] Example 1

[0353] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0354] When evaluating employee performance, traditional evaluation systems tend to rely on subjective judgment and often lack fairness and transparency. Furthermore, because they only collect a portion of work data, it is difficult to accurately evaluate an employee's overall performance. Furthermore, the lack of feedback on evaluation results means that they are unable to provide guidance for employee growth or work improvement.

[0355] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0356] In this invention, the server includes means for collecting employee work data in real time, means for appropriately structuring the collected work data and converting it into an analyzable format, means for analyzing the preprocessed data using natural language processing and machine learning techniques, means for calculating an evaluation score for each employee based on the analysis results, and means for generating and notifying a report based on the evaluation score and detailed evaluation content. This enables detailed and fair evaluation of employee work performance, ensuring transparency and fairness.

[0357] "Business data" refers to information about the work that employees perform on a daily basis, including audio data from meetings, statements, email content, and data from project management tools.

[0358] "Real-time" refers to data being collected or processed immediately as it is generated, with little or no time delay.

[0359] "Structuring" refers to organizing and converting raw data into a table format, database format, or other format that makes it easier to analyze and process.

[0360] "Natural language processing (NLP)" is a technology that uses computers to analyze human language, and includes topic modeling and sentiment analysis of text data.

[0361] "Machine learning" is a technology that allows computers to use data to learn patterns and automatically perform tasks such as prediction and classification.

[0362] An "evaluation score" is a numerical representation of an employee's work performance, calculated based on specific evaluation criteria.

[0363] A "report" refers to a document or electronic data that compiles information such as evaluation scores, detailed evaluation content, feedback, and areas for improvement.

[0364] "Notification" refers to informing relevant parties of the evaluation results and reports, and includes means such as email or uploading to a portal site.

[0365] "Automatic speech recognition (ASR)" is a technology that converts voice data into text data.

[0366] "Topic modeling" is a technology that automatically extracts hidden topics (themes) from large amounts of text data.

[0367] "Sentiment analysis" is a technique that analyzes emotions and opinions within text data and determines whether they are positive, negative, or neutral.

[0368] "Accuracy" is an evaluation criterion that indicates how error-free a task is being performed.

[0369] "Efficiency" is an evaluation criterion that indicates how efficiently work is being carried out.

[0370] "Creativity" is a measure of the ability to provide new ideas and innovative solutions in the workplace.

[0371] The following description is provided as an embodiment of the present invention: The system is realized through the cooperation of a server, a terminal, and a user, each of which plays a specific role.

[0372] Business data collection

[0373] The server collects employees' work data in real time. Specifically, meeting audio data, comments, email content, and project management tool data are automatically sent to the server from the devices used by employees (PCs and smartphones). For example, what an employee says during an online meeting is collected as audio data using the device's microphone and immediately sent to the server.

[0374] Data Preprocessing

[0375] The server structures the collected business data and converts it into an analyzable format. Voice data is converted into text using automatic speech recognition (ASR) technology, and email content is tokenized. Data obtained from project management tools is also converted into a unified format, allowing for centralized management and easier analysis.

[0376] Analyzing the data

[0377] The server then analyzes the preprocessed data using natural language processing (NLP) and machine learning techniques. Specifically, it performs topic modeling and sentiment analysis on the text data to analyze the content and context of comments. For example, it determines the extent to which comments made during a meeting contribute to the progress of a project. In this process, it classifies the data based on evaluation criteria such as work accuracy, efficiency, and creativity, and generates a score.

[0378] Calculation of evaluation score

[0379] The server calculates an evaluation score for each employee based on the results of the data analysis. For example, if an employee's comments in a meeting significantly contribute to the progress of a project, a high score will be given based on the analysis of the content of those comments. The score also reflects the number of tasks completed in the project management tool and the efficiency of email exchanges.

[0380] Report generation and notification

[0381] The server generates an evaluation report for each employee based on the evaluation score and detailed evaluation content. This report includes specific evaluation details, feedback, and areas for improvement. The generated report is notified to the terminal by email and is also uploaded to an employee-only portal site.

[0382] Examples of concrete examples and prompts

[0383] For example, if employee A participates in a Zoom meeting and makes an important comment during the meeting, the device (PC or smartphone) collects the audio data and sends it to the server. The server then converts this audio data into text using automatic speech recognition technology and analyzes it using natural language processing. If the analysis determines that employee A's comments contributed to the project's success, a high evaluation score is calculated. Similarly, if employee B proposes a new idea for improving work efficiency via email and the content of that proposal has a positive impact on the entire company, the server analyzes the content of that email and reflects it in the evaluation score. Finally, the server generates an evaluation report, notifies the human resources department and superiors via email, and uploads it to a dedicated portal site.

[0384] An example of a prompt sentence might be:

[0385] "Please tell me a specific method for converting what Employee A said during a Zoom meeting into text, analyzing the context, and evaluating his / her contribution to the project."

[0386] "Employee B proposed an idea for improving work efficiency via email. Please explain in detail how the contents of this email can be automatically analyzed and reflected in the evaluation score."

[0387] The above explanation shows how this system collects, pre-processes, analyzes, evaluates, and generates reports to provide a detailed and fair evaluation of employees' work performance, ensuring transparency and fairness and promoting employee growth.

[0388] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0389] Step 1:

[0390] The server collects employee work data in real time.

[0391] Input: Voice data, email data, project management tool data, etc. sent from devices used by employees

[0392] Specific operation: The device (PC or smartphone) captures audio data during the meeting through a microphone and sends it to the server. It also captures task completion information from the project management tool and email content as appropriate and sends them to the server.

[0393] Output: Business data aggregated on the server

[0394] Step 2:

[0395] The server preprocesses and structures the collected business data.

[0396] Input: Raw data collected on the server (voice data, email data, project management tool data, etc.)

[0397] Specific operation: Voice data is converted to text data using automatic speech recognition (ASR), email content is structured by a tokenization server, and data from project management tools is also converted into a unified format.

[0398] Output: Structured data

[0399] Step 3:

[0400] The server analyzes the structured data using natural language processing (NLP) and machine learning techniques.

[0401] Input: Preprocessed structured data (text data, email data, project management data, etc.)

[0402] Specific operations: Topic modeling and sentiment analysis are performed on text data to analyze its context and content, and the data is then classified and scored based on evaluation criteria for operational accuracy, efficiency, and creativity.

[0403] Output: Scored evaluation data

[0404] Step 4:

[0405] The server calculates an evaluation score for each employee based on the results of the data analysis.

[0406] Input: Scored assessment data

[0407] Specific operation: Comprehensively evaluate individual evaluations (for example, contributions made in meetings, number of completed tasks, etc.) and calculate an overall evaluation score for each employee.

[0408] Output: Evaluation score for each employee

[0409] Step 5:

[0410] The server generates and notifies an evaluation report based on the evaluation score and detailed evaluation content.

[0411] Input: Evaluation score and detailed evaluation content for each employee

[0412] Specific operation: A report is generated based on the evaluation results. This report includes detailed evaluations, feedback, and areas for improvement for each task. The generated report is notified by email and also uploaded to the employee-only portal site.

[0413] Output: Notified evaluation report

[0414] By following the above steps, the system can provide a detailed and fair evaluation of employees' work performance, ensuring transparency and fairness.

[0415] (Application example 1)

[0416] 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."

[0417] It is necessary to collect and analyze not only employee work data but also activity data from the work machines in the factory and conduct comprehensive evaluations to improve production efficiency and ensure transparency and fairness in evaluations. It is also considered necessary to take measures to consistently monitor and evaluate the performance of employees and work machines.

[0418] 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.

[0419] In this invention, the server includes means for collecting work data for each employee and activity data for each work machine, means for analyzing the collected work data and activity data and evaluating the performance of employees and work machines based on evaluation indices, means for calculating evaluation scores for each employee and work machine based on the evaluation results, and means for generating and notifying detailed reports of the evaluation scores and evaluation contents. This makes it possible to comprehensively evaluate and improve the performance of employees and work machines, and to increase production efficiency and the transparency and fairness of evaluations.

[0420] "Business data" refers to information related to the work performed by employees, including meeting audio, statements, email content, project management tool data, and the like.

[0421] "Work machines" are automated machines and robots used to carry out production work in factories.

[0422] "Activity data" refers to data related to the activity of a machine, such as the work performed by the machine, its operating status, the occurrence of errors, and the results of quality checks.

[0423] The "server" is an information processing device that collects and analyzes data, calculates evaluation scores, and generates and notifies reports.

[0424] "Evaluation indicators" are standards or criteria for evaluating business and work performance, including accuracy, efficiency, creativity, etc.

[0425] "Natural language processing" is a technology that converts text data into a form that is easy for computers to understand and analyze, and analyzes the content and context.

[0426] "Machine learning technology" is a technology that allows computers to learn from data and perform analysis, predictions, classification, etc.

[0427] An "evaluation score" is a numerical value calculated based on the evaluation index, and represents the performance of an employee and a work machine.

[0428] A "detailed report" is a report that includes the evaluation score and details of the evaluation, and is notified to employees and managers.

[0429] The present invention provides a system for unifying employee and machine performance evaluation. The system operates in the following manner.

[0430] First, the server collects each employee's work data and work machine activity data. Work data includes audio data and comments from meetings attended by employees, email content, and data from project management tools, all of which are collected via the microphones and logs of devices (such as PCs and smartphones). Work machine activity data includes work content, operating status, error occurrence status, quality check results, etc.

[0431] The server then analyzes the collected data using natural language processing (NLP) and machine learning techniques, including:

[0432] For natural language processing, SpaCy is used to convert audio data into text and then analyze the content and context.

[0433] For machine learning technology, Scikit-learn and TensorFlow are used to input collected data into a learning model and perform analysis based on evaluation indicators.

[0434] Based on the analysis results, the server calculates an evaluation score for each employee and work machine. The evaluation score is determined based on the accuracy, efficiency, and creativity of the work and tasks. For example, if an employee's comments in a meeting contribute significantly to the progress of a project, the comments will receive a high score. Similarly, if a work machine performs production tasks efficiently and detects errors early, its activities will receive a high score.

[0435] Finally, the server generates a report based on the evaluation score and detailed evaluation content. This report includes detailed evaluations of each task and work, feedback, and areas for improvement. The generated report is notified by email and also uploaded to a dedicated portal site.

[0436] For example, at the end of each day in a factory, robots automatically send their activity logs to a server, which then analyzes the logs and evaluates the robot's performance. An evaluation report is sent to the manager via email, highlighting areas for improvement and strengths of the robot. Employee comments made during project meetings and ideas for improving work efficiency proposed via email are also evaluated.

[0437] Example prompt sentence:

[0438] "Design a system to analyze the robot's activity log and evaluate its work performance. The log will include records of the work performed, error detection, and quality checks. Include a process to calculate the evaluation score and generate a report to notify the user."

[0439] The main components of the invention are a server equipped with a data collection device, a data analysis device, an evaluation score calculation device, a report generation device and a notification means, which enables integrated management and evaluation of the performance of employees and work machines in factory and office environments.

[0440] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0441] Step 1:

[0442] The server collects each employee's work data and work machine activity data. Specifically, it collects meeting audio data, comments, email content, and project management tool data in real time through the microphones and logs of terminals (PCs and smartphones). It also collects data such as operating status, error occurrences, and quality check results from the sensors and loggers of the work machines. The input is data from the terminals and work machines, and the output is the collected work data and activity data.

[0443] Step 2:

[0444] The server analyzes the collected business data and activity data using natural language processing (NLP) and machine learning technologies. First, it uses speech recognition technology (e.g., Google Speech-to-Text API) to convert the voice data into text. Then, it uses SpaCy to perform content analysis on the text data. The activity data of the work machines is input into a learning model using Scikit-learn or TensorFlow, which classifies and analyzes the data. The input is the collected data, and the output is the data analysis results.

[0445] Step 3:

[0446] The server calculates an evaluation score for each employee and work machine based on the analysis results. Evaluation indicators include the accuracy, efficiency, and creativity of work and tasks. Scores for each indicator are calculated from the analysis results, and an evaluation score is generated by combining these. Specifically, the evaluation criteria include how much each employee's comments in meetings or the content of their emails contribute to the progress of the project, and how early the work machine detects errors. The input is the data analysis results, and the output is the evaluation score.

[0447] Step 4:

[0448] The server generates a detailed report of the evaluation score and the evaluation content. The report includes detailed evaluations and feedback for each task and operation, as well as points for improvement. Specifically, it describes the breakdown of scores for each indicator and how each is reflected in the overall evaluation. The input is the evaluation score and analysis results, and the output is the evaluation report.

[0449] Step 5:

[0450] The server notifies the relevant parties of the generated evaluation report by sending an email or uploading it to a dedicated portal site. The user can check the report via the email or portal site where the notification was received and get feedback. The input is the evaluation report, and the output is a notification message.

[0451] This series of processes enables comprehensive evaluation of the performance of employees and work machines, improving production efficiency and transparency and fairness of evaluations.

[0452] 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.

[0453] The following describes an embodiment of the present invention. The present invention is a system that collects work data of each employee, analyzes the collected data, and evaluates work performance based on evaluation indicators, and further combines it with an emotion engine that recognizes the user's emotions.

[0454] Explanation of program processing

[0455] Business data collection

[0456] The device collects in real time audio spoken during meetings, work-related emails, data from project management tools, etc. For example, audio data recorded with a microphone during a meeting and email data extracted from the email server are all sent to the server.

[0457] Data analysis

[0458] The server converts the voice data into text using a speech recognition engine and analyzes it using natural language processing (NLP). Email data and project management data are also analyzed in the same way, and the importance and contribution of work are classified as evaluation indicators. An emotion engine is also built in, and the user's emotions are analyzed from the voice and text data. This emotion data is used to evaluate the motivation and stress levels of employees when performing their work.

[0459] Emotion Engine Operation

[0460] The emotion engine analyzes voice tone and text writing to identify emotions such as joy, anger, sadness, and surprise. Features such as volume, speed, and intonation are extracted from voice data, while keywords and context are analyzed from text data. For example, if a person speaks passionately during a meeting, they will be evaluated as "highly motivated," while if the content of an email is calm, they will be evaluated as "low stress."

[0461] Calculation of evaluation score

[0462] The server calculates an employee's evaluation score by combining the work evaluation indicators and emotional data. If the work data is highly evaluated and the emotion engine analysis identifies high motivation, the employee's score will be high. Evaluation criteria include work accuracy, efficiency, and creativity, and evaluation weights are set based on these.

[0463] Report generation and notification

[0464] The server generates an evaluation report for each employee based on the evaluation score, detailed evaluation content, and sentiment analysis results. The report includes the evaluation content of each task, a breakdown of the score, feedback based on sentiment data, and areas for improvement. The generated report is automatically sent by email to the person in charge in the relevant department and also uploaded to an employee-only portal site.

[0465] Specific examples

[0466] For example, suppose employee A actively speaks up during a project meeting, and his or her comments contribute significantly to the progress of the project. At that time, the device records the voice data and sends it to the server. The server converts the voice data into text and analyzes the content of the comments using natural language processing technology.

[0467] Furthermore, the emotion engine recognizes high motivation from the tone and content of Employee A's comments. This data is reflected in the evaluation indicators, and the final evaluation score is calculated.

[0468] The evaluation report for Employee A clearly shows his high motivation and contribution to his work, and his supervisor can provide accurate feedback based on the report. In this way, a fair and impartial evaluation is achieved.

[0469] The above is a specific embodiment of an employee evaluation system that combines an emotion engine. This system enables comprehensive evaluation that takes into account not only an employee's work performance but also their emotional state.

[0470] The processing flow will be explained below.

[0471] Step 1: Collect business data

[0472] The devices collect data on employees' daily work. For example, speech during meetings is recorded through a microphone, and work-related email data is obtained from the email server. Data from project management tools is also collected periodically. This data is sent to the server in real time.

[0473] Step 2: Preprocessing the data

[0474] The server converts voice data received from the device into text data using a voice recognition engine, and also converts email data and project management data into a format that can be analyzed directly and stored in a database.

[0475] Step 3: Extracting emotion data

[0476] The server then uses an emotion engine to analyze the user's emotions from the converted text data. Features such as volume, speed, and intonation are extracted from the voice data, while specific keywords and context are analyzed to identify emotions from the text data. For example, if the speech is passionate, the analysis result is stored in the database as "high motivation."

[0477] Step 4: Analyze business data

[0478] The server analyzes text data and project management data using natural language processing (NLP) technology, classifying the contribution and importance of work as evaluation indicators. For example, it analyzes how comments made during a meeting contributed to the progress of a project, and stores the results in a database.

[0479] Step 5: Calculating the evaluation score

[0480] The server calculates an evaluation score for each employee by combining the analyzed work data and emotional data. Evaluation weights are set based on evaluation criteria such as work accuracy, efficiency, and creativity, and the emotional data is also taken into account when calculating the score. For example, if an employee's work contribution is high and their emotional data is "highly motivated," the employee's evaluation score will be high.

[0481] Step 6: Generate reports

[0482] The server generates an evaluation report for each employee based on the evaluation score and detailed evaluation content. The report includes the evaluation content of each task, a breakdown of the score, feedback based on emotional data, and areas for improvement. The generated report is saved in a database.

[0483] Step 7: Notification and Delivery

[0484] The server notifies the automatically generated evaluation report to the user (supervisor or HR department) by email, and also uploads the report to an employee-only portal site so that employees can check their own evaluations at any time.

[0485] Step 8: Managing Feedback

[0486] Users can review the evaluation report and add feedback as needed. This feedback is also saved on the server and reflected in the next evaluation. Through this process, fair and impartial employee evaluations are achieved.

[0487] Example 2

[0488] 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."

[0489] When evaluating employee performance, conventional systems only consider work data, making it difficult to properly reflect employees' emotional state and motivation. Furthermore, there are insufficient methods for efficiently and automatically processing collected data to provide fair and impartial evaluations. This results in one-sided evaluations, which makes it difficult to fully evaluate employees' true contributions and motivation.

[0490] 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.

[0491] In this invention, the server includes means for analyzing each employee's work data using natural language processing and emotion analysis technology, and evaluating the employee's work performance based on work evaluation indicators and emotion data, means for calculating an evaluation score for each employee by combining the evaluation indicators and emotion data, and means for generating a detailed report of the evaluation score and evaluation content and notifying related departments and employees. This makes it possible to analyze and evaluate the work data and emotion data in an integrated manner, and to comprehensively evaluate the employee's work performance and emotions.

[0492] "Employee business data" refers to all data generated by or related to an employee's daily work, including, for example, audio recordings, work-related emails, and data from project management tools.

[0493] "Natural language processing" is a technology that enables computers to understand, analyze, and generate natural human language, and is a technology that can analyze text data and audio data to extract meaning.

[0494] "Emotion analysis technology" is a technology that identifies and analyzes human emotions from voice and text data, and evaluates emotional states by analyzing volume, intonation, keywords, and context.

[0495] "Evaluation indicators" are standards for evaluating an employee's work performance and contribution, and specifically include accuracy, efficiency, creativity, and emotional aspects of work.

[0496] An "evaluation score" is a numerical value calculated based on evaluation indicators, and is used to comprehensively evaluate an employee's work performance and emotional state.

[0497] A "detailed report" is a document that summarizes the evaluation score, evaluation content, and sentiment analysis results, and is used to communicate the evaluation results to employees and related departments.

[0498] "Speech recognition technology" is a technology that converts voice data into text data, and is a technology that can analyze voice data and accurately convert what is spoken into text.

[0499] "Machine learning technology" is a technology in which a computer learns patterns from data and makes predictions and judgments based on those patterns, and is used to analyze and evaluate business data.

[0500] "Emotional data" is data obtained using emotion analysis technology, and indicates employees' emotional state, motivation, stress level, etc.

[0501] The following describes in detail the mode for carrying out this invention. This system uses major hardware and software to collect and analyze employee work data and emotional data, and calculate and notify an evaluation score. The procedure is explained below.

[0502] Business data collection

[0503] The device collects various business data in real time, such as the audio of employees' speech during meetings, work-related emails, and data from project management tools. Specifically, audio recordings are made using a microphone during meetings, and emails are extracted using an email client. This data is then immediately sent to the server.

[0504] Converting audio data to text

[0505] The server converts the received audio data into text using the Google Speech-to-Text API, and during this process, it also performs pre-processing such as cleaning and noise removal.

[0506] Data analysis

[0507] The server uses natural language processing (NLP) technology to analyze text data (voice data converted to text and email data) and data obtained from project management tools. Specific NLP technologies include the Python NLTK library and SpaCy. For example, the server evaluates the contribution and importance of employees' comments and sets appropriate evaluation indicators.

[0508] Emotional Data Analysis

[0509] The server uses emotion analysis technology (for example, IBM Watson Natural Language Understanding) to analyze employee emotions from voice and text data. Features such as volume, intonation, and speed are extracted from voice data, while keywords and context are analyzed from text data. For example, passionate comments during a meeting can be evaluated as "highly motivated," while calm email content can be evaluated as "low stress."

[0510] Calculation of evaluation score

[0511] The server combines work evaluation indicators and emotional data to calculate an evaluation score for each employee. This evaluation uses evaluation criteria such as accuracy, efficiency, and creativity, each of which is weighted. For example, if an employee's work is highly accurate and the emotional analysis results indicate high motivation, the employee's evaluation score will be high.

[0512] Report generation and notification

[0513] The server generates an evaluation report for each employee based on the calculated evaluation score and detailed evaluation content. This report includes the evaluation content of each job, a breakdown of the score, the results of sentiment analysis, feedback, and areas for improvement. The generated report is sent by email to the person in charge in the relevant department and also uploaded to an employee-only portal site.

[0514] Specific examples

[0515] For example, suppose Employee A actively speaks up during a project meeting, and his or her comments contribute significantly to the progress of the project. At that time, the device records the voice data and sends it to the server in real time. The server converts the received voice data into text and analyzes the content of the comments using NLP technology. Furthermore, the emotion engine recognizes Employee A's high motivation from the tone and content of his or her comments, and this data is reflected in the evaluation indicators.

[0516] Example prompts to input to the generative AI model

[0517] "Employee A actively spoke up during the project meeting, and his comments contributed greatly to the progress of the project. Please explain in detail the data collected, the analysis method, the specific operation of the emotion engine, how the evaluation score was calculated, and the contents of the generated report."

[0518] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0519] Step 1:

[0520] Business data collection

[0521] The device collects real-time data such as employee speech during meetings, work-related emails, and data from project management tools. For example, it can record audio using a conference microphone and extract work-related emails from an email client.

[0522] Input: Meeting audio data, email data, project management tool data

[0523] Output: Send collected data (audio file, email data file, project data file) to the server.

[0524] Step 2:

[0525] Converting audio data to text

[0526] The server converts the received audio data into text using the Google Speech-to-Text API, which also cleans and removes noise from the audio data.

[0527] Input: Audio file

[0528] Output: Text data (audio file converted to text)

[0529] Step 3:

[0530] Data analysis

[0531] The server analyzes text data, email data, and project management data using natural language processing (NLP) technology. Specifically, it uses Python's NLTK library and SpaCy to analyze the text data and classify it into evaluation indicators such as the importance and contribution of tasks.

[0532] Input: Text data, email data, project data

[0533] Output: Data with business performance indicators

[0534] Step 4:

[0535] Emotional Data Analysis

[0536] The server uses emotion analysis technology (e.g., IBM Watson Natural Language Understanding) to analyze emotions from voice and text data. Specifically, it extracts volume, speed, and intonation from voice data, and analyzes keywords and context from text data to assess the employee's emotional state.

[0537] Input: Text data, speech analysis data

[0538] Output: Emotion analysis results (emotional state evaluation data)

[0539] Step 5:

[0540] Calculation of evaluation score

[0541] The server combines performance metrics and emotional data to calculate an employee evaluation score, which includes criteria such as accuracy, efficiency, and creativity, each of which is weighted.

[0542] Input: Data with business evaluation indicators, sentiment analysis results

[0543] Output: Evaluation score

[0544] Step 6:

[0545] Report generation and notification

[0546] The server generates an evaluation report for each employee based on the evaluation score and detailed evaluation content. This report includes the evaluation content of each task, a breakdown of the score, the results of sentiment analysis, feedback and areas for improvement, etc. The generated report is sent by email to the person in charge in the relevant department and also uploaded to the employee-only portal site.

[0547] Input: Evaluation score, detailed evaluation content (job evaluation, emotional data)

[0548] Output: Evaluation report (email and upload to portal site)

[0549] (Application example 2)

[0550] 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."

[0551] Conventional employee evaluation systems only evaluate employees' work performance, making it difficult to provide a comprehensive evaluation that reflects their actual emotions and motivation levels. Furthermore, there is a lack of means to grasp the quality of customer service in physical stores in real time and provide appropriate feedback. To address these issues, there is a need for a system that comprehensively evaluates employees' work performance and emotions.

[0552] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting work data of each employee, means for analyzing the collected work data and evaluating the work performance of the employee based on the evaluation index, means for calculating an evaluation score for each employee based on the evaluation results, means for generating and notifying a detailed report of the evaluation score and evaluation content, means for using a wearable device to collect voice data during customer interactions, and means for analyzing the collected voice data using natural language processing and an emotion engine to evaluate the emotional tone and work performance of the employee. This enables real-time evaluation and feedback of employees in physical stores.

[0553] "Each employee's business data" refers to all data generated when an employee performs their work, such as audio spoken during business meetings, work-related emails, and data from project management tools.

[0554] "Natural language processing" is a technology that allows computers to understand and process human language, and involves tasks such as analyzing sentences and recognizing emotions.

[0555] An "emotion engine" refers to a system that includes algorithms that analyze voice tone and text content to identify specific emotions.

[0556] A "wearable device" is an electronic device that can be worn on the body and is equipped with a microphone and sensors for collecting voice data.

[0557] "Evaluation indicators" are specific standards or measures used to evaluate an employee's work performance, and include accuracy, efficiency, creativity, etc.

[0558] An "evaluation score" is numerical data calculated based on evaluation indicators, and quantitatively indicates an employee's work performance and emotional state.

[0559] A "report" is a document containing an evaluation score, detailed evaluation content, and feedback, which is communicated to employees and managers.

[0560] An embodiment of this invention is a comprehensive evaluation system that collects employee work data, evaluates work performance based on evaluation indicators, and also considers employee motivation and stress levels in combination with an emotion engine. Specifically, it includes a series of processes: collecting voice data using a wearable device, analyzing the data using natural language processing (NLP), evaluating emotions using the emotion engine, and generating and notifying reports of the evaluation results.

[0561] Program Description

[0562] Audio data collection

[0563] The server uses wearable devices (e.g., smart glasses or smartphones) as terminals to collect voice data in real time during customer interactions, thereby recording the content and tone of the employee's dialogue.

[0564] Analysis of audio data

[0565] The server converts the collected voice data into text using a speech recognition engine and analyzes it using natural language processing (NLP) technology. Specifically, it converts voice to text using Python's speech_recognition library and uses Hugging Face's transformers library to use daigo / bert-base-japanese-sentiment, a sentiment analysis model specifically for Japanese.

[0566] Emotion Engine Operation

[0567] The server calculates an emotion score from the analyzed text data using an emotion engine, for example, the textblob library, to analyze the polarity (positive or negative) and subjectivity of the text data and evaluate the employee's emotional state.

[0568] Calculation of evaluation score

[0569] The server combines the work evaluation indicators and emotional data to calculate an employee evaluation score, which is calculated based on the emotion score, polarity score, and subjectivity score, and uses the results to comprehensively evaluate the employee's work performance and emotional state.

[0570] Report generation and notification

[0571] The server generates an evaluation report for each employee based on the evaluation score, detailed evaluation content, and sentiment analysis results. The generated report is automatically sent by email to the relevant department and also uploaded to an employee-only portal site.

[0572] Specific examples

[0573] For example, if a staff member is engaging in friendly and enthusiastic conversation while interacting with a customer, the voice data will be collected and analyzed by the smart glasses. Based on the analysis results, the staff member's evaluation score will be increased, and the results will be generated as a report and notified to the manager. In this way, real-time evaluation and feedback of employees in physical stores will be possible.

[0574] Prompt Sentence Examples

[0575] "Evaluate your sentiment and performance score based on the following text: 'Hey customer, what do you think of this product? It's very popular and we think you'll be pleased with it.'"

[0576] This invention enables the evaluation of the work performance of employees in physical stores in a fair and efficient manner in real time, thereby enabling the provision of high-quality customer service.

[0577] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0578] Step 1:

[0579] The terminal collects voice data in real time when employees interact with customers via wearable devices (smart glasses or smartphones). The input is the voice of the conversation with the customer, and the output is the collected voice data. This voice data is sent to the server.

[0580] Step 2:

[0581] The server converts the collected voice data into text using a voice recognition engine. The input is voice data and the output is text data. This process uses the Python speech_recognition library.

[0582] Step 3:

[0583] The server analyzes the text data using natural language processing (NLP) and calculates a sentiment score using an emotion engine. The input is text data, and the output is the sentiment score and the analyzed text data. This analysis is performed using the daigo / bert-base-japanese-sentiment model from the transformers library.

[0584] Step 4:

[0585] The server analyzes the polarity (positive or negative) and subjectivity of the text data based on the output of the emotion engine. The input is the analyzed text data, and the output is the polarity score and the subjectivity score. This process uses the textblob library.

[0586] Step 5:

[0587] The server calculates an employee evaluation score by combining the work evaluation indicators and emotional data. The inputs are the emotional score, polarity score, and subjectivity score, and the output is a comprehensive evaluation score. This allows for a comprehensive evaluation of the employee's work performance and emotional state.

[0588] Step 6:

[0589] The server generates an evaluation report for each employee based on the evaluation score, detailed evaluation content, and sentiment analysis results. The input is the overall evaluation score and analysis results, and the output is the evaluation report.

[0590] Step 7:

[0591] The server automatically sends the generated evaluation report to the relevant department by email and also uploads it to the employee-only portal site.The input is the evaluation report and the output is the delivered report.

[0592] In this way, through a series of processes from collecting voice data to analyzing, evaluating, and notifying, this system makes it possible to comprehensively evaluate employees' work performance and emotional state and provide feedback in real time.

[0593] 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.

[0594] 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.

[0595] 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.

[0596] [Third embodiment]

[0597] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0598] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0599] 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).

[0600] 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.

[0601] 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.

[0602] 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).

[0603] 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.

[0604] 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.

[0605] 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.

[0606] 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.

[0607] 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.

[0608] 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."

[0609] As a form for implementing the invention, this system performs a series of processes: collects work data for each employee, analyzes the collected data, evaluates work performance based on evaluation indicators, calculates an evaluation score for each employee based on the results, and generates and notifies a detailed report of the evaluation content.

[0610] Explanation of program processing

[0611] Business data collection

[0612] The server collects in real time audio data and comments from meetings attended by employees, email content, data from project management tools, etc. For example, audio data and operation logs are sent to the server via the microphones and logs of devices (PCs and smartphones) used during meetings.

[0613] Data analysis and evaluation

[0614] The server analyzes the collected data using natural language processing (NLP) and machine learning technologies. Specifically, it converts the audio data from meetings into text and analyzes the content and context of what is being said. It also analyzes email content and project progress data in the same way, categorizing each person's contribution to the task and their importance as evaluation indicators. In this process, it assigns scores based on fixed evaluation criteria (such as accuracy, efficiency, and creativity of the task).

[0615] Calculation of evaluation score

[0616] The server calculates an evaluation score for each employee based on the analysis results. For example, if an employee speaks in a meeting and their comments contribute significantly to the progress of a project, that comment will be given a high score. Other factors that contribute to the score include the number of completed project tasks and the efficiency of email exchanges.

[0617] Report generation and notification

[0618] The server generates an evaluation report for each employee based on the calculated evaluation score and detailed evaluation content. This report includes detailed evaluations and feedback for each task, as well as areas for improvement for the employee. The generated report is notified to relevant parties by email and is also uploaded to an employee-only portal site.

[0619] Specific examples

[0620] For example, suppose employee A has achieved results in an important project. All comments made in meetings using devices (PCs or smartphones) and task completion data recorded in the project management tool are collected on a server. The collected voice data is converted into text and analyzed using natural language processing. If it turns out that these comments made in the meeting contributed significantly to the success of the project, employee A's evaluation score will be high.

[0621] If Employee B proposes a new idea for improving work efficiency by email and the proposal has a positive impact on the company as a whole, the server analyzes the email content and reflects it in the evaluation score.Finally, the server generates an evaluation report for Employees A and B and notifies the HR department and their superiors.This report includes specific evaluation details as well as areas for improvement and additional feedback.

[0622] As described above, the present invention ensures transparency and fairness in evaluations by collecting detailed and fair employee work data and conducting multifaceted evaluations.

[0623] The processing flow will be explained below.

[0624] Step 1: Collect business data

[0625] The devices collect data on the daily work of each employee. For example, speech during meetings is recorded through a microphone, and work-related email data sent and received from the email server is also collected. The collected data is sent to the server in real time.

[0626] Step 2: Save your data

[0627] The server temporarily stores the business data received from the terminal in a buffer, then transfers it to the database and stores it in the appropriate format. This storage process is necessary to prevent data loss and facilitate subsequent analysis.

[0628] Step 3: Preprocessing the data

[0629] The server preprocesses the stored data: voice data is converted to text using a speech recognition engine; email data is processed using natural language processing (NLP) techniques to extract important keywords and phrases; and project management data is extracted to identify the progress and completion status of each task.

[0630] Step 4: Analyze the evaluation metrics

[0631] The server then analyzes the preprocessed data according to evaluation criteria. For example, it analyzes the context of comments made in meetings and evaluates how much those comments contributed to the progress of the project. Other evaluation criteria include the quality of submitted ideas and documents, the content of emails, and the speed of responses.

[0632] Step 5: Scoring and evaluation

[0633] The server calculates an evaluation score for each employee based on the analysis results. For example, it sets evaluation weights for each job based on evaluation criteria such as accuracy, efficiency, and creativity, and calculates an overall score. This score is saved in a database and used to generate reports, which will be described later.

[0634] Step 6: Generate reports

[0635] The server generates an evaluation report for each employee based on the evaluation score and detailed evaluation content. This report includes the evaluation content of each job, a score breakdown, areas for improvement, and feedback. The generated report is prepared in a format suitable for the HR department or supervisor.

[0636] Step 7: Notification and Delivery

[0637] The server notifies the automatically generated evaluation report to the user (supervisor or HR department) by email, and also uploads the report to an employee-only portal site so that employees can check their own evaluations at any time.

[0638] This is the specific process flow of an employee evaluation system that utilizes AI. This enables fair and impartial evaluations, which improves employee motivation and provides evaluations that employees can be satisfied with.

[0639] Example 1

[0640] 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."

[0641] When evaluating employee performance, traditional evaluation systems tend to rely on subjective judgment and often lack fairness and transparency. Furthermore, because they only collect a portion of work data, it is difficult to accurately evaluate an employee's overall performance. Furthermore, the lack of feedback on evaluation results means that they are unable to provide guidance for employee growth or work improvement.

[0642] 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.

[0643] In this invention, the server includes means for collecting employee work data in real time, means for appropriately structuring the collected work data and converting it into an analyzable format, means for analyzing the preprocessed data using natural language processing and machine learning techniques, means for calculating an evaluation score for each employee based on the analysis results, and means for generating and notifying a report based on the evaluation score and detailed evaluation content. This enables detailed and fair evaluation of employee work performance, ensuring transparency and fairness.

[0644] "Business data" refers to information about the work that employees perform on a daily basis, including audio data from meetings, statements, email content, and data from project management tools.

[0645] "Real-time" refers to data being collected or processed immediately as it is generated, with little or no time delay.

[0646] "Structuring" refers to organizing and converting raw data into a table format, database format, or other format that makes it easier to analyze and process.

[0647] "Natural language processing (NLP)" is a technology that uses computers to analyze human language, and includes topic modeling and sentiment analysis of text data.

[0648] "Machine learning" is a technology that allows computers to use data to learn patterns and automatically perform tasks such as prediction and classification.

[0649] An "evaluation score" is a numerical representation of an employee's work performance, calculated based on specific evaluation criteria.

[0650] A "report" refers to a document or electronic data that compiles information such as evaluation scores, detailed evaluation content, feedback, and areas for improvement.

[0651] "Notification" refers to informing relevant parties of the evaluation results and reports, and includes means such as email or uploading to a portal site.

[0652] "Automatic speech recognition (ASR)" is a technology that converts voice data into text data.

[0653] "Topic modeling" is a technology that automatically extracts hidden topics (themes) from large amounts of text data.

[0654] "Sentiment analysis" is a technique that analyzes emotions and opinions within text data and determines whether they are positive, negative, or neutral.

[0655] "Accuracy" is an evaluation criterion that indicates how error-free a task is being performed.

[0656] "Efficiency" is an evaluation criterion that indicates how efficiently work is being carried out.

[0657] "Creativity" is a measure of the ability to provide new ideas and innovative solutions in the workplace.

[0658] The following description is provided as an embodiment of the present invention: The system is realized through the cooperation of a server, a terminal, and a user, each of which plays a specific role.

[0659] Business data collection

[0660] The server collects employees' work data in real time. Specifically, meeting audio data, comments, email content, and project management tool data are automatically sent to the server from the devices used by employees (PCs and smartphones). For example, what an employee says during an online meeting is collected as audio data using the device's microphone and immediately sent to the server.

[0661] Data Preprocessing

[0662] The server structures the collected business data and converts it into an analyzable format. Voice data is converted into text using automatic speech recognition (ASR) technology, and email content is tokenized. Data obtained from project management tools is also converted into a unified format, allowing for centralized management and easier analysis.

[0663] Analyzing the data

[0664] The server then analyzes the preprocessed data using natural language processing (NLP) and machine learning techniques. Specifically, it performs topic modeling and sentiment analysis on the text data to analyze the content and context of comments. For example, it determines the extent to which comments made during a meeting contribute to the progress of a project. In this process, it classifies the data based on evaluation criteria such as work accuracy, efficiency, and creativity, and generates a score.

[0665] Calculation of evaluation score

[0666] The server calculates an evaluation score for each employee based on the results of the data analysis. For example, if an employee's comments in a meeting significantly contribute to the progress of a project, a high score will be given based on the analysis of the content of those comments. The score also reflects the number of tasks completed in the project management tool and the efficiency of email exchanges.

[0667] Report generation and notification

[0668] The server generates an evaluation report for each employee based on the evaluation score and detailed evaluation content. This report includes specific evaluation details, feedback, and areas for improvement. The generated report is notified to the terminal by email and is also uploaded to an employee-only portal site.

[0669] Examples of concrete examples and prompts

[0670] For example, if employee A participates in a Zoom meeting and makes an important comment during the meeting, the device (PC or smartphone) collects the audio data and sends it to the server. The server then converts this audio data into text using automatic speech recognition technology and analyzes it using natural language processing. If the analysis determines that employee A's comments contributed to the project's success, a high evaluation score is calculated. Similarly, if employee B proposes a new idea for improving work efficiency via email and the content of that proposal has a positive impact on the entire company, the server analyzes the content of that email and reflects it in the evaluation score. Finally, the server generates an evaluation report, notifies the human resources department and superiors via email, and uploads it to a dedicated portal site.

[0671] An example of a prompt sentence might be:

[0672] "Please tell me a specific method for converting what Employee A said during a Zoom meeting into text, analyzing the context, and evaluating his / her contribution to the project."

[0673] "Employee B proposed an idea for improving work efficiency via email. Please explain in detail how the contents of this email can be automatically analyzed and reflected in the evaluation score."

[0674] The above explanation shows how this system collects, pre-processes, analyzes, evaluates, and generates reports to provide a detailed and fair evaluation of employees' work performance, ensuring transparency and fairness and promoting employee growth.

[0675] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0676] Step 1:

[0677] The server collects employee work data in real time.

[0678] Input: Voice data, email data, project management tool data, etc. sent from devices used by employees

[0679] Specific operation: The device (PC or smartphone) captures audio data during the meeting through a microphone and sends it to the server. It also captures task completion information from the project management tool and email content as appropriate and sends them to the server.

[0680] Output: Business data aggregated on the server

[0681] Step 2:

[0682] The server preprocesses and structures the collected business data.

[0683] Input: Raw data collected on the server (voice data, email data, project management tool data, etc.)

[0684] Specific operation: Voice data is converted to text data using automatic speech recognition (ASR), email content is structured by a tokenization server, and data from project management tools is also converted into a unified format.

[0685] Output: Structured data

[0686] Step 3:

[0687] The server analyzes the structured data using natural language processing (NLP) and machine learning techniques.

[0688] Input: Preprocessed structured data (text data, email data, project management data, etc.)

[0689] Specific operations: Topic modeling and sentiment analysis are performed on text data to analyze its context and content, and the data is then classified and scored based on evaluation criteria for operational accuracy, efficiency, and creativity.

[0690] Output: Scored evaluation data

[0691] Step 4:

[0692] The server calculates an evaluation score for each employee based on the results of the data analysis.

[0693] Input: Scored assessment data

[0694] Specific operation: Comprehensively evaluate individual evaluations (for example, contributions made in meetings, number of completed tasks, etc.) and calculate an overall evaluation score for each employee.

[0695] Output: Evaluation score for each employee

[0696] Step 5:

[0697] The server generates and notifies an evaluation report based on the evaluation score and detailed evaluation content.

[0698] Input: Evaluation score and detailed evaluation content for each employee

[0699] Specific operation: A report is generated based on the evaluation results. This report includes detailed evaluations, feedback, and areas for improvement for each task. The generated report is notified by email and also uploaded to the employee-only portal site.

[0700] Output: Notified evaluation report

[0701] By following the above steps, the system can provide a detailed and fair evaluation of employees' work performance, ensuring transparency and fairness.

[0702] (Application example 1)

[0703] 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."

[0704] It is necessary to collect and analyze not only employee work data but also activity data from the work machines in the factory and conduct comprehensive evaluations to improve production efficiency and ensure transparency and fairness in evaluations. It is also considered necessary to take measures to consistently monitor and evaluate the performance of employees and work machines.

[0705] 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.

[0706] In this invention, the server includes means for collecting work data for each employee and activity data for each work machine, means for analyzing the collected work data and activity data and evaluating the performance of employees and work machines based on evaluation indices, means for calculating evaluation scores for each employee and work machine based on the evaluation results, and means for generating and notifying detailed reports of the evaluation scores and evaluation contents. This makes it possible to comprehensively evaluate and improve the performance of employees and work machines, and to increase production efficiency and the transparency and fairness of evaluations.

[0707] "Business data" refers to information related to the work performed by employees, including meeting audio, statements, email content, project management tool data, and the like.

[0708] "Work machines" are automated machines and robots used to carry out production work in factories.

[0709] "Activity data" refers to data related to the activity of a machine, such as the work performed by the machine, its operating status, the occurrence of errors, and the results of quality checks.

[0710] The "server" is an information processing device that collects and analyzes data, calculates evaluation scores, and generates and notifies reports.

[0711] "Evaluation indicators" are standards or criteria for evaluating business and work performance, including accuracy, efficiency, creativity, etc.

[0712] "Natural language processing" is a technology that converts text data into a form that is easy for computers to understand and analyze, and analyzes the content and context.

[0713] "Machine learning technology" is a technology that allows computers to learn from data and perform analysis, predictions, classification, etc.

[0714] An "evaluation score" is a numerical value calculated based on the evaluation index, and represents the performance of an employee and a work machine.

[0715] A "detailed report" is a report that includes the evaluation score and details of the evaluation, and is notified to employees and managers.

[0716] The present invention provides a system for unifying employee and machine performance evaluation. The system operates in the following manner.

[0717] First, the server collects each employee's work data and work machine activity data. Work data includes audio data and comments from meetings attended by employees, email content, and data from project management tools, all of which are collected via the microphones and logs of devices (such as PCs and smartphones). Work machine activity data includes work content, operating status, error occurrence status, quality check results, etc.

[0718] The server then analyzes the collected data using natural language processing (NLP) and machine learning techniques, including:

[0719] For natural language processing, SpaCy is used to convert audio data into text and then analyze the content and context.

[0720] For machine learning technology, Scikit-learn and TensorFlow are used to input collected data into a learning model and perform analysis based on evaluation indicators.

[0721] Based on the analysis results, the server calculates an evaluation score for each employee and work machine. The evaluation score is determined based on the accuracy, efficiency, and creativity of the work and tasks. For example, if an employee's comments in a meeting contribute significantly to the progress of a project, the comments will receive a high score. Similarly, if a work machine performs production tasks efficiently and detects errors early, its activities will receive a high score.

[0722] Finally, the server generates a report based on the evaluation score and detailed evaluation content. This report includes detailed evaluations of each task and work, feedback, and areas for improvement. The generated report is notified by email and also uploaded to a dedicated portal site.

[0723] For example, at the end of each day in a factory, robots automatically send their activity logs to a server, which then analyzes the logs and evaluates the robot's performance. An evaluation report is sent to the manager via email, highlighting areas for improvement and strengths of the robot. Employee comments made during project meetings and ideas for improving work efficiency proposed via email are also evaluated.

[0724] Example prompt sentence:

[0725] "Design a system to analyze the robot's activity log and evaluate its work performance. The log will include records of the work performed, error detection, and quality checks. Include a process to calculate the evaluation score and generate a report to notify the user."

[0726] The main components of the invention are a server equipped with a data collection device, a data analysis device, an evaluation score calculation device, a report generation device and a notification means, which enables integrated management and evaluation of the performance of employees and work machines in factory and office environments.

[0727] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0728] Step 1:

[0729] The server collects each employee's work data and work machine activity data. Specifically, it collects meeting audio data, comments, email content, and project management tool data in real time through the microphones and logs of terminals (PCs and smartphones). It also collects data such as operating status, error occurrences, and quality check results from the sensors and loggers of the work machines. The input is data from the terminals and work machines, and the output is the collected work data and activity data.

[0730] Step 2:

[0731] The server analyzes the collected business data and activity data using natural language processing (NLP) and machine learning technologies. First, it uses speech recognition technology (e.g., Google Speech-to-Text API) to convert the voice data into text. Then, it uses SpaCy to perform content analysis on the text data. The activity data of the work machines is input into a learning model using Scikit-learn or TensorFlow, which classifies and analyzes the data. The input is the collected data, and the output is the data analysis results.

[0732] Step 3:

[0733] The server calculates an evaluation score for each employee and work machine based on the analysis results. Evaluation indicators include the accuracy, efficiency, and creativity of work and tasks. Scores for each indicator are calculated from the analysis results, and an evaluation score is generated by combining these. Specifically, the evaluation criteria include how much each employee's comments in meetings or the content of their emails contribute to the progress of the project, and how early the work machine detects errors. The input is the data analysis results, and the output is the evaluation score.

[0734] Step 4:

[0735] The server generates a detailed report of the evaluation score and the evaluation content. The report includes detailed evaluations and feedback for each task and operation, as well as points for improvement. Specifically, it describes the breakdown of scores for each indicator and how each is reflected in the overall evaluation. The input is the evaluation score and analysis results, and the output is the evaluation report.

[0736] Step 5:

[0737] The server notifies the relevant parties of the generated evaluation report by sending an email or uploading it to a dedicated portal site. The user can check the report via the email or portal site where the notification was received and get feedback. The input is the evaluation report, and the output is a notification message.

[0738] This series of processes enables comprehensive evaluation of the performance of employees and work machines, improving production efficiency and transparency and fairness of evaluations.

[0739] 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.

[0740] The following describes an embodiment of the present invention. The present invention is a system that collects work data of each employee, analyzes the collected data, and evaluates work performance based on evaluation indicators, and further combines it with an emotion engine that recognizes the user's emotions.

[0741] Explanation of program processing

[0742] Business data collection

[0743] The device collects in real time audio spoken during meetings, work-related emails, data from project management tools, etc. For example, audio data recorded with a microphone during a meeting and email data extracted from the email server are all sent to the server.

[0744] Data analysis

[0745] The server converts the voice data into text using a speech recognition engine and analyzes it using natural language processing (NLP). Email data and project management data are also analyzed in the same way, and the importance and contribution of work are classified as evaluation indicators. An emotion engine is also built in, and the user's emotions are analyzed from the voice and text data. This emotion data is used to evaluate the motivation and stress levels of employees when performing their work.

[0746] Emotion Engine Operation

[0747] The emotion engine analyzes voice tone and text writing to identify emotions such as joy, anger, sadness, and surprise. Features such as volume, speed, and intonation are extracted from voice data, while keywords and context are analyzed from text data. For example, if a person speaks passionately during a meeting, they will be evaluated as "highly motivated," while if the content of an email is calm, they will be evaluated as "low stress."

[0748] Calculation of evaluation score

[0749] The server calculates an employee's evaluation score by combining the work evaluation indicators and emotional data. If the work data is highly evaluated and the emotion engine analysis identifies high motivation, the employee's score will be high. Evaluation criteria include work accuracy, efficiency, and creativity, and evaluation weights are set based on these.

[0750] Report generation and notification

[0751] The server generates an evaluation report for each employee based on the evaluation score, detailed evaluation content, and sentiment analysis results. The report includes the evaluation content of each task, a breakdown of the score, feedback based on sentiment data, and areas for improvement. The generated report is automatically sent by email to the person in charge in the relevant department and also uploaded to an employee-only portal site.

[0752] Specific examples

[0753] For example, suppose employee A actively speaks up during a project meeting, and his or her comments contribute significantly to the progress of the project. At that time, the device records the voice data and sends it to the server. The server converts the voice data into text and analyzes the content of the comments using natural language processing technology.

[0754] Furthermore, the emotion engine recognizes high motivation from the tone and content of Employee A's comments. This data is reflected in the evaluation indicators, and the final evaluation score is calculated.

[0755] The evaluation report for Employee A clearly shows his high motivation and contribution to his work, and his supervisor can provide accurate feedback based on the report. In this way, a fair and impartial evaluation is achieved.

[0756] The above is a specific embodiment of an employee evaluation system that combines an emotion engine. This system enables comprehensive evaluation that takes into account not only an employee's work performance but also their emotional state.

[0757] The processing flow will be explained below.

[0758] Step 1: Collect business data

[0759] The devices collect data on employees' daily work. For example, speech during meetings is recorded through a microphone, and work-related email data is obtained from the email server. Data from project management tools is also collected periodically. This data is sent to the server in real time.

[0760] Step 2: Preprocessing the data

[0761] The server converts voice data received from the device into text data using a voice recognition engine, and also converts email data and project management data into a format that can be analyzed directly and stored in a database.

[0762] Step 3: Extracting emotion data

[0763] The server then uses an emotion engine to analyze the user's emotions from the converted text data. Features such as volume, speed, and intonation are extracted from the voice data, while specific keywords and context are analyzed to identify emotions from the text data. For example, if the speech is passionate, the analysis result is stored in the database as "high motivation."

[0764] Step 4: Analyze business data

[0765] The server analyzes text data and project management data using natural language processing (NLP) technology, classifying the contribution and importance of work as evaluation indicators. For example, it analyzes how comments made during a meeting contributed to the progress of a project, and stores the results in a database.

[0766] Step 5: Calculating the evaluation score

[0767] The server calculates an evaluation score for each employee by combining the analyzed work data and emotional data. Evaluation weights are set based on evaluation criteria such as work accuracy, efficiency, and creativity, and the emotional data is also taken into account when calculating the score. For example, if an employee's work contribution is high and their emotional data is "highly motivated," the employee's evaluation score will be high.

[0768] Step 6: Generate reports

[0769] The server generates an evaluation report for each employee based on the evaluation score and detailed evaluation content. The report includes the evaluation content of each task, a breakdown of the score, feedback based on emotional data, and areas for improvement. The generated report is saved in a database.

[0770] Step 7: Notification and Delivery

[0771] The server notifies the automatically generated evaluation report to the user (supervisor or HR department) by email, and also uploads the report to an employee-only portal site so that employees can check their own evaluations at any time.

[0772] Step 8: Managing Feedback

[0773] Users can review the evaluation report and add feedback as needed. This feedback is also saved on the server and reflected in the next evaluation. Through this process, fair and impartial employee evaluations are achieved.

[0774] Example 2

[0775] 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."

[0776] When evaluating employee performance, conventional systems only consider work data, making it difficult to properly reflect employees' emotional state and motivation. Furthermore, there are insufficient methods for efficiently and automatically processing collected data to provide fair and impartial evaluations. This results in one-sided evaluations, which makes it difficult to fully evaluate employees' true contributions and motivation.

[0777] 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.

[0778] In this invention, the server includes means for analyzing each employee's work data using natural language processing and emotion analysis technology, and evaluating the employee's work performance based on work evaluation indicators and emotion data, means for calculating an evaluation score for each employee by combining the evaluation indicators and emotion data, and means for generating a detailed report of the evaluation score and evaluation content and notifying related departments and employees. This makes it possible to analyze and evaluate the work data and emotion data in an integrated manner, and to comprehensively evaluate the employee's work performance and emotions.

[0779] "Employee business data" refers to all data generated by or related to an employee's daily work, including, for example, audio recordings, work-related emails, and data from project management tools.

[0780] "Natural language processing" is a technology that enables computers to understand, analyze, and generate natural human language, and is a technology that can analyze text data and audio data to extract meaning.

[0781] "Emotion analysis technology" is a technology that identifies and analyzes human emotions from voice and text data, and evaluates emotional states by analyzing volume, intonation, keywords, and context.

[0782] "Evaluation indicators" are standards for evaluating an employee's work performance and contribution, and specifically include accuracy, efficiency, creativity, and emotional aspects of work.

[0783] An "evaluation score" is a numerical value calculated based on evaluation indicators, and is used to comprehensively evaluate an employee's work performance and emotional state.

[0784] A "detailed report" is a document that summarizes the evaluation score, evaluation content, and sentiment analysis results, and is used to communicate the evaluation results to employees and related departments.

[0785] "Speech recognition technology" is a technology that converts voice data into text data, and is a technology that can analyze voice data and accurately convert what is spoken into text.

[0786] "Machine learning technology" is a technology in which a computer learns patterns from data and makes predictions and judgments based on those patterns, and is used to analyze and evaluate business data.

[0787] "Emotional data" is data obtained using emotion analysis technology, and indicates employees' emotional state, motivation, stress level, etc.

[0788] The following describes in detail the mode for carrying out this invention. This system uses major hardware and software to collect and analyze employee work data and emotional data, and calculate and notify an evaluation score. The procedure is explained below.

[0789] Business data collection

[0790] The device collects various business data in real time, such as the audio of employees' speech during meetings, work-related emails, and data from project management tools. Specifically, audio recordings are made using a microphone during meetings, and emails are extracted using an email client. This data is then immediately sent to the server.

[0791] Converting audio data to text

[0792] The server converts the received audio data into text using the Google Speech-to-Text API, and during this process, it also performs pre-processing such as cleaning and noise removal.

[0793] Data analysis

[0794] The server uses natural language processing (NLP) technology to analyze text data (voice data converted to text and email data) and data obtained from project management tools. Specific NLP technologies include the Python NLTK library and SpaCy. For example, the server evaluates the contribution and importance of employees' comments and sets appropriate evaluation indicators.

[0795] Emotional Data Analysis

[0796] The server uses emotion analysis technology (for example, IBM Watson Natural Language Understanding) to analyze employee emotions from voice and text data. Features such as volume, intonation, and speed are extracted from voice data, while keywords and context are analyzed from text data. For example, passionate comments during a meeting can be evaluated as "highly motivated," while calm email content can be evaluated as "low stress."

[0797] Calculation of evaluation score

[0798] The server combines work evaluation indicators and emotional data to calculate an evaluation score for each employee. This evaluation uses evaluation criteria such as accuracy, efficiency, and creativity, each of which is weighted. For example, if an employee's work is highly accurate and the emotional analysis results indicate high motivation, the employee's evaluation score will be high.

[0799] Report generation and notification

[0800] The server generates an evaluation report for each employee based on the calculated evaluation score and detailed evaluation content. This report includes the evaluation content of each job, a breakdown of the score, the results of sentiment analysis, feedback, and areas for improvement. The generated report is sent by email to the person in charge in the relevant department and also uploaded to an employee-only portal site.

[0801] Specific examples

[0802] For example, suppose Employee A actively speaks up during a project meeting, and his or her comments contribute significantly to the progress of the project. At that time, the device records the voice data and sends it to the server in real time. The server converts the received voice data into text and analyzes the content of the comments using NLP technology. Furthermore, the emotion engine recognizes Employee A's high motivation from the tone and content of his or her comments, and this data is reflected in the evaluation indicators.

[0803] Example prompts to input to the generative AI model

[0804] "Employee A actively spoke up during the project meeting, and his comments contributed greatly to the progress of the project. Please explain in detail the data collected, the analysis method, the specific operation of the emotion engine, how the evaluation score was calculated, and the contents of the generated report."

[0805] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0806] Step 1:

[0807] Business data collection

[0808] The device collects real-time data such as employee speech during meetings, work-related emails, and data from project management tools. For example, it can record audio using a conference microphone and extract work-related emails from an email client.

[0809] Input: Meeting audio data, email data, project management tool data

[0810] Output: Send collected data (audio file, email data file, project data file) to the server.

[0811] Step 2:

[0812] Converting audio data to text

[0813] The server converts the received audio data into text using the Google Speech-to-Text API, which also cleans and removes noise from the audio data.

[0814] Input: Audio file

[0815] Output: Text data (audio file converted to text)

[0816] Step 3:

[0817] Data analysis

[0818] The server analyzes text data, email data, and project management data using natural language processing (NLP) technology. Specifically, it uses Python's NLTK library and SpaCy to analyze the text data and classify it into evaluation indicators such as the importance and contribution of tasks.

[0819] Input: Text data, email data, project data

[0820] Output: Data with business performance indicators

[0821] Step 4:

[0822] Emotional Data Analysis

[0823] The server uses emotion analysis technology (e.g., IBM Watson Natural Language Understanding) to analyze emotions from voice and text data. Specifically, it extracts volume, speed, and intonation from voice data, and analyzes keywords and context from text data to assess the employee's emotional state.

[0824] Input: Text data, speech analysis data

[0825] Output: Emotion analysis results (emotional state evaluation data)

[0826] Step 5:

[0827] Calculation of evaluation score

[0828] The server combines performance metrics and emotional data to calculate an employee evaluation score, which includes criteria such as accuracy, efficiency, and creativity, each of which is weighted.

[0829] Input: Data with business evaluation indicators, sentiment analysis results

[0830] Output: Evaluation score

[0831] Step 6:

[0832] Report generation and notification

[0833] The server generates an evaluation report for each employee based on the evaluation score and detailed evaluation content. This report includes the evaluation content of each task, a breakdown of the score, the results of sentiment analysis, feedback and areas for improvement, etc. The generated report is sent by email to the person in charge in the relevant department and also uploaded to the employee-only portal site.

[0834] Input: Evaluation score, detailed evaluation content (job evaluation, emotional data)

[0835] Output: Evaluation report (email and upload to portal site)

[0836] (Application example 2)

[0837] 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."

[0838] Conventional employee evaluation systems only evaluate employees' work performance, making it difficult to provide a comprehensive evaluation that reflects their actual emotions and motivation levels. Furthermore, there is a lack of means to grasp the quality of customer service in physical stores in real time and provide appropriate feedback. To address these issues, there is a need for a system that comprehensively evaluates employees' work performance and emotions.

[0839] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting work data of each employee, means for analyzing the collected work data and evaluating the work performance of the employee based on the evaluation index, means for calculating an evaluation score for each employee based on the evaluation results, means for generating and notifying a detailed report of the evaluation score and evaluation content, means for using a wearable device to collect voice data during customer interactions, and means for analyzing the collected voice data using natural language processing and an emotion engine to evaluate the emotional tone and work performance of the employee. This enables real-time evaluation and feedback of employees in physical stores.

[0840] "Each employee's business data" refers to all data generated when an employee performs their work, such as audio spoken during business meetings, work-related emails, and data from project management tools.

[0841] "Natural language processing" is a technology that allows computers to understand and process human language, and involves tasks such as analyzing sentences and recognizing emotions.

[0842] An "emotion engine" refers to a system that includes algorithms that analyze voice tone and text content to identify specific emotions.

[0843] A "wearable device" is an electronic device that can be worn on the body and is equipped with a microphone and sensors for collecting voice data.

[0844] "Evaluation indicators" are specific standards or measures used to evaluate an employee's work performance, and include accuracy, efficiency, creativity, etc.

[0845] An "evaluation score" is numerical data calculated based on evaluation indicators, and quantitatively indicates an employee's work performance and emotional state.

[0846] A "report" is a document containing an evaluation score, detailed evaluation content, and feedback, which is communicated to employees and managers.

[0847] An embodiment of this invention is a comprehensive evaluation system that collects employee work data, evaluates work performance based on evaluation indicators, and also considers employee motivation and stress levels in combination with an emotion engine. Specifically, it includes a series of processes: collecting voice data using a wearable device, analyzing the data using natural language processing (NLP), evaluating emotions using the emotion engine, and generating and notifying reports of the evaluation results.

[0848] Program Description

[0849] Audio data collection

[0850] The server uses wearable devices (e.g., smart glasses or smartphones) as terminals to collect voice data in real time during customer interactions, thereby recording the content and tone of the employee's dialogue.

[0851] Analysis of audio data

[0852] The server converts the collected voice data into text using a speech recognition engine and analyzes it using natural language processing (NLP) technology. Specifically, it converts voice to text using Python's speech_recognition library and uses Hugging Face's transformers library to use daigo / bert-base-japanese-sentiment, a sentiment analysis model specifically for Japanese.

[0853] Emotion Engine Operation

[0854] The server calculates an emotion score from the analyzed text data using an emotion engine, for example, the textblob library, to analyze the polarity (positive or negative) and subjectivity of the text data and evaluate the employee's emotional state.

[0855] Calculation of evaluation score

[0856] The server combines the work evaluation indicators and emotional data to calculate an employee evaluation score, which is calculated based on the emotion score, polarity score, and subjectivity score, and uses the results to comprehensively evaluate the employee's work performance and emotional state.

[0857] Report generation and notification

[0858] The server generates an evaluation report for each employee based on the evaluation score, detailed evaluation content, and sentiment analysis results. The generated report is automatically sent by email to the relevant department and also uploaded to an employee-only portal site.

[0859] Specific examples

[0860] For example, if a staff member is engaging in friendly and enthusiastic conversation while interacting with a customer, the voice data will be collected and analyzed by the smart glasses. Based on the analysis results, the staff member's evaluation score will be increased, and the results will be generated as a report and notified to the manager. In this way, real-time evaluation and feedback of employees in physical stores will be possible.

[0861] Prompt Sentence Examples

[0862] "Evaluate your sentiment and performance score based on the following text: 'Hey customer, what do you think of this product? It's very popular and we think you'll be pleased with it.'"

[0863] This invention enables the evaluation of the work performance of employees in physical stores in a fair and efficient manner in real time, thereby enabling the provision of high-quality customer service.

[0864] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0865] Step 1:

[0866] The terminal collects voice data in real time when employees interact with customers via wearable devices (smart glasses or smartphones). The input is the voice of the conversation with the customer, and the output is the collected voice data. This voice data is sent to the server.

[0867] Step 2:

[0868] The server converts the collected voice data into text using a voice recognition engine. The input is voice data and the output is text data. This process uses the Python speech_recognition library.

[0869] Step 3:

[0870] The server analyzes the text data using natural language processing (NLP) and calculates a sentiment score using an emotion engine. The input is text data, and the output is the sentiment score and the analyzed text data. This analysis is performed using the daigo / bert-base-japanese-sentiment model from the transformers library.

[0871] Step 4:

[0872] The server analyzes the polarity (positive or negative) and subjectivity of the text data based on the output of the emotion engine. The input is the analyzed text data, and the output is the polarity score and the subjectivity score. This process uses the textblob library.

[0873] Step 5:

[0874] The server calculates an employee evaluation score by combining the work evaluation indicators and emotional data. The inputs are the emotional score, polarity score, and subjectivity score, and the output is a comprehensive evaluation score. This allows for a comprehensive evaluation of the employee's work performance and emotional state.

[0875] Step 6:

[0876] The server generates an evaluation report for each employee based on the evaluation score, detailed evaluation content, and sentiment analysis results. The input is the overall evaluation score and analysis results, and the output is the evaluation report.

[0877] Step 7:

[0878] The server automatically sends the generated evaluation report to the relevant department by email and also uploads it to the employee-only portal site.The input is the evaluation report and the output is the delivered report.

[0879] In this way, through a series of processes from collecting voice data to analyzing, evaluating, and notifying, this system makes it possible to comprehensively evaluate employees' work performance and emotional state and provide feedback in real time.

[0880] 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.

[0881] 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.

[0882] 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.

[0883] [Fourth embodiment]

[0884] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0885] 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.

[0886] 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).

[0887] 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.

[0888] 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.

[0889] 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).

[0890] 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.

[0891] 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.

[0892] 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.

[0893] 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.

[0894] 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.

[0895] 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.

[0896] 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."

[0897] As a form for implementing the invention, this system performs a series of processes: collects work data for each employee, analyzes the collected data, evaluates work performance based on evaluation indicators, calculates an evaluation score for each employee based on the results, and generates and notifies a detailed report of the evaluation content.

[0898] Explanation of program processing

[0899] Business data collection

[0900] The server collects in real time audio data and comments from meetings attended by employees, email content, data from project management tools, etc. For example, audio data and operation logs are sent to the server via the microphones and logs of devices (PCs and smartphones) used during meetings.

[0901] Data analysis and evaluation

[0902] The server analyzes the collected data using natural language processing (NLP) and machine learning technologies. Specifically, it converts the audio data from meetings into text and analyzes the content and context of what is being said. It also analyzes email content and project progress data in the same way, categorizing each person's contribution to the task and their importance as evaluation indicators. In this process, it assigns scores based on fixed evaluation criteria (such as accuracy, efficiency, and creativity of the task).

[0903] Calculation of evaluation score

[0904] The server calculates an evaluation score for each employee based on the analysis results. For example, if an employee speaks in a meeting and their comments contribute significantly to the progress of a project, that comment will be given a high score. Other factors that contribute to the score include the number of project tasks completed and the efficiency of email exchanges.

[0905] Report generation and notification

[0906] The server generates an evaluation report for each employee based on the calculated evaluation score and detailed evaluation content. This report includes detailed evaluations and feedback for each task, as well as areas for improvement for the employee. The generated report is notified to relevant parties by email and is also uploaded to an employee-only portal site.

[0907] Specific examples

[0908] For example, suppose employee A has achieved results in an important project. All comments made in meetings using devices (PCs or smartphones) and task completion data recorded in the project management tool are collected on a server. The collected voice data is converted into text and analyzed using natural language processing. If it turns out that these comments made in the meeting contributed significantly to the success of the project, employee A's evaluation score will be high.

[0909] If Employee B proposes a new idea for improving work efficiency by email and the proposal has a positive impact on the company as a whole, the server analyzes the email content and reflects it in the evaluation score.Finally, the server generates an evaluation report for Employees A and B and notifies the HR department and their superiors.This report includes specific evaluation details as well as areas for improvement and additional feedback.

[0910] As described above, the present invention ensures transparency and fairness in evaluations by collecting detailed and fair employee work data and conducting multifaceted evaluations.

[0911] The processing flow will be explained below.

[0912] Step 1: Collect business data

[0913] The devices collect data on the daily work of each employee. For example, speech during meetings is recorded through a microphone, and work-related email data sent and received from the email server is also collected. The collected data is sent to the server in real time.

[0914] Step 2: Save your data

[0915] The server temporarily stores the business data received from the terminal in a buffer, then transfers it to the database and stores it in the appropriate format. This storage process is necessary to prevent data loss and facilitate subsequent analysis.

[0916] Step 3: Preprocessing the data

[0917] The server preprocesses the stored data: voice data is converted to text using a speech recognition engine; email data is processed using natural language processing (NLP) techniques to extract important keywords and phrases; and project management data is extracted to identify the progress and completion status of each task.

[0918] Step 4: Analyze the evaluation metrics

[0919] The server then analyzes the preprocessed data according to evaluation criteria. For example, it analyzes the context of comments made in meetings and evaluates how much those comments contributed to the progress of the project. Other evaluation criteria include the quality of submitted ideas and documents, the content of emails, and the speed of responses.

[0920] Step 5: Scoring and evaluation

[0921] The server calculates an evaluation score for each employee based on the analysis results. For example, it sets evaluation weights for each job based on evaluation criteria such as accuracy, efficiency, and creativity, and calculates an overall score. This score is saved in a database and used to generate reports, which will be described later.

[0922] Step 6: Generate reports

[0923] The server generates an evaluation report for each employee based on the evaluation score and detailed evaluation content. This report includes the evaluation content of each job, a score breakdown, areas for improvement, and feedback. The generated report is prepared in a format suitable for the HR department or supervisor.

[0924] Step 7: Notification and Delivery

[0925] The server notifies the automatically generated evaluation report to the user (supervisor or HR department) by email, and also uploads the report to an employee-only portal site so that employees can check their own evaluations at any time.

[0926] This is the specific process flow of an employee evaluation system that utilizes AI. This enables fair and impartial evaluations, which improves employee motivation and provides evaluations that employees can be satisfied with.

[0927] Example 1

[0928] 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."

[0929] When evaluating employee performance, traditional evaluation systems tend to rely on subjective judgment and often lack fairness and transparency. Furthermore, because they only collect a portion of work data, it is difficult to accurately evaluate an employee's overall performance. Furthermore, the lack of feedback on evaluation results means that they are unable to provide guidance for employee growth or work improvement.

[0930] 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.

[0931] In this invention, the server includes means for collecting employee work data in real time, means for appropriately structuring the collected work data and converting it into an analyzable format, means for analyzing the preprocessed data using natural language processing and machine learning techniques, means for calculating an evaluation score for each employee based on the analysis results, and means for generating and notifying a report based on the evaluation score and detailed evaluation content. This enables detailed and fair evaluation of employee work performance, ensuring transparency and fairness.

[0932] "Business data" refers to information about the work that employees perform on a daily basis, including audio data from meetings, statements, email content, and data from project management tools.

[0933] "Real-time" refers to data being collected or processed immediately as it is generated, with little or no time delay.

[0934] "Structuring" refers to organizing and converting raw data into a table format, database format, or other format that makes it easier to analyze and process.

[0935] "Natural language processing (NLP)" is a technology that uses computers to analyze human language, and includes topic modeling and sentiment analysis of text data.

[0936] "Machine learning" is a technology that allows computers to use data to learn patterns and automatically perform tasks such as prediction and classification.

[0937] An "evaluation score" is a numerical representation of an employee's work performance, calculated based on specific evaluation criteria.

[0938] A "report" refers to a document or electronic data that compiles information such as evaluation scores, detailed evaluation content, feedback, and areas for improvement.

[0939] "Notification" refers to informing relevant parties of the evaluation results and reports, and includes means such as email or uploading to a portal site.

[0940] "Automatic speech recognition (ASR)" is a technology that converts voice data into text data.

[0941] "Topic modeling" is a technology that automatically extracts hidden topics (themes) from large amounts of text data.

[0942] "Sentiment analysis" is a technique that analyzes emotions and opinions within text data and determines whether they are positive, negative, or neutral.

[0943] "Accuracy" is an evaluation criterion that indicates how error-free a task is being performed.

[0944] "Efficiency" is an evaluation criterion that indicates how efficiently work is being carried out.

[0945] "Creativity" is a measure of the ability to provide new ideas and innovative solutions in the workplace.

[0946] The following description is provided as an embodiment of the present invention: The system is realized through the cooperation of a server, a terminal, and a user, each of which plays a specific role.

[0947] Business data collection

[0948] The server collects employees' work data in real time. Specifically, meeting audio data, comments, email content, and project management tool data are automatically sent to the server from the devices used by employees (PCs and smartphones). For example, what an employee says during an online meeting is collected as audio data using the device's microphone and immediately sent to the server.

[0949] Data Preprocessing

[0950] The server structures the collected business data and converts it into an analyzable format. Voice data is converted into text using automatic speech recognition (ASR) technology, and email content is tokenized. Data obtained from project management tools is also converted into a unified format, allowing for centralized management and easier analysis.

[0951] Analyzing the data

[0952] The server then analyzes the preprocessed data using natural language processing (NLP) and machine learning techniques. Specifically, it performs topic modeling and sentiment analysis on the text data to analyze the content and context of comments. For example, it determines the extent to which comments made during a meeting contribute to the progress of a project. In this process, it classifies the data based on evaluation criteria such as work accuracy, efficiency, and creativity, and generates a score.

[0953] Calculation of evaluation score

[0954] The server calculates an evaluation score for each employee based on the results of the data analysis. For example, if an employee's comments in a meeting significantly contribute to the progress of a project, a high score will be given based on the analysis of the content of those comments. The score also reflects the number of tasks completed in the project management tool and the efficiency of email exchanges.

[0955] Report generation and notification

[0956] The server generates an evaluation report for each employee based on the evaluation score and detailed evaluation content. This report includes specific evaluation details, feedback, and areas for improvement. The generated report is notified to the terminal by email and is also uploaded to an employee-only portal site.

[0957] Examples of concrete examples and prompts

[0958] For example, if employee A participates in a Zoom meeting and makes an important comment during the meeting, the device (PC or smartphone) collects the audio data and sends it to the server. The server then converts this audio data into text using automatic speech recognition technology and analyzes it using natural language processing. If the analysis determines that employee A's comments contributed to the project's success, a high evaluation score is calculated. Similarly, if employee B proposes a new idea for improving work efficiency via email and the content of that proposal has a positive impact on the entire company, the server analyzes the content of that email and reflects it in the evaluation score. Finally, the server generates an evaluation report, notifies the human resources department and superiors via email, and uploads it to a dedicated portal site.

[0959] An example of a prompt sentence might be:

[0960] "Please tell me a specific method for converting what Employee A said during a Zoom meeting into text, analyzing the context, and evaluating his / her contribution to the project."

[0961] "Employee B proposed an idea for improving work efficiency via email. Please explain in detail how the contents of this email can be automatically analyzed and reflected in the evaluation score."

[0962] The above explanation shows how this system collects, pre-processes, analyzes, evaluates, and generates reports to provide a detailed and fair evaluation of employees' work performance, ensuring transparency and fairness and promoting employee growth.

[0963] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0964] Step 1:

[0965] The server collects employee work data in real time.

[0966] Input: Voice data, email data, project management tool data, etc. sent from devices used by employees

[0967] Specific operation: The device (PC or smartphone) captures audio data during the meeting through a microphone and sends it to the server. It also captures task completion information from the project management tool and email content as appropriate and sends them to the server.

[0968] Output: Business data aggregated on the server

[0969] Step 2:

[0970] The server preprocesses and structures the collected business data.

[0971] Input: Raw data collected on the server (voice data, email data, project management tool data, etc.)

[0972] Specific operation: Voice data is converted to text data using automatic speech recognition (ASR), email content is structured by a tokenization server, and data from project management tools is also converted into a unified format.

[0973] Output: Structured data

[0974] Step 3:

[0975] The server analyzes the structured data using natural language processing (NLP) and machine learning techniques.

[0976] Input: Preprocessed structured data (text data, email data, project management data, etc.)

[0977] Specific operations: Topic modeling and sentiment analysis are performed on text data to analyze its context and content, and the data is then classified and scored based on evaluation criteria for operational accuracy, efficiency, and creativity.

[0978] Output: Scored evaluation data

[0979] Step 4:

[0980] The server calculates an evaluation score for each employee based on the results of the data analysis.

[0981] Input: Scored assessment data

[0982] Specific operation: Comprehensively evaluate individual evaluations (for example, contributions made in meetings, number of completed tasks, etc.) and calculate an overall evaluation score for each employee.

[0983] Output: Evaluation score for each employee

[0984] Step 5:

[0985] The server generates and notifies an evaluation report based on the evaluation score and detailed evaluation content.

[0986] Input: Evaluation score and detailed evaluation content for each employee

[0987] Specific operation: A report is generated based on the evaluation results. This report includes detailed evaluations, feedback, and areas for improvement for each task. The generated report is notified by email and also uploaded to the employee-only portal site.

[0988] Output: Notified evaluation report

[0989] By following the above steps, the system can provide a detailed and fair evaluation of employees' work performance, ensuring transparency and fairness.

[0990] (Application example 1)

[0991] 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."

[0992] It is necessary to collect and analyze not only employee work data but also activity data from the work machines in the factory and conduct comprehensive evaluations to improve production efficiency and ensure transparency and fairness in evaluations. It is also considered necessary to take measures to consistently monitor and evaluate the performance of employees and work machines.

[0993] 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.

[0994] In this invention, the server includes means for collecting work data for each employee and activity data for each work machine, means for analyzing the collected work data and activity data and evaluating the performance of employees and work machines based on evaluation indices, means for calculating evaluation scores for each employee and work machine based on the evaluation results, and means for generating and notifying detailed reports of the evaluation scores and evaluation contents. This makes it possible to comprehensively evaluate and improve the performance of employees and work machines, and to increase production efficiency and the transparency and fairness of evaluations.

[0995] "Business data" refers to information related to the work performed by employees, including meeting audio, statements, email content, project management tool data, and the like.

[0996] "Work machines" are automated machines and robots used to carry out production work in factories.

[0997] "Activity data" refers to data related to the activity of a machine, such as the work performed by the machine, its operating status, the occurrence of errors, and the results of quality checks.

[0998] The "server" is an information processing device that collects and analyzes data, calculates evaluation scores, and generates and notifies reports.

[0999] "Evaluation indicators" are standards or criteria for evaluating business and work performance, including accuracy, efficiency, creativity, etc.

[1000] "Natural language processing" is a technology that converts text data into a form that is easy for computers to understand and analyze, and analyzes the content and context.

[1001] "Machine learning technology" is a technology that allows computers to learn from data and perform analysis, predictions, classification, etc.

[1002] An "evaluation score" is a numerical value calculated based on the evaluation index, and represents the performance of an employee and a work machine.

[1003] A "detailed report" is a report that includes the evaluation score and details of the evaluation, and is notified to employees and managers.

[1004] The present invention provides a system for unifying employee and machine performance evaluation. The system operates in the following manner.

[1005] First, the server collects each employee's work data and work machine activity data. Work data includes audio data and comments from meetings attended by employees, email content, and data from project management tools, all of which are collected via the microphones and logs of devices (such as PCs and smartphones). Work machine activity data includes work content, operating status, error occurrence status, quality check results, etc.

[1006] The server then analyzes the collected data using natural language processing (NLP) and machine learning techniques, including:

[1007] For natural language processing, SpaCy is used to convert audio data into text and then analyze the content and context.

[1008] For machine learning technology, Scikit-learn and TensorFlow are used to input collected data into a learning model and perform analysis based on evaluation indicators.

[1009] Based on the analysis results, the server calculates an evaluation score for each employee and work machine. The evaluation score is determined based on the accuracy, efficiency, and creativity of the work and tasks. For example, if an employee's comments in a meeting contribute significantly to the progress of a project, the comments will receive a high score. Similarly, if a work machine performs production tasks efficiently and detects errors early, its activities will receive a high score.

[1010] Finally, the server generates a report based on the evaluation score and detailed evaluation content. This report includes detailed evaluations of each task and work, feedback, and areas for improvement. The generated report is notified by email and also uploaded to a dedicated portal site.

[1011] For example, at the end of each day in a factory, robots automatically send their activity logs to a server, which then analyzes the logs and evaluates the robot's performance. An evaluation report is sent to the manager via email, highlighting areas for improvement and strengths of the robot. Employee comments made during project meetings and ideas for improving work efficiency proposed via email are also evaluated.

[1012] Example prompt sentence:

[1013] "Design a system to analyze the robot's activity log and evaluate its work performance. The log will include records of the work performed, error detection, and quality checks. Include a process to calculate the evaluation score and generate a report to notify the user."

[1014] The main components of the invention are a server equipped with a data collection device, a data analysis device, an evaluation score calculation device, a report generation device and a notification means, which enables integrated management and evaluation of the performance of employees and work machines in factory and office environments.

[1015] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1016] Step 1:

[1017] The server collects each employee's work data and work machine activity data. Specifically, it collects meeting audio data, comments, email content, and project management tool data in real time through the microphones and logs of terminals (PCs and smartphones). It also collects data such as operating status, error occurrences, and quality check results from the sensors and loggers of the work machines. The input is data from the terminals and work machines, and the output is the collected work data and activity data.

[1018] Step 2:

[1019] The server analyzes the collected business data and activity data using natural language processing (NLP) and machine learning technologies. First, it uses speech recognition technology (e.g., Google Speech-to-Text API) to convert the voice data into text. Then, it uses SpaCy to perform content analysis on the text data. The activity data of the work machines is input into a learning model using Scikit-learn or TensorFlow, which classifies and analyzes the data. The input is the collected data, and the output is the data analysis results.

[1020] Step 3:

[1021] The server calculates an evaluation score for each employee and work machine based on the analysis results. Evaluation indicators include the accuracy, efficiency, and creativity of work and tasks. Scores for each indicator are calculated from the analysis results, and an evaluation score is generated by combining these. Specifically, the evaluation criteria include how much each employee's comments in meetings or the content of their emails contribute to the progress of the project, and how early the work machine detects errors. The input is the data analysis results, and the output is the evaluation score.

[1022] Step 4:

[1023] The server generates a detailed report of the evaluation score and the evaluation content. The report includes detailed evaluations and feedback for each task and operation, as well as points for improvement. Specifically, it describes the breakdown of scores for each indicator and how each is reflected in the overall evaluation. The input is the evaluation score and analysis results, and the output is the evaluation report.

[1024] Step 5:

[1025] The server notifies the relevant parties of the generated evaluation report by sending an email or uploading it to a dedicated portal site. The user can check the report via the email or portal site where the notification was received and get feedback. The input is the evaluation report, and the output is a notification message.

[1026] This series of processes enables comprehensive evaluation of the performance of employees and work machines, improving production efficiency and transparency and fairness of evaluations.

[1027] 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.

[1028] The following describes an embodiment of the present invention. The present invention is a system that collects work data of each employee, analyzes the collected data, and evaluates work performance based on evaluation indicators, and further combines it with an emotion engine that recognizes the user's emotions.

[1029] Explanation of program processing

[1030] Business data collection

[1031] The device collects in real time audio spoken during meetings, work-related emails, data from project management tools, etc. For example, audio data recorded with a microphone during a meeting and email data extracted from the email server are all sent to the server.

[1032] Data analysis

[1033] The server converts the voice data into text using a speech recognition engine and analyzes it using natural language processing (NLP). Email data and project management data are also analyzed in the same way, and the importance and contribution of work are classified as evaluation indicators. An emotion engine is also built in, and the user's emotions are analyzed from the voice and text data. This emotion data is used to evaluate the motivation and stress levels of employees when performing their work.

[1034] Emotion Engine Operation

[1035] The emotion engine analyzes voice tone and text writing to identify emotions such as joy, anger, sadness, and surprise. Features such as volume, speed, and intonation are extracted from voice data, while keywords and context are analyzed from text data. For example, if a person speaks passionately during a meeting, they will be evaluated as "highly motivated," while if the content of an email is calm, they will be evaluated as "low stress."

[1036] Calculation of evaluation score

[1037] The server calculates an employee's evaluation score by combining the work evaluation indicators and emotional data. If the work data is highly evaluated and the emotion engine analysis identifies high motivation, the employee's score will be high. Evaluation criteria include work accuracy, efficiency, and creativity, and evaluation weights are set based on these.

[1038] Report generation and notification

[1039] The server generates an evaluation report for each employee based on the evaluation score, detailed evaluation content, and sentiment analysis results. The report includes the evaluation content of each task, a breakdown of the score, feedback based on sentiment data, and areas for improvement. The generated report is automatically sent by email to the person in charge in the relevant department and also uploaded to an employee-only portal site.

[1040] Specific examples

[1041] For example, suppose employee A actively speaks up during a project meeting, and his or her comments contribute significantly to the progress of the project. At that time, the device records the voice data and sends it to the server. The server converts the voice data into text and analyzes the content of the comments using natural language processing technology.

[1042] Furthermore, the emotion engine recognizes high motivation from the tone and content of Employee A's comments. This data is reflected in the evaluation indicators, and the final evaluation score is calculated.

[1043] The evaluation report for Employee A clearly shows his high motivation and contribution to his work, and his supervisor can provide accurate feedback based on the report. In this way, a fair and impartial evaluation is achieved.

[1044] The above is a specific embodiment of an employee evaluation system that combines an emotion engine. This system enables comprehensive evaluation that takes into account not only an employee's work performance but also their emotional state.

[1045] The processing flow will be explained below.

[1046] Step 1: Collect business data

[1047] The devices collect data on employees' daily work. For example, speech during meetings is recorded through a microphone, and work-related email data is obtained from the email server. Data from project management tools is also collected periodically. This data is sent to the server in real time.

[1048] Step 2: Preprocessing the data

[1049] The server converts voice data received from the device into text data using a voice recognition engine, and also converts email data and project management data into a format that can be analyzed directly and stored in a database.

[1050] Step 3: Extracting emotion data

[1051] The server then uses an emotion engine to analyze the user's emotions from the converted text data. Features such as volume, speed, and intonation are extracted from the voice data, while specific keywords and context are analyzed to identify emotions from the text data. For example, if the speech is passionate, the analysis result is stored in the database as "high motivation."

[1052] Step 4: Analyze business data

[1053] The server analyzes text data and project management data using natural language processing (NLP) technology, classifying the contribution and importance of work as evaluation indicators. For example, it analyzes how comments made during a meeting contributed to the progress of a project, and stores the results in a database.

[1054] Step 5: Calculating the evaluation score

[1055] The server calculates an evaluation score for each employee by combining the analyzed work data and emotional data. Evaluation weights are set based on evaluation criteria such as work accuracy, efficiency, and creativity, and the emotional data is also taken into account when calculating the score. For example, if an employee's work contribution is high and their emotional data is "highly motivated," the employee's evaluation score will be high.

[1056] Step 6: Generate reports

[1057] The server generates an evaluation report for each employee based on the evaluation score and detailed evaluation content. The report includes the evaluation content of each task, a breakdown of the score, feedback based on emotional data, and areas for improvement. The generated report is saved in a database.

[1058] Step 7: Notification and Delivery

[1059] The server notifies the automatically generated evaluation report to the user (supervisor or HR department) by email, and also uploads the report to an employee-only portal site so that employees can check their own evaluations at any time.

[1060] Step 8: Managing Feedback

[1061] Users can review the evaluation report and add feedback as needed. This feedback is also saved on the server and reflected in the next evaluation. Through this process, fair and impartial employee evaluations are achieved.

[1062] Example 2

[1063] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1064] When evaluating employee performance, conventional systems only consider work data, making it difficult to properly reflect employees' emotional state and motivation. Furthermore, there are insufficient methods for efficiently and automatically processing collected data to provide fair and impartial evaluations. This results in one-sided evaluations, which makes it difficult to fully evaluate employees' true contributions and motivation.

[1065] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1066] In this invention, the server includes means for analyzing each employee's work data using natural language processing and emotion analysis technology, and evaluating the employee's work performance based on work evaluation indicators and emotion data, means for calculating an evaluation score for each employee by combining the evaluation indicators and emotion data, and means for generating a detailed report of the evaluation score and evaluation content and notifying related departments and employees. This makes it possible to analyze and evaluate the work data and emotion data in an integrated manner, and to comprehensively evaluate the employee's work performance and emotions.

[1067] "Employee business data" refers to all data generated by or related to an employee's daily work, including, for example, audio recordings, work-related emails, and data from project management tools.

[1068] "Natural language processing" is a technology that enables computers to understand, analyze, and generate natural human language, and is a technology that can analyze text data and audio data to extract meaning.

[1069] "Emotion analysis technology" is a technology that identifies and analyzes human emotions from voice and text data, and evaluates emotional states by analyzing volume, intonation, keywords, and context.

[1070] "Evaluation indicators" are standards for evaluating an employee's work performance and contribution, and specifically include accuracy, efficiency, creativity, and emotional aspects of work.

[1071] An "evaluation score" is a numerical value calculated based on evaluation indicators, and is used to comprehensively evaluate an employee's work performance and emotional state.

[1072] A "detailed report" is a document that summarizes the evaluation score, evaluation content, and sentiment analysis results, and is used to communicate the evaluation results to employees and related departments.

[1073] "Speech recognition technology" is a technology that converts voice data into text data, and is a technology that can analyze voice data and accurately convert what is spoken into text.

[1074] "Machine learning technology" is a technology in which a computer learns patterns from data and makes predictions and judgments based on those patterns, and is used to analyze and evaluate business data.

[1075] "Emotional data" is data obtained using emotion analysis technology, and indicates employees' emotional state, motivation, stress level, etc.

[1076] The following describes in detail the mode for carrying out this invention. This system uses major hardware and software to collect and analyze employee work data and emotional data, and calculate and notify an evaluation score. The procedure is explained below.

[1077] Business data collection

[1078] The device collects various business data in real time, such as the audio of employees' speech during meetings, work-related emails, and data from project management tools. Specifically, audio recordings are made using a microphone during meetings, and emails are extracted using an email client. This data is then immediately sent to the server.

[1079] Converting audio data to text

[1080] The server converts the received audio data into text using the Google Speech-to-Text API, and during this process, it also performs pre-processing such as cleaning and noise removal.

[1081] Data analysis

[1082] The server uses natural language processing (NLP) technology to analyze text data (voice data converted to text and email data) and data obtained from project management tools. Specific NLP technologies include the Python NLTK library and SpaCy. For example, the server evaluates the contribution and importance of employees' comments and sets appropriate evaluation indicators.

[1083] Emotional Data Analysis

[1084] The server uses emotion analysis technology (for example, IBM Watson Natural Language Understanding) to analyze employee emotions from voice and text data. Features such as volume, intonation, and speed are extracted from voice data, while keywords and context are analyzed from text data. For example, passionate comments during a meeting can be evaluated as "highly motivated," while calm email content can be evaluated as "low stress."

[1085] Calculation of evaluation score

[1086] The server combines work evaluation indicators and emotional data to calculate an evaluation score for each employee. This evaluation uses evaluation criteria such as accuracy, efficiency, and creativity, each of which is weighted. For example, if an employee's work is highly accurate and the emotional analysis results indicate high motivation, the employee's evaluation score will be high.

[1087] Report generation and notification

[1088] The server generates an evaluation report for each employee based on the calculated evaluation score and detailed evaluation content. This report includes the evaluation content of each job, a breakdown of the score, the results of sentiment analysis, feedback, and areas for improvement. The generated report is sent by email to the person in charge in the relevant department and also uploaded to an employee-only portal site.

[1089] Specific examples

[1090] For example, suppose Employee A actively speaks up during a project meeting, and his or her comments contribute significantly to the progress of the project. At that time, the device records the voice data and sends it to the server in real time. The server converts the received voice data into text and analyzes the content of the comments using NLP technology. Furthermore, the emotion engine recognizes Employee A's high motivation from the tone and content of his or her comments, and this data is reflected in the evaluation indicators.

[1091] Example prompts to input to the generative AI model

[1092] "Employee A actively spoke up during the project meeting, and his comments contributed greatly to the progress of the project. Please explain in detail the data collected, the analysis method, the specific operation of the emotion engine, how the evaluation score was calculated, and the contents of the generated report."

[1093] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1094] Step 1:

[1095] Business data collection

[1096] The device collects real-time data such as employee speech during meetings, work-related emails, and data from project management tools. For example, it can record audio using a conference microphone and extract work-related emails from an email client.

[1097] Input: Meeting audio data, email data, project management tool data

[1098] Output: Send collected data (audio file, email data file, project data file) to the server.

[1099] Step 2:

[1100] Converting audio data to text

[1101] The server converts the received audio data into text using the Google Speech-to-Text API, which also cleans and removes noise from the audio data.

[1102] Input: Audio file

[1103] Output: Text data (audio file converted to text)

[1104] Step 3:

[1105] Data analysis

[1106] The server analyzes text data, email data, and project management data using natural language processing (NLP) technology. Specifically, it uses Python's NLTK library and SpaCy to analyze the text data and classify it into evaluation indicators such as the importance and contribution of tasks.

[1107] Input: Text data, email data, project data

[1108] Output: Data with business performance indicators

[1109] Step 4:

[1110] Emotional Data Analysis

[1111] The server uses emotion analysis technology (e.g., IBM Watson Natural Language Understanding) to analyze emotions from voice and text data. Specifically, it extracts volume, speed, and intonation from voice data, and analyzes keywords and context from text data to assess the employee's emotional state.

[1112] Input: Text data, speech analysis data

[1113] Output: Emotion analysis results (emotional state evaluation data)

[1114] Step 5:

[1115] Calculation of evaluation score

[1116] The server combines performance metrics and emotional data to calculate an employee evaluation score, which includes criteria such as accuracy, efficiency, and creativity, each of which is weighted.

[1117] Input: Data with business evaluation indicators, sentiment analysis results

[1118] Output: Evaluation score

[1119] Step 6:

[1120] Report generation and notification

[1121] The server generates an evaluation report for each employee based on the evaluation score and detailed evaluation content. This report includes the evaluation content of each task, a breakdown of the score, the results of sentiment analysis, feedback and areas for improvement, etc. The generated report is sent by email to the person in charge in the relevant department and also uploaded to the employee-only portal site.

[1122] Input: Evaluation score, detailed evaluation content (job evaluation, emotional data)

[1123] Output: Evaluation report (email and upload to portal site)

[1124] (Application example 2)

[1125] 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."

[1126] Conventional employee evaluation systems only evaluate employees' work performance, making it difficult to provide a comprehensive evaluation that reflects their actual emotions and motivation levels. Furthermore, there is a lack of means to grasp the quality of customer service in physical stores in real time and provide appropriate feedback. To address these issues, there is a need for a system that comprehensively evaluates employees' work performance and emotions.

[1127] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting work data of each employee, means for analyzing the collected work data and evaluating the work performance of the employee based on the evaluation index, means for calculating an evaluation score for each employee based on the evaluation results, means for generating and notifying a detailed report of the evaluation score and evaluation content, means for using a wearable device to collect voice data during customer interactions, and means for analyzing the collected voice data using natural language processing and an emotion engine to evaluate the emotional tone and work performance of the employee. This enables real-time evaluation and feedback of employees in physical stores.

[1128] "Each employee's business data" refers to all data generated when an employee performs their work, such as audio spoken during business meetings, work-related emails, and data from project management tools.

[1129] "Natural language processing" is a technology that allows computers to understand and process human language, and involves tasks such as analyzing sentences and recognizing emotions.

[1130] An "emotion engine" refers to a system that includes algorithms that analyze voice tone and text content to identify specific emotions.

[1131] A "wearable device" is an electronic device that can be worn on the body and is equipped with a microphone and sensors for collecting voice data.

[1132] "Evaluation indicators" are specific standards or measures used to evaluate an employee's work performance, and include accuracy, efficiency, creativity, etc.

[1133] An "evaluation score" is numerical data calculated based on evaluation indicators, and quantitatively indicates an employee's work performance and emotional state.

[1134] A "report" is a document containing an evaluation score, detailed evaluation content, and feedback, which is communicated to employees and managers.

[1135] An embodiment of this invention is a comprehensive evaluation system that collects employee work data, evaluates work performance based on evaluation indicators, and also considers employee motivation and stress levels in combination with an emotion engine. Specifically, it includes a series of processes: collecting voice data using a wearable device, analyzing the data using natural language processing (NLP), evaluating emotions using the emotion engine, and generating and notifying reports of the evaluation results.

[1136] Program Description

[1137] Audio data collection

[1138] The server uses wearable devices (e.g., smart glasses or smartphones) as terminals to collect voice data in real time during customer interactions, thereby recording the content and tone of the employee's dialogue.

[1139] Analysis of audio data

[1140] The server converts the collected voice data into text using a speech recognition engine and analyzes it using natural language processing (NLP) technology. Specifically, it converts voice to text using Python's speech_recognition library and uses Hugging Face's transformers library to use daigo / bert-base-japanese-sentiment, a sentiment analysis model specifically for Japanese.

[1141] Emotion Engine Operation

[1142] The server calculates an emotion score from the analyzed text data using an emotion engine, for example, the textblob library, to analyze the polarity (positive or negative) and subjectivity of the text data and evaluate the employee's emotional state.

[1143] Calculation of evaluation score

[1144] The server combines the work evaluation indicators and emotional data to calculate an employee evaluation score, which is calculated based on the emotion score, polarity score, and subjectivity score, and uses the results to comprehensively evaluate the employee's work performance and emotional state.

[1145] Report generation and notification

[1146] The server generates an evaluation report for each employee based on the evaluation score, detailed evaluation content, and sentiment analysis results. The generated report is automatically sent by email to the relevant department and also uploaded to an employee-only portal site.

[1147] Specific examples

[1148] For example, if a staff member is engaging in friendly and enthusiastic conversation while interacting with a customer, the voice data will be collected and analyzed by the smart glasses. Based on the analysis results, the staff member's evaluation score will be increased, and the results will be generated as a report and notified to the manager. In this way, real-time evaluation and feedback of employees in physical stores will be possible.

[1149] Prompt Sentence Examples

[1150] "Evaluate your sentiment and performance score based on the following text: 'Hey customer, what do you think of this product? It's very popular and we think you'll be pleased with it.'"

[1151] This invention enables the evaluation of the work performance of employees in physical stores in a fair and efficient manner in real time, thereby enabling the provision of high-quality customer service.

[1152] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1153] Step 1:

[1154] The terminal collects voice data in real time when employees interact with customers via wearable devices (smart glasses or smartphones). The input is the voice of the conversation with the customer, and the output is the collected voice data. This voice data is sent to the server.

[1155] Step 2:

[1156] The server converts the collected voice data into text using a voice recognition engine. The input is voice data and the output is text data. This process uses the Python speech_recognition library.

[1157] Step 3:

[1158] The server analyzes the text data using natural language processing (NLP) and calculates a sentiment score using an emotion engine. The input is text data, and the output is the sentiment score and the analyzed text data. This analysis is performed using the daigo / bert-base-japanese-sentiment model from the transformers library.

[1159] Step 4:

[1160] The server analyzes the polarity (positive or negative) and subjectivity of the text data based on the output of the emotion engine. The input is the analyzed text data, and the output is the polarity score and the subjectivity score. This process uses the textblob library.

[1161] Step 5:

[1162] The server calculates an employee evaluation score by combining the work evaluation indicators and emotional data. The inputs are the emotional score, polarity score, and subjectivity score, and the output is a comprehensive evaluation score. This allows for a comprehensive evaluation of the employee's work performance and emotional state.

[1163] Step 6:

[1164] The server generates an evaluation report for each employee based on the evaluation score, detailed evaluation content, and sentiment analysis results. The input is the overall evaluation score and analysis results, and the output is the evaluation report.

[1165] Step 7:

[1166] The server automatically sends the generated evaluation report to the relevant department by email and also uploads it to the employee-only portal site.The input is the evaluation report and the output is the delivered report.

[1167] In this way, through a series of processes from collecting voice data to analyzing, evaluating, and notifying, this system makes it possible to comprehensively evaluate employees' work performance and emotional state and provide feedback in real time.

[1168] 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.

[1169] 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.

[1170] 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.

[1171] 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.

[1172] 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.

[1173] 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.

[1174] 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).

[1175] 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.

[1176] 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."

[1177] 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.

[1178] 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).

[1179] 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.

[1180] 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.

[1181] 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.

[1182] 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.

[1183] 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.

[1184] 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.

[1185] 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.

[1186] 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.

[1187] 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.

[1188] 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.

[1189] The following is further disclosed regarding the above embodiment.

[1190] (Claim 1)

[1191] A means of collecting work data for each employee;

[1192] A means for analyzing the collected work data and evaluating the work performance of employees based on the evaluation indicators;

[1193] A means for calculating an evaluation score for each employee based on the evaluation results;

[1194] A means for generating and notifying a detailed report of the evaluation score and the evaluation content;

[1195] A system including:

[1196] (Claim 2)

[1197] The system according to claim 1, further comprising means for analyzing the collected business data using natural language processing and machine learning techniques to determine the importance and contribution of the business.

[1198] (Claim 3)

[1199] 2. The system according to claim 1, further comprising means for using accuracy, efficiency, and creativity of work as evaluation criteria and setting evaluation weights based thereon.

[1200] "Example 1"

[1201] (Claim 1)

[1202] A means of collecting employee work data in real time;

[1203] A means of converting collected business data into a properly structured and analyzable format;

[1204] means for analyzing the preprocessed data using natural language processing and machine learning techniques; and

[1205] A means of calculating an evaluation score for each employee based on the analysis results, and

[1206] A means for generating and notifying reports based on the evaluation score and detailed evaluation content;

[1207] A system including:

[1208] (Claim 2)

[1209] A means for converting the collected business data into text data using automatic speech recognition technology;

[1210] It also includes means to perform topic modeling and sentiment analysis on text data to analyze the content and context of statements.

[1211] 10. The system of claim 1.

[1212] (Claim 3)

[1213] Evaluation criteria include additional scoring methods based on accuracy, efficiency, and creativity of work.

[1214] 10. The system of claim 1.

[1215] "Application Example 1"

[1216] (Claim 1)

[1217] a means for collecting work data for each employee and activity data for each work machine;

[1218] a means for analyzing collected work data and activity data and evaluating the performance of employees and work machines based on evaluation indicators;

[1219] A means for calculating an evaluation score for each employee and each work machine based on the evaluation results;

[1220] A means for generating and notifying a detailed report of the evaluation score and the evaluation content;

[1221] A system including:

[1222] (Claim 2)

[1223] The system according to claim 1, further comprising means for analyzing the collected business data and activity data using natural language processing and machine learning techniques to determine the importance and contribution of business and tasks.

[1224] (Claim 3)

[1225] 2. The system according to claim 1, further comprising means for using accuracy, efficiency, and creativity of work and tasks as evaluation criteria and setting evaluation weights based thereon.

[1226] "Example 2: Combining Emotion Engines"

[1227] (Claim 1)

[1228] A means of collecting work data for each employee;

[1229] A means for analyzing the collected work data using natural language processing and sentiment analysis technology and evaluating the work performance of employees based on work evaluation indicators and sentiment data;

[1230] A means for calculating an evaluation score for each employee by combining the evaluation index and emotion data;

[1231] A method for generating detailed reports of evaluation scores and evaluation contents and notifying relevant departments and employees.

[1232] A system including:

[1233] (Claim 2)

[1234] The system according to claim 1, further comprising means for converting the collected business data into text data using speech recognition technology and natural language processing technology, and determining the importance and contribution of the business based on the text data.

[1235] (Claim 3)

[1236] 2. The system according to claim 1, further comprising means for using accuracy, efficiency, creativity, and emotional aspects of work as evaluation criteria and setting evaluation weights based thereon.

[1237] "Application example 2 when combining emotion engines"

[1238] (Claim 1)

[1239] A means of collecting work data for each employee;

[1240] A means for analyzing the collected work data and evaluating the work performance of employees based on the evaluation indicators;

[1241] A means for calculating an evaluation score for each employee based on the evaluation results;

[1242] A means for generating and notifying a detailed report of the evaluation score and the evaluation content;

[1243] A means for utilizing a wearable device to collect voice data during customer interactions;

[1244] A means of analyzing collected voice data using natural language processing and an emotion engine to assess employee emotional tone and job performance;

[1245] A system including:

[1246] (Claim 2)

[1247] The system according to claim 1, further comprising means for analyzing the collected business data using natural language processing and machine learning techniques to determine the importance and contribution of the business.

[1248] (Claim 3)

[1249] 2. The system according to claim 1, further comprising means for using accuracy, efficiency, and creativity of work as evaluation criteria and setting evaluation weights based thereon. [Explanation of symbols]

[1250] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting work data for each employee; A means for analyzing the collected work data and evaluating the work performance of employees based on the evaluation indicators; A means for calculating an evaluation score for each employee based on the evaluation results; A means for generating and notifying a detailed report of the evaluation score and the evaluation content; A system including:

2. The system according to claim 1 , further comprising means for analyzing the collected business data using natural language processing and machine learning techniques to determine the importance and contribution of the business.

3. 2. The system according to claim 1, further comprising means for using accuracy, efficiency and creativity of work as evaluation criteria and setting evaluation weights based thereon.

Images