System

Abstract

To provide a system.SOLUTION: The system includes: means for collecting at least one of actions and performance of an evaluation target person; means for certifying the grade of the evaluation target person on the basis of an artificial intelligence which evaluates the evaluation target person on the basis of the collected data and the result of evaluation by the artificial intelligence; means for analyzing an emotion engine for recognizing the emotion of the evaluation target person in real time and emotion data recognized by the emotion engine; and means for updating the evaluation of the evaluation target person on the basis of the result of the evaluation.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 a description and related instruction sentence regarding 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] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] Evaluations of people working in corporate organizations cannot be free from emotion and arbitrariness. Due to the discrepancy between promotion promotion policies and final evaluations, there are times when major risks arise, such as the destruction of trust, deterioration or collapse of relationships, unexpected transfers, resignations, and lawsuits. [Means for solving the problem]

[0005] We propose introducing AI as an evaluation committee to ensure objectivity. Grade certification, which is equivalent to a change in employment conditions or directly affects wages, is ultimately determined at the discretion of the department, but we also manage human resources from a third-party perspective, set company-wide standards, and act as a going concern. [Brief description of the drawings]

[0006] [Figure 1]1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 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. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 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. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 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. 2 is a sequence diagram showing a process flow of the data processing system in the first embodiment of the first form example. [Figure 12] FIG. 11 is a sequence diagram showing a process flow of the data processing system in the application example 1 of the first embodiment. [Figure 13] FIG. 11 is a sequence diagram showing a process flow of the data processing system in the second embodiment of the second embodiment. [Figure 14] FIG. 13 is a sequence diagram showing a process flow of the data processing system in application example 2 of embodiment 2. [Figure 15] FIG. 13 is a sequence diagram showing a process flow of a data processing system in a third embodiment of the present invention. [Figure 16] FIG. 13 is a sequence diagram showing a process flow of the data processing system in the third application example of the third embodiment. [Figure 17] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system in the first embodiment of the first form example when an emotion engine is combined. [Figure 18] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Form Example 1 when combined with an emotion engine. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0007] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0008] First, the terms used in the following description will be explained.

[0009] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one 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), an APU (Accelerated Processing Unit), or a TPU (TENSOR PROCESSING UNIT (registered trademark)).

[0010] In the following embodiments, a signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the processor.

[0011] 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.

[0012] In the following embodiments, a communication I / F (Interface) with a code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0013] 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. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "and / or."

[0014] [First embodiment]

[0015] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0016] 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.

[0017] 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 wide area network (WAN) and / or a local area network (LAN).

[0018] 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.

[0019] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (e.g., a pen or a finger) to receive user input by the touch of the pointer. 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.

[0020] 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 (e.g., voice and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs voice according to instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0021] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

[0022] FIG. 2 shows an example of main functions of the data processing device 12 and the smart device 14.

[0023] As shown in Fig. 2, 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. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process 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 process program 56 executed on the RAM 30.

[0024] 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.

[0025] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores a reception output program 60. The reception output program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads out the reception output program 60 from the storage 50, and executes the read reception output program 60 on the RAM 48. The reception output processing 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.

[0026] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0027] "Example 1"

[0028] As one embodiment of the present invention, an AI system that evaluates people in a corporate organization is provided. This system has a means for collecting data on the behavior and performance of the person being evaluated. For example, data such as the success rate of projects carried out by the person being evaluated and the quality of reports submitted by the person being evaluated is collected. The collected data is analyzed by AI, and the person being evaluated is evaluated. The evaluation results are used to certify the grade of the person being evaluated. Grade certification is performed at the discretion of the department, and affects changes to the employment conditions and wages of the person being evaluated. In addition, the evaluation results are standardized company-wide, and human resource management is also carried out as a going concern.

[0029] "Example 2"

[0030] As another embodiment of the present invention, a form is provided in which an AI system collects data on the behavior, performance, etc. of the person to be evaluated in real time and performs the evaluation in real time. In this form, data on the behavior, performance, etc. of the person to be evaluated is collected immediately after the person to be evaluated performs an action or achieves an achievement, and is analyzed immediately by AI. As a result, the evaluation of the person to be evaluated is updated in real time, and the grade of the person to be evaluated is also certified in real time.

[0031] The process flow of each embodiment will be described below.

[0032] "Example 1"

[0033] Step 1: Collect data on the behavior and performance of the person being evaluated. For example, collect data on the success rate of projects carried out by the person being evaluated and the quality of reports submitted by the person being evaluated.

[0034] Step 2: The collected data is analyzed by AI, which then evaluates the person being evaluated based on the collected data.

[0035] Step 3: The grade of the person being evaluated is determined based on the results of the AI ​​evaluation. Grade determination is done at the discretion of the department and will affect changes to the employment conditions and wages of the person being evaluated.

[0036] Step 4: The evaluation results are standardized across the company and are used in human resource management as a going concern.

[0037] "Example 2"

[0038] Step 1: Collect data on the behavior and performance of the person being evaluated in real time. Data is collected immediately after the person being evaluated performs an action or achieves a result.

[0039] Step 2: The collected data is immediately analyzed by AI, which then evaluates the person being evaluated in real time based on the collected data.

[0040] Step 3: Based on the results of the AI ​​evaluation, the grade of the person being evaluated is determined in real time. Grade determination is done at the discretion of the department and has an immediate effect on changes to the employment conditions and wages of the person being evaluated.

[0041] Example 1

[0042] Next, a description will be given of Example 1 of the embodiment 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".

[0043] In conventional talent evaluation systems, data collection on the behavior and performance of those being evaluated was insufficient, and the evaluations often lacked objectivity and accuracy. In addition, because grade certification and talent management based on the evaluation results were not performed consistently, there was a problem that talent management throughout the organization was not performed efficiently. Furthermore, the evaluation process was often performed manually, which was time-consuming and labor-intensive.

[0044] 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.

[0045] In this invention, the server includes a means for collecting data on the behavior and performance of the person to be evaluated, a means for preprocessing the collected data, a means including a generative AI model for analyzing the preprocessed data, a means for evaluating the person to be evaluated based on the analysis result by the generative AI model, and a means for certifying the grade of the person to be evaluated based on the evaluation result. This enables objective and highly accurate evaluation based on the behavior and performance of the person to be evaluated, and consistent grade certification and human resource management based on the evaluation result can be efficiently performed.

[0046] "Assesseeee" refers to the individual within the business organization who is the subject of the assessment.

[0047] "Data on behavior, performance, etc." refers to data containing information necessary for evaluation, such as the success rate of projects carried out by the person being evaluated and the quality of reports submitted.

[0048] "Means of collection" refers to the hardware and software used to obtain data on the behavior, performance, etc. of the person being evaluated.

[0049] "Preprocessing means" refers to hardware and software used to fill in missing values ​​in collected data, correct outliers, standardize data formats, and so on.

[0050] A "generative AI model" refers to an artificial intelligence model that analyzes data such as the behavior and performance of the person being evaluated and generates an evaluation score.

[0051] "Means of analysis" refers to the hardware and / or software used to input preprocessed data into a generative AI model and generate an evaluation score.

[0052] "Means of evaluation" refers to hardware and software used to evaluate the subject based on the analysis results of the generative AI model.

[0053] "Means of grade certification" refers to hardware or software used to certify the grade of the person being evaluated based on the evaluation results.

[0054] "Departmental discretion" refers to each department within a company deciding the grade of each person being evaluated at its own discretion.

[0055] "Human resource management" refers to changing the employment conditions, adjusting wages, setting career paths, etc. of those being evaluated based on the evaluation results and grade certification.

[0056] The present invention relates to an AI system for evaluating people in a corporate organization. A specific embodiment of this system will be described below.

[0057] The server has a means for collecting data on the behavior, performance, etc. of the person being evaluated. Specifically, it obtains project success rate data from project management software (e.g., JIRA, Trello) and collects quality data on submitted reports from document management systems (e.g., Google (registered trademark) Drive, SharePoint).

[0058] Next, the server preprocesses the collected data. It complements missing values ​​in the data and detects and corrects outliers. It also standardizes the data format and prepares it in a form that is easy for the AI ​​model to analyze. For example, if there are missing values, they are complemented with the average value, and if there are outliers, they are corrected with the median value. The data format is standardized and converted into CSV format.

[0059] The preprocessed data is input into a generative AI model (e.g., TENSORFLOW (registered trademark), PyTorch) on the server. The AI ​​model analyzes the behavioral patterns and performance of the person being evaluated and generates an evaluation score. For example, if the success rate of the projects in which person being evaluated A was in charge was 90% and the quality of the reports he submitted was highly evaluated, the AI ​​model will generate an evaluation score based on this data.

[0060] Based on the generated evaluation score, the server generates an overall evaluation of the person being evaluated. This evaluation result is used to certify the grade of the person being evaluated. Grade certification is performed at the discretion of the department and affects changes to the employment conditions and wages of the person being evaluated. In addition, the evaluation result is standardized across the company and is also used for human resource management as a going concern.

[0061] As a concrete example, consider a case where the success rate of projects carried out by assessee A was 90% and the quality of the submitted reports was highly evaluated. The server collects success rate data from the project management software and report quality data from the document management system. These data are input into the AI ​​model for evaluation.

[0062] Example of a prompt to be input to a generative AI model:

[0063] The project success rate of assessee A is 90%, and the quality of the reports he submitted is highly rated. Based on this data, please give an overall evaluation of assessee A.

[0064] Using this prompt, the AI ​​model generates an overall evaluation of the person being evaluated A. The evaluation results are used for grading at the department's discretion and for company-wide standardization.

[0065] In this way, the server evaluates people within the corporate organization and provides grades and feedback based on the evaluation results.

[0066] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0067] Step 1: Data collection

[0068] The server collects data on the behavior and performance of the assessees. Specifically, it obtains project success rate data from project management software (e.g., JIRA, Trello) and collects quality data on submitted reports from document management systems (e.g., Google Drive, SharePoint). The input is the assessee's ID and project ID, and the output is project success rate data and report quality data.

[0069] Step 2: Data Preprocessing

[0070] The server preprocesses the collected data. Specifically, it complements missing values ​​in the data and detects and corrects outliers. It also standardizes the data format and prepares it in a form that is easy for the AI ​​model to analyze. The input is the collected raw data, and the output is preprocessed, clean data. For example, if there are missing values, they are complemented with the average value, and if there are outliers, they are corrected with the median. The data format is standardized and converted to CSV format.

[0071] Step 3: Data analysis

[0072] The server inputs the preprocessed data into a generative AI model. The AI ​​model (e.g., TensorFlow, PyTorch) analyzes the behavioral patterns and performance of the person being evaluated and generates an evaluation score. The input is the preprocessed data, and the output is the evaluation score. For example, if the success rate of the projects in which person being evaluated A was in charge was 90% and the quality of the reports he submitted was highly evaluated, the AI ​​model will generate an evaluation score based on this data.

[0073] Step 4: Generate evaluation results

[0074] The server generates an overall evaluation of the person being evaluated based on the generated evaluation score. The input is the evaluation score obtained from the AI ​​model, and the output is the overall evaluation of the person being evaluated. For example, based on an evaluation score of 85 points, the overall evaluation of person A is set to "excellent."

[0075] Step 5: Grading and feedback

[0076] The server certifies the grade of the person being evaluated based on the generated evaluation results. The input is the overall evaluation, and the output is the grade certification result of the person being evaluated. Grade certification is done at the discretion of the department and affects changes to the employment conditions and wages of the person being evaluated. The evaluation results are also standardized company-wide and are used in human resource management as a going concern. For example, the grade of person A being evaluated is certified as "A" and his / her wage is increased by 10%.

[0077] (Application example 1)

[0078] Next, a description will be given of Application Example 1 of Form 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."

[0079] Traditionally, the performance evaluation of robots working in factories was mainly carried out by human managers, which led to problems with the lack of objectivity and efficiency of the evaluation. In addition, robot maintenance schedules and upgrade plans often relied on experience and intuition and were not optimized. This reduced the robot's operating rate and lifespan, and had a negative impact on the productivity of the entire factory.

[0080] 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.

[0081] In this invention, the server includes a means for collecting data such as the work efficiency, error rate, and maintenance history of the machine to be evaluated, an AI for evaluating the machine to be evaluated based on the collected data, a means for optimizing a maintenance schedule for the machine to be evaluated based on the evaluation results by the AI, and a means for proposing an upgrade plan for the machine to be evaluated based on the evaluation results. This makes it possible to objectively and efficiently evaluate the performance of a robot and to optimize the maintenance schedule and upgrade plan.

[0082] "Machinery to be evaluated" refers to robots and automated machinery that perform work in factories.

[0083] "Work efficiency" is an index that indicates how much work the evaluated machine can complete within a certain amount of time.

[0084] The "error rate" is an index showing the frequency of errors and breakdowns that occur when the machine being evaluated is in operation.

[0085] "Maintenance history" refers to the records of maintenance and repairs that the machine being evaluated has received in the past.

[0086] "Means of collecting data" refers to sensors and communication devices for obtaining data such as work efficiency, error rate, and maintenance history from the machine being evaluated.

[0087] "Evaluation AI" refers to an artificial intelligence system that analyzes collected data and evaluates the performance of the machine being evaluated.

[0088] "Means for optimizing maintenance schedules" refers to algorithms or programs for optimizing the timing and content of maintenance for the evaluated machinery based on the results of the AI ​​evaluation.

[0089] "Means for proposing an upgrade plan" refers to algorithms or programs for proposing upgrades to improve the performance or add functions to the machine being evaluated based on the results of the AI ​​evaluation.

[0090] As an embodiment of the present invention, a system for evaluating the performance of robots working in a factory is constructed. The system includes an AI that collects data such as the work efficiency, error rate, and maintenance history of the machine to be evaluated, and evaluates the machine based on the collected data. Furthermore, the system optimizes the maintenance schedule of the machine to be evaluated based on the evaluation results by the AI, and proposes an upgrade plan for the machine to be evaluated based on the evaluation results.

[0091] Hardware and Software Used

[0092] Hardware

[0093] Server: A high-performance server for data collection and analysis.

[0094] Robot: A robot in a factory that is the subject of data collection

[0095] Sensors: Sensors to collect data such as the robot's work efficiency, error rate, and maintenance history

[0096] software

[0097] Python: Used for data analysis and model training

[0098] Pandas: Used to load and preprocess data

[0099] Scikit-learn: Used to train and evaluate machine learning models.

[0100] Data processing and calculation

[0101] The server first collects data from the robot in real time. The collected data is preprocessed using Pandas and divided into features and targets such as work efficiency, error rate, and maintenance history. Then, a model is trained using Scikit-learn's RandomForestRegressor to predict the performance of the machine being evaluated. The prediction results are used to optimize the maintenance schedule of the machine being evaluated and propose an upgrade plan.

[0102] Examples

[0103] For example, if a robot's work efficiency is 90%, its error rate is 5%, and its maintenance history is three times, the server will collect these data and analyze them with the AI ​​model. Based on the analysis results, it will predict the robot's performance score and suggest the optimal maintenance schedule and necessary upgrades.

[0104] Examples of prompt statements

[0105] Enter your robot's work efficiency, error rate, and maintenance history to predict its performance score.

[0106] In this way, it is possible to build a system that evaluates the performance of robots working in factories and optimizes maintenance schedules and upgrade plans.

[0107] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0108] Step 1:

[0109] The server collects data such as work efficiency, error rate, and maintenance history from the robots in the factory in real time. This data is acquired using sensors and communication devices and stored in a database.

[0110] Input: Robot work efficiency, error rate, maintenance history

[0111] Output: Robot performance data stored in a database

[0112] Step 2:

[0113] The server preprocesses the collected data using Pandas. Specifically, it complements missing values ​​and removes outliers to make the data clean.

[0114] Input: Robot performance data stored in a database

[0115] Output: Preprocessed and clean data

[0116] Step 3:

[0117] The server divides the preprocessed data into features and targets. Work efficiency, error rate, and maintenance history are used as features, and performance score is set as a target.

[0118] Input: Preprocessed and clean data

[0119] Output: Data split into features and targets

[0120] Step 4:

[0121] The server trains a machine learning model using Scikit-learn's RandomForestRegressor. It uses the features and targets as training data to build the model.

[0122] Input: Data split into features and targets

[0123] Output: A trained machine learning model

[0124] Step 5:

[0125] The server uses the trained model to predict the robot's performance score based on new data collected in real time.

[0126] Input: New robot performance data collected in real time

[0127] Output: Predicted performance score

[0128] Step 6:

[0129] The server optimizes the robot's maintenance schedule based on the predicted performance score, determining the timing and content of maintenance and updating the schedule.

[0130] Input: Predicted performance score

[0131] Output: Optimized maintenance schedule

[0132] Step 7:

[0133] The server then proposes an upgrade plan for the robot based on the predicted performance score, determining what upgrades are required and when, and creating a proposal.

[0134] Input: Predicted performance score

[0135] Output: Proposed upgrade plan

[0136] In this way, the server can evaluate the robot's performance and optimize maintenance schedules and upgrade plans.

[0137] Example 2

[0138] Next, a second embodiment of the second embodiment will be described. 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."

[0139] In the conventional evaluation system, data collection and analysis of the behavior and performance of the person being evaluated was not done in real time, and updates to evaluation results and grade certification were often delayed. In addition, there was also the problem that the evaluation criteria were uniform and it was difficult to reflect the discretion of each department. Furthermore, there was an issue that human resource management based on the evaluation results was not carried out efficiently.

[0140] 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.

[0141] In this invention, the server includes a means for collecting data such as the behavior and performance of the person to be evaluated in real time, a means for storing the collected data in a database, a means for using a generative AI model to analyze the stored data, a means for updating the evaluation score of the person to be evaluated in real time based on the analysis result, a means for certifying the grade of the person to be evaluated based on the evaluation score, and a means for notifying the terminal of the person to be evaluated of the result of the grade certification. This makes it possible to collect and analyze the data of the behavior and performance of the person to be evaluated in real time, quickly update the evaluation result, and certify the grade reflecting the discretion of each department. In addition, efficient human resource management based on the evaluation result can be realized.

[0142] "Appraisee" refers to the individual or group whose behavior or performance is evaluated by the appraisal system.

[0143] "Data on behavior, achievements, etc." refers to information on the specific behavior and achievements of the person being evaluated, including the progress and results of work, behavioral history, etc.

[0144] "Means of collecting data in real time" refers to methods and technologies for instantly obtaining data on the behavior and performance of the person being evaluated and incorporating it into the system without delay.

[0145] "Means of storing in a database" refers to the methods and technologies used to organize collected data and keep it accessible later.

[0146] A "generative AI model" refers to an algorithm or model that uses machine learning and artificial intelligence techniques to analyze data and evaluate the behavior and performance of individuals being evaluated.

[0147] "Evaluation score" refers to a numerical indicator of the performance of the person being evaluated based on the results of analysis by the generative AI model.

[0148] "Grade certification" refers to the process of determining the rank or grade of an assessee based on their assessment score.

[0149] "Means of notifying the device" refers to the methods and technologies for notifying the subject of the evaluation of the results of the evaluation and the grade certification, including email and push notifications.

[0150] "Departmental discretion" refers to the authority of each department to evaluate and grade based on its own criteria and policies.

[0151] "Human resource management" refers to the process of allocating, developing, and evaluating human resources within an organization based on evaluation results and grade certification.

[0152] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0153] The present invention is a system for collecting data on the behavior and performance of an evaluation target in real time, analyzing the data, updating the evaluation score, and certifying a grade. A specific embodiment of the system will be described below.

[0154] 1. Program Generation

[0155] The server collects data on the behavior and performance of the person being evaluated in real time and generates a program for evaluating the person. This program has the function of instantly analyzing the behavior and performance of the person being evaluated and updating the evaluation in real time.

[0156] 2. Program Processing

[0157] The server works with various sensors and databases to collect data on the behavior and performance of the person being evaluated. Specifically, data is collected from the devices (e.g., smartphones, PCs) and business systems (e.g., customer management systems, business management systems) used by the person being evaluated. This data is stored in the database on the server.

[0158] The server then uses a generative AI model to analyze the collected data. Specifically, it uses machine learning frameworks such as TensorFlow and PyTorch to analyze the behavior and performance of the person being evaluated. The analysis results are updated in real time as the person being evaluated's evaluation score.

[0159] Furthermore, the server certifies the grade of the person to be evaluated based on the evaluation score. In this process, the grade of the person to be evaluated is determined based on the evaluation criteria set in advance. The result of the grade certification is notified to the terminal of the person to be evaluated.

[0160] 3. Specific Examples

[0161] As a concrete example, consider the performance evaluation of a sales representative. When a sales representative wins a new contract, the information is automatically sent from the customer management system to a server. The server uses a generative AI model to analyze the value of the new contract and updates the sales representative's evaluation score. The updated evaluation score is notified to the sales representative's smartphone in real time.

[0162] Example prompt:

[0163] "When a sales rep wins a new deal, collect that information from your customer relationship management system and use a generative AI model to update the reputation score."

[0164] In this way, a system is realized in which the server, terminals, and users work together to evaluate the behavior and performance of the person being evaluated in real time and certify a grade.

[0165] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0166] Step 1: Data collection

[0167] The server collects data on the behavior and performance of the person being evaluated in real time. Specifically, it obtains data from the devices (e.g., smartphones, PCs) and business systems (e.g., customer management systems, business management systems) used by the person being evaluated. The input is data on the behavior and performance of the person being evaluated, and the output is the raw data sent to the server. For example, when a sales representative secures a new contract, that information is sent from the customer management system to the server.

[0168] Step 2: Save Data

[0169] The server stores the collected data in a database. Specifically, a relational database such as MySQL (registered trademark) or PostgreSQL is used. The input is the collected raw data, and the output is structured data stored in the database. For example, detailed information on a new contract is stored in the database.

[0170] Step 3: Data analysis

[0171] The server uses a generative AI model to analyze the stored data. Specifically, it uses machine learning frameworks such as TensorFlow and PyTorch to analyze the behavior and performance of the person being evaluated. The input is structured data stored in a database, and the output is an evaluation score as the analysis result. For example, a predictive model based on past data is used to evaluate the value of a new contract.

[0172] Step 4: Update your reputation scores

[0173] The server updates the evaluation score of the person being evaluated based on the results of the data analysis. The input is the evaluation score as the analysis result, and the output is the updated evaluation score. For example, if the value of a new contract is high, the evaluation score of a sales representative increases.

[0174] Step 5: Grade Certification

[0175] The server certifies the grade of the person to be evaluated based on the updated evaluation score. The input is the updated evaluation score, and the output is the grade of the person to be evaluated. For example, if the evaluation score exceeds a certain threshold, the grade of the salesperson is promoted from "silver" to "gold."

[0176] Step 6: Notification

[0177] The server notifies the terminal of the person being evaluated of the result of the grade certification. The input is the grade of the person being evaluated, and the output is a notification sent to the terminal of the person being evaluated. For example, a notification saying "Your grade has been promoted to gold" is sent to the smartphone of a sales representative.

[0178] (Application example 2)

[0179] Next, a description will be given of Application Example 2 of Form 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."

[0180] With conventional factory robot evaluation systems, it was difficult to evaluate the robot's operation and production efficiency in real time and provide immediate feedback. As a result, it was not possible to properly instruct the robot on the timing of improvements to its operation or maintenance, which led to problems such as reduced production efficiency and an increased risk of breakdowns.

[0181] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0182] In this invention, the server includes a means for collecting data such as the behavior and performance of the evaluation target in real time, an AI for evaluating the evaluation target in real time based on the collected data, a means for certifying the grade of the evaluation target in real time based on the evaluation result by the AI, and a means for feeding back the evaluation result in real time and instructing the timing of behavior improvement and maintenance. This makes it possible to evaluate the behavior and production efficiency of a factory robot in real time and provide immediate feedback.

[0183] The "subject of evaluation" refers to factory robots, their operations, and production efficiency.

[0184] "Operational Data" refers to information about the operation of a factory robot, including performance indicators such as efficiency and error rates.

[0185] "Performance data" refers to information regarding the production volume and quality achieved by factory robots.

[0186] "Means of collecting data in real time" refers to methods of using sensors or data collection devices to instantly obtain the behavior and performance data of the subject being evaluated.

[0187] "Real-time AI" refers to an artificial intelligence system that instantly analyzes and evaluates collected data.

[0188] "Grade certification" refers to ranking the quality and efficiency of an item based on its performance.

[0189] "Feedback" refers to providing the subject of evaluation with immediate instructions for operational improvement or maintenance based on the evaluation results.

[0190] "Behavioral improvement" refers to adjustments or modifications made to improve the performance of the subject of evaluation.

[0191] "Timing of maintenance" refers to the time when maintenance work is performed to keep the object of evaluation functioning properly.

[0192] The system for carrying out the present invention evaluates the operation and production efficiency of factory robots in real time and provides immediate feedback. A specific embodiment of the system is described below.

[0193] 1. System Configuration

[0194] The system consists of the following main components:

[0195] Hardware: Factory robots, sensors (to measure efficiency and error rates)

[0196] Software: Python, AI analysis libraries (e.g. TensorFlow, Scikit-learn)

[0197] 2. Data Collection

[0198] The server collects the robot's operational data (efficiency and error rate) in real time using sensors attached to the factory robots, making it possible to immediately grasp the robot's performance.

[0199] 3. Data Analysis

[0200] The collected data is instantly analyzed using AI analysis libraries (e.g. TensorFlow, Scikit-learn) on the server. The AI ​​evaluates the robots based on their efficiency and error rate and generates an evaluation result.

[0201] 4. Grade Certification

[0202] The server will assign a grade to the robot in real time based on the AI ​​evaluation results. For example, if the efficiency is 90% or more and the error rate is less than 1%, the evaluation grade will be "A."

[0203] 5. Feedback and Improvements

[0204] The evaluation results are fed back to the robot in real time. The server then instructs the robot on operational improvements and maintenance timing based on the evaluation results, optimizing the robot's performance and improving production efficiency.

[0205] Examples

[0206] Example 1: If a robot assembles parts with an efficiency of 90% or more and an error rate of less than 1%, the evaluation grade will be "A" and the robot will continue to operate.

[0207] Example 2: If efficiency is below 80%, the evaluation grade will be "C" and a notification will be sent indicating that maintenance is required.

[0208] Examples of prompt statements

[0209] Collect the robot's operation data and evaluate its efficiency and error rate in real time. If the efficiency is 90% or more and the error rate is less than 1%, the evaluation grade should be "A". If the efficiency is 80% or less, the evaluation grade should be "C". Provide feedback on the evaluation results in real time and instruct maintenance as necessary.

[0210] In this way, a system can be realized that evaluates the operation of factory robots and production efficiency in real time and provides immediate feedback.

[0211] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0212] Step 1:

[0213] The server collects operational data (efficiency and error rate) in real time from sensors attached to factory robots. The input is the raw data from the sensors, and the output is the collected operational data. Specifically, the sensors monitor the robot's operation and measure its efficiency and error rate.

[0214] Step 2:

[0215] The server analyzes the collected motion data using AI analysis libraries (e.g. TensorFlow, Scikit-learn). The input is the collected motion data, and the output is the analysis result. Specifically, the AI ​​evaluates the robot's performance based on efficiency and error rate, and generates an evaluation result.

[0216] Step 3:

[0217] The server certifies the robot's grade in real time based on the AI ​​evaluation results. The input is the AI ​​evaluation result, and the output is the grade certification result. Specifically, if the efficiency is 90% or more and the error rate is less than 1%, the evaluation grade will be "A".

[0218] Step 4:

[0219] The server feeds back the evaluation results to the robot in real time. The input is the grade certification result, and the output is feedback information. Specifically, it provides the robot with instructions for improving its behavior and maintenance based on the evaluation results.

[0220] Step 5:

[0221] The server optimizes the robot's operation based on the feedback information. The input is the feedback information, and the output is the optimized operation parameters. Specifically, the robot adjusts its operation according to the instructions, improving production efficiency.

[0222] Step 6:

[0223] The server monitors the robot's operational improvements and maintenance timing, and provides additional instructions as necessary. The input is the optimized operational parameters, and the output is additional instructions. Specifically, the server continuously monitors the robot's performance and provides maintenance instructions as necessary.

[0224] Furthermore, an emotion engine that estimates the emotion of the user may be combined. That is, the identification processing unit 290 may estimate the emotion of the user using the emotion identification model 59, and perform identification processing using the emotion of the user.

[0225] "Example 1"

[0226] As one embodiment of the present invention, there is a system that combines an emotion engine. This system includes a means for collecting data such as the behavior and performance of the person to be evaluated, an AI that evaluates the person to be evaluated based on the collected data, and a means for certifying the grade of the person to be evaluated based on the evaluation result by the AI. Furthermore, it includes an emotion engine that recognizes the emotion of the person to be evaluated. Specifically, the emotion engine recognizes the emotion of the person to be evaluated from the facial expression, tone of voice, choice of words, etc. of the person to be evaluated, and the AI ​​analyzes the emotion data. For example, if the person to be evaluated feels nervous during a presentation, the AI ​​analyzes that information and reflects it in the evaluation of the person to be evaluated.

[0227] "Example 2"

[0228] Another embodiment of the present invention is a system that combines an emotion engine with a real-time data collection and analysis function. This system includes an AI that collects data on the behavior and performance of the person being evaluated in real time and evaluates the person being evaluated in real time based on the collected data, and a means for certifying the grade of the person being evaluated in real time based on the evaluation result by the AI. Furthermore, the system includes an emotion engine that recognizes the emotion of the person being evaluated in real time. Specifically, the emotion engine recognizes the emotion of the person being evaluated in real time from the facial expression, tone of voice, choice of words, etc. of the person being evaluated, and the AI ​​instantly analyzes the emotion data. For example, if the person being evaluated expresses anger during a meeting, the AI ​​instantly analyzes the information and reflects it in the evaluation of the person being evaluated.

[0229] The process flow of each embodiment will be described below.

[0230] "Example 1"

[0231] Step 1: Collect data on the behavior and performance of the person being evaluated.

[0232] Step 2: Use AI to evaluate the subjects based on the collected data.

[0233] Step 3: The person being evaluated is graded based on the AI ​​evaluation results.

[0234] Step 4: Use an emotion engine to recognize the emotions of the person being evaluated. The emotion engine recognizes the emotions of the person being evaluated from their facial expressions, tone of voice, choice of words, etc.

[0235] Step 5: AI analyzes the emotional data recognized by the emotion engine.

[0236] Step 6: The subject is evaluated based on the emotional data analyzed by the AI.

[0237] "Example 2"

[0238] Step 1: Collect data on the behavior and performance of the person being evaluated in real time.

[0239] Step 2: Use AI to evaluate subjects in real time based on the collected data.

[0240] Step 3: Based on the AI ​​evaluation results, the person being evaluated is graded in real time.

[0241] Step 4: An emotion engine is used to recognize the emotions of the person being evaluated in real time. The emotion engine recognizes emotions in real time from the person being evaluated's facial expressions, tone of voice, choice of words, etc.

[0242] Step 5: The AI ​​immediately analyzes the emotional data recognized by the emotion engine.

[0243] Step 6: The subject is evaluated based on the emotional data analyzed by the AI.

[0244] Example 1

[0245] Next, a description will be given of Example 1 of the embodiment 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".

[0246] In conventional human evaluation systems, evaluations were based on the behavior and performance of the person being evaluated, but the evaluation did not take into account the emotional state of the person being evaluated. As a result, the evaluations were sometimes lacking in fairness and accuracy. In addition, it was difficult to grade the evaluation results at the discretion of the department, making it difficult to standardize the results across the company. This led to a lack of consistency in affecting changes to the employment conditions and wages of the person being evaluated.

[0247] 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.

[0248] In this invention, the server includes a means for collecting data such as the behavior and performance of the person to be evaluated, an artificial intelligence for evaluating the person to be evaluated based on the collected data, a means for certifying the grade of the person to be evaluated based on the evaluation result by the artificial intelligence, a means including an emotion engine for recognizing the emotions of the person to be evaluated, and a means for analyzing the emotion data collected by the emotion engine. This enables evaluation that takes into account the behavior and performance of the person to be evaluated as well as their emotional state, improving the fairness and accuracy of the evaluation. In addition, grade certification can be done at the discretion of the department, and consistent human resource management can be achieved through company-wide standardization.

[0249] "Appraisee" refers to the individual whose behavior, performance, or emotional state is evaluated by the appraisal system.

[0250] "Data on behavior, performance, etc." refers to data containing information necessary for evaluation, such as the success rate of projects carried out by the person being evaluated and the quality of reports submitted.

[0251] "Artificial intelligence" refers to machine learning algorithms and data analysis techniques used to analyze collected data and evaluate subjects.

[0252] "Grade certification" refers to the process of determining a grade for an individual based on their job or position, based on the results of an evaluation using artificial intelligence.

[0253] An "emotion engine" refers to technology that recognizes emotions from the facial expressions, tone of voice, choice of words, etc. of the person being evaluated, and collects that data.

[0254] "Emotional Data" refers to information regarding the emotional state of a Subject collected by the Emotion Engine.

[0255] "Departmental discretion" refers to the authority of each department to determine the grade of individuals being evaluated at its own discretion.

[0256] "Company-wide standardization" refers to the process of managing evaluation results based on uniform standards across the entire company, thereby ensuring consistent human resource management.

[0257] This invention relates to an AI system for evaluating people in a business organization. This system includes artificial intelligence (AI) that collects data on the behavior and performance of the person being evaluated and evaluates them based on the collected data. In addition, by combining it with an emotion engine that recognizes the emotions of the person being evaluated, a more accurate and fair evaluation is achieved.

[0258] Data collection

[0259] Users use the company's in-house project management software (e.g., JIRA) and document management systems (e.g., Google Drive) to collect data on the behavior and performance of appraisee(s), such as the success rate of projects undertaken by appraisee(s) and the quality of reports submitted.

[0260] Data transmission

[0261] The terminal transmits the collected data to the server. Specifically, the terminal transmits the project success rate data and the report quality data to the server using an HTTP request.

[0262] 4. Data Analysis

[0263] The server then sends the received data to the AI ​​system for analysis. The server uses machine learning algorithms such as TensorFlow to analyze the data and evaluate the behavior and performance of the person being evaluated.

[0264] emotion recognition

[0265] The device uses a camera and microphone to collect facial expressions and tone of voice of the person being evaluated during the presentation. The device uses emotion analysis software such as Microsoft® Azure® Emotion API to recognize emotions from this data.

[0266] Emotion Data Analysis

[0267] The device transmits the recognized emotion data to a server, which then transmits the emotion data to an AI system to analyze the subject's emotional state.

[0268] Generating evaluation results

[0269] The server receives the analysis results from the AI ​​system and generates an evaluation of the person being evaluated. Specifically, it comprehensively evaluates the person being evaluated based on their project success rate, report quality, and emotional state, and generates an evaluation score.

[0270] Grade Certification

[0271] The server certifies the grade of the person being evaluated based on the generated evaluation score. The grade certification is performed at the discretion of the department and affects the employment conditions and wages of the person being evaluated.

[0272] Company-wide standardization

[0273] The server standardizes the evaluation results company-wide and manages human resources. Specifically, the server uses a human resources management system such as SAP SuccessFactors to standardize the evaluation results to company-wide standards and manages human resources as a going concern.

[0274] Examples

[0275] For example, if assessee A succeeds in project X and submits report Y, the user uses JIRA to collect the success rate data of project X and Google Drive to collect the quality data of report Y. The terminal sends these data to the server via HTTP request. The server uses TensorFlow to analyze the data and evaluates the behavior and performance of assessee A. In addition, the terminal uses Microsoft Azure Emotion API to collect emotion data during the presentation of assessee A and sends it to the server. The server sends the emotion data to the AI ​​system and generates an evaluation score for assessee A based on the analysis results. The server performs grade certification based on the evaluation score and standardizes it company-wide using SAP SuccessFactors.

[0276] Examples of prompt statements

[0277] "Collect the success rate data of project X and the quality data of report Y of assessee A, and use the emotion engine to analyze the emotion data during the presentation. Generate an evaluation of assessee A based on the analysis results, and standardize it across the company."

[0278] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0279] Step 1:

[0280] The user collects data on the behavior and performance of the person being evaluated. Specifically, the user uses the company's project management software (e.g., project management tool) to collect data on the success rate of projects carried out by the person being evaluated, and uses a document management system (e.g., document management tool) to collect data on the quality of reports submitted by the person being evaluated. These data become input data for evaluating the behavior and performance of the person being evaluated.

[0281] Step 2:

[0282] The terminal transmits the collected data to the server. Specifically, the terminal transmits the project success rate data and the report quality data to the server using an HTTP request. The input data are the project success rate data and the report quality data, and the output is the data transmitted to the server.

[0283] Step 3:

[0284] The server sends the received data to the AI ​​system for analysis. The server analyzes the data using a machine learning algorithm (e.g., machine learning framework) and evaluates the behavior and performance of the person being evaluated. The input data is project success rate data and report quality data, and the output is the evaluation result based on the behavior and performance of the person being evaluated.

[0285] Step 4:

[0286] The device uses a camera and microphone to collect facial expressions and tone of voice of the person being evaluated during the presentation. The device uses emotion analysis software (e.g., emotion analysis tool) to recognize emotions from these data. The input data is facial expression data and tone of voice data, and the output is the recognized emotion data.

[0287] Step 5:

[0288] The terminal transmits the recognized emotion data to the server. Specifically, the terminal transmits the emotion data to the server using an HTTP request. The input data is the recognized emotion data, and the output is the emotion data transmitted to the server.

[0289] Step 6:

[0290] The server sends the emotion data to the AI ​​system for analysis. The server analyzes the emotion data and reflects the emotion state of the person being evaluated in the evaluation. The input data is emotion data, and the output is the evaluation result based on the emotion state.

[0291] Step 7:

[0292] The server receives the analysis results from the AI ​​system and generates an evaluation of the person being evaluated. Specifically, it comprehensively evaluates the project success rate, report quality, and emotional state of the person being evaluated to generate an evaluation score. The input data are the evaluation results based on behavior and performance and the evaluation results based on emotional state, and the output is the evaluation score.

[0293] Step 8:

[0294] The server certifies the grade of the person being evaluated based on the generated evaluation score. Grade certification is performed at the discretion of the department and affects the employment conditions and wages of the person being evaluated. The input data is the evaluation score, and the output is the grade certification result.

[0295] Step 9:

[0296] The server standardizes the evaluation results company-wide and manages human resources. Specifically, a human resources management system (e.g., human resources management tool) is used to unify the evaluation results to company-wide standards and manage human resources as a going concern. The input data is the grade certification results, and the output is the standardized evaluation results.

[0297] (Application example 1)

[0298] Next, a description will be given of Application Example 1 of Form 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."

[0299] In conventional evaluation systems, evaluations were based only on the behavior and performance of the person being evaluated, which resulted in one-sided evaluations and failure to consider the emotions and psychological state of the person being evaluated. In addition, it was difficult to appropriately reflect the evaluation results in skill level certification, transfers, and wage adjustments. This could lead to a decrease in the fairness and accuracy of evaluations, which could have a negative impact on the efficiency and motivation of the entire organization.

[0300] 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.

[0301] In this invention, the server includes a means for collecting data such as the behavior and performance of the person to be evaluated, an AI for evaluating the person to be evaluated based on the collected data, a means for certifying the grade of the person to be evaluated based on the evaluation results by the AI, an emotion engine for recognizing the emotions of the person to be evaluated, a means for analyzing the emotion data collected by the emotion engine, and a means for using the emotion data for certifying the skill level of the person to be evaluated, transferring the person to a new position, and adjusting the wages of the person to be evaluated. This enables a comprehensive evaluation that takes into account not only the behavior and performance of the person to be evaluated, but also their emotions and psychological state. Furthermore, the evaluation results can be appropriately reflected in the certification of skill level, transfer, and wage adjustment, which is expected to improve the efficiency and motivation of the entire organization.

[0302] An "evaluation target" is a person whose behavior, performance, emotions, etc. are evaluated by the evaluation system.

[0303] "Behavioral data" refers to information about the behavior of the person being evaluated, including, for example, the progress of work and the accuracy of movements.

[0304] "Performance Data" refers to information about an individual's work accomplishments or performance, including, for example, project success rates and quality of deliverables.

[0305] The "emotion engine" is a technology for recognizing the emotions of the person being evaluated, analyzing emotions from facial expressions, tone of voice, choice of words, etc.

[0306] "Emotional data" refers to information about the emotions of the person being evaluated that is collected by the emotion engine, and includes, for example, emotional states such as tension, joy, sadness, etc.

[0307] "AI" refers to artificial intelligence, a technology that analyzes collected data and evaluates individuals being evaluated.

[0308] "Grade certification" involves evaluating the skill level and abilities of the person being evaluated and ranking them based on certain criteria.

[0309] "Skill level certification" means evaluating the level of skills and abilities of the person being assessed and granting an appropriate rank or qualification.

[0310] "Reassignment" refers to changing the duties or role of the person being evaluated based on the results of the evaluation.

[0311] A "wage adjustment" is a change in the salary or remuneration of an individual being evaluated based on the results of the evaluation.

[0312] The system for carrying out the present invention collects data on the behavior, performance, and emotions of the person being evaluated, and performs a comprehensive evaluation using AI. A specific embodiment of this system will be described below.

[0313] System Configuration

[0314] 1. Data collection methods:

[0315] The server collects the behavioral data, performance data, and emotional data of the person being evaluated. The behavioral data and performance data are saved in a format such as a CSV file. Emotional data is collected in real time using a camera.

[0316] 2. Data Analysis Methods:

[0317] The server pre-processes the collected data and performs analysis using an AI model. Specifically, it integrates behavioral data and performance data, and adds emotion data collected by an emotion engine. This allows for a comprehensive evaluation of the person being evaluated.

[0318] 3. Evaluation method:

[0319] The server uses an AI model (e.g., RandomForestClassifier) ​​to evaluate the candidates. The evaluation results are used to certify skill levels, transfer employees, and adjust wages.

[0320] Hardware and Software Used

[0321] Hardware:

[0322] Camera: Used to collect emotion data from the subjects.

[0323] Server: Used to collect, analyze, and evaluate data.

[0324] software:

[0325] OpenCV: Used to process camera images.

[0326] DeepFace: Used to analyze emotion data.

[0327] pandas: Used for data preprocessing.

[0328] scikit-learn: Used to train and evaluate AI models.

[0329] Examples

[0330] For example, consider a system that evaluates workers in a factory. The system collects data on the workers' behavior (progress of work and accuracy of movements), performance data (success rate of projects and quality of submitted work), and emotion data (emotional states such as tension, joy, sadness, etc.), and uses an AI model to perform a comprehensive evaluation. The evaluation results are used to certify the worker's skill level, transfer them, and adjust their wages.

[0331] Examples of prompt statements

[0332] Below are examples of prompts to be input to a generative AI model.

[0333] Please design a system to collect data on the behavior, performance, and emotions of workers in the factory and use an AI model to evaluate them. The evaluation results will be used to certify the skill level of workers, transfer them, and adjust their wages. Please also explain in detail how to collect the specific data, select the AI ​​model, and how to output the evaluation results.

[0334] Using this prompt, the generative AI model can provide more detailed designs and improvement suggestions.

[0335] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0336] Step 1:

[0337] The server collects the behavioral data of the subjects. Specifically, it reads data such as task progress and accuracy of actions from a CSV file. The input is a CSV file, and the output is a data frame of behavioral data. Converting the data into a data frame makes subsequent data analysis easier.

[0338] Step 2:

[0339] The server collects the performance data of the assessees. Specifically, it reads data such as project success rate and quality of submissions from a CSV file. The input is a CSV file, and the output is a data frame of performance data, which makes it easier to integrate with behavioral data.

[0340] Step 3:

[0341] The server collects the emotion data of the person being evaluated. Specifically, it captures video in real time using a camera and analyzes the emotions using DeepFace. The input is the camera video, and the output is a data frame of emotion data. The emotion data includes the person being evaluated's facial expressions, tone of voice, choice of words, etc.

[0342] Step 4:

[0343] The server integrates the collected behavioral data, performance data, and emotion data. Specifically, it combines each data frame to create a single comprehensive dataset. The input is a data frame of behavioral data, performance data, and emotion data, and the output is an integrated dataset. This makes it possible to comprehensively evaluate the person being evaluated.

[0344] Step 5:

[0345] The server preprocesses the integrated dataset. Specifically, it completes missing values ​​and normalizes the data. The input is the integrated dataset, and the output is the preprocessed dataset. Preprocessing improves the accuracy of the AI ​​model.

[0346] Step 6:

[0347] The server trains an AI model using the preprocessed dataset. Specifically, it trains the model using RandomForestClassifier. The input is the preprocessed dataset, and the output is the trained AI model. Using the trained model, it becomes possible to evaluate the subject.

[0348] Step 7:

[0349] The server uses a trained AI model to evaluate the person being evaluated. Specifically, it evaluates the person being evaluated for skill level certification, transfer, and wage adjustment. The input is a preprocessed dataset and a trained AI model, and the output is the evaluation result. The evaluation result contributes to improving the efficiency and motivation of the entire organization.

[0350] Step 8:

[0351] The server stores the evaluation results and notifies the administrator or the person being evaluated as necessary. Specifically, the evaluation results are stored in a database and notified to relevant parties through a notification system. The input is the evaluation results, and the output is the stored evaluation results and notifications. This ensures the transparency and reliability of the evaluation results.

[0352] Example 2

[0353] Next, a second embodiment of the second embodiment will be described. 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."

[0354] In conventional evaluation systems, it takes time to collect the behavior and performance data of the person being evaluated and then to evaluate them, making it difficult to perform evaluations in real time. In addition, there was a problem of reduced accuracy of evaluations because evaluations did not take into account emotional data. Furthermore, there was an issue that rapid human resource management was difficult due to delays in updating evaluation results and grading.

[0355] 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.

[0356] In this invention, the server includes a means for collecting behavior, performance, and emotion data of the person to be evaluated in real time, a means for transmitting the collected data to the server, a means for analyzing the data received by the server with an AI analysis engine, a means for updating the evaluation of the person to be evaluated in real time based on the analysis result, and a means for certifying the grade of the person to be evaluated in real time based on the evaluation result. This makes it possible to evaluate the behavior, performance, and emotion of the person to be evaluated in real time and provide quick and accurate feedback.

[0357] "Appraisee" refers to the individual whose behavior, performance, feelings, etc. are evaluated by the appraisal system.

[0358] "Behavioral data" refers to information about the actions and behavior of the person being evaluated, including, for example, remarks made during a meeting or the content of a presentation.

[0359] "Performance data" refers to information regarding the work results and performance of the person being evaluated, including, for example, sales performance and project progress.

[0360] "Emotional data" refers to information about the emotional state of the person being evaluated, including, for example, facial expressions, tone of voice, and choice of words.

[0361] "Real-time" means that data is collected, analyzed, and evaluated immediately, without delay.

[0362] "Collection means" refers to devices and software used to obtain behavioral, performance, and emotional data about the person being evaluated.

[0363] "Transmission means" refers to the communication device or protocol used to send collected data to the server.

[0364] "Server" refers to a computer system for receiving, analyzing, and evaluating data.

[0365] "AI analysis engine" refers to artificial intelligence software for analyzing and evaluating collected data.

[0366] "Evaluation update means" refers to a device or software for updating the evaluation of the person being evaluated in real time based on the analysis results.

[0367] "Grade certification means" refers to a device or software for determining and certifying the grade of an individual being evaluated in real time based on the evaluation results.

[0368] "Emotion recognition engine" refers to artificial intelligence software for recognizing the emotions of the person being evaluated in real time.

[0369] "Human resource management tools" refers to devices and software for allocating and developing personnel based on the grade certification of those being evaluated.

[0370] The present invention is a system that collects data on the behavior, performance, and emotions of an individual to be evaluated in real time and instantly analyzes and evaluates the data using AI. A specific embodiment of this system will be described below.

[0371] Hardware and Software Used

[0372] Hardware: high performance servers, cameras, microphones, sensors

[0373] Software: AI analysis engine, emotion recognition engine, data collection software

[0374] Data collection

[0375] The device collects the behavior, performance, and emotional data of the person being evaluated in real time. Specifically, the camera installed in the device captures the facial expression of the person being evaluated, and the microphone records the tone of voice. In addition, the sensor detects the movement of the person being evaluated. For example, the camera and microphone collect the facial expression and tone of voice of the person being evaluated who is giving a presentation in a meeting.

[0376] Data transmission

[0377] The data collected by the device is sent to the server. The data collected by the device is compressed in real time and sent to the server using a secure communication protocol. For example, the collected facial expression data and tone of voice data are sent to the server.

[0378] 4. Data Analysis

[0379] The data received by the server is immediately analyzed using an AI analysis engine. The data received by the server is input into the AI ​​analysis engine, which analyzes behavioral and performance data. In addition, an emotion recognition engine is used to analyze emotional data. For example, the content of a presentation is analyzed to evaluate the performance of the person being evaluated. Emotions such as anger and joy are recognized from facial expressions and tone of voice.

[0380] Rating Update

[0381] The server updates the evaluation of the person being evaluated in real time based on the analysis results. The server reflects the analysis results in the evaluation database and updates the evaluation score of the person being evaluated. For example, the evaluation score of the person being evaluated is updated based on the performance evaluation of the presentation and the emotion data.

[0382] Grade Certification

[0383] The server certifies the grade of the person being evaluated in real time based on the evaluation results. The server determines the grade of the person being evaluated based on the updated evaluation score and notifies the result of the certification. For example, the person being evaluated is certified as "Excellent" based on the updated evaluation score.

[0384] Examples

[0385] For example, when the person being evaluated is giving a presentation during a meeting, the following process is carried out.

[0386] 1. The device uses a camera and microphone to collect the subject's facial expressions, tone of voice, and presentation content in real time.

[0387] 2. The device sends the collected data to the server.

[0388] 3. The server uses an AI analysis engine to analyze the content of the presentation and the performance of the person being evaluated.

[0389] 4. The server uses an emotion recognition engine to recognize the emotions of the person being evaluated from their facial expressions and tone of voice. For example, if the person being evaluated expresses anger, the server analyzes that information.

[0390] 5. The server updates the evaluation of the person being evaluated in real time based on the analysis results and certifies the grade.

[0391] Examples of prompt statements

[0392] "If an evaluation subject expresses anger during a meeting, please explain in detail the processing steps of the system where the AI ​​immediately analyzes that information and reflects it in the evaluation of the evaluation subject."

[0393] The system makes it possible to evaluate the behavior, performance, and emotions of individuals in real time, providing fast and accurate feedback.

[0394] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0395] Step 1:

[0396] The device collects real-time data on the behavior, performance, and emotions of the person being evaluated.

[0397] Input: Facial expressions, tone of voice, and movements of the person being evaluated

[0398] How it works: The device's camera captures the subject's facial expressions, the microphone records the tone of the subject's voice, and the sensor detects the subject's movements.

[0399] Output: Collected facial expression data, tone of voice data, movement data

[0400] Step 2:

[0401] The terminal transmits the collected data to the server.

[0402] Input: Collected facial expression data, tone of voice data, movement data

[0403] Specific operation: The data collected by the terminal is compressed in real time and sent to the server using a secure communication protocol.

[0404] Output: Data sent to the server

[0405] Step 3:

[0406] The data received by the server is instantly analyzed using an AI analysis engine.

[0407] Input: Data sent to the server

[0408] Specific operation: The server inputs the received data into the AI ​​analysis engine to analyze behavioral data and performance data. It also uses an emotion recognition engine to analyze emotion data.

[0409] Output: Analysis results (behavioral evaluation, performance evaluation, emotional evaluation)

[0410] Step 4:

[0411] The server updates the evaluation of the person being evaluated in real time based on the analysis results.

[0412] Input: Analysis results (behavioral evaluation, performance evaluation, emotional evaluation)

[0413] Specific operation: The server reflects the analysis results in the evaluation database and updates the evaluation score of the person being evaluated.

[0414] Output: Updated rating score

[0415] Step 5:

[0416] The server certifies the grade of the person being evaluated in real time based on the evaluation results.

[0417] Input: Updated rating score

[0418] Specific operation: The server determines the grade of the person being evaluated based on the updated evaluation score and notifies the certification result.

[0419] Output: Grade certification results

[0420] In this way, it is possible to evaluate the behavior, performance, and emotions of the person being evaluated in real time and provide fast and accurate feedback.

[0421] (Application example 2)

[0422] Next, a description will be given of Application Example 2 of Form 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."

[0423] In conventional evaluation systems, evaluations were based only on the behavior and performance of the person being evaluated, which resulted in one-sided evaluations and did not take into account the emotions and psychological state of the person being evaluated. In addition, it was difficult to update the evaluations in real time, which sometimes resulted in a time lag in the evaluations. This could lead to a loss of accuracy and fairness in the evaluations. Furthermore, there was a lack of real-time feedback to improve the efficiency and safety of workers in the factory.

[0424] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0425] In this invention, the server includes a means for collecting data on the behavior and performance of the person to be evaluated, an artificial intelligence for evaluating the person to be evaluated based on the collected data, a means for certifying the grade of the person to be evaluated based on the evaluation result by the artificial intelligence, an emotion engine for recognizing the emotion of the person to be evaluated in real time, a means for analyzing the emotion data recognized by the emotion engine, and a means for updating the evaluation of the person to be evaluated in real time based on the analysis result. This enables a comprehensive evaluation that takes into account not only the behavior and performance of the person to be evaluated, but also their emotion and psychological state, and allows evaluation updates and feedback in real time.

[0426] An "evaluatee" is an individual whose behavior, achievements, feelings, etc. are evaluated by the evaluation system.

[0427] "Behavioral data" refers to information regarding the actions and behavior of the person being evaluated.

[0428] "Performance Data" refers to information regarding the results and accomplishments of the person being evaluated.

[0429] "Artificial intelligence" refers to a computer system that analyzes collected data and evaluates individuals being evaluated.

[0430] "Grade certification" is the process of determining the rank or grade of an individual based on the results of evaluation by artificial intelligence.

[0431] The "emotion engine" is a system that recognizes emotions in real time from the facial expressions, tone of voice, choice of words, etc. of the person being evaluated.

[0432] "Emotion Data" refers to information regarding the emotions of the subject of evaluation recognized by the emotion engine.

[0433] "Real-time update" refers to the process of instantly reflecting the evaluation of the person being evaluated and always maintaining the latest evaluation status.

[0434] "Feedback" is the process of notifying the person being evaluated of the results of the evaluation in real time.

[0435] As an embodiment of the present invention, a system for evaluating the behavior, performance, and emotions of workers in a factory in real time is constructed. A specific embodiment of the system is described below.

[0436] System Configuration

[0437] The system consists of the following main components:

[0438] 1. Cameras: Used to capture worker movements in real time.

[0439] 2. Microphone: Used to collect the voices of workers.

[0440] 3. Server: The central computer system that collects, analyzes, and evaluates the data.

[0441] 4. Artificial Intelligence (AI): Analyzes collected data and evaluates the subjects.

[0442] 5. Emotion engine: Recognizes emotions in real time from workers' facial expressions, tone of voice, choice of words, etc.

[0443] 6. Feedback system: Notify workers of evaluation results in real time.

[0444] Program Processing

[0445] The server collects data from the camera and microphone in real time and analyzes it. Specifically, it performs the following processes:

[0446] 1. Data collection: A camera is used to capture the worker's movements and a microphone is used to collect the worker's voice.

[0447] 2. Emotion Recognition: Using an emotion engine, we recognize the emotions of workers from the collected tone of voice and facial expressions. The emotion engine uses Google Cloud's emotion analysis API.

[0448] 3. Data analysis: Artificial intelligence will analyze and evaluate the collected behavioral data, performance data, and emotional data.

[0449] 4. Evaluation update: Update worker evaluations in real time based on the analysis results.

[0450] 5. Feedback: Communicate updated evaluation results to workers in real time.

[0451] Hardware and Software Used

[0452] Hardware: Cameras, microphones, servers

[0453] Software: OpenCV (camera image acquisition and display), Google Cloud emotion analysis API (emotion recognition)

[0454] Examples

[0455] For example, if a worker says, "This task is very difficult," the emotion engine will detect "anxiety" from the tone and content of the voice, and the AI ​​will update the worker's evaluation based on that information.

[0456] Examples of prompt statements

[0457] If a worker says, "This task is very difficult," the emotion engine will detect "anxiety" from the tone and content of the voice, and the AI ​​will update the worker's evaluation based on that information.

[0458] In this way, a system can be created that evaluates worker behavior and emotions in real time and provides feedback.

[0459] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0460] Step 1:

[0461] The server uses a camera to capture the worker's movements in real time. The input is the camera image and the output is the captured movement data. Specifically, it uses OpenCV to acquire the image from the camera and record the worker's movements frame by frame.

[0462] Step 2:

[0463] The server collects the voices of workers using a microphone. The input is voice data, and the output is the collected voice data. Specifically, the server captures voice input from the microphone in real time and saves it as an audio file.

[0464] Step 3:

[0465] The server uses an emotion engine to recognize the emotions of workers from the collected tone of voice and facial expressions. The input is voice data and video data, and the output is the recognized emotion data. Specifically, the voice data is analyzed using the Google Cloud emotion analysis API to obtain an emotion score. In addition, facial expressions are analyzed from the video data to recognize emotions.

[0466] Step 4:

[0467] The server uses artificial intelligence to analyze the collected behavioral data, performance data, and emotional data and performs the evaluation. The input is behavioral data, performance data, and emotional data, and the output is the evaluation results. Specifically, the data is analyzed using a generative AI model and the performance of the person being evaluated is scored.

[0468] Step 5:

[0469] The server updates the evaluation of the worker in real time based on the analysis results. The input is the evaluation result, and the output is the updated evaluation data. Specifically, the evaluation result is saved in a database and the profile of the person being evaluated is updated.

[0470] Step 6:

[0471] The server notifies the worker of the updated evaluation results in real time. The input is the updated evaluation data, and the output is a notification message. Specifically, the server sends the evaluation results to the worker's device as a push notification, providing feedback to the worker.

[0472] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice 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 voice data.

[0473] 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<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to 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.

[0474] Another example of generative AI is Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) are mentioned.

[0475] In the above embodiment, an example has been given in which the specific process is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0476] [Second embodiment]

[0477] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0478] 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.

[0479] 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 wide area network (WAN) and / or a local area network (LAN).

[0480] 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.

[0481] 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 the voice according to instructions from the processor 46.

[0482] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0483] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0484] Fig. 4 shows an example of 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.

[0485] 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.

[0486] 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.

[0487] In the smart glasses 214, the reception output process is performed by the processor 46. The storage 50 stores a reception output program 60. The processor 46 reads out the reception output program 60 from the storage 50 and executes the read reception output program 60 as the RA.

[0488] The reception and output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception and output program 60 executed on the RAM 48.

[0489] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0490] "Example 1"

[0491] As one embodiment of the present invention, an AI system that evaluates people in a corporate organization is provided. This system has a means for collecting data on the behavior and performance of the person being evaluated. For example, data such as the success rate of projects carried out by the person being evaluated and the quality of reports submitted by the person being evaluated is collected. The collected data is analyzed by AI, and the person being evaluated is evaluated. The evaluation results are used to certify the grade of the person being evaluated. Grade certification is performed at the discretion of the department, and affects changes to the employment conditions and wages of the person being evaluated. In addition, the evaluation results are standardized company-wide, and human resource management is also carried out as a going concern.

[0492] "Example 2"

[0493] As another embodiment of the present invention, a form is provided in which an AI system collects data on the behavior, performance, etc. of the person to be evaluated in real time and performs the evaluation in real time. In this form, data on the behavior, performance, etc. of the person to be evaluated is collected immediately after the person to be evaluated performs an action or achieves an achievement, and is analyzed immediately by AI. As a result, the evaluation of the person to be evaluated is updated in real time, and the grade of the person to be evaluated is also certified in real time.

[0494] The process flow of each embodiment will be described below.

[0495] "Example 1"

[0496] Step 1: Collect data on the behavior and performance of the person being evaluated. For example, collect data on the success rate of projects carried out by the person being evaluated and the quality of reports submitted by the person being evaluated.

[0497] Step 2: The collected data is analyzed by AI, which then evaluates the person being evaluated based on the collected data.

[0498] Step 3: The grade of the person being evaluated is determined based on the results of the AI ​​evaluation. Grade determination is done at the discretion of the department and will affect changes to the employment conditions and wages of the person being evaluated.

[0499] Step 4: The evaluation results are standardized across the company and are used in human resource management as a going concern.

[0500] "Example 2"

[0501] Step 1: Collect data on the behavior and performance of the person being evaluated in real time. Data is collected immediately after the person being evaluated performs an action or achieves a result.

[0502] Step 2: The collected data is immediately analyzed by AI, which then evaluates the person being evaluated in real time based on the collected data.

[0503] Step 3: Based on the results of the AI ​​evaluation, the grade of the person being evaluated is determined in real time. Grade determination is done at the discretion of the department and has an immediate effect on changes to the employment conditions and wages of the person being evaluated.

[0504] Example 1

[0505] Next, a description will be given of Example 1 of Form 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".

[0506] In conventional talent evaluation systems, data collection on the behavior and performance of those being evaluated was insufficient, and the evaluations often lacked objectivity and accuracy. In addition, because grade certification and talent management based on the evaluation results were not performed consistently, there was a problem that talent management throughout the organization was not performed efficiently. Furthermore, the evaluation process was often performed manually, which was time-consuming and labor-intensive.

[0507] 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.

[0508] In this invention, the server includes a means for collecting data on the behavior and performance of the person to be evaluated, a means for preprocessing the collected data, a means including a generative AI model for analyzing the preprocessed data, a means for evaluating the person to be evaluated based on the analysis result by the generative AI model, and a means for certifying the grade of the person to be evaluated based on the evaluation result. This enables objective and highly accurate evaluation based on the behavior and performance of the person to be evaluated, and consistent grade certification and human resource management based on the evaluation result can be efficiently performed.

[0509] "Assesseeee" refers to the individual within the business organization who is the subject of the assessment.

[0510] "Data on behavior, performance, etc." refers to data containing information necessary for evaluation, such as the success rate of projects carried out by the person being evaluated and the quality of reports submitted.

[0511] "Means of collection" refers to the hardware and software used to obtain data on the behavior, performance, etc. of the person being evaluated.

[0512] "Preprocessing means" refers to hardware and software used to fill in missing values ​​in collected data, correct outliers, standardize data formats, and so on.

[0513] A "generative AI model" refers to an artificial intelligence model that analyzes data such as the behavior and performance of the person being evaluated and generates an evaluation score.

[0514] "Means of analysis" refers to the hardware and / or software used to input preprocessed data into a generative AI model and generate an evaluation score.

[0515] "Means of evaluation" refers to hardware and software used to evaluate the subject based on the analysis results of the generative AI model.

[0516] "Means of grade certification" refers to hardware or software used to certify the grade of the person being evaluated based on the evaluation results.

[0517] "Departmental discretion" refers to each department within a company deciding the grade of each person being evaluated at its own discretion.

[0518] "Human resource management" refers to changing the employment conditions, adjusting wages, setting career paths, etc. of those being evaluated based on the evaluation results and grade certification.

[0519] The present invention relates to an AI system for evaluating people in a corporate organization. A specific embodiment of this system will be described below.

[0520] The server has a means of collecting data on the behavior and performance of the assessees. Specifically, it obtains project success rate data from project management software (e.g., JIRA, Trello) and collects quality data on submitted reports from document management systems (e.g., Google Drive, SharePoint).

[0521] Next, the server preprocesses the collected data. It complements missing values ​​in the data and detects and corrects outliers. It also standardizes the data format and prepares it in a form that is easy for the AI ​​model to analyze. For example, if there are missing values, they are complemented with the average value, and if there are outliers, they are corrected with the median value. The data format is standardized and converted into CSV format.

[0522] The preprocessed data is input into a generative AI model (e.g., TensorFlow, PyTorch) on the server. The AI ​​model analyzes the behavioral patterns and performance of the person being evaluated and generates an evaluation score. For example, if the success rate of the projects in which person being evaluated A was in charge was 90% and the quality of the reports he submitted was highly evaluated, the AI ​​model will generate an evaluation score based on this data.

[0523] Based on the generated evaluation score, the server generates an overall evaluation of the person being evaluated. This evaluation result is used to certify the grade of the person being evaluated. Grade certification is performed at the discretion of the department and affects changes to the employment conditions and wages of the person being evaluated. In addition, the evaluation result is standardized across the company and is also used for human resource management as a going concern.

[0524] As a concrete example, consider a case where the success rate of projects carried out by assessee A was 90% and the quality of the submitted reports was highly evaluated. The server collects success rate data from the project management software and report quality data from the document management system. These data are input into the AI ​​model for evaluation.

[0525] Example of a prompt to be input to a generative AI model:

[0526] The project success rate of assessee A is 90%, and the quality of the reports he submitted is highly rated. Based on this data, please give an overall evaluation of assessee A.

[0527] Using this prompt, the AI ​​model generates an overall evaluation of the person being evaluated A. The evaluation results are used for grading at the department's discretion and for company-wide standardization.

[0528] In this way, the server evaluates people within the corporate organization and provides grades and feedback based on the evaluation results.

[0529] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0530] Step 1: Data collection

[0531] The server collects data on the behavior and performance of the assessees. Specifically, it obtains project success rate data from project management software (e.g., JIRA, Trello) and collects quality data on submitted reports from document management systems (e.g., Google Drive, SharePoint). The input is the assessee's ID and project ID, and the output is project success rate data and report quality data.

[0532] Step 2: Data Preprocessing

[0533] The server preprocesses the collected data. Specifically, it complements missing values ​​in the data and detects and corrects outliers. It also standardizes the data format and prepares it in a form that is easy for the AI ​​model to analyze. The input is the collected raw data, and the output is preprocessed, clean data. For example, if there are missing values, they are complemented with the average value, and if there are outliers, they are corrected with the median. The data format is standardized and converted to CSV format.

[0534] Step 3: Data analysis

[0535] The server inputs the preprocessed data into a generative AI model. The AI ​​model (e.g., TensorFlow, PyTorch) analyzes the behavioral patterns and performance of the person being evaluated and generates an evaluation score. The input is the preprocessed data, and the output is the evaluation score. For example, if the success rate of the projects in which person being evaluated A was in charge was 90% and the quality of the reports he submitted was highly evaluated, the AI ​​model will generate an evaluation score based on this data.

[0536] Step 4: Generate evaluation results

[0537] The server generates an overall evaluation of the person being evaluated based on the generated evaluation score. The input is the evaluation score obtained from the AI ​​model, and the output is the overall evaluation of the person being evaluated. For example, based on an evaluation score of 85 points, the overall evaluation of person A is set to "excellent."

[0538] Step 5: Grading and feedback

[0539] The server certifies the grade of the person being evaluated based on the generated evaluation results. The input is the overall evaluation, and the output is the grade certification result of the person being evaluated. Grade certification is done at the discretion of the department and affects changes to the employment conditions and wages of the person being evaluated. The evaluation results are also standardized company-wide and are used in human resource management as a going concern. For example, the grade of person A being evaluated is certified as "A" and his / her wage is increased by 10%.

[0540] (Application example 1)

[0541] Next, a description will be given of Application Example 1 of Form 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".

[0542] Traditionally, the performance evaluation of robots working in factories was mainly carried out by human managers, which led to problems with the lack of objectivity and efficiency of the evaluation. In addition, robot maintenance schedules and upgrade plans often relied on experience and intuition and were not optimized. This reduced the robot's operating rate and lifespan, and had a negative impact on the productivity of the entire factory.

[0543] 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.

[0544] In this invention, the server includes a means for collecting data such as the work efficiency, error rate, and maintenance history of the machine to be evaluated, an AI for evaluating the machine to be evaluated based on the collected data, a means for optimizing a maintenance schedule for the machine to be evaluated based on the evaluation results by the AI, and a means for proposing an upgrade plan for the machine to be evaluated based on the evaluation results. This makes it possible to objectively and efficiently evaluate the performance of a robot and to optimize the maintenance schedule and upgrade plan.

[0545] "Machinery to be evaluated" refers to robots and automated machinery that perform work in factories.

[0546] "Work efficiency" is an index that indicates how much work the evaluated machine can complete within a certain amount of time.

[0547] The "error rate" is an index showing the frequency of errors and breakdowns that occur when the machine being evaluated is in operation.

[0548] "Maintenance history" refers to the records of maintenance and repairs that the machine being evaluated has received in the past.

[0549] "Means of collecting data" refers to sensors and communication devices for obtaining data such as work efficiency, error rate, and maintenance history from the machine being evaluated.

[0550] "Evaluation AI" refers to an artificial intelligence system that analyzes collected data and evaluates the performance of the machine being evaluated.

[0551] "Means for optimizing maintenance schedules" refers to algorithms or programs for optimizing the timing and content of maintenance for the evaluated machinery based on the results of the AI ​​evaluation.

[0552] "Means for proposing an upgrade plan" refers to algorithms or programs for proposing upgrades to improve the performance or add functions to the machine being evaluated based on the results of the AI ​​evaluation.

[0553] As an embodiment of the present invention, a system for evaluating the performance of robots working in a factory is constructed. The system includes an AI that collects data such as the work efficiency, error rate, and maintenance history of the machine to be evaluated, and evaluates the machine based on the collected data. Furthermore, the system optimizes the maintenance schedule of the machine to be evaluated based on the evaluation results by the AI, and proposes an upgrade plan for the machine to be evaluated based on the evaluation results.

[0554] Hardware and Software Used

[0555] Hardware

[0556] Server: A high-performance server for data collection and analysis.

[0557] Robot: A robot in a factory that is the subject of data collection

[0558] Sensors: Sensors to collect data such as the robot's work efficiency, error rate, and maintenance history

[0559] software

[0560] Python: Used for data analysis and model training

[0561] Pandas: Used to load and preprocess data

[0562] Scikit-learn: Used to train and evaluate machine learning models.

[0563] Data processing and calculation

[0564] The server first collects data from the robot in real time. The collected data is preprocessed using Pandas and divided into features and targets such as work efficiency, error rate, and maintenance history. Then, a model is trained using Scikit-learn's RandomForestRegressor to predict the performance of the machine being evaluated. The prediction results are used to optimize the maintenance schedule of the machine being evaluated and propose an upgrade plan.

[0565] Examples

[0566] For example, if a robot's work efficiency is 90%, its error rate is 5%, and its maintenance history is three times, the server will collect these data and analyze them with the AI ​​model. Based on the analysis results, it will predict the robot's performance score and suggest the optimal maintenance schedule and necessary upgrades.

[0567] Examples of prompt statements

[0568] Enter your robot's work efficiency, error rate, and maintenance history to predict its performance score.

[0569] In this way, it is possible to build a system that evaluates the performance of robots working in factories and optimizes maintenance schedules and upgrade plans.

[0570] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0571] Step 1:

[0572] The server collects data such as work efficiency, error rate, and maintenance history from the robots in the factory in real time. This data is acquired using sensors and communication devices and stored in a database.

[0573] Input: Robot work efficiency, error rate, maintenance history

[0574] Output: Robot performance data stored in a database

[0575] Step 2:

[0576] The server preprocesses the collected data using Pandas. Specifically, it complements missing values ​​and removes outliers to make the data clean.

[0577] Input: Robot performance data stored in a database

[0578] Output: Preprocessed and clean data

[0579] Step 3:

[0580] The server divides the preprocessed data into features and targets. Work efficiency, error rate, and maintenance history are used as features, and performance score is set as a target.

[0581] Input: Preprocessed and clean data

[0582] Output: Data split into features and targets

[0583] Step 4:

[0584] The server trains a machine learning model using Scikit-learn's RandomForestRegressor. It uses the features and targets as training data to build the model.

[0585] Input: Data split into features and targets

[0586] Output: A trained machine learning model

[0587] Step 5:

[0588] The server uses the trained model to predict the robot's performance score based on new data collected in real time.

[0589] Input: New robot performance data collected in real time

[0590] Output: Predicted performance score

[0591] Step 6:

[0592] The server optimizes the robot's maintenance schedule based on the predicted performance score, determining the timing and content of maintenance and updating the schedule.

[0593] Input: Predicted performance score

[0594] Output: Optimized maintenance schedule

[0595] Step 7:

[0596] The server then proposes an upgrade plan for the robot based on the predicted performance score, determining what upgrades are required and when, and creating a proposal.

[0597] Input: Predicted performance score

[0598] Output: Proposed upgrade plan

[0599] In this way, the server can evaluate the robot's performance and optimize maintenance schedules and upgrade plans.

[0600] Example 2

[0601] Next, a description will be given of Example 2 of the embodiment 2. In the following description, the data processing device 12 is referred to as a "server" and the smart glasses 214 are referred to as a "terminal".

[0602] In the conventional evaluation system, data collection and analysis of the behavior and performance of the person being evaluated was not done in real time, and updates to evaluation results and grade certification were often delayed. In addition, there was also the problem that the evaluation criteria were uniform and it was difficult to reflect the discretion of each department. Furthermore, there was an issue that human resource management based on the evaluation results was not carried out efficiently.

[0603] 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.

[0604] In this invention, the server includes a means for collecting data such as the behavior and performance of the person to be evaluated in real time, a means for storing the collected data in a database, a means for using a generative AI model to analyze the stored data, a means for updating the evaluation score of the person to be evaluated in real time based on the analysis result, a means for certifying the grade of the person to be evaluated based on the evaluation score, and a means for notifying the terminal of the person to be evaluated of the result of the grade certification. This makes it possible to collect and analyze the data of the behavior and performance of the person to be evaluated in real time, quickly update the evaluation result, and certify the grade reflecting the discretion of each department. In addition, efficient human resource management based on the evaluation result can be realized.

[0605] "Appraisee" refers to the individual or group whose behavior or performance is evaluated by the appraisal system.

[0606] "Data on behavior, achievements, etc." refers to information on the specific behavior and achievements of the person being evaluated, including the progress and results of work, behavioral history, etc.

[0607] "Means of collecting data in real time" refers to methods and technologies for instantly obtaining data on the behavior and performance of the person being evaluated and incorporating it into the system without delay.

[0608] "Means of storing in a database" refers to the methods and technologies used to organize collected data and keep it accessible later.

[0609] A "generative AI model" refers to an algorithm or model that uses machine learning and artificial intelligence techniques to analyze data and evaluate the behavior and performance of individuals being evaluated.

[0610] "Evaluation score" refers to a numerical indicator of the performance of the person being evaluated based on the results of analysis by the generative AI model.

[0611] "Grade certification" refers to the process of determining the rank or grade of an assessee based on their assessment score.

[0612] "Means of notifying the device" refers to the methods and technologies for notifying the subject of the evaluation of the results of the evaluation and the grade certification, including email and push notifications.

[0613] "Departmental discretion" refers to the authority of each department to evaluate and grade based on its own criteria and policies.

[0614] "Human resource management" refers to the process of allocating, developing, and evaluating human resources within an organization based on evaluation results and grade certification.

[0615] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0616] The present invention is a system for collecting data on the behavior and performance of an evaluation target in real time, analyzing the data, updating the evaluation score, and certifying a grade. A specific embodiment of the system will be described below.

[0617] 1. Program Generation

[0618] The server collects data on the behavior and performance of the person being evaluated in real time and generates a program for evaluating the person. This program has the function of instantly analyzing the behavior and performance of the person being evaluated and updating the evaluation in real time.

[0619] 2. Program Processing

[0620] The server works with various sensors and databases to collect data on the behavior and performance of the person being evaluated. Specifically, data is collected from the devices (e.g., smartphones, PCs) and business systems (e.g., customer management systems, business management systems) used by the person being evaluated. This data is stored in the database on the server.

[0621] The server then uses a generative AI model to analyze the collected data. Specifically, it uses machine learning frameworks such as TensorFlow and PyTorch to analyze the behavior and performance of the person being evaluated. The analysis results are updated in real time as the person being evaluated's evaluation score.

[0622] Furthermore, the server certifies the grade of the person to be evaluated based on the evaluation score. In this process, the grade of the person to be evaluated is determined based on the evaluation criteria set in advance. The result of the grade certification is notified to the terminal of the person to be evaluated.

[0623] 3. Specific Examples

[0624] As a concrete example, consider the performance evaluation of a sales representative. When a sales representative wins a new contract, the information is automatically sent from the customer management system to a server. The server uses a generative AI model to analyze the value of the new contract and updates the sales representative's evaluation score. The updated evaluation score is notified to the sales representative's smartphone in real time.

[0625] Example prompt:

[0626] "When a sales rep wins a new deal, collect that information from your customer relationship management system and use a generative AI model to update the reputation score."

[0627] In this way, a system is realized in which the server, terminals, and users work together to evaluate the behavior and performance of the person being evaluated in real time and certify a grade.

[0628] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0629] Step 1: Data collection

[0630] The server collects data on the behavior and performance of the person being evaluated in real time. Specifically, it obtains data from the devices (e.g., smartphones, PCs) and business systems (e.g., customer management systems, business management systems) used by the person being evaluated. The input is data on the behavior and performance of the person being evaluated, and the output is the raw data sent to the server. For example, when a sales representative secures a new contract, that information is sent from the customer management system to the server.

[0631] Step 2: Save Data

[0632] The server stores the collected data in a database. Specifically, it uses a relational database such as MySQL or PostgreSQL. The input is the collected raw data, and the output is the structured data stored in the database. For example, the details of a new contract are stored in the database.

[0633] Step 3: Data analysis

[0634] The server uses a generative AI model to analyze the stored data. Specifically, it uses machine learning frameworks such as TensorFlow and PyTorch to analyze the behavior and performance of the person being evaluated. The input is structured data stored in a database, and the output is an evaluation score as the analysis result. For example, a predictive model based on past data is used to evaluate the value of a new contract.

[0635] Step 4: Update your reputation scores

[0636] The server updates the evaluation score of the person being evaluated based on the results of the data analysis. The input is the evaluation score as the analysis result, and the output is the updated evaluation score. For example, if the value of a new contract is high, the evaluation score of a sales representative increases.

[0637] Step 5: Grade Certification

[0638] The server certifies the grade of the person to be evaluated based on the updated evaluation score. The input is the updated evaluation score, and the output is the grade of the person to be evaluated. For example, if the evaluation score exceeds a certain threshold, the grade of the salesperson is promoted from "silver" to "gold."

[0639] Step 6: Notification

[0640] The server notifies the terminal of the person being evaluated of the result of the grade certification. The input is the grade of the person being evaluated, and the output is a notification sent to the terminal of the person being evaluated. For example, a notification saying "Your grade has been promoted to gold" is sent to the smartphone of a sales representative.

[0641] (Application example 2)

[0642] Next, a description will be given of Application Example 2 of Form 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".

[0643] With conventional factory robot evaluation systems, it was difficult to evaluate the robot's operation and production efficiency in real time and provide immediate feedback. As a result, it was not possible to properly instruct the robot on the timing of improvements to its operation or maintenance, which led to problems such as reduced production efficiency and an increased risk of breakdowns.

[0644] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0645] In this invention, the server includes a means for collecting data such as the behavior and performance of the evaluation target in real time, an AI for evaluating the evaluation target in real time based on the collected data, a means for certifying the grade of the evaluation target in real time based on the evaluation result by the AI, and a means for feeding back the evaluation result in real time and instructing the timing of behavior improvement and maintenance. This makes it possible to evaluate the behavior and production efficiency of a factory robot in real time and provide immediate feedback.

[0646] The "subject of evaluation" refers to factory robots, their operations, and production efficiency.

[0647] "Operational Data" refers to information about the operation of a factory robot, including performance indicators such as efficiency and error rates.

[0648] "Performance data" refers to information regarding the production volume and quality achieved by factory robots.

[0649] "Means of collecting data in real time" refers to methods of using sensors or data collection devices to instantly obtain the behavior and performance data of the subject being evaluated.

[0650] "Real-time AI" refers to an artificial intelligence system that instantly analyzes and evaluates collected data.

[0651] "Grade certification" refers to ranking the quality and efficiency of an item based on its performance.

[0652] "Feedback" refers to providing the subject of evaluation with immediate instructions for operational improvement or maintenance based on the evaluation results.

[0653] "Behavioral improvement" refers to adjustments or modifications made to improve the performance of the subject of evaluation.

[0654] "Timing of maintenance" refers to the time when maintenance work is performed to keep the object of evaluation functioning properly.

[0655] The system for carrying out the present invention evaluates the operation and production efficiency of factory robots in real time and provides immediate feedback. A specific embodiment of the system is described below.

[0656] 1. System Configuration

[0657] The system consists of the following main components:

[0658] Hardware: Factory robots, sensors (to measure efficiency and error rates)

[0659] Software: Python, AI analysis libraries (e.g. TensorFlow, Scikit-learn)

[0660] 2. Data Collection

[0661] The server collects the robot's operational data (efficiency and error rate) in real time using sensors attached to the factory robots, making it possible to immediately grasp the robot's performance.

[0662] 3. Data Analysis

[0663] The collected data is instantly analyzed using AI analysis libraries (e.g. TensorFlow, Scikit-learn) on the server. The AI ​​evaluates the robots based on their efficiency and error rate and generates an evaluation result.

[0664] 4. Grade Certification

[0665] The server will assign a grade to the robot in real time based on the AI ​​evaluation results. For example, if the efficiency is 90% or more and the error rate is less than 1%, the evaluation grade will be "A."

[0666] 5. Feedback and Improvements

[0667] The evaluation results are fed back to the robot in real time. The server then instructs the robot on operational improvements and maintenance timing based on the evaluation results, optimizing the robot's performance and improving production efficiency.

[0668] Examples

[0669] Example 1: If a robot assembles parts with an efficiency of 90% or more and an error rate of less than 1%, the evaluation grade will be "A" and the robot will continue to operate.

[0670] Example 2: If efficiency is below 80%, the evaluation grade will be "C" and a notification will be sent indicating that maintenance is required.

[0671] Examples of prompt statements

[0672] Collect the robot's operation data and evaluate its efficiency and error rate in real time. If the efficiency is 90% or more and the error rate is less than 1%, the evaluation grade should be "A". If the efficiency is 80% or less, the evaluation grade should be "C". Provide feedback on the evaluation results in real time and instruct maintenance as necessary.

[0673] In this way, a system can be realized that evaluates the operation of factory robots and production efficiency in real time and provides immediate feedback.

[0674] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0675] Step 1:

[0676] The server collects operational data (efficiency and error rate) in real time from sensors attached to factory robots. The input is the raw data from the sensors, and the output is the collected operational data. Specifically, the sensors monitor the robot's operation and measure its efficiency and error rate.

[0677] Step 2:

[0678] The server analyzes the collected motion data using AI analysis libraries (e.g. TensorFlow, Scikit-learn). The input is the collected motion data, and the output is the analysis result. Specifically, the AI ​​evaluates the robot's performance based on efficiency and error rate, and generates an evaluation result.

[0679] Step 3:

[0680] The server certifies the robot's grade in real time based on the AI ​​evaluation results. The input is the AI ​​evaluation result, and the output is the grade certification result. Specifically, if the efficiency is 90% or more and the error rate is less than 1%, the evaluation grade will be "A".

[0681] Step 4:

[0682] The server feeds back the evaluation results to the robot in real time. The input is the grade certification result, and the output is feedback information. Specifically, it provides the robot with instructions for improving its behavior and maintenance based on the evaluation results.

[0683] Step 5:

[0684] The server optimizes the robot's operation based on the feedback information. The input is the feedback information, and the output is the optimized operation parameters. Specifically, the robot adjusts its operation according to the instructions, improving production efficiency.

[0685] Step 6:

[0686] The server monitors the robot's operational improvements and maintenance timing, and provides additional instructions as necessary. The input is the optimized operational parameters, and the output is additional instructions. Specifically, the server continuously monitors the robot's performance and provides maintenance instructions as necessary.

[0687] In addition, 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.

[0688] "Example 1"

[0689] As one embodiment of the present invention, there is a system that combines an emotion engine. This system includes a means for collecting data such as the behavior and performance of the person to be evaluated, an AI that evaluates the person to be evaluated based on the collected data, and a means for certifying the grade of the person to be evaluated based on the evaluation result by the AI. Furthermore, it includes an emotion engine that recognizes the emotion of the person to be evaluated. Specifically, the emotion engine recognizes the emotion of the person to be evaluated from the facial expression, tone of voice, choice of words, etc. of the person to be evaluated, and the AI ​​analyzes the emotion data. For example, if the person to be evaluated feels nervous during a presentation, the AI ​​analyzes that information and reflects it in the evaluation of the person to be evaluated.

[0690] "Example 2"

[0691] Another embodiment of the present invention is a system that combines an emotion engine with a real-time data collection and analysis function. This system includes an AI that collects data on the behavior and performance of the person being evaluated in real time and evaluates the person being evaluated in real time based on the collected data, and a means for certifying the grade of the person being evaluated in real time based on the evaluation result by the AI. Furthermore, the system includes an emotion engine that recognizes the emotion of the person being evaluated in real time. Specifically, the emotion engine recognizes the emotion of the person being evaluated in real time from the facial expression, tone of voice, choice of words, etc. of the person being evaluated, and the AI ​​instantly analyzes the emotion data. For example, if the person being evaluated expresses anger during a meeting, the AI ​​instantly analyzes the information and reflects it in the evaluation of the person being evaluated.

[0692] The process flow of each embodiment will be described below.

[0693] "Example 1"

[0694] Step 1: Collect data on the behavior and performance of the person being evaluated.

[0695] Step 2: Use AI to evaluate the subjects based on the collected data.

[0696] Step 3: The person being evaluated is graded based on the AI ​​evaluation results.

[0697] Step 4: Use an emotion engine to recognize the emotions of the person being evaluated. The emotion engine recognizes the emotions of the person being evaluated from their facial expressions, tone of voice, choice of words, etc.

[0698] Step 5: AI analyzes the emotional data recognized by the emotion engine.

[0699] Step 6: The subject is evaluated based on the emotional data analyzed by the AI.

[0700] "Example 2"

[0701] Step 1: Collect data on the behavior and performance of the person being evaluated in real time.

[0702] Step 2: Use AI to evaluate subjects in real time based on the collected data.

[0703] Step 3: Based on the AI ​​evaluation results, the person being evaluated is graded in real time.

[0704] Step 4: An emotion engine is used to recognize the emotions of the person being evaluated in real time. The emotion engine recognizes emotions in real time from the person being evaluated's facial expressions, tone of voice, choice of words, etc.

[0705] Step 5: The AI ​​immediately analyzes the emotional data recognized by the emotion engine.

[0706] Step 6: The subject is evaluated based on the emotional data analyzed by the AI.

[0707] Example 1

[0708] Next, a description will be given of Example 1 of Form 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".

[0709] In conventional human evaluation systems, evaluations were based on the behavior and performance of the person being evaluated, but the evaluation did not take into account the emotional state of the person being evaluated. As a result, the evaluations were sometimes lacking in fairness and accuracy. In addition, it was difficult to grade the evaluation results at the discretion of the department, making it difficult to standardize the results across the company. This led to a lack of consistency in affecting changes to the employment conditions and wages of the person being evaluated.

[0710] 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.

[0711] In this invention, the server includes a means for collecting data such as the behavior and performance of the person to be evaluated, an artificial intelligence for evaluating the person to be evaluated based on the collected data, a means for certifying the grade of the person to be evaluated based on the evaluation result by the artificial intelligence, a means including an emotion engine for recognizing the emotions of the person to be evaluated, and a means for analyzing the emotion data collected by the emotion engine. This enables evaluation that takes into account the behavior and performance of the person to be evaluated as well as their emotional state, improving the fairness and accuracy of the evaluation. In addition, grade certification can be done at the discretion of the department, and consistent human resource management can be achieved through company-wide standardization.

[0712] "Appraisee" refers to the individual whose behavior, performance, or emotional state is evaluated by the appraisal system.

[0713] "Data on behavior, performance, etc." refers to data containing information necessary for evaluation, such as the success rate of projects carried out by the person being evaluated and the quality of reports submitted.

[0714] "Artificial intelligence" refers to machine learning algorithms and data analysis techniques used to analyze collected data and evaluate subjects.

[0715] "Grade certification" refers to the process of determining a grade for an individual based on their job or position, based on the results of an evaluation using artificial intelligence.

[0716] An "emotion engine" refers to technology that recognizes emotions from the facial expressions, tone of voice, choice of words, etc. of the person being evaluated, and collects that data.

[0717] "Emotional Data" refers to information regarding the emotional state of a Subject collected by the Emotion Engine.

[0718] "Departmental discretion" refers to the authority of each department to determine the grade of individuals being evaluated at its own discretion.

[0719] "Company-wide standardization" refers to the process of managing evaluation results based on uniform standards across the entire company, thereby ensuring consistent human resource management.

[0720] This invention relates to an AI system for evaluating people in a business organization. This system includes artificial intelligence (AI) that collects data on the behavior and performance of the person being evaluated and evaluates them based on the collected data. In addition, by combining it with an emotion engine that recognizes the emotions of the person being evaluated, a more accurate and fair evaluation is achieved.

[0721] Data collection

[0722] Users use the company's in-house project management software (e.g., JIRA) and document management systems (e.g., Google Drive) to collect data on the behavior and performance of appraisee(s), such as the success rate of projects undertaken by appraisee(s) and the quality of reports submitted.

[0723] Data transmission

[0724] The terminal transmits the collected data to the server. Specifically, the terminal transmits the project success rate data and the report quality data to the server using an HTTP request.

[0725] 4. Data Analysis

[0726] The server then sends the received data to the AI ​​system for analysis. The server uses machine learning algorithms such as TensorFlow to analyze the data and evaluate the behavior and performance of the person being evaluated.

[0727] emotion recognition

[0728] The device uses a camera and microphone to collect facial expressions and tone of voice of the person being evaluated while presenting, and can then use emotion analysis software such as the Microsoft Azure Emotion API to recognize emotions from this data.

[0729] Emotion Data Analysis

[0730] The device transmits the recognized emotion data to a server, which then transmits the emotion data to an AI system to analyze the subject's emotional state.

[0731] Generating evaluation results

[0732] The server receives the analysis results from the AI ​​system and generates an evaluation of the person being evaluated. Specifically, it comprehensively evaluates the person being evaluated based on their project success rate, report quality, and emotional state, and generates an evaluation score.

[0733] Grade Certification

[0734] The server certifies the grade of the person being evaluated based on the generated evaluation score. The grade certification is performed at the discretion of the department and affects the employment conditions and wages of the person being evaluated.

[0735] Company-wide standardization

[0736] The server standardizes the evaluation results company-wide and manages human resources. Specifically, the server uses a human resources management system such as SAP SuccessFactors to standardize the evaluation results to company-wide standards and manages human resources as a going concern.

[0737] Examples

[0738] For example, if assessee A succeeds in project X and submits report Y, the user uses JIRA to collect the success rate data of project X and Google Drive to collect the quality data of report Y. The terminal sends these data to the server via HTTP request. The server uses TensorFlow to analyze the data and evaluates the behavior and performance of assessee A. In addition, the terminal uses Microsoft Azure Emotion API to collect emotion data during the presentation of assessee A and sends it to the server. The server sends the emotion data to the AI ​​system and generates an evaluation score for assessee A based on the analysis results. The server performs grade certification based on the evaluation score and standardizes it company-wide using SAP SuccessFactors.

[0739] Examples of prompt statements

[0740] "Collect the success rate data of project X and the quality data of report Y of assessee A, and use the emotion engine to analyze the emotion data during the presentation. Generate an evaluation of assessee A based on the analysis results, and standardize it across the company."

[0741] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0742] Step 1:

[0743] The user collects data on the behavior and performance of the person being evaluated. Specifically, the user uses the company's project management software (e.g., project management tool) to collect data on the success rate of projects carried out by the person being evaluated, and uses a document management system (e.g., document management tool) to collect data on the quality of reports submitted by the person being evaluated. These data become input data for evaluating the behavior and performance of the person being evaluated.

[0744] Step 2:

[0745] The terminal transmits the collected data to the server. Specifically, the terminal transmits the project success rate data and the report quality data to the server using an HTTP request. The input data are the project success rate data and the report quality data, and the output is the data transmitted to the server.

[0746] Step 3:

[0747] The server sends the received data to the AI ​​system for analysis. The server analyzes the data using a machine learning algorithm (e.g., machine learning framework) and evaluates the behavior and performance of the person being evaluated. The input data is project success rate data and report quality data, and the output is the evaluation result based on the behavior and performance of the person being evaluated.

[0748] Step 4:

[0749] The device uses a camera and microphone to collect facial expressions and tone of voice of the person being evaluated during the presentation. The device uses emotion analysis software (e.g., emotion analysis tool) to recognize emotions from these data. The input data is facial expression data and tone of voice data, and the output is the recognized emotion data.

[0750] Step 5:

[0751] The terminal transmits the recognized emotion data to the server. Specifically, the terminal transmits the emotion data to the server using an HTTP request. The input data is the recognized emotion data, and the output is the emotion data transmitted to the server.

[0752] Step 6:

[0753] The server sends the emotion data to the AI ​​system for analysis. The server analyzes the emotion data and reflects the emotion state of the person being evaluated in the evaluation. The input data is emotion data, and the output is the evaluation result based on the emotion state.

[0754] Step 7:

[0755] The server receives the analysis results from the AI ​​system and generates an evaluation of the person being evaluated. Specifically, it comprehensively evaluates the project success rate, report quality, and emotional state of the person being evaluated to generate an evaluation score. The input data are the evaluation results based on behavior and performance and the evaluation results based on emotional state, and the output is the evaluation score.

[0756] Step 8:

[0757] The server certifies the grade of the person being evaluated based on the generated evaluation score. Grade certification is performed at the discretion of the department and affects the employment conditions and wages of the person being evaluated. The input data is the evaluation score, and the output is the grade certification result.

[0758] Step 9:

[0759] The server standardizes the evaluation results company-wide and manages human resources. Specifically, a human resources management system (e.g., human resources management tool) is used to unify the evaluation results to company-wide standards and manage human resources as a going concern. The input data is the grade certification results, and the output is the standardized evaluation results.

[0760] (Application example 1)

[0761] Next, a description will be given of Application Example 1 of Form 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".

[0762] In conventional evaluation systems, evaluations were based only on the behavior and performance of the person being evaluated, which resulted in one-sided evaluations and failure to consider the emotions and psychological state of the person being evaluated. In addition, it was difficult to appropriately reflect the evaluation results in skill level certification, transfers, and wage adjustments. This could lead to a decrease in the fairness and accuracy of evaluations, which could have a negative impact on the efficiency and motivation of the entire organization.

[0763] 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.

[0764] In this invention, the server includes a means for collecting data such as the behavior and performance of the person to be evaluated, an AI for evaluating the person to be evaluated based on the collected data, a means for certifying the grade of the person to be evaluated based on the evaluation results by the AI, an emotion engine for recognizing the emotions of the person to be evaluated, a means for analyzing the emotion data collected by the emotion engine, and a means for using the emotion data for certifying the skill level of the person to be evaluated, transferring the person to a new position, and adjusting the wages of the person to be evaluated. This enables a comprehensive evaluation that takes into account not only the behavior and performance of the person to be evaluated, but also their emotions and psychological state. Furthermore, the evaluation results can be appropriately reflected in the certification of skill level, transfer, and wage adjustment, which is expected to improve the efficiency and motivation of the entire organization.

[0765] An "evaluation target" is a person whose behavior, performance, emotions, etc. are evaluated by the evaluation system.

[0766] "Behavioral data" refers to information about the behavior of the person being evaluated, including, for example, the progress of work and the accuracy of movements.

[0767] "Performance Data" refers to information about an individual's work accomplishments or performance, including, for example, project success rates and quality of deliverables.

[0768] The "emotion engine" is a technology for recognizing the emotions of the person being evaluated, analyzing emotions from facial expressions, tone of voice, choice of words, etc.

[0769] "Emotional data" refers to information about the emotions of the person being evaluated that is collected by the emotion engine, and includes, for example, emotional states such as tension, joy, sadness, etc.

[0770] "AI" refers to artificial intelligence, a technology that analyzes collected data and evaluates individuals being evaluated.

[0771] "Grade certification" involves evaluating the skill level and abilities of the person being evaluated and ranking them based on certain criteria.

[0772] "Skill level certification" means evaluating the level of skills and abilities of the person being assessed and granting an appropriate rank or qualification.

[0773] "Reassignment" refers to changing the duties or role of the person being evaluated based on the results of the evaluation.

[0774] A "wage adjustment" is a change in the salary or remuneration of an individual being evaluated based on the results of the evaluation.

[0775] The system for carrying out the present invention collects data on the behavior, performance, and emotions of the person being evaluated, and performs a comprehensive evaluation using AI. A specific embodiment of this system will be described below.

[0776] System Configuration

[0777] 1. Data collection methods:

[0778] The server collects the behavioral data, performance data, and emotional data of the person being evaluated. The behavioral data and performance data are saved in a format such as a CSV file. Emotional data is collected in real time using a camera.

[0779] 2. Data Analysis Methods:

[0780] The server pre-processes the collected data and performs analysis using an AI model. Specifically, it integrates behavioral data and performance data, and adds emotion data collected by an emotion engine. This allows for a comprehensive evaluation of the person being evaluated.

[0781] 3. Evaluation method:

[0782] The server uses an AI model (e.g., RandomForestClassifier) ​​to evaluate the candidates. The evaluation results are used to certify skill levels, transfer employees, and adjust wages.

[0783] Hardware and Software Used

[0784] Hardware:

[0785] Camera: Used to collect emotion data from the subjects.

[0786] Server: Used to collect, analyze, and evaluate data.

[0787] software:

[0788] OpenCV: Used to process camera images.

[0789] DeepFace: Used to analyze emotion data.

[0790] pandas: Used for data preprocessing.

[0791] scikit-learn: Used to train and evaluate AI models.

[0792] Examples

[0793] For example, consider a system that evaluates workers in a factory. The system collects data on the workers' behavior (progress of work and accuracy of movements), performance data (success rate of projects and quality of submitted work), and emotion data (emotional states such as tension, joy, sadness, etc.), and uses an AI model to perform a comprehensive evaluation. The evaluation results are used to certify the worker's skill level, transfer them, and adjust their wages.

[0794] Examples of prompt statements

[0795] Below are examples of prompts to be input to a generative AI model.

[0796] Please design a system to collect data on the behavior, performance, and emotions of workers in the factory and use an AI model to evaluate them. The evaluation results will be used to certify the skill level of workers, transfer them, and adjust their wages. Please also explain in detail how to collect the specific data, select the AI ​​model, and how to output the evaluation results.

[0797] Using this prompt, the generative AI model can provide more detailed designs and improvement suggestions.

[0798] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0799] Step 1:

[0800] The server collects the behavioral data of the subjects. Specifically, it reads data such as task progress and accuracy of actions from a CSV file. The input is a CSV file, and the output is a data frame of behavioral data. Converting the data into a data frame makes subsequent data analysis easier.

[0801] Step 2:

[0802] The server collects the performance data of the assessees. Specifically, it reads data such as project success rate and quality of submissions from a CSV file. The input is a CSV file, and the output is a data frame of performance data, which makes it easier to integrate with behavioral data.

[0803] Step 3:

[0804] The server collects the emotion data of the person being evaluated. Specifically, it captures video in real time using a camera and analyzes the emotions using DeepFace. The input is the camera video, and the output is a data frame of emotion data. The emotion data includes the person being evaluated's facial expressions, tone of voice, choice of words, etc.

[0805] Step 4:

[0806] The server integrates the collected behavioral data, performance data, and emotion data. Specifically, it combines each data frame to create a single comprehensive dataset. The input is a data frame of behavioral data, performance data, and emotion data, and the output is an integrated dataset. This makes it possible to comprehensively evaluate the person being evaluated.

[0807] Step 5:

[0808] The server preprocesses the integrated dataset. Specifically, it completes missing values ​​and normalizes the data. The input is the integrated dataset, and the output is the preprocessed dataset. Preprocessing improves the accuracy of the AI ​​model.

[0809] Step 6:

[0810] The server trains an AI model using the preprocessed dataset. Specifically, it trains the model using RandomForestClassifier. The input is the preprocessed dataset, and the output is the trained AI model. Using the trained model, it becomes possible to evaluate the subject.

[0811] Step 7:

[0812] The server uses a trained AI model to evaluate the person being evaluated. Specifically, it evaluates the person being evaluated for skill level certification, transfer, and wage adjustment. The input is a preprocessed dataset and a trained AI model, and the output is the evaluation result. The evaluation result contributes to improving the efficiency and motivation of the entire organization.

[0813] Step 8:

[0814] The server stores the evaluation results and notifies the administrator or the person being evaluated as necessary. Specifically, the evaluation results are stored in a database and notified to relevant parties through a notification system. The input is the evaluation results, and the output is the stored evaluation results and notifications. This ensures the transparency and reliability of the evaluation results.

[0815] Example 2

[0816] Next, a description will be given of Example 2 of the embodiment 2. In the following description, the data processing device 12 is referred to as a "server" and the smart glasses 214 are referred to as a "terminal".

[0817] In conventional evaluation systems, it takes time to collect the behavior and performance data of the person being evaluated and then to evaluate them, making it difficult to perform evaluations in real time. In addition, there was a problem of reduced accuracy of evaluations because evaluations did not take into account emotional data. Furthermore, there was an issue that rapid human resource management was difficult due to delays in updating evaluation results and grading.

[0818] 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.

[0819] In this invention, the server includes a means for collecting behavior, performance, and emotion data of the person to be evaluated in real time, a means for transmitting the collected data to the server, a means for analyzing the data received by the server with an AI analysis engine, a means for updating the evaluation of the person to be evaluated in real time based on the analysis result, and a means for certifying the grade of the person to be evaluated in real time based on the evaluation result. This makes it possible to evaluate the behavior, performance, and emotion of the person to be evaluated in real time and provide quick and accurate feedback.

[0820] "Appraisee" refers to the individual whose behavior, performance, feelings, etc. are evaluated by the appraisal system.

[0821] "Behavioral data" refers to information about the actions and behavior of the person being evaluated, including, for example, remarks made during a meeting or the content of a presentation.

[0822] "Performance data" refers to information regarding the work results and performance of the person being evaluated, including, for example, sales performance and project progress.

[0823] "Emotional data" refers to information about the emotional state of the person being evaluated, including, for example, facial expressions, tone of voice, and choice of words.

[0824] "Real-time" means that data is collected, analyzed, and evaluated immediately, without delay.

[0825] "Collection means" refers to devices and software used to obtain behavioral, performance, and emotional data about the person being evaluated.

[0826] "Transmission means" refers to the communication device or protocol used to send collected data to the server.

[0827] "Server" refers to a computer system for receiving, analyzing, and evaluating data.

[0828] "AI analysis engine" refers to artificial intelligence software for analyzing and evaluating collected data.

[0829] "Evaluation update means" refers to a device or software for updating the evaluation of the person being evaluated in real time based on the analysis results.

[0830] "Grade certification means" refers to a device or software for determining and certifying the grade of an individual being evaluated in real time based on the evaluation results.

[0831] "Emotion recognition engine" refers to artificial intelligence software for recognizing the emotions of the person being evaluated in real time.

[0832] "Human resource management tools" refers to devices and software for allocating and developing personnel based on the grade certification of those being evaluated.

[0833] The present invention is a system that collects data on the behavior, performance, and emotions of an individual to be evaluated in real time and instantly analyzes and evaluates the data using AI. A specific embodiment of this system will be described below.

[0834] Hardware and Software Used

[0835] Hardware: high performance servers, cameras, microphones, sensors

[0836] Software: AI analysis engine, emotion recognition engine, data collection software

[0837] Data collection

[0838] The device collects the behavior, performance, and emotional data of the person being evaluated in real time. Specifically, the camera installed in the device captures the facial expression of the person being evaluated, and the microphone records the tone of voice. In addition, the sensor detects the movement of the person being evaluated. For example, the camera and microphone collect the facial expression and tone of voice of the person being evaluated who is giving a presentation in a meeting.

[0839] Data transmission

[0840] The data collected by the device is sent to the server. The data collected by the device is compressed in real time and sent to the server using a secure communication protocol. For example, the collected facial expression data and tone of voice data are sent to the server.

[0841] 4. Data Analysis

[0842] The data received by the server is immediately analyzed using an AI analysis engine. The data received by the server is input into the AI ​​analysis engine, which analyzes behavioral and performance data. In addition, an emotion recognition engine is used to analyze emotional data. For example, the content of a presentation is analyzed to evaluate the performance of the person being evaluated. Emotions such as anger and joy are recognized from facial expressions and tone of voice.

[0843] Rating Update

[0844] The server updates the evaluation of the person being evaluated in real time based on the analysis results. The server reflects the analysis results in the evaluation database and updates the evaluation score of the person being evaluated. For example, the evaluation score of the person being evaluated is updated based on the performance evaluation of the presentation and the emotion data.

[0845] Grade Certification

[0846] The server certifies the grade of the person being evaluated in real time based on the evaluation results. The server determines the grade of the person being evaluated based on the updated evaluation score and notifies the result of the certification. For example, the person being evaluated is certified as "Excellent" based on the updated evaluation score.

[0847] Examples

[0848] For example, when the person being evaluated is giving a presentation during a meeting, the following process is carried out.

[0849] 1. The device uses a camera and microphone to collect the subject's facial expressions, tone of voice, and presentation content in real time.

[0850] 2. The device sends the collected data to the server.

[0851] 3. The server uses an AI analysis engine to analyze the content of the presentation and the performance of the person being evaluated.

[0852] 4. The server uses an emotion recognition engine to recognize the emotions of the person being evaluated from their facial expressions and tone of voice. For example, if the person being evaluated expresses anger, the server analyzes that information.

[0853] 5. The server updates the evaluation of the person being evaluated in real time based on the analysis results and certifies the grade.

[0854] Examples of prompt statements

[0855] "If an evaluation subject expresses anger during a meeting, please explain in detail the processing steps of the system where the AI ​​immediately analyzes that information and reflects it in the evaluation of the evaluation subject."

[0856] The system makes it possible to evaluate the behavior, performance, and emotions of individuals in real time, providing fast and accurate feedback.

[0857] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0858] Step 1:

[0859] The device collects real-time data on the behavior, performance, and emotions of the person being evaluated.

[0860] Input: Facial expressions, tone of voice, and movements of the person being evaluated

[0861] How it works: The device's camera captures the subject's facial expressions, the microphone records the tone of the subject's voice, and the sensor detects the subject's movements.

[0862] Output: Collected facial expression data, tone of voice data, movement data

[0863] Step 2:

[0864] The terminal transmits the collected data to the server.

[0865] Input: Collected facial expression data, tone of voice data, movement data

[0866] Specific operation: The data collected by the terminal is compressed in real time and sent to the server using a secure communication protocol.

[0867] Output: Data sent to the server

[0868] Step 3:

[0869] The data received by the server is instantly analyzed using an AI analysis engine.

[0870] Input: Data sent to the server

[0871] Specific operation: The server inputs the received data into the AI ​​analysis engine to analyze behavioral data and performance data. It also uses an emotion recognition engine to analyze emotion data.

[0872] Output: Analysis results (behavioral evaluation, performance evaluation, emotional evaluation)

[0873] Step 4:

[0874] The server updates the evaluation of the person being evaluated in real time based on the analysis results.

[0875] Input: Analysis results (behavioral evaluation, performance evaluation, emotional evaluation)

[0876] Specific operation: The server reflects the analysis results in the evaluation database and updates the evaluation score of the person being evaluated.

[0877] Output: Updated rating score

[0878] Step 5:

[0879] The server certifies the grade of the person being evaluated in real time based on the evaluation results.

[0880] Input: Updated rating score

[0881] Specific operation: The server determines the grade of the person being evaluated based on the updated evaluation score and notifies the certification result.

[0882] Output: Grade certification results

[0883] In this way, it is possible to evaluate the behavior, performance, and emotions of the person being evaluated in real time and provide fast and accurate feedback.

[0884] (Application example 2)

[0885] Next, a description will be given of Application Example 2 of Form 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".

[0886] In conventional evaluation systems, evaluations were based only on the behavior and performance of the person being evaluated, which resulted in one-sided evaluations and did not take into account the emotions and psychological state of the person being evaluated. In addition, it was difficult to update the evaluations in real time, which sometimes resulted in a time lag in the evaluations. This could lead to a loss of accuracy and fairness in the evaluations. Furthermore, there was a lack of real-time feedback to improve the efficiency and safety of workers in the factory.

[0887] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0888] In this invention, the server includes a means for collecting data on the behavior and performance of the person to be evaluated, an artificial intelligence for evaluating the person to be evaluated based on the collected data, a means for certifying the grade of the person to be evaluated based on the evaluation result by the artificial intelligence, an emotion engine for recognizing the emotion of the person to be evaluated in real time, a means for analyzing the emotion data recognized by the emotion engine, and a means for updating the evaluation of the person to be evaluated in real time based on the analysis result. This enables a comprehensive evaluation that takes into account not only the behavior and performance of the person to be evaluated, but also their emotion and psychological state, and allows evaluation updates and feedback in real time.

[0889] An "evaluatee" is an individual whose behavior, achievements, feelings, etc. are evaluated by the evaluation system.

[0890] "Behavioral data" refers to information regarding the actions and behavior of the person being evaluated.

[0891] "Performance Data" refers to information regarding the results and accomplishments of the person being evaluated.

[0892] "Artificial intelligence" refers to a computer system that analyzes collected data and evaluates individuals being evaluated.

[0893] "Grade certification" is the process of determining the rank or grade of an individual based on the results of evaluation by artificial intelligence.

[0894] The "emotion engine" is a system that recognizes emotions in real time from the facial expressions, tone of voice, choice of words, etc. of the person being evaluated.

[0895] "Emotion Data" refers to information regarding the emotions of the subject of evaluation recognized by the emotion engine.

[0896] "Real-time update" refers to the process of instantly reflecting the evaluation of the person being evaluated and always maintaining the latest evaluation status.

[0897] "Feedback" is the process of notifying the person being evaluated of the results of the evaluation in real time.

[0898] As an embodiment of the present invention, a system for evaluating the behavior, performance, and emotions of workers in a factory in real time is constructed. A specific embodiment of the system is described below.

[0899] System Configuration

[0900] The system consists of the following main components:

[0901] 1. Cameras: Used to capture worker movements in real time.

[0902] 2. Microphone: Used to collect the voices of workers.

[0903] 3. Server: The central computer system that collects, analyzes, and evaluates the data.

[0904] 4. Artificial Intelligence (AI): Analyzes collected data and evaluates the subjects.

[0905] 5. Emotion engine: Recognizes emotions in real time from workers' facial expressions, tone of voice, choice of words, etc.

[0906] 6. Feedback system: Notify workers of evaluation results in real time.

[0907] Program Processing

[0908] The server collects data from the camera and microphone in real time and analyzes it. Specifically, it performs the following processes:

[0909] 1. Data collection: A camera is used to capture the worker's movements and a microphone is used to collect the worker's voice.

[0910] 2. Emotion Recognition: Using an emotion engine, we recognize the emotions of workers from the collected tone of voice and facial expressions. The emotion engine uses Google Cloud's emotion analysis API.

[0911] 3. Data analysis: Artificial intelligence will analyze and evaluate the collected behavioral data, performance data, and emotional data.

[0912] 4. Evaluation update: Update worker evaluations in real time based on the analysis results.

[0913] 5. Feedback: Communicate updated evaluation results to workers in real time.

[0914] Hardware and Software Used

[0915] Hardware: Cameras, microphones, servers

[0916] Software: OpenCV (camera image acquisition and display), Google Cloud emotion analysis API (emotion recognition)

[0917] Examples

[0918] For example, if a worker says, "This task is very difficult," the emotion engine will detect "anxiety" from the tone and content of the voice, and the AI ​​will update the worker's evaluation based on that information.

[0919] Examples of prompt statements

[0920] If a worker says, "This task is very difficult," the emotion engine will detect "anxiety" from the tone and content of the voice, and the AI ​​will update the worker's evaluation based on that information.

[0921] In this way, a system can be created that evaluates worker behavior and emotions in real time and provides feedback.

[0922] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0923] Step 1:

[0924] The server uses a camera to capture the worker's movements in real time. The input is the camera image and the output is the captured movement data. Specifically, it uses OpenCV to acquire the image from the camera and record the worker's movements frame by frame.

[0925] Step 2:

[0926] The server collects the voices of workers using a microphone. The input is voice data, and the output is the collected voice data. Specifically, the server captures voice input from the microphone in real time and saves it as an audio file.

[0927] Step 3:

[0928] The server uses an emotion engine to recognize the emotions of workers from the collected tone of voice and facial expressions. The input is voice data and video data, and the output is the recognized emotion data. Specifically, the voice data is analyzed using the Google Cloud emotion analysis API to obtain an emotion score. In addition, facial expressions are analyzed from the video data to recognize emotions.

[0929] Step 4:

[0930] The server uses artificial intelligence to analyze the collected behavioral data, performance data, and emotional data and performs the evaluation. The input is behavioral data, performance data, and emotional data, and the output is the evaluation results. Specifically, the data is analyzed using a generative AI model and the performance of the person being evaluated is scored.

[0931] Step 5:

[0932] The server updates the evaluation of the worker in real time based on the analysis results. The input is the evaluation result, and the output is the updated evaluation data. Specifically, the evaluation result is saved in a database and the profile of the person being evaluated is updated.

[0933] Step 6:

[0934] The server notifies the worker of the updated evaluation results in real time. The input is the updated evaluation data, and the output is a notification message. Specifically, the server sends the evaluation results to the worker's device as a push notification, providing feedback to the worker.

[0935] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the 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.

[0936] 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> ) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to 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.

[0937] Another example of generative AI is Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) are mentioned.

[0938] 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 smart glasses 214.

[0939] [Third embodiment]

[0940] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0941] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0942] 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 wide area network (WAN) and / or a local area network (LAN).

[0943] 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.

[0944] 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 the voice according to instructions from the processor 46.

[0945] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0946] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0947] Fig. 6 shows an example of 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.

[0948] 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.

[0949] 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.

[0950] In the headset type terminal 314, 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.

[0951] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0952] "Example 1"

[0953] As one embodiment of the present invention, an AI system that evaluates people in a corporate organization is provided. This system has a means for collecting data on the behavior and performance of the person being evaluated. For example, data such as the success rate of projects carried out by the person being evaluated and the quality of reports submitted by the person being evaluated is collected. The collected data is analyzed by AI, and the person being evaluated is evaluated. The evaluation results are used to certify the grade of the person being evaluated. Grade certification is performed at the discretion of the department, and affects changes to the employment conditions and wages of the person being evaluated. In addition, the evaluation results are standardized company-wide, and human resource management is also carried out as a going concern.

[0954] "Example 2"

[0955] As another embodiment of the present invention, a form is provided in which an AI system collects data on the behavior, performance, etc. of the person to be evaluated in real time and performs the evaluation in real time. In this form, data on the behavior, performance, etc. of the person to be evaluated is collected immediately after the person to be evaluated performs an action or achieves an achievement, and is analyzed immediately by AI. As a result, the evaluation of the person to be evaluated is updated in real time, and the grade of the person to be evaluated is also certified in real time.

[0956] The process flow of each embodiment will be described below.

[0957] "Example 1"

[0958] Step 1: Collect data on the behavior and performance of the person being evaluated. For example, collect data on the success rate of projects carried out by the person being evaluated and the quality of reports submitted by the person being evaluated.

[0959] Step 2: The collected data is analyzed by AI, which then evaluates the person being evaluated based on the collected data.

[0960] Step 3: The grade of the person being evaluated is determined based on the results of the AI ​​evaluation. Grade determination is done at the discretion of the department and will affect changes to the employment conditions and wages of the person being evaluated.

[0961] Step 4: The evaluation results are standardized across the company and are used in human resource management as a going concern.

[0962] "Example 2"

[0963] Step 1: Collect data on the behavior and performance of the person being evaluated in real time. Data is collected immediately after the person being evaluated performs an action or achieves a result.

[0964] Step 2: The collected data is immediately analyzed by AI.

[0965] Based on this, evaluation of the person being evaluated is carried out in real time.

[0966] Step 3: Based on the results of the AI ​​evaluation, the grade of the person being evaluated is determined in real time. Grade determination is done at the discretion of the department and has an immediate effect on changes to the employment conditions and wages of the person being evaluated.

[0967] Example 1

[0968] Next, a description will be given of Example 1 of the embodiment 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".

[0969] In conventional talent evaluation systems, data collection on the behavior and performance of those being evaluated was insufficient, and the evaluations often lacked objectivity and accuracy. In addition, because grade certification and talent management based on the evaluation results were not performed consistently, there was a problem that talent management throughout the organization was not performed efficiently. Furthermore, the evaluation process was often performed manually, which was time-consuming and labor-intensive.

[0970] 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.

[0971] In this invention, the server includes a means for collecting data on the behavior and performance of the person to be evaluated, a means for preprocessing the collected data, a means including a generative AI model for analyzing the preprocessed data, a means for evaluating the person to be evaluated based on the analysis result by the generative AI model, and a means for certifying the grade of the person to be evaluated based on the evaluation result. This enables objective and highly accurate evaluation based on the behavior and performance of the person to be evaluated, and consistent grade certification and human resource management based on the evaluation result can be efficiently performed.

[0972] "Assesseeee" refers to the individual within the business organization who is the subject of the assessment.

[0973] "Data on behavior, performance, etc." refers to data containing information necessary for evaluation, such as the success rate of projects carried out by the person being evaluated and the quality of reports submitted.

[0974] "Means of collection" refers to the hardware and software used to obtain data on the behavior, performance, etc. of the person being evaluated.

[0975] "Preprocessing means" refers to hardware and software used to fill in missing values ​​in collected data, correct outliers, standardize data formats, and so on.

[0976] A "generative AI model" refers to an artificial intelligence model that analyzes data such as the behavior and performance of the person being evaluated and generates an evaluation score.

[0977] "Means of analysis" refers to the hardware and / or software used to input preprocessed data into a generative AI model and generate an evaluation score.

[0978] "Means of evaluation" refers to hardware and software used to evaluate the subject based on the analysis results of the generative AI model.

[0979] "Means of grade certification" refers to hardware or software used to certify the grade of the person being evaluated based on the evaluation results.

[0980] "Departmental discretion" refers to each department within a company deciding the grade of each person being evaluated at its own discretion.

[0981] "Human resource management" refers to changing the employment conditions, adjusting wages, setting career paths, etc. of those being evaluated based on the evaluation results and grade certification.

[0982] The present invention relates to an AI system for evaluating people in a corporate organization. A specific embodiment of this system will be described below.

[0983] The server has a means of collecting data on the behavior and performance of the assessees. Specifically, it obtains project success rate data from project management software (e.g., JIRA, Trello) and collects quality data on submitted reports from document management systems (e.g., Google Drive, SharePoint).

[0984] Next, the server preprocesses the collected data. It complements missing values ​​in the data and detects and corrects outliers. It also standardizes the data format and prepares it in a form that is easy for the AI ​​model to analyze. For example, if there are missing values, they are complemented with the average value, and if there are outliers, they are corrected with the median value. The data format is standardized and converted into CSV format.

[0985] The preprocessed data is input into a generative AI model (e.g., TensorFlow, PyTorch) on the server. The AI ​​model analyzes the behavioral patterns and performance of the person being evaluated and generates an evaluation score. For example, if the success rate of the projects in which person being evaluated A was in charge was 90% and the quality of the reports he submitted was highly evaluated, the AI ​​model will generate an evaluation score based on this data.

[0986] Based on the generated evaluation score, the server generates an overall evaluation of the person being evaluated. This evaluation result is used to certify the grade of the person being evaluated. Grade certification is performed at the discretion of the department and affects changes to the employment conditions and wages of the person being evaluated. In addition, the evaluation result is standardized across the company and is also used for human resource management as a going concern.

[0987] As a concrete example, consider a case where the success rate of projects carried out by assessee A was 90% and the quality of the submitted reports was highly evaluated. The server collects success rate data from the project management software and report quality data from the document management system. These data are input into the AI ​​model for evaluation.

[0988] Example of a prompt to be input to a generative AI model:

[0989] The project success rate of assessee A is 90%, and the quality of the reports he submitted is highly rated. Based on this data, please give an overall evaluation of assessee A.

[0990] Using this prompt, the AI ​​model generates an overall evaluation of the person being evaluated A. The evaluation results are used for grading at the department's discretion and for company-wide standardization.

[0991] In this way, the server evaluates people within the corporate organization and provides grades and feedback based on the evaluation results.

[0992] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0993] Step 1: Data collection

[0994] The server collects data on the behavior and performance of the assessees. Specifically, it obtains project success rate data from project management software (e.g., JIRA, Trello) and collects quality data on submitted reports from document management systems (e.g., Google Drive, SharePoint). The input is the assessee's ID and project ID, and the output is project success rate data and report quality data.

[0995] Step 2: Data Preprocessing

[0996] The server preprocesses the collected data. Specifically, it complements missing values ​​in the data and detects and corrects outliers. It also standardizes the data format and prepares it in a form that is easy for the AI ​​model to analyze. The input is the collected raw data, and the output is preprocessed, clean data. For example, if there are missing values, they are complemented with the average value, and if there are outliers, they are corrected with the median. The data format is standardized and converted to CSV format.

[0997] Step 3: Data analysis

[0998] The server inputs the preprocessed data into a generative AI model. The AI ​​model (e.g., TensorFlow, PyTorch) analyzes the behavioral patterns and performance of the person being evaluated and generates an evaluation score. The input is the preprocessed data, and the output is the evaluation score. For example, if the success rate of the projects in which person being evaluated A was in charge was 90% and the quality of the reports he submitted was highly evaluated, the AI ​​model will generate an evaluation score based on this data.

[0999] Step 4: Generate evaluation results

[1000] The server generates an overall evaluation of the person being evaluated based on the generated evaluation score. The input is the evaluation score obtained from the AI ​​model, and the output is the overall evaluation of the person being evaluated. For example, based on an evaluation score of 85 points, the overall evaluation of person A is set to "excellent."

[1001] Step 5: Grading and feedback

[1002] The server certifies the grade of the person being evaluated based on the generated evaluation results. The input is the overall evaluation, and the output is the grade certification result of the person being evaluated. Grade certification is done at the discretion of the department and affects changes to the employment conditions and wages of the person being evaluated. The evaluation results are also standardized company-wide and are used in human resource management as a going concern. For example, the grade of person A being evaluated is certified as "A" and his / her wage is increased by 10%.

[1003] (Application example 1)

[1004] Next, a description will be given of Application Example 1 of Form 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".

[1005] Traditionally, the performance evaluation of robots working in factories was mainly carried out by human managers, which led to problems with the lack of objectivity and efficiency of the evaluation. In addition, robot maintenance schedules and upgrade plans often relied on experience and intuition and were not optimized. This reduced the robot's operating rate and lifespan, and had a negative impact on the productivity of the entire factory.

[1006] 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.

[1007] In this invention, the server includes a means for collecting data such as the work efficiency, error rate, and maintenance history of the machine to be evaluated, an AI for evaluating the machine to be evaluated based on the collected data, a means for optimizing a maintenance schedule for the machine to be evaluated based on the evaluation results by the AI, and a means for proposing an upgrade plan for the machine to be evaluated based on the evaluation results. This makes it possible to objectively and efficiently evaluate the performance of a robot and to optimize the maintenance schedule and upgrade plan.

[1008] "Machinery to be evaluated" refers to robots and automated machinery that perform work in factories.

[1009] "Work efficiency" is an index that indicates how much work the evaluated machine can complete within a certain amount of time.

[1010] The "error rate" is an index showing the frequency of errors and breakdowns that occur when the machine being evaluated is in operation.

[1011] "Maintenance history" refers to the records of maintenance and repairs that the machine being evaluated has received in the past.

[1012] "Means of collecting data" refers to sensors and communication devices for obtaining data such as work efficiency, error rate, and maintenance history from the machine being evaluated.

[1013] "Evaluation AI" refers to an artificial intelligence system that analyzes collected data and evaluates the performance of the machine being evaluated.

[1014] "Means for optimizing maintenance schedules" refers to algorithms or programs for optimizing the timing and content of maintenance for the evaluated machinery based on the results of the AI ​​evaluation.

[1015] "Means for proposing an upgrade plan" refers to algorithms or programs for proposing upgrades to improve the performance or add functions to the machine being evaluated based on the results of the AI ​​evaluation.

[1016] As an embodiment of the present invention, a system for evaluating the performance of robots working in a factory is constructed. The system includes an AI that collects data such as the work efficiency, error rate, and maintenance history of the machine to be evaluated, and evaluates the machine based on the collected data. Furthermore, the system optimizes the maintenance schedule of the machine to be evaluated based on the evaluation results by the AI, and proposes an upgrade plan for the machine to be evaluated based on the evaluation results.

[1017] Hardware and Software Used

[1018] Hardware

[1019] Server: A high-performance server for data collection and analysis.

[1020] Robot: A robot in a factory that is the subject of data collection

[1021] Sensors: Sensors to collect data such as the robot's work efficiency, error rate, and maintenance history

[1022] software

[1023] Python: Used for data analysis and model training

[1024] Pandas: Used to load and preprocess data

[1025] Scikit-learn: Used to train and evaluate machine learning models.

[1026] Data processing and calculation

[1027] The server first collects data from the robot in real time. The collected data is preprocessed using Pandas and divided into features and targets such as work efficiency, error rate, and maintenance history. Then, a model is trained using Scikit-learn's RandomForestRegressor to predict the performance of the machine being evaluated. The prediction results are used to optimize the maintenance schedule of the machine being evaluated and propose an upgrade plan.

[1028] Examples

[1029] For example, if a robot's work efficiency is 90%, its error rate is 5%, and its maintenance history is three times, the server will collect these data and analyze them with the AI ​​model. Based on the analysis results, it will predict the robot's performance score and suggest the optimal maintenance schedule and necessary upgrades.

[1030] Examples of prompt statements

[1031] Enter your robot's work efficiency, error rate, and maintenance history to predict its performance score.

[1032] In this way, it is possible to build a system that evaluates the performance of robots working in factories and optimizes maintenance schedules and upgrade plans.

[1033] The flow of the specific process in the application example 1 will be described with reference to FIG.

[1034] Step 1:

[1035] The server collects data such as work efficiency, error rate, and maintenance history from the robots in the factory in real time. This data is acquired using sensors and communication devices and stored in a database.

[1036] Input: Robot work efficiency, error rate, maintenance history

[1037] Output: Robot performance data stored in a database

[1038] Step 2:

[1039] The server preprocesses the collected data using Pandas. Specifically, it complements missing values ​​and removes outliers to make the data clean.

[1040] Input: Robot performance data stored in a database

[1041] Output: Preprocessed and clean data

[1042] Step 3:

[1043] The server divides the preprocessed data into features and targets. Work efficiency, error rate, and maintenance history are used as features, and performance score is set as a target.

[1044] Input: Preprocessed and clean data

[1045] Output: Data split into features and targets

[1046] Step 4:

[1047] The server trains a machine learning model using Scikit-learn's RandomForestRegressor. It uses the features and targets as training data to build the model.

[1048] Input: Data split into features and targets

[1049] Output: A trained machine learning model

[1050] Step 5:

[1051] The server uses the trained model to predict the robot's performance score based on new data collected in real time.

[1052] Input: New robot performance data collected in real time

[1053] Output: Predicted performance score

[1054] Step 6:

[1055] The server optimizes the robot's maintenance schedule based on the predicted performance score, determining the timing and content of maintenance and updating the schedule.

[1056] Input: Predicted performance score

[1057] Output: Optimized maintenance schedule

[1058] Step 7:

[1059] The server then proposes an upgrade plan for the robot based on the predicted performance score, determining what upgrades are required and when, and creating a proposal.

[1060] Input: Predicted performance score

[1061] Output: Proposed upgrade plan

[1062] In this way, the server can evaluate the robot's performance and optimize maintenance schedules and upgrade plans.

[1063] Example 2

[1064] Next, a second embodiment of the second form will be described. 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".

[1065] In the conventional evaluation system, data collection and analysis of the behavior and performance of the person being evaluated was not done in real time, and updates to evaluation results and grade certification were often delayed. In addition, there was also the problem that the evaluation criteria were uniform and it was difficult to reflect the discretion of each department. Furthermore, there was an issue that human resource management based on the evaluation results was not carried out efficiently.

[1066] 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.

[1067] In this invention, the server includes a means for collecting data such as the behavior and performance of the person to be evaluated in real time, a means for storing the collected data in a database, a means for using a generative AI model to analyze the stored data, a means for updating the evaluation score of the person to be evaluated in real time based on the analysis result, a means for certifying the grade of the person to be evaluated based on the evaluation score, and a means for notifying the terminal of the person to be evaluated of the result of the grade certification. This makes it possible to collect and analyze the data of the behavior and performance of the person to be evaluated in real time, quickly update the evaluation result, and certify the grade reflecting the discretion of each department. In addition, efficient human resource management based on the evaluation result can be realized.

[1068] "Appraisee" refers to the individual or group whose behavior or performance is evaluated by the appraisal system.

[1069] "Data on behavior, achievements, etc." refers to information on the specific behavior and achievements of the person being evaluated, including the progress and results of work, behavioral history, etc.

[1070] "Means of collecting data in real time" refers to methods and technologies for instantly obtaining data on the behavior and performance of the person being evaluated and incorporating it into the system without delay.

[1071] "Means of storing in a database" refers to the methods and technologies used to organize collected data and keep it accessible later.

[1072] A "generative AI model" refers to an algorithm or model that uses machine learning and artificial intelligence techniques to analyze data and evaluate the behavior and performance of individuals being evaluated.

[1073] "Evaluation score" refers to a numerical indicator of the performance of the person being evaluated based on the results of analysis by the generative AI model.

[1074] "Grade certification" refers to the process of determining the rank or grade of an assessee based on their assessment score.

[1075] "Means of notifying the device" refers to the methods and technologies for notifying the subject of the evaluation of the results of the evaluation and the grade certification, including email and push notifications.

[1076] "Departmental discretion" refers to the authority of each department to evaluate and grade based on its own criteria and policies.

[1077] "Human resource management" refers to the process of allocating, developing, and evaluating human resources within an organization based on evaluation results and grade certification.

[1078] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[1079] The present invention is a system for collecting data on the behavior and performance of an evaluation target in real time, analyzing the data, updating the evaluation score, and certifying a grade. A specific embodiment of the system will be described below.

[1080] 1. Program Generation

[1081] The server collects data on the behavior and performance of the person being evaluated in real time and generates a program for evaluating the person. This program has the function of instantly analyzing the behavior and performance of the person being evaluated and updating the evaluation in real time.

[1082] 2. Program Processing

[1083] The server works with various sensors and databases to collect data on the behavior and performance of the person being evaluated. Specifically, data is collected from the devices (e.g., smartphones, PCs) and business systems (e.g., customer management systems, business management systems) used by the person being evaluated. This data is stored in the database on the server.

[1084] The server then uses a generative AI model to analyze the collected data. Specifically, it uses machine learning frameworks such as TensorFlow and PyTorch to analyze the behavior and performance of the person being evaluated. The analysis results are updated in real time as the person being evaluated's evaluation score.

[1085] Furthermore, the server certifies the grade of the person to be evaluated based on the evaluation score. In this process, the grade of the person to be evaluated is determined based on the evaluation criteria set in advance. The result of the grade certification is notified to the terminal of the person to be evaluated.

[1086] 3. Specific Examples

[1087] As a concrete example, consider the performance evaluation of a sales representative. When a sales representative wins a new contract, the information is automatically sent from the customer management system to a server. The server uses a generative AI model to analyze the value of the new contract and updates the sales representative's evaluation score. The updated evaluation score is notified to the sales representative's smartphone in real time.

[1088] Example prompt:

[1089] "When a sales rep wins a new deal, collect that information from your customer relationship management system and use a generative AI model to update the reputation score."

[1090] In this way, a system is realized in which the server, terminals, and users work together to evaluate the behavior and performance of the person being evaluated in real time and certify a grade.

[1091] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1092] Step 1: Data collection

[1093] The server collects data on the behavior and performance of the person being evaluated in real time. Specifically, it obtains data from the devices (e.g., smartphones, PCs) and business systems (e.g., customer management systems, business management systems) used by the person being evaluated. The input is data on the behavior and performance of the person being evaluated, and the output is the raw data sent to the server. For example, when a sales representative secures a new contract, that information is sent from the customer management system to the server.

[1094] Step 2: Save Data

[1095] The server stores the collected data in a database. Specifically, it uses a relational database such as MySQL or PostgreSQL. The input is the collected raw data, and the output is the structured data stored in the database. For example, the details of a new contract are stored in the database.

[1096] Step 3: Data analysis

[1097] The server uses a generative AI model to analyze the stored data. Specifically, it uses machine learning frameworks such as TensorFlow and PyTorch to analyze the behavior and performance of the person being evaluated. The input is structured data stored in a database, and the output is an evaluation score as the analysis result. For example, a predictive model based on past data is used to evaluate the value of a new contract.

[1098] Step 4: Update your reputation scores

[1099] The server updates the evaluation score of the person being evaluated based on the results of the data analysis. The input is the evaluation score as the analysis result, and the output is the updated evaluation score. For example, if the value of a new contract is high, the evaluation score of a sales representative increases.

[1100] Step 5: Grade Certification

[1101] The server certifies the grade of the person to be evaluated based on the updated evaluation score. The input is the updated evaluation score, and the output is the grade of the person to be evaluated. For example, if the evaluation score exceeds a certain threshold, the grade of the salesperson is promoted from "silver" to "gold."

[1102] Step 6: Notification

[1103] The server notifies the terminal of the person being evaluated of the result of the grade certification. The input is the grade of the person being evaluated, and the output is a notification sent to the terminal of the person being evaluated. For example, a notification saying "Your grade has been promoted to gold" is sent to the smartphone of a sales representative.

[1104] (Application example 2)

[1105] Next, a description will be given of Application Example 2 of Form 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".

[1106] With conventional factory robot evaluation systems, it was difficult to evaluate the robot's operation and production efficiency in real time and provide immediate feedback. As a result, it was not possible to properly instruct the robot on the timing of improvements to its operation or maintenance, which led to problems such as reduced production efficiency and an increased risk of breakdowns.

[1107] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1108] In this invention, the server includes a means for collecting data such as the behavior and performance of the evaluation target in real time, an AI for evaluating the evaluation target in real time based on the collected data, a means for certifying the grade of the evaluation target in real time based on the evaluation result by the AI, and a means for feeding back the evaluation result in real time and instructing the timing of behavior improvement and maintenance. This makes it possible to evaluate the behavior and production efficiency of a factory robot in real time and provide immediate feedback.

[1109] The "subject of evaluation" refers to factory robots, their operations, and production efficiency.

[1110] "Operational Data" refers to information about the operation of a factory robot, including performance indicators such as efficiency and error rates.

[1111] "Performance data" refers to information regarding the production volume and quality achieved by factory robots.

[1112] "Means of collecting data in real time" refers to methods of using sensors or data collection devices to instantly obtain the behavior and performance data of the subject being evaluated.

[1113] "Real-time AI" refers to an artificial intelligence system that instantly analyzes and evaluates collected data.

[1114] "Grade certification" refers to ranking the quality and efficiency of an item based on its performance.

[1115] "Feedback" refers to providing the subject of evaluation with immediate instructions for operational improvement or maintenance based on the evaluation results.

[1116] "Behavioral improvement" refers to adjustments or modifications made to improve the performance of the subject of evaluation.

[1117] "Timing of maintenance" refers to the time when maintenance work is performed to keep the object of evaluation functioning properly.

[1118] The system for carrying out the present invention evaluates the operation and production efficiency of factory robots in real time and provides immediate feedback. A specific embodiment of the system is described below.

[1119] 1. System Configuration

[1120] The system consists of the following main components:

[1121] Hardware: Factory robots, sensors (to measure efficiency and error rates)

[1122] Software: Python, AI analysis libraries (e.g. TensorFlow, Scikit-learn)

[1123] 2. Data Collection

[1124] The server collects the robot's operational data (efficiency and error rate) in real time using sensors attached to the factory robots, making it possible to immediately grasp the robot's performance.

[1125] 3. Data Analysis

[1126] The collected data is instantly analyzed using AI analysis libraries (e.g. TensorFlow, Scikit-learn) on the server. The AI ​​evaluates the robots based on their efficiency and error rate and generates an evaluation result.

[1127] 4. Grade Certification

[1128] The server will assign a grade to the robot in real time based on the AI ​​evaluation results. For example, if the efficiency is 90% or more and the error rate is less than 1%, the evaluation grade will be "A."

[1129] 5. Feedback and Improvements

[1130] The evaluation results are fed back to the robot in real time. The server then instructs the robot on operational improvements and maintenance timing based on the evaluation results, optimizing the robot's performance and improving production efficiency.

[1131] Examples

[1132] Example 1: If a robot assembles parts with an efficiency of 90% or more and an error rate of less than 1%, the evaluation grade will be "A" and the robot will continue to operate.

[1133] Example 2: If efficiency is below 80%, the evaluation grade will be "C" and a notification will be sent indicating that maintenance is required.

[1134] Examples of prompt statements

[1135] Collect the robot's operation data and evaluate its efficiency and error rate in real time. If the efficiency is 90% or more and the error rate is less than 1%, the evaluation grade should be "A". If the efficiency is 80% or less, the evaluation grade should be "C". Provide feedback on the evaluation results in real time and instruct maintenance as necessary.

[1136] In this way, a system can be realized that evaluates the operation of factory robots and production efficiency in real time and provides immediate feedback.

[1137] The flow of the specific process in the application example 2 will be described with reference to FIG.

[1138] Step 1:

[1139] The server collects operational data (efficiency and error rate) in real time from sensors attached to factory robots. The input is the raw data from the sensors, and the output is the collected operational data. Specifically, the sensors monitor the robot's operation and measure its efficiency and error rate.

[1140] Step 2:

[1141] The server analyzes the collected motion data using AI analysis libraries (e.g. TensorFlow, Scikit-learn). The input is the collected motion data, and the output is the analysis result. Specifically, the AI ​​evaluates the robot's performance based on efficiency and error rate, and generates an evaluation result.

[1142] Step 3:

[1143] The server certifies the robot's grade in real time based on the AI ​​evaluation results. The input is the AI ​​evaluation result, and the output is the grade certification result. Specifically, if the efficiency is 90% or more and the error rate is less than 1%, the evaluation grade will be "A".

[1144] Step 4:

[1145] The server feeds back the evaluation results to the robot in real time. The input is the grade certification result, and the output is feedback information. Specifically, it provides the robot with instructions for improving its behavior and maintenance based on the evaluation results.

[1146] Step 5:

[1147] The server optimizes the robot's operation based on the feedback information. The input is the feedback information, and the output is the optimized operation parameters. Specifically, the robot adjusts its operation according to the instructions, improving production efficiency.

[1148] Step 6:

[1149] The server monitors the robot's operational improvements and maintenance timing, and provides additional instructions as necessary. The input is the optimized operational parameters, and the output is additional instructions. Specifically, the server continuously monitors the robot's performance and provides maintenance instructions as necessary.

[1150] In addition, 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.

[1151] "Example 1"

[1152] As one embodiment of the present invention, there is a system that combines an emotion engine. This system includes a means for collecting data such as the behavior and performance of the person to be evaluated, an AI that evaluates the person to be evaluated based on the collected data, and a means for certifying the grade of the person to be evaluated based on the evaluation result by the AI. Furthermore, it includes an emotion engine that recognizes the emotion of the person to be evaluated. Specifically, the emotion engine recognizes the emotion of the person to be evaluated from the facial expression, tone of voice, choice of words, etc. of the person to be evaluated, and the AI ​​analyzes the emotion data. For example, if the person to be evaluated feels nervous during a presentation, the AI ​​analyzes that information and reflects it in the evaluation of the person to be evaluated.

[1153] "Example 2"

[1154] Another embodiment of the present invention is a system that combines an emotion engine with a real-time data collection and analysis function. This system includes an AI that collects data on the behavior and performance of the person being evaluated in real time and evaluates the person being evaluated in real time based on the collected data, and a means for certifying the grade of the person being evaluated in real time based on the evaluation result by the AI. Furthermore, the system includes an emotion engine that recognizes the emotion of the person being evaluated in real time. Specifically, the emotion engine recognizes the emotion of the person being evaluated in real time from the facial expression, tone of voice, choice of words, etc. of the person being evaluated, and the AI ​​instantly analyzes the emotion data. For example, if the person being evaluated expresses anger during a meeting, the AI ​​instantly analyzes the information and reflects it in the evaluation of the person being evaluated.

[1155] The process flow of each embodiment will be described below.

[1156] "Example 1"

[1157] Step 1: Collect data on the behavior and performance of the person being evaluated.

[1158] Step 2: Use AI to evaluate the subjects based on the collected data.

[1159] Step 3: The person being evaluated is graded based on the AI ​​evaluation results.

[1160] Step 4: Use an emotion engine to recognize the emotions of the person being evaluated. The emotion engine recognizes the emotions of the person being evaluated from their facial expressions, tone of voice, choice of words, etc.

[1161] Step 5: AI analyzes the emotional data recognized by the emotion engine.

[1162] Step 6: The subject is evaluated based on the emotional data analyzed by the AI.

[1163] "Example 2"

[1164] Step 1: Collect data on the behavior and performance of the person being evaluated in real time.

[1165] Step 2: Use AI to evaluate subjects in real time based on the collected data.

[1166] Step 3: Based on the AI ​​evaluation results, the person being evaluated is graded in real time.

[1167] Step 4: An emotion engine is used to recognize the emotions of the person being evaluated in real time. The emotion engine recognizes emotions in real time from the person being evaluated's facial expressions, tone of voice, choice of words, etc.

[1168] Step 5: The AI ​​immediately analyzes the emotional data recognized by the emotion engine.

[1169] Step 6: The subject is evaluated based on the emotional data analyzed by the AI.

[1170] Example 1

[1171] Next, a description will be given of Example 1 of the embodiment 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".

[1172] In conventional human evaluation systems, evaluations were based on the behavior and performance of the person being evaluated, but the evaluation did not take into account the emotional state of the person being evaluated. As a result, the evaluations were sometimes lacking in fairness and accuracy. In addition, it was difficult to grade the evaluation results at the discretion of the department, making it difficult to standardize the results across the company. This led to a lack of consistency in affecting changes to the employment conditions and wages of the person being evaluated.

[1173] 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.

[1174] In this invention, the server includes a means for collecting data such as the behavior and performance of the person to be evaluated, an artificial intelligence for evaluating the person to be evaluated based on the collected data, a means for certifying the grade of the person to be evaluated based on the evaluation result by the artificial intelligence, a means including an emotion engine for recognizing the emotions of the person to be evaluated, and a means for analyzing the emotion data collected by the emotion engine. This enables evaluation that takes into account the behavior and performance of the person to be evaluated as well as their emotional state, improving the fairness and accuracy of the evaluation. In addition, grade certification can be done at the discretion of the department, and consistent human resource management can be achieved through company-wide standardization.

[1175] "Appraisee" refers to the individual whose behavior, performance, or emotional state is evaluated by the appraisal system.

[1176] "Data on behavior, performance, etc." refers to data containing information necessary for evaluation, such as the success rate of projects carried out by the person being evaluated and the quality of reports submitted.

[1177] "Artificial intelligence" refers to machine learning algorithms and data analysis techniques used to analyze collected data and evaluate subjects.

[1178] "Grade certification" refers to the process of determining a grade for an individual based on their job or position, based on the results of an evaluation using artificial intelligence.

[1179] An "emotion engine" refers to technology that recognizes emotions from the facial expressions, tone of voice, choice of words, etc. of the person being evaluated, and collects that data.

[1180] "Emotional Data" refers to information regarding the emotional state of a Subject collected by the Emotion Engine.

[1181] "Departmental discretion" refers to the authority of each department to determine the grade of individuals being evaluated at its own discretion.

[1182] "Company-wide standardization" refers to the process of managing evaluation results based on uniform standards across the entire company, thereby ensuring consistent human resource management.

[1183] This invention relates to an AI system for evaluating people in a business organization. This system includes artificial intelligence (AI) that collects data on the behavior and performance of the person being evaluated and evaluates them based on the collected data. In addition, by combining it with an emotion engine that recognizes the emotions of the person being evaluated, a more accurate and fair evaluation is achieved.

[1184] Data collection

[1185] Users use the company's in-house project management software (e.g., JIRA) and document management systems (e.g., Google Drive) to collect data on the behavior and performance of appraisee(s), such as the success rate of projects undertaken by appraisee(s) and the quality of reports submitted.

[1186] Data transmission

[1187] The terminal transmits the collected data to the server. Specifically, the terminal transmits the project success rate data and the report quality data to the server using an HTTP request.

[1188] 4. Data Analysis

[1189] The server then sends the received data to the AI ​​system for analysis. The server uses machine learning algorithms such as TensorFlow to analyze the data and evaluate the behavior and performance of the person being evaluated.

[1190] emotion recognition

[1191] The device uses a camera and microphone to collect facial expressions and tone of voice of the person being evaluated while presenting, and can then use emotion analysis software such as the Microsoft Azure Emotion API to recognize emotions from this data.

[1192] Emotion Data Analysis

[1193] The device transmits the recognized emotion data to a server, which then transmits the emotion data to an AI system to analyze the subject's emotional state.

[1194] Generating evaluation results

[1195] The server receives the analysis results from the AI ​​system and generates an evaluation of the person being evaluated. Specifically, it comprehensively evaluates the person being evaluated based on their project success rate, report quality, and emotional state, and generates an evaluation score.

[1196] Grade Certification

[1197] The server certifies the grade of the person being evaluated based on the generated evaluation score. The grade certification is performed at the discretion of the department and affects the employment conditions and wages of the person being evaluated.

[1198] Company-wide standardization

[1199] The server standardizes the evaluation results company-wide and manages human resources. Specifically, the server uses a human resources management system such as SAP SuccessFactors to standardize the evaluation results to company-wide standards and manages human resources as a going concern.

[1200] Examples

[1201] For example, if assessee A succeeds in project X and submits report Y, the user uses JIRA to collect the success rate data of project X and Google Drive to collect the quality data of report Y. The terminal sends these data to the server via HTTP request. The server uses TensorFlow to analyze the data and evaluates the behavior and performance of assessee A. In addition, the terminal uses Microsoft Azure Emotion API to collect emotion data during the presentation of assessee A and sends it to the server. The server sends the emotion data to the AI ​​system and generates an evaluation score for assessee A based on the analysis results. The server performs grade certification based on the evaluation score and standardizes it company-wide using SAP SuccessFactors.

[1202] Examples of prompt statements

[1203] "Collect the success rate data of project X and the quality data of report Y of assessee A, and use the emotion engine to analyze the emotion data during the presentation. Generate an evaluation of assessee A based on the analysis results, and standardize it across the company."

[1204] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1205] Step 1:

[1206] The user collects data on the behavior and performance of the person being evaluated. Specifically, the user uses the company's project management software (e.g., project management tool) to collect data on the success rate of projects carried out by the person being evaluated, and uses a document management system (e.g., document management tool) to collect data on the quality of reports submitted by the person being evaluated. These data become input data for evaluating the behavior and performance of the person being evaluated.

[1207] Step 2:

[1208] The terminal transmits the collected data to the server. Specifically, the terminal transmits the project success rate data and the report quality data to the server using an HTTP request. The input data are the project success rate data and the report quality data, and the output is the data transmitted to the server.

[1209] Step 3:

[1210] The server sends the received data to the AI ​​system for analysis. The server analyzes the data using a machine learning algorithm (e.g., machine learning framework) and evaluates the behavior and performance of the person being evaluated. The input data is project success rate data and report quality data, and the output is the evaluation result based on the behavior and performance of the person being evaluated.

[1211] Step 4:

[1212] The device uses a camera and microphone to collect facial expressions and tone of voice of the person being evaluated during the presentation. The device uses emotion analysis software (e.g., emotion analysis tool) to recognize emotions from these data. The input data is facial expression data and tone of voice data, and the output is the recognized emotion data.

[1213] Step 5:

[1214] The terminal transmits the recognized emotion data to the server. Specifically, the terminal transmits the emotion data to the server using an HTTP request. The input data is the recognized emotion data, and the output is the emotion data transmitted to the server.

[1215] Step 6:

[1216] The server sends the emotion data to the AI ​​system for analysis. The server analyzes the emotion data and reflects the emotion state of the person being evaluated in the evaluation. The input data is emotion data, and the output is the evaluation result based on the emotion state.

[1217] Step 7:

[1218] The server receives the analysis results from the AI ​​system and generates an evaluation of the person being evaluated. Specifically, it comprehensively evaluates the project success rate, report quality, and emotional state of the person being evaluated to generate an evaluation score. The input data are the evaluation results based on behavior and performance and the evaluation results based on emotional state, and the output is the evaluation score.

[1219] Step 8:

[1220] The server certifies the grade of the person being evaluated based on the generated evaluation score. Grade certification is performed at the discretion of the department and affects the employment conditions and wages of the person being evaluated. The input data is the evaluation score, and the output is the grade certification result.

[1221] Step 9:

[1222] The server standardizes the evaluation results company-wide and manages human resources. Specifically, a human resources management system (e.g., human resources management tool) is used to unify the evaluation results to company-wide standards and manage human resources as a going concern. The input data is the grade certification results, and the output is the standardized evaluation results.

[1223] (Application example 1)

[1224] Next, a description will be given of Application Example 1 of Form 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".

[1225] In conventional evaluation systems, evaluations were based only on the behavior and performance of the person being evaluated, which resulted in one-sided evaluations and failure to consider the emotions and psychological state of the person being evaluated. In addition, it was difficult to appropriately reflect the evaluation results in skill level certification, transfers, and wage adjustments. This could lead to a decrease in the fairness and accuracy of evaluations, which could have a negative impact on the efficiency and motivation of the entire organization.

[1226] 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.

[1227] In this invention, the server includes a means for collecting data such as the behavior and performance of the person to be evaluated, an AI for evaluating the person to be evaluated based on the collected data, a means for certifying the grade of the person to be evaluated based on the evaluation results by the AI, an emotion engine for recognizing the emotions of the person to be evaluated, a means for analyzing the emotion data collected by the emotion engine, and a means for using the emotion data for certifying the skill level of the person to be evaluated, transferring the person to a new position, and adjusting the wages of the person to be evaluated. This enables a comprehensive evaluation that takes into account not only the behavior and performance of the person to be evaluated, but also their emotions and psychological state. Furthermore, the evaluation results can be appropriately reflected in the certification of skill level, transfer, and wage adjustment, which is expected to improve the efficiency and motivation of the entire organization.

[1228] An "evaluation target" is a person whose behavior, performance, emotions, etc. are evaluated by the evaluation system.

[1229] "Behavioral data" refers to information about the behavior of the person being evaluated, including, for example, the progress of work and the accuracy of movements.

[1230] "Performance Data" refers to information about an individual's work accomplishments or performance, including, for example, project success rates and quality of deliverables.

[1231] The "emotion engine" is a technology for recognizing the emotions of the person being evaluated, analyzing emotions from facial expressions, tone of voice, choice of words, etc.

[1232] "Emotional data" refers to information about the emotions of the person being evaluated that is collected by the emotion engine, and includes, for example, emotional states such as tension, joy, sadness, etc.

[1233] "AI" refers to artificial intelligence, a technology that analyzes collected data and evaluates individuals being evaluated.

[1234] "Grade certification" involves evaluating the skill level and abilities of the person being evaluated and ranking them based on certain criteria.

[1235] "Skill level certification" means evaluating the level of skills and abilities of the person being assessed and granting an appropriate rank or qualification.

[1236] "Reassignment" refers to changing the duties or role of the person being evaluated based on the results of the evaluation.

[1237] A "wage adjustment" is a change in the salary or remuneration of an individual being evaluated based on the results of the evaluation.

[1238] The system for carrying out the present invention collects data on the behavior, performance, and emotions of the person being evaluated, and performs a comprehensive evaluation using AI. A specific embodiment of this system will be described below.

[1239] System Configuration

[1240] 1. Data collection methods:

[1241] The server collects the behavioral data, performance data, and emotional data of the person being evaluated. The behavioral data and performance data are saved in a format such as a CSV file. Emotional data is collected in real time using a camera.

[1242] 2. Data Analysis Methods:

[1243] The server pre-processes the collected data and performs analysis using an AI model. Specifically, it integrates behavioral data and performance data, and adds emotion data collected by an emotion engine. This allows for a comprehensive evaluation of the person being evaluated.

[1244] 3. Evaluation method:

[1245] The server uses an AI model (e.g., RandomForestClassifier) ​​to evaluate the candidates. The evaluation results are used to certify skill levels, transfer employees, and adjust wages.

[1246] Hardware and Software Used

[1247] Hardware:

[1248] Camera: Used to collect emotion data from the subjects.

[1249] Server: Used to collect, analyze, and evaluate data.

[1250] software:

[1251] OpenCV: Used to process camera images.

[1252] DeepFace: Used to analyze emotion data.

[1253] pandas: Used for data preprocessing.

[1254] scikit-learn: Used to train and evaluate AI models.

[1255] Examples

[1256] For example, consider a system that evaluates workers in a factory. The system collects data on the workers' behavior (progress of work and accuracy of movements), performance data (success rate of projects and quality of submitted work), and emotion data (emotional states such as tension, joy, sadness, etc.), and uses an AI model to perform a comprehensive evaluation. The evaluation results are used to certify the worker's skill level, transfer them, and adjust their wages.

[1257] Examples of prompt statements

[1258] Below are examples of prompts to be input to a generative AI model.

[1259] Please design a system to collect data on the behavior, performance, and emotions of workers in the factory and use an AI model to evaluate them. The evaluation results will be used to certify the skill level of workers, transfer them, and adjust their wages. Please also explain in detail how to collect the specific data, select the AI ​​model, and how to output the evaluation results.

[1260] Using this prompt, the generative AI model can provide more detailed designs and improvement suggestions.

[1261] The flow of the specific process in the application example 1 will be described with reference to FIG.

[1262] Step 1:

[1263] The server collects the behavioral data of the subjects. Specifically, it reads data such as task progress and accuracy of actions from a CSV file. The input is a CSV file, and the output is a data frame of behavioral data. Converting the data into a data frame makes subsequent data analysis easier.

[1264] Step 2:

[1265] The server collects the performance data of the assessees. Specifically, it reads data such as project success rate and quality of submissions from a CSV file. The input is a CSV file, and the output is a data frame of performance data, which makes it easier to integrate with behavioral data.

[1266] Step 3:

[1267] The server collects the emotion data of the person being evaluated. Specifically, it captures video in real time using a camera and analyzes the emotions using DeepFace. The input is the camera video, and the output is a data frame of emotion data. The emotion data includes the person being evaluated's facial expressions, tone of voice, choice of words, etc.

[1268] Step 4:

[1269] The server integrates the collected behavioral data, performance data, and emotion data. Specifically, it combines each data frame to create a single comprehensive dataset. The input is a data frame of behavioral data, performance data, and emotion data, and the output is an integrated dataset. This makes it possible to comprehensively evaluate the person being evaluated.

[1270] Step 5:

[1271] The server preprocesses the integrated dataset. Specifically, it completes missing values ​​and normalizes the data. The input is the integrated dataset, and the output is the preprocessed dataset. Preprocessing improves the accuracy of the AI ​​model.

[1272] Step 6:

[1273] The server trains an AI model using the preprocessed dataset. Specifically, it trains the model using RandomForestClassifier. The input is the preprocessed dataset, and the output is the trained AI model. Using the trained model, it becomes possible to evaluate the subject.

[1274] Step 7:

[1275] The server uses a trained AI model to evaluate the person being evaluated. Specifically, it evaluates the person being evaluated for skill level certification, transfer, and wage adjustment. The input is a preprocessed dataset and a trained AI model, and the output is the evaluation result. The evaluation result contributes to improving the efficiency and motivation of the entire organization.

[1276] Step 8:

[1277] The server stores the evaluation results and notifies the administrator or the person being evaluated as necessary. Specifically, the evaluation results are stored in a database and notified to relevant parties through a notification system. The input is the evaluation results, and the output is the stored evaluation results and notifications. This ensures the transparency and reliability of the evaluation results.

[1278] Example 2

[1279] Next, a second embodiment of the second form will be described. 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".

[1280] In conventional evaluation systems, it takes time to collect the behavior and performance data of the person being evaluated and then to evaluate them, making it difficult to perform evaluations in real time. In addition, there was a problem of reduced accuracy of evaluations because evaluations did not take into account emotional data. Furthermore, there was an issue that rapid human resource management was difficult due to delays in updating evaluation results and grading.

[1281] 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.

[1282] In this invention, the server includes a means for collecting behavior, performance, and emotion data of the person to be evaluated in real time, a means for transmitting the collected data to the server, a means for analyzing the data received by the server with an AI analysis engine, a means for updating the evaluation of the person to be evaluated in real time based on the analysis result, and a means for certifying the grade of the person to be evaluated in real time based on the evaluation result. This makes it possible to evaluate the behavior, performance, and emotion of the person to be evaluated in real time and provide quick and accurate feedback.

[1283] "Appraisee" refers to the individual whose behavior, performance, feelings, etc. are evaluated by the appraisal system.

[1284] "Behavioral data" refers to information about the actions and behavior of the person being evaluated, including, for example, remarks made during a meeting or the content of a presentation.

[1285] "Performance data" refers to information regarding the work results and performance of the person being evaluated, including, for example, sales performance and project progress.

[1286] "Emotional data" refers to information about the emotional state of the person being evaluated, including, for example, facial expressions, tone of voice, and choice of words.

[1287] "Real-time" means that data is collected, analyzed, and evaluated immediately, without delay.

[1288] "Collection means" refers to devices and software used to obtain behavioral, performance, and emotional data about the person being evaluated.

[1289] "Transmission means" refers to the communication device or protocol used to send collected data to the server.

[1290] "Server" refers to a computer system for receiving, analyzing, and evaluating data.

[1291] "AI analysis engine" refers to artificial intelligence software for analyzing and evaluating collected data.

[1292] "Evaluation update means" refers to a device or software for updating the evaluation of the person being evaluated in real time based on the analysis results.

[1293] "Grade certification means" refers to a device or software for determining and certifying the grade of an individual being evaluated in real time based on the evaluation results.

[1294] "Emotion recognition engine" refers to artificial intelligence software for recognizing the emotions of the person being evaluated in real time.

[1295] "Human resource management tools" refers to devices and software for allocating and developing personnel based on the grade certification of those being evaluated.

[1296] The present invention is a system that collects data on the behavior, performance, and emotions of an individual to be evaluated in real time and instantly analyzes and evaluates the data using AI. A specific embodiment of this system will be described below.

[1297] Hardware and Software Used

[1298] Hardware: high performance servers, cameras, microphones, sensors

[1299] Software: AI analysis engine, emotion recognition engine, data collection software

[1300] Data collection

[1301] The device collects the behavior, performance, and emotional data of the person being evaluated in real time. Specifically, the camera installed in the device captures the facial expression of the person being evaluated, and the microphone records the tone of voice. In addition, the sensor detects the movement of the person being evaluated. For example, the camera and microphone collect the facial expression and tone of voice of the person being evaluated who is giving a presentation during a meeting.

[1302] Data transmission

[1303] The data collected by the device is sent to the server. The data collected by the device is compressed in real time and sent to the server using a secure communication protocol. For example, the collected facial expression data and tone of voice data are sent to the server.

[1304] 4. Data Analysis

[1305] The data received by the server is immediately analyzed using an AI analysis engine. The data received by the server is input into the AI ​​analysis engine, which analyzes behavioral and performance data. In addition, an emotion recognition engine is used to analyze emotional data. For example, the content of a presentation is analyzed to evaluate the performance of the person being evaluated. Emotions such as anger and joy are recognized from facial expressions and tone of voice.

[1306] Rating Update

[1307] The server updates the evaluation of the person being evaluated in real time based on the analysis results. The server reflects the analysis results in the evaluation database and updates the evaluation score of the person being evaluated. For example, the evaluation score of the person being evaluated is updated based on the performance evaluation of the presentation and the emotion data.

[1308] Grade Certification

[1309] The server certifies the grade of the person being evaluated in real time based on the evaluation results. The server determines the grade of the person being evaluated based on the updated evaluation score and notifies the result of the certification. For example, the person being evaluated is certified as "Excellent" based on the updated evaluation score.

[1310] Examples

[1311] For example, when the person being evaluated is giving a presentation during a meeting, the following process is carried out.

[1312] 1. The device uses a camera and microphone to collect the subject's facial expressions, tone of voice, and presentation content in real time.

[1313] 2. The device sends the collected data to the server.

[1314] 3. The server uses an AI analysis engine to analyze the content of the presentation and the performance of the person being evaluated.

[1315] 4. The server uses an emotion recognition engine to recognize the emotions of the person being evaluated from their facial expressions and tone of voice. For example, if the person being evaluated expresses anger, the server analyzes that information.

[1316] 5. The server updates the evaluation of the person being evaluated in real time based on the analysis results and certifies the grade.

[1317] Examples of prompt statements

[1318] "If an evaluation subject expresses anger during a meeting, please explain in detail the processing steps of the system where the AI ​​immediately analyzes that information and reflects it in the evaluation of the evaluation subject."

[1319] The system makes it possible to evaluate the behavior, performance, and emotions of individuals in real time, providing fast and accurate feedback.

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

[1321] Step 1:

[1322] The device collects real-time data on the behavior, performance, and emotions of the person being evaluated.

[1323] Input: Facial expressions, tone of voice, and movements of the person being evaluated

[1324] How it works: The device's camera captures the subject's facial expressions, the microphone records the tone of the subject's voice, and the sensor detects the subject's movements.

[1325] Output: Collected facial expression data, tone of voice data, movement data

[1326] Step 2:

[1327] The terminal transmits the collected data to the server.

[1328] Input: Collected facial expression data, tone of voice data, movement data

[1329] Specific operation: The data collected by the terminal is compressed in real time and sent to the server using a secure communication protocol.

[1330] Output: Data sent to the server

[1331] Step 3:

[1332] The data received by the server is instantly analyzed using an AI analysis engine.

[1333] Input: Data sent to the server

[1334] Specific operation: The server inputs the received data into the AI ​​analysis engine to analyze behavioral data and performance data. It also uses an emotion recognition engine to analyze emotion data.

[1335] Output: Analysis results (behavioral evaluation, performance evaluation, emotional evaluation)

[1336] Step 4:

[1337] The server updates the evaluation of the person being evaluated in real time based on the analysis results.

[1338] Input: Analysis results (behavioral evaluation, performance evaluation, emotional evaluation)

[1339] Specific operation: The server reflects the analysis results in the evaluation database and updates the evaluation score of the person being evaluated.

[1340] Output: Updated rating score

[1341] Step 5:

[1342] The server certifies the grade of the person being evaluated in real time based on the evaluation results.

[1343] Input: Updated rating score

[1344] Specific operation: The server determines the grade of the person being evaluated based on the updated evaluation score and notifies the certification result.

[1345] Output: Grade certification results

[1346] In this way, it is possible to evaluate the behavior, performance, and emotions of the person being evaluated in real time and provide fast and accurate feedback.

[1347] (Application example 2)

[1348] Next, a description will be given of Application Example 2 of Form 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".

[1349] In conventional evaluation systems, evaluations were based only on the behavior and performance of the person being evaluated, which resulted in one-sided evaluations and did not take into account the emotions and psychological state of the person being evaluated. In addition, it was difficult to update the evaluations in real time, which sometimes resulted in a time lag in the evaluations. This could lead to a loss of accuracy and fairness in the evaluations. Furthermore, there was a lack of real-time feedback to improve the efficiency and safety of workers in the factory.

[1350] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1351] In this invention, the server includes a means for collecting data on the behavior and performance of the person to be evaluated, an artificial intelligence for evaluating the person to be evaluated based on the collected data, a means for certifying the grade of the person to be evaluated based on the evaluation result by the artificial intelligence, an emotion engine for recognizing the emotion of the person to be evaluated in real time, a means for analyzing the emotion data recognized by the emotion engine, and a means for updating the evaluation of the person to be evaluated in real time based on the analysis result. This enables a comprehensive evaluation that takes into account not only the behavior and performance of the person to be evaluated, but also their emotion and psychological state, and allows evaluation updates and feedback in real time.

[1352] An "evaluatee" is an individual whose behavior, achievements, feelings, etc. are evaluated by the evaluation system.

[1353] "Behavioral data" refers to information regarding the actions and behavior of the person being evaluated.

[1354] "Performance Data" refers to information regarding the results and accomplishments of the person being evaluated.

[1355] "Artificial intelligence" refers to a computer system that analyzes collected data and evaluates individuals being evaluated.

[1356] "Grade certification" is the process of determining the rank or grade of an individual based on the results of evaluation by artificial intelligence.

[1357] The "emotion engine" is a system that recognizes emotions in real time from the facial expressions, tone of voice, choice of words, etc. of the person being evaluated.

[1358] "Emotion Data" refers to information regarding the emotions of the subject of evaluation recognized by the emotion engine.

[1359] "Real-time update" refers to the process of instantly reflecting the evaluation of the person being evaluated and always maintaining the latest evaluation status.

[1360] "Feedback" is the process of notifying the person being evaluated of the results of the evaluation in real time.

[1361] As an embodiment of the present invention, a system for evaluating the behavior, performance, and emotions of workers in a factory in real time is constructed. A specific embodiment of the system is described below.

[1362] System Configuration

[1363] The system consists of the following main components:

[1364] 1. Cameras: Used to capture worker movements in real time.

[1365] 2. Microphone: Used to collect the voices of workers.

[1366] 3. Server: The central computer system that collects, analyzes, and evaluates the data.

[1367] 4. Artificial Intelligence (AI): Analyzes collected data and evaluates the subjects.

[1368] 5. Emotion engine: Recognizes emotions in real time from workers' facial expressions, tone of voice, choice of words, etc.

[1369] 6. Feedback system: Notify workers of evaluation results in real time.

[1370] Program Processing

[1371] The server collects data from the camera and microphone in real time and analyzes it. Specifically, it performs the following processes:

[1372] 1. Data collection: A camera is used to capture the worker's movements and a microphone is used to collect the worker's voice.

[1373] 2. Emotion Recognition: Using an emotion engine, we recognize the emotions of workers from the collected tone of voice and facial expressions. The emotion engine uses Google Cloud's emotion analysis API.

[1374] 3. Data analysis: Artificial intelligence will analyze and evaluate the collected behavioral data, performance data, and emotional data.

[1375] 4. Evaluation update: Update worker evaluations in real time based on the analysis results.

[1376] 5. Feedback: Communicate updated evaluation results to workers in real time.

[1377] Hardware and Software Used

[1378] Hardware: Cameras, microphones, servers

[1379] Software: OpenCV (camera image acquisition and display), Google Cloud emotion analysis API (emotion recognition)

[1380] Examples

[1381] For example, if a worker says, "This task is very difficult," the emotion engine will detect "anxiety" from the tone and content of the voice, and the AI ​​will update the worker's evaluation based on that information.

[1382] Examples of prompt statements

[1383] If a worker says, "This task is very difficult," the emotion engine will detect "anxiety" from the tone and content of the voice, and the AI ​​will update the worker's evaluation based on that information.

[1384] In this way, a system can be created that evaluates worker behavior and emotions in real time and provides feedback.

[1385] The flow of the specific process in the application example 2 will be described with reference to FIG.

[1386] Step 1:

[1387] The server uses a camera to capture the worker's movements in real time. The input is the camera image and the output is the captured movement data. Specifically, it uses OpenCV to acquire the image from the camera and record the worker's movements frame by frame.

[1388] Step 2:

[1389] The server collects the voices of workers using a microphone. The input is voice data, and the output is the collected voice data. Specifically, the server captures voice input from the microphone in real time and saves it as an audio file.

[1390] Step 3:

[1391] The server uses an emotion engine to recognize the emotions of workers from the collected tone of voice and facial expressions. The input is voice data and video data, and the output is the recognized emotion data. Specifically, the voice data is analyzed using the Google Cloud emotion analysis API to obtain an emotion score. In addition, facial expressions are analyzed from the video data to recognize emotions.

[1392] Step 4:

[1393] The server uses artificial intelligence to analyze the collected behavioral data, performance data, and emotional data and performs the evaluation. The input is behavioral data, performance data, and emotional data, and the output is the evaluation results. Specifically, the data is analyzed using a generative AI model and the performance of the person being evaluated is scored.

[1394] Step 5:

[1395] The server updates the evaluation of the worker in real time based on the analysis results. The input is the evaluation result, and the output is the updated evaluation data. Specifically, the evaluation result is saved in a database and the profile of the person being evaluated is updated.

[1396] Step 6:

[1397] The server notifies the worker of the updated evaluation results in real time. The input is the updated evaluation data, and the output is a notification message. Specifically, the server sends the evaluation results to the worker's device as a push notification, providing feedback to the worker.

[1398] 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 voice indicating a user input for 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.

[1399] 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> ) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to 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.

[1400] Another example of generative AI is Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) are mentioned.

[1401] 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.

[1402] [Fourth embodiment]

[1403] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1404] 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.

[1405] 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 wide area network (WAN) and / or a local area network (LAN).

[1406] 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. In addition, the microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1407] 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 the voice according to instructions from the processor 46.

[1408] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[1409] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[1410] The control target 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, legs, etc. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, legs, etc. 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.

[1411] Fig. 8 shows an example of 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.

[1412] 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.

[1413] 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.

[1414] In the robot 414, 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.

[1415] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1416] "Example 1"

[1417] As one embodiment of the present invention, an AI system that evaluates people in a corporate organization is provided. This system has a means for collecting data on the behavior and performance of the person being evaluated. For example, data such as the success rate of projects carried out by the person being evaluated and the quality of reports submitted by the person being evaluated is collected. The collected data is analyzed by AI, and the person being evaluated is evaluated. The evaluation results are used to certify the grade of the person being evaluated. Grade certification is performed at the discretion of the department, and affects changes to the employment conditions and wages of the person being evaluated. In addition, the evaluation results are standardized company-wide, and human resource management is also carried out as a going concern.

[1418] "Example 2"

[1419] As another embodiment of the present invention, a form is provided in which an AI system collects data on the behavior, performance, etc. of the person to be evaluated in real time and performs the evaluation in real time. In this form, data on the behavior, performance, etc. of the person to be evaluated is collected immediately after the person to be evaluated performs an action or achieves an achievement, and is analyzed immediately by AI. As a result, the evaluation of the person to be evaluated is updated in real time, and the grade of the person to be evaluated is also certified in real time.

[1420] The process flow of each embodiment will be described below.

[1421] "Example 1"

[1422] Step 1: Collect data on the behavior and performance of the person being evaluated. For example, collect data on the success rate of projects carried out by the person being evaluated and the quality of reports submitted by the person being evaluated.

[1423] Step 2: The collected data is analyzed by AI, which then evaluates the person being evaluated based on the collected data.

[1424] Step 3: The grade of the person being evaluated is determined based on the results of the AI ​​evaluation. Grade determination is done at the discretion of the department and will affect changes to the employment conditions and wages of the person being evaluated.

[1425] Step 4: The evaluation results are standardized across the company and are used in human resource management as a going concern.

[1426] "Example 2"

[1427] Step 1: Collect data on the behavior and performance of the person being evaluated in real time. Data is collected immediately after the person being evaluated performs an action or achieves a result.

[1428] Step 2: The collected data is immediately analyzed by AI, which then evaluates the person being evaluated in real time based on the collected data.

[1429] Step 3: Based on the results of the AI ​​evaluation, the grade of the person being evaluated is determined in real time. Grade determination is done at the discretion of the department and has an immediate effect on changes to the employment conditions and wages of the person being evaluated.

[1430] Example 1

[1431] Next, a description will be given of Example 1 of the embodiment 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".

[1432] In conventional talent evaluation systems, data collection on the behavior and performance of those being evaluated was insufficient, and the evaluations often lacked objectivity and accuracy. In addition, because grade certification and talent management based on the evaluation results were not performed consistently, there was a problem that talent management throughout the organization was not performed efficiently. Furthermore, the evaluation process was often performed manually, which was time-consuming and labor-intensive.

[1433] 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.

[1434] In this invention, the server includes a means for collecting data on the behavior and performance of the person to be evaluated, a means for preprocessing the collected data, a means including a generative AI model for analyzing the preprocessed data, a means for evaluating the person to be evaluated based on the analysis result by the generative AI model, and a means for certifying the grade of the person to be evaluated based on the evaluation result. This enables objective and highly accurate evaluation based on the behavior and performance of the person to be evaluated, and consistent grade certification and human resource management based on the evaluation result can be efficiently performed.

[1435] "Assesseeee" refers to the individual within the business organization who is the subject of the assessment.

[1436] "Data on behavior, performance, etc." refers to data containing information necessary for evaluation, such as the success rate of projects carried out by the person being evaluated and the quality of reports submitted.

[1437] "Means of collection" refers to the hardware and software used to obtain data on the behavior, performance, etc. of the person being evaluated.

[1438] "Preprocessing means" refers to hardware and software used to fill in missing values ​​in collected data, correct outliers, standardize data formats, and so on.

[1439] A "generative AI model" refers to an artificial intelligence model that analyzes data such as the behavior and performance of the person being evaluated and generates an evaluation score.

[1440] "Means of analysis" refers to the hardware and / or software used to input preprocessed data into a generative AI model and generate an evaluation score.

[1441] "Means of evaluation" refers to hardware and software used to evaluate the subject based on the analysis results of the generative AI model.

[1442] "Means of grade certification" refers to hardware or software used to certify the grade of the person being evaluated based on the evaluation results.

[1443] "Departmental discretion" refers to each department within a company deciding the grade of each person being evaluated at its own discretion.

[1444] "Human resource management" refers to changing the employment conditions, adjusting wages, setting career paths, etc. of those being evaluated based on the evaluation results and grade certification.

[1445] The present invention relates to an AI system for evaluating people in a corporate organization. A specific embodiment of this system will be described below.

[1446] The server has a means of collecting data on the behavior and performance of the assessees. Specifically, it obtains project success rate data from project management software (e.g., JIRA, Trello) and collects quality data on submitted reports from document management systems (e.g., Google Drive, SharePoint).

[1447] Next, the server preprocesses the collected data. It complements missing values ​​in the data and detects and corrects outliers. It also standardizes the data format and prepares it in a form that is easy for the AI ​​model to analyze. For example, if there are missing values, they are complemented with the average value, and if there are outliers, they are corrected with the median value. The data format is standardized and converted into CSV format.

[1448] The preprocessed data is input into a generative AI model (e.g., TensorFlow, PyTorch) on the server. The AI ​​model analyzes the behavioral patterns and performance of the person being evaluated and generates an evaluation score. For example, if the success rate of the projects in which person being evaluated A was in charge was 90% and the quality of the reports he submitted was highly evaluated, the AI ​​model will generate an evaluation score based on this data.

[1449] Based on the generated evaluation score, the server generates an overall evaluation of the person being evaluated. This evaluation result is used to certify the grade of the person being evaluated. Grade certification is performed at the discretion of the department and affects changes to the employment conditions and wages of the person being evaluated. In addition, the evaluation result is standardized across the company and is also used for human resource management as a going concern.

[1450] As a concrete example, consider a case where the success rate of projects carried out by assessee A was 90% and the quality of the submitted reports was highly evaluated. The server collects success rate data from the project management software and report quality data from the document management system. These data are input into the AI ​​model for evaluation.

[1451] Example of a prompt to be input to a generative AI model:

[1452] The project success rate of assessee A is 90%, and the quality of the reports he submitted is highly rated. Based on this data, please give an overall evaluation of assessee A.

[1453] Using this prompt, the AI ​​model generates an overall evaluation of the person being evaluated A. The evaluation results are used for grading at the department's discretion and for company-wide standardization.

[1454] In this way, the server evaluates people within the corporate organization and provides grades and feedback based on the evaluation results.

[1455] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1456] Step 1: Data collection

[1457] The server collects data on the behavior and performance of the assessees. Specifically, it obtains project success rate data from project management software (e.g., JIRA, Trello) and collects quality data on submitted reports from document management systems (e.g., Google Drive, SharePoint). The input is the assessee's ID and project ID, and the output is project success rate data and report quality data.

[1458] Step 2: Data Preprocessing

[1459] The server preprocesses the collected data. Specifically, it complements missing values ​​in the data and detects and corrects outliers. It also standardizes the data format and prepares it in a form that is easy for the AI ​​model to analyze. The input is the collected raw data, and the output is preprocessed, clean data. For example, if there are missing values, they are complemented with the average value, and if there are outliers, they are corrected with the median. The data format is standardized and converted to CSV format.

[1460] Step 3: Data analysis

[1461] The server inputs the preprocessed data into a generative AI model. The AI ​​model (e.g., TensorFlow, PyTorch) analyzes the behavioral patterns and performance of the person being evaluated and generates an evaluation score. The input is the preprocessed data, and the output is the evaluation score. For example, if the success rate of the projects in which person being evaluated A was in charge was 90% and the quality of the reports he submitted was highly evaluated, the AI ​​model will generate an evaluation score based on this data.

[1462] Step 4: Generate evaluation results

[1463] The server generates an overall evaluation of the person being evaluated based on the generated evaluation score. The input is the evaluation score obtained from the AI ​​model, and the output is the overall evaluation of the person being evaluated. For example, based on an evaluation score of 85 points, the overall evaluation of person A is set to "excellent."

[1464] Step 5: Grading and feedback

[1465] The server certifies the grade of the person being evaluated based on the generated evaluation results. The input is the overall evaluation, and the output is the grade certification result of the person being evaluated. Grade certification is done at the discretion of the department and affects changes to the employment conditions and wages of the person being evaluated. The evaluation results are also standardized company-wide and are used in human resource management as a going concern. For example, the grade of person A being evaluated is certified as "A" and his / her wage is increased by 10%.

[1466] (Application example 1)

[1467] Next, a description will be given of Application Example 1 of Form 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".

[1468] Traditionally, the performance evaluation of robots working in factories was mainly carried out by human managers, which led to problems with the lack of objectivity and efficiency of the evaluation. In addition, robot maintenance schedules and upgrade plans often relied on experience and intuition and were not optimized. This reduced the robot's operating rate and lifespan, and had a negative impact on the productivity of the entire factory.

[1469] 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.

[1470] In this invention, the server includes a means for collecting data such as the work efficiency, error rate, and maintenance history of the machine to be evaluated, an AI for evaluating the machine to be evaluated based on the collected data, a means for optimizing a maintenance schedule for the machine to be evaluated based on the evaluation results by the AI, and a means for proposing an upgrade plan for the machine to be evaluated based on the evaluation results. This makes it possible to objectively and efficiently evaluate the performance of a robot and to optimize the maintenance schedule and upgrade plan.

[1471] "Machinery to be evaluated" refers to robots and automated machinery that perform work in factories.

[1472] "Work efficiency" is an index that indicates how much work the evaluated machine can complete within a certain amount of time.

[1473] The "error rate" is an index showing the frequency of errors and breakdowns that occur when the machine being evaluated is in operation.

[1474] "Maintenance history" refers to the records of maintenance and repairs that the machine being evaluated has received in the past.

[1475] "Means of collecting data" refers to sensors and communication devices for obtaining data such as work efficiency, error rate, and maintenance history from the machine being evaluated.

[1476] "Evaluation AI" refers to an artificial intelligence system that analyzes collected data and evaluates the performance of the machine being evaluated.

[1477] "Means for optimizing maintenance schedules" refers to algorithms or programs for optimizing the timing and content of maintenance for the evaluated machinery based on the results of the AI ​​evaluation.

[1478] "Means for proposing an upgrade plan" refers to algorithms or programs for proposing upgrades to improve the performance or add functions to the machine being evaluated based on the results of the AI ​​evaluation.

[1479] As an embodiment of the present invention, a system for evaluating the performance of robots working in a factory is constructed. The system includes an AI that collects data such as the work efficiency, error rate, and maintenance history of the machine to be evaluated, and evaluates the machine based on the collected data. Furthermore, the system optimizes the maintenance schedule of the machine to be evaluated based on the evaluation results by the AI, and proposes an upgrade plan for the machine to be evaluated based on the evaluation results.

[1480] Hardware and Software Used

[1481] Hardware

[1482] Server: A high-performance server for data collection and analysis.

[1483] Robot: A robot in a factory that is the subject of data collection

[1484] Sensors: Sensors to collect data such as the robot's work efficiency, error rate, and maintenance history

[1485] software

[1486] Python: Used for data analysis and model training

[1487] Pandas: Used to load and preprocess data

[1488] Scikit-learn: Used to train and evaluate machine learning models.

[1489] Data processing and calculation

[1490] The server first collects data from the robot in real time. The collected data is preprocessed using Pandas and divided into features and targets such as work efficiency, error rate, and maintenance history. Then, a model is trained using Scikit-learn's RandomForestRegressor to predict the performance of the machine being evaluated. The prediction results are used to optimize the maintenance schedule of the machine being evaluated and propose an upgrade plan.

[1491] Examples

[1492] For example, if a robot's work efficiency is 90%, its error rate is 5%, and its maintenance history is three times, the server will collect these data and analyze them with the AI ​​model. Based on the analysis results, it will predict the robot's performance score and suggest the optimal maintenance schedule and necessary upgrades.

[1493] Examples of prompt statements

[1494] Enter your robot's work efficiency, error rate, and maintenance history to predict its performance score.

[1495] In this way, it is possible to build a system that evaluates the performance of robots working in factories and optimizes maintenance schedules and upgrade plans.

[1496] The flow of the specific process in the application example 1 will be described with reference to FIG.

[1497] Step 1:

[1498] The server collects data such as work efficiency, error rate, and maintenance history from the robots in the factory in real time. This data is acquired using sensors and communication devices and stored in a database.

[1499] Input: Robot work efficiency, error rate, maintenance history

[1500] Output: Robot performance data stored in a database

[1501] Step 2:

[1502] The server preprocesses the collected data using Pandas. Specifically, it complements missing values ​​and removes outliers to make the data clean.

[1503] Input: Robot performance data stored in a database

[1504] Output: Preprocessed and clean data

[1505] Step 3:

[1506] The server divides the preprocessed data into features and targets. Work efficiency, error rate, and maintenance history are used as features, and performance score is set as a target.

[1507] Input: Preprocessed and clean data

[1508] Output: Data split into features and targets

[1509] Step 4:

[1510] The server trains a machine learning model using Scikit-learn's RandomForestRegressor. It uses the features and targets as training data to build the model.

[1511] Input: Data split into features and targets

[1512] Output: A trained machine learning model

[1513] Step 5:

[1514] The server uses the trained model to predict the robot's performance score based on new data collected in real time.

[1515] Input: New robot performance data collected in real time

[1516] Output: Predicted performance score

[1517] Step 6:

[1518] The server optimizes the robot's maintenance schedule based on the predicted performance score, determining the timing and content of maintenance and updating the schedule.

[1519] Input: Predicted performance score

[1520] Output: Optimized maintenance schedule

[1521] Step 7:

[1522] The server then proposes an upgrade plan for the robot based on the predicted performance score, determining what upgrades are required and when, and creating a proposal.

[1523] Input: Predicted performance score

[1524] Output: Proposed upgrade plan

[1525] In this way, the server can evaluate the robot's performance and optimize maintenance schedules and upgrade plans.

[1526] Example 2

[1527] Next, a second embodiment of the second embodiment will be described. 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".

[1528] In the conventional evaluation system, data collection and analysis of the behavior and performance of the person being evaluated was not done in real time, and updates to evaluation results and grade certification were often delayed. In addition, there was also the problem that the evaluation criteria were uniform and it was difficult to reflect the discretion of each department. Furthermore, there was an issue that human resource management based on the evaluation results was not carried out efficiently.

[1529] 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.

[1530] In this invention, the server includes a means for collecting data such as the behavior and performance of the person to be evaluated in real time, a means for storing the collected data in a database, a means for using a generative AI model to analyze the stored data, a means for updating the evaluation score of the person to be evaluated in real time based on the analysis result, a means for certifying the grade of the person to be evaluated based on the evaluation score, and a means for notifying the terminal of the person to be evaluated of the result of the grade certification. This makes it possible to collect and analyze the data of the behavior and performance of the person to be evaluated in real time, quickly update the evaluation result, and certify the grade reflecting the discretion of each department. In addition, efficient human resource management based on the evaluation result can be realized.

[1531] "Appraisee" refers to the individual or group whose behavior or performance is evaluated by the appraisal system.

[1532] "Data on behavior, achievements, etc." refers to information on the specific behavior and achievements of the person being evaluated, including the progress and results of work, behavioral history, etc.

[1533] "Means of collecting data in real time" refers to methods and technologies for instantly obtaining data on the behavior and performance of the person being evaluated and incorporating it into the system without delay.

[1534] "Means of storing in a database" refers to the methods and technologies used to organize collected data and keep it accessible later.

[1535] A "generative AI model" refers to an algorithm or model that uses machine learning and artificial intelligence techniques to analyze data and evaluate the behavior and performance of individuals being evaluated.

[1536] "Evaluation score" refers to a numerical indicator of the performance of the person being evaluated based on the results of analysis by the generative AI model.

[1537] "Grade certification" refers to the process of determining the rank or grade of an assessee based on their assessment score.

[1538] "Means of notifying the device" refers to the methods and technologies for notifying the subject of the evaluation of the results of the evaluation and the grade certification, including email and push notifications.

[1539] "Departmental discretion" refers to the authority of each department to evaluate and grade based on its own criteria and policies.

[1540] "Human resource management" refers to the process of allocating, developing, and evaluating human resources within an organization based on evaluation results and grade certification.

[1541] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[1542] The present invention is a system for collecting data on the behavior and performance of an evaluation target in real time, analyzing the data, updating the evaluation score, and certifying a grade. A specific embodiment of the system will be described below.

[1543] 1. Program Generation

[1544] The server collects data on the behavior and performance of the person being evaluated in real time and generates a program for evaluating the person. This program has the function of instantly analyzing the behavior and performance of the person being evaluated and updating the evaluation in real time.

[1545] 2. Program Processing

[1546] The server works with various sensors and databases to collect data on the behavior and performance of the person being evaluated. Specifically, data is collected from the devices (e.g., smartphones, PCs) and business systems (e.g., customer management systems, business management systems) used by the person being evaluated. This data is stored in the database on the server.

[1547] The server then uses a generative AI model to analyze the collected data. Specifically, it uses machine learning frameworks such as TensorFlow and PyTorch to analyze the behavior and performance of the person being evaluated. The analysis results are updated in real time as the person being evaluated's evaluation score.

[1548] Furthermore, the server certifies the grade of the person to be evaluated based on the evaluation score. In this process, the grade of the person to be evaluated is determined based on the evaluation criteria set in advance. The result of the grade certification is notified to the terminal of the person to be evaluated.

[1549] 3. Specific Examples

[1550] As a concrete example, consider the performance evaluation of a sales representative. When a sales representative wins a new contract, the information is automatically sent from the customer management system to a server. The server uses a generative AI model to analyze the value of the new contract and updates the sales representative's evaluation score. The updated evaluation score is notified to the sales representative's smartphone in real time.

[1551] Example prompt:

[1552] "When a sales rep wins a new deal, collect that information from your customer relationship management system and use a generative AI model to update the reputation score."

[1553] In this way, a system is realized in which the server, terminals, and users work together to evaluate the behavior and performance of the person being evaluated in real time and certify a grade.

[1554] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1555] Step 1: Data collection

[1556] The server collects data on the behavior and performance of the person being evaluated in real time. Specifically, it obtains data from the devices (e.g., smartphones, PCs) and business systems (e.g., customer management systems, business management systems) used by the person being evaluated. The input is data on the behavior and performance of the person being evaluated, and the output is the raw data sent to the server. For example, when a sales representative secures a new contract, that information is sent from the customer management system to the server.

[1557] Step 2: Save Data

[1558] The server stores the collected data in a database. Specifically, it uses a relational database such as MySQL or PostgreSQL. The input is the collected raw data, and the output is the structured data stored in the database. For example, the details of a new contract are stored in the database.

[1559] Step 3: Data analysis

[1560] The server uses a generative AI model to analyze the stored data. Specifically, it uses machine learning frameworks such as TensorFlow and PyTorch to analyze the behavior and performance of the person being evaluated. The input is structured data stored in a database, and the output is an evaluation score as the analysis result. For example, a predictive model based on past data is used to evaluate the value of a new contract.

[1561] Step 4: Update your reputation scores

[1562] The server updates the evaluation score of the person being evaluated based on the results of the data analysis. The input is the evaluation score as the analysis result, and the output is the updated evaluation score. For example, if the value of a new contract is high, the evaluation score of a sales representative increases.

[1563] Step 5: Grade Certification

[1564] The server certifies the grade of the person to be evaluated based on the updated evaluation score. The input is the updated evaluation score, and the output is the grade of the person to be evaluated. For example, if the evaluation score exceeds a certain threshold, the grade of the salesperson is promoted from "silver" to "gold."

[1565] Step 6: Notification

[1566] The server notifies the terminal of the person being evaluated of the result of the grade certification. The input is the grade of the person being evaluated, and the output is a notification sent to the terminal of the person being evaluated. For example, a notification saying "Your grade has been promoted to gold" is sent to the smartphone of a sales representative.

[1567] (Application example 2)

[1568] Next, a description will be given of Application Example 2 of Form 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".

[1569] With conventional factory robot evaluation systems, it was difficult to evaluate the robot's operation...

Claims

1. A means for collecting data on at least one of the behavior and performance of the person to be evaluated; An artificial intelligence system that evaluates the person being evaluated based on collected data; A means for certifying a grade of an evaluation subject based on the evaluation result by the artificial intelligence; An emotion engine that recognizes the emotions of the person being evaluated in real time; means for analyzing the emotion data recognized by the emotion engine; A means for updating the evaluation of the person being evaluated in real time based on the analysis results; and A system including:

2. 2. The system according to claim 1, further comprising means for enabling a grade certification of an assessee to be performed at the discretion of the department.

3. The system according to claim 1, further comprising a means for performing human resource management based on the grade certification of the person to be evaluated.

Images