system

Abstract

We provide the system. [Solution] A means for having the user input target data, A means for collecting the aforementioned target data and recording it in a database, A means for cleansing the collected data of the aforementioned target data, A means of setting evaluation criteria using generative artificial intelligence, A means for evaluating the degree of achievement of the target data based on the aforementioned evaluation criteria, A system including means for providing feedback to the user on the evaluation results of the aforementioned target data.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the current Management by Objectives (MBO) system, it is common for superiors to conduct individual evaluations, which tend to make the evaluations subjective. In addition, since the evaluation criteria vary among different superiors and departments, there is a problem that the evaluations within the organization are not consistent and a sense of unfairness arises. The purpose of the present invention is to solve these problems and improve the reliability and motivation of the entire organization by ensuring the objectivity and fairness of evaluations.

Means for Solving the Problems

[0005] The present invention is a system that includes means for having users input target data and recording it in a database, means for cleansing the collected target data, means for setting evaluation criteria using generative artificial intelligence, means for evaluating the degree of target achievement based on the evaluation criteria, and means for providing feedback of the evaluation results to the user. Specifically, it utilizes generative artificial intelligence to automatically generate objective evaluation criteria, evaluates the user's degree of target achievement based on these criteria, and provides standardized feedback. This mechanism eliminates subjectivity in evaluation and realizes fair and consistent evaluation.

[0006] "Target data" refers to information such as specific business goals, numerical targets, and progress that users aim to achieve.

[0007] A "user" is an individual or member of an organization who inputs target data and receives evaluation.

[0008] A "database" is an information system used to record and store collected target data and evaluation data.

[0009] "Cleansing" is the process of identifying and removing or correcting duplicate, inconsistent, or unnecessary data from collected data.

[0010] "Generative artificial intelligence" refers to a system that uses machine learning algorithms and natural language processing technologies to automatically generate and adjust new evaluation criteria based on past evaluation data, industry standards, and organizational policies.

[0011] "Evaluation criteria" refer to a set of unified standards and metrics used to assess a user's level of goal achievement.

[0012] "Achievement level" refers to the percentage or score of how much of the user's set goal they actually achieved.

[0013] "Feedback" is the process of providing information that includes evaluation results and areas for improvement regarding the user's achievement of goals. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, when an emotion engine is combined. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0015] 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.

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

[0017] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units 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), and the like.

[0018] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

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

[0024] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio 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 audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0031] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] This invention relates to a system that automates the evaluation of management by objectives (MBO) and ensures objectivity and fairness. The system performs a series of processes in which the user inputs goal data, a generative artificial intelligence evaluates the degree of goal achievement based on evaluation criteria, and provides feedback on the results.

[0036] User goal input and recording

[0037] Users input annual, quarterly, and monthly target data through their work terminals. For example, a sales staff member might input a specific target such as "Achieve a sales target of 5 million yen in Q1." The target data entered by the user is immediately sent to the server and recorded in the database.

[0038] Data collection and cleansing

[0039] The server periodically collects target data submitted by users and stores it in a database. Since the collected data may include duplicates or inconsistent formats, the server cleanses this data. The cleansing process involves removing duplicate data, correcting inconsistent data, and eliminating noisy data.

[0040] Setting evaluation criteria

[0041] The server uses generative artificial intelligence to set evaluation criteria. The generative AI receives input such as the organization's past evaluation data, industry standards, and organizational policies. Based on this data, the generative AI performs analysis and automatically generates unified evaluation criteria. For example, the evaluation criteria for the sales department might include metrics such as sales targets, number of contracts, and customer satisfaction.

[0042] Evaluation of goal achievement

[0043] The server evaluates the user's achievement of their goals based on the set evaluation criteria. During the evaluation process, the generative artificial intelligence analyzes the user's goal data and calculates an achievement score. In addition to the score, the generative artificial intelligence also automatically generates feedback comments. For example, if a user achieves 4.5 million yen against a sales target of 5 million yen, a score of 90% achievement is calculated, and a comment such as "Although the target was slightly missed, the sales effort was remarkable" is generated.

[0044] Provide feedback

[0045] After the evaluation results are generated, the server sends them to the user's device. The user can then view the evaluation score and feedback comments on their device. This feedback includes not only numerical data on achievement but also specific areas for improvement and advice for setting future goals.

[0046] Specific example

[0047] Case Study A: Sato's Evaluation Process in the Sales Department

[0048] 1. Target Input: Sato inputs "Achieve a sales target of 5 million yen in Q1" into the terminal.

[0049] 2. Data Collection and Cleansing: The server collects the target data sent from Sato and cleanses away any unnecessary data.

[0050] 3. Setting Evaluation Criteria: The server uses generative artificial intelligence to set unified evaluation criteria based on past evaluation data and industry standards.

[0051] 4. Evaluation of Goal Achievement: The generative artificial intelligence analyzes Sato's sales performance (e.g., 4.5 million yen) and calculates an achievement score of 90%. It also generates feedback comments.

[0052] 5. Providing feedback: The server sends the evaluation results and feedback comments to Sato's terminal, and Sato checks the results on his terminal.

[0053] This system ensures that evaluations are conducted based on objective criteria, eliminating subjectivity and resulting in fair and unbiased assessments. Furthermore, users receive specific feedback and guidance for setting future goals.

[0054] The following describes the processing flow.

[0055] Step 1:

[0056] Users use a terminal to input their work objectives. Specifically, they input goals and numerical targets that must be achieved by the end of the period (for example, "Achieve a sales target of 5 million yen in Q1").

[0057] Step 2:

[0058] The terminal sends the entered target data to the server. A secure communication protocol is used for transmission, and the target data is immediately stored on the server.

[0059] Step 3:

[0060] The server records the received target data in a database. The database also stores metadata such as the date and time and user ID.

[0061] Step 4:

[0062] The server periodically collects all target data from the database and performs a cleansing process. Specifically, this involves removing duplicate data, correcting inconsistent data, and eliminating noisy data.

[0063] Step 5:

[0064] Based on the cleansed data, the server requests the generative artificial intelligence to set evaluation criteria. The server inputs industry standards, past evaluation data, and the organization's evaluation policies into the generative artificial intelligence.

[0065] Step 6:

[0066] Generative artificial intelligence analyzes input data and generates unified evaluation criteria for assessing goal achievement. The generated evaluation criteria are returned to the server and stored.

[0067] Step 7:

[0068] The server applies evaluation criteria generated by generative artificial intelligence to the cleansed target data to assess the user's degree of goal achievement. Specifically, it calculates a score by comparing the user's performance data (e.g., end-of-period sales performance) with the evaluation criteria.

[0069] Step 8:

[0070] Generative artificial intelligence automatically generates feedback comments in addition to achievement scores. For example, it might generate a comment such as, "Although the target was slightly missed, the sales efforts were commendable."

[0071] Step 9:

[0072] The server sends the evaluation results and feedback comments to the user's device. A secure communication protocol is used for transmission.

[0073] Step 10:

[0074] Users use their devices to view evaluation results and feedback comments. This allows users to understand their own performance and gain specific guidance for setting future goals.

[0075] (Example 1)

[0076] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0077] Traditional management by objectives (MBO) systems suffer from problems such as subjectivity and lack of fairness in evaluations, and inconsistency in evaluation criteria. This can lead to a lack of appropriate feedback, hindering employee motivation and performance improvement. Furthermore, the evaluation process is complex and time-consuming, placing a significant burden on managers. This invention aims to solve these problems and provide a system that enables objective and efficient evaluation.

[0078] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0079] In this invention, the server includes means for receiving target data from a user, means for collecting the target data and recording it in a database, means for cleansing the collected target data, means for setting evaluation criteria using generative artificial intelligence, means for evaluating the degree of achievement of the target data based on the evaluation criteria, means for generating feedback comments based on the degree of achievement, and means for providing feedback to the user on the evaluation results and feedback comments of the target data. This ensures objectivity and fairness in the evaluation and enables an efficient evaluation process.

[0080] "Target data" refers to specific business goals that users enter on an annual, quarterly, or monthly basis.

[0081] A "user" refers to an employee of a company or organization who uses the system to input target data and receives evaluation results.

[0082] "Terminal" refers to computers, mobile devices, and other devices that users use to input target data or check evaluation results.

[0083] A "server" refers to a central computer system that collects and stores target data sent by users, performs data cleansing and analysis, sets evaluation criteria, assesses achievement, and generates feedback comments.

[0084] A "database" refers to a data storage system located on or outside a server, used to store target data, historical evaluation data, industry standards, organizational policies, and other similar information.

[0085] "Cleansing" refers to the data preparation process that corrects duplicates and format inconsistencies in the collected target data and eliminates noisy data.

[0086] "Generative artificial intelligence" refers to artificial intelligence technology that automatically generates evaluation criteria and creates evaluation scores and feedback comments based on an organization's past evaluation data, industry standards, and organizational policies.

[0087] "Evaluation criteria" refers to indicators set by generative artificial intelligence that serve as standards for objectively evaluating the degree of goal achievement.

[0088] "Achievement score" refers to a numerical representation of the degree to which a user has achieved their goals.

[0089] "Feedback comments" refer to comments automatically generated by a generative artificial intelligence system based on the user's achievement score, regarding their progress toward achieving their goals.

[0090] This invention relates to a system that automates the evaluation of management by objectives (MBO) and ensures objectivity and fairness. The system performs a series of processes in which the user inputs goal data from a work terminal, the data is collected and cleansed, evaluation criteria are set using generative artificial intelligence, the degree of goal achievement is evaluated, and the results are fed back to the user.

[0091] Users first use their work terminals to input specific target data on an annual, quarterly, or monthly basis. For example, a user in the sales department might input, "Achieve a sales target of 5 million yen in Q1." This target data is sent to the server in real time and recorded in the server's database. The server periodically collects target data from all users and performs data cleansing. This process removes duplicate data, corrects format inconsistencies, and eliminates noisy data.

[0092] Next, the server uses generative artificial intelligence to collect data such as past evaluation data, industry standards, and organizational policies in order to set evaluation criteria. Based on this data, the generative AI performs analysis and automatically generates unified evaluation criteria. In the sales department, indicators such as sales target achievement rate, number of contracts, and customer satisfaction are included in the evaluation criteria.

[0093] The server analyzes the user's target data and actual performance data based on the set evaluation criteria and calculates an achievement score. For example, if a user achieves 4.5 million yen against a sales target of 5 million yen, the achievement score would be calculated as 90%. Furthermore, the generative artificial intelligence automatically generates feedback comments based on this evaluation result. Specifically, comments such as "Although the target was slightly missed, the sales effort was remarkable" are generated.

[0094] After the evaluation results and feedback comments are generated, the server sends them to the user's device. The user can then review the received evaluation results and feedback comments on their device and receive specific advice for setting goals for the next time.

[0095] (Specific example)

[0096] Case Study A: Sato's Evaluation Process in the Sales Department

[0097] 1. Target Input: Sato inputs "Achieve a sales target of 5 million yen in Q1" into the terminal.

[0098] 2. Data Transmission: The terminal transmits target data from Sato to the server in real time. The server records this target data in its database.

[0099] 3. Data Collection and Cleansing: The server collects target data submitted by all users, including Sato, and corrects and removes duplicates, inconsistencies, and noise.

[0100] 4. Setting evaluation criteria: The server collects past evaluation data, industry standards, and organizational policies, and generates evaluation criteria using generative artificial intelligence.

[0101] 5. Evaluation of goal achievement: The generative artificial intelligence analyzes Sato's sales performance (e.g., 4.5 million yen), calculates an achievement score of 90%, and generates feedback comments.

[0102] 6. Providing feedback: The server sends the evaluation results and feedback comments to Sato's terminal, and Sato checks the results on his terminal.

[0103] (Example of a prompt message)

[0104] "Evaluate the achievement level of Sato from the Sales Department against the Q1 target of 5 million yen, and generate feedback comments. Sato's actual sales performance was 4.5 million yen."

[0105] This system eliminates subjectivity and uses objective criteria for evaluation, ensuring fair and unbiased assessments. Furthermore, users receive specific feedback and guidance for setting future goals.

[0106] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0107] Step 1:

[0108] Input and submission of target data

[0109] Users use their work terminals to input annual, quarterly, or monthly target data. For example, a user might input, "Achieve a sales target of 5 million yen in Q1." The entered target data is transmitted from the terminal to the server in real time.

[0110] Input: Target data entered by the user on the device.

[0111] Output: The transmitted target data has arrived at the server.

[0112] Specific operation: The terminal sends the target data entered by the user to the server, and the server verifies the received target data.

[0113] Step 2:

[0114] Recording target data

[0115] The server records the target data received from the terminal in its database. It then sends a response message to the terminal to confirm successful data reception.

[0116] Input: Target data that arrived at the server

[0117] Output: Target data stored in the database

[0118] Specific operation: The server saves the target data to the database and sends a response message to the terminal indicating that the data has been received and saved.

[0119] Step 3:

[0120] Data collection and cleansing

[0121] The server periodically collects target data submitted by all users and stores it in a database. It also performs data cleansing to eliminate duplicates, format inconsistencies, and noise from the collected data.

[0122] Input: Target data submitted by all users

[0123] Output: Cleansed target data

[0124] Specific operation: The server performs data collection tasks at regular intervals, such as at night, and cleanses the data to remove duplicates, inconsistencies, and noise.

[0125] Step 4:

[0126] Setting evaluation criteria

[0127] The server collects data such as past evaluation data, industry standards, and organizational policies, and sets evaluation criteria using generative artificial intelligence.

[0128] Input: Historical evaluation data, industry standards, organizational policy data

[0129] Output: Unified evaluation criteria

[0130] Specific operation: The server retrieves the necessary data from the database, provides it as input to the generative artificial intelligence, and has it perform analysis.

[0131] Step 5:

[0132] Evaluation of goal achievement

[0133] Based on the set evaluation criteria, the server uses generative artificial intelligence to analyze the user's target data and actual performance data, and calculates an achievement score. It also generates feedback comments.

[0134] Input: User's target data, performance data, and set evaluation criteria.

[0135] Output: Achievement score, feedback comments

[0136] Specific operation: The server passes target data and actual data to a generative artificial intelligence, which calculates an achievement score and generates feedback comments.

[0137] Step 6:

[0138] Provide feedback

[0139] The server sends the generated achievement score and feedback comments to the user's terminal. The user checks the received evaluation results and feedback comments on their work terminal.

[0140] Input: Achievement score, feedback comments

[0141] Output: Evaluation results and feedback comments displayed on the user's device.

[0142] Specific operation: The server sends the achievement score and feedback comments to the user's device, and the user reviews the evaluation.

[0143] These steps enable the system to automate the goal management system and ensure objectivity and fairness in evaluations.

[0144] (Application Example 1)

[0145] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0146] In current management by objectives (MBO) systems, the evaluation process is prone to subjectivity, resulting in a lack of objectivity and fairness. Furthermore, particularly in production systems, accurately and efficiently evaluating individual work performance is difficult, requiring significant effort and time for managers to provide appropriate feedback. Therefore, automation and improved accuracy of evaluations are essential.

[0147] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0148] In this invention, the server includes means for receiving target data from a user, means for collecting target data and recording it in a database, means for cleaning the collected target data, means for setting evaluation criteria using generative artificial intelligence, means for evaluating the degree of achievement of the target data based on the evaluation criteria, means for providing feedback on the evaluation results of the target data to the user, means for collecting and cleaning performance data of the production system, means for the generative artificial intelligence to automatically generate evaluation criteria based on the performance data of the production system, means for evaluating the degree of achievement of production targets in the production system and generating achievement scores and feedback comments, and means for providing the evaluation results and feedback comments to the production system administrator. This enables the automation of the evaluation process, realizes objective and fair evaluation, and allows administrators to provide feedback efficiently.

[0149] "Target data" refers to specific numerical values ​​or standards that users aim to achieve in their activities or tasks.

[0150] "Generative artificial intelligence" is an artificial intelligence technology that analyzes collected data and automatically generates evaluation criteria and feedback comments.

[0151] "Evaluation criteria" are standards set by generative artificial intelligence based on past data, industry standards, and organizational policies to evaluate the degree of goal achievement.

[0152] "Goal achievement" is a numerical metric that indicates how well a user or system has achieved the set goals.

[0153] "Feedback comments" are comments generated based on the evaluation results of goal achievement, and include suggestions for improvement and advice for setting future goals for the user.

[0154] A "production system" refers to automated equipment and mechanisms used in factories and manufacturing lines, and is a system that performs specific tasks or manufacturing processes.

[0155] "Performance data" refers to data such as the tasks performed by the production system, the quantities achieved, and the working hours.

[0156] "Cleansing" is the process of removing duplicate or incorrectly formatted data from collected data to improve its quality.

[0157] An "achievement score" is a numerical value that indicates the degree of achievement towards a goal, calculated based on established evaluation criteria.

[0158] A "manager" is a person responsible for monitoring the production system and the achievement of user goals, and for providing appropriate evaluations and feedback.

[0159] This invention relates to a system that automates management by objectives (MBO) and improves objectivity and fairness. This system performs the processes of inputting, collecting, and cleaning goal data, setting evaluation criteria, evaluating achievement, and providing feedback as follows.

[0160] Overall system configuration

[0161] The entire system consists mainly of the following components:

[0162] 1. User terminal

[0163] 2. Server

[0164] 3. Database

[0165] 4. Generative Artificial Intelligence

[0166] Program implementation overview

[0167] Input and recording of target data

[0168] Users input their daily production targets into their user terminals. For example, within the production system, an administrator might set a target of "assembling 1,000 units of parts today." This data is immediately sent to the server and recorded in the database.

[0169] Data collection and cleansing

[0170] The server collects performance data (e.g., number of completed tasks and working hours) from the production system in real time. It then cleanses the collected data, removing duplicates and erroneous entries. A data cleaner class is used for this cleansing.

[0171] Setting evaluation criteria

[0172] Generative artificial intelligence (AI) sets evaluation criteria based on past evaluation data, industry standards, and organizational policies. These established evaluation criteria include specific indicators for assessing the degree of goal achievement.

[0173] Evaluation of goal achievement

[0174] The server uses generative artificial intelligence to analyze production performance data and evaluate the degree of achievement. For example, if the set target is 1000 units and the actual result is 950 units, the achievement score will be calculated as 95%. Furthermore, the generative artificial intelligence also generates feedback comments based on the evaluation results.

[0175] Provide feedback

[0176] The evaluation results and feedback comments are sent from the server to the user's terminal. The user's terminal displays this feedback, which the administrator can use to identify areas for improvement and set goals for the future.

[0177] Hardware and software used

[0178] User terminal: A device used to input production targets and check feedback (e.g., PC, tablet).

[0179] Server: Hosts databases and generative artificial intelligence, performing aggregation, cleansing, evaluation, and feedback generation.

[0180] Database: SQL database, etc., used to store and manage target data and actual data.

[0181] Generative artificial intelligence: An AI system used to analyze past data and automatically generate evaluation criteria.

[0182] Specific examples and prompt statements

[0183] Specific example

[0184] Target data: The target is to assemble 1000 units of parts.

[0185] Performance data: Achieved 950 units.

[0186] Example of a prompt

[0187] "Robot ID 'robot_001' was set to achieve a production target of 1000 units today. Today's actual production is 950 units. Please generate a progress report and feedback based on this information."

[0188] As described above, the system automates the goal management system and provides objective and fair evaluations. Managers can efficiently receive feedback and use it to set future goals.

[0189] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0190] Step 1:

[0191] The user enters their production target into the terminal. For example, they might enter a specific target such as "assemble 1000 units of parts today" and send that data. The input is production target data, and the output is target data recorded by the server.

[0192] Step 2:

[0193] The server receives target data sent by the user and records it in the database. The input is the received target data, and the output is the target data stored in the database.

[0194] Step 3:

[0195] The server collects performance data from the production system in real time. This performance data includes the number of tasks completed, the time taken, and the accuracy of each task. The input is the collected performance data, and the output is the raw performance data.

[0196] Step 4:

[0197] The server cleanses the collected data. This process includes removing duplicate data, correcting erroneous data, and resolving format inconsistencies. Data cleansing improves the reliability of the data. The input is raw historical data, and the output is cleansed historical data.

[0198] Step 5:

[0199] The server uses generative artificial intelligence to set evaluation criteria. These criteria include numerical indicators based on data such as past evaluation data, industry standards, and organizational policies. The input is past evaluation data and industry standards, and the output is the set evaluation criteria.

[0200] Step 6:

[0201] The server uses generative artificial intelligence to analyze performance data based on predefined evaluation criteria. For example, if 950 units are achieved against a target of 1000 units, the achievement score is calculated as 95%. The input is cleansed performance data and evaluation criteria, and the output is the achievement score.

[0202] Step 7:

[0203] The server uses generative artificial intelligence to generate feedback comments. Based on the achievement score, it automatically generates comments that provide specific areas for improvement and help in setting future goals. For example, it might generate comments such as, "Achievement level 95%. The goal was not reached, but the work accuracy was high." The input is the achievement score, and the output is the feedback comment.

[0204] Step 8:

[0205] The server sends the evaluation results and feedback comments to the user's terminal. The administrator checks the results on the terminal and uses them to set goals for the next time and consider areas for improvement. The input is the evaluation results and feedback comments, and the output is the feedback information displayed on the user's terminal.

[0206] The above processing steps enable the automation of the evaluation process and ensure objective and fair evaluations. Managers can efficiently receive feedback and use it to set future goals.

[0207] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0208] This invention combines a system in which the user inputs target data and the degree of goal achievement is objectively evaluated by a generative artificial intelligence system with an emotion engine to recognize the user's emotions and reflect them in the feedback. This allows for objective and fair evaluation, as well as more effective feedback that takes into account the user's emotional state.

[0209] User goal input and recording

[0210] Users input annual, quarterly, and monthly target data through their work terminals. For example, a sales staff member might input a specific target such as "Achieve a sales target of 5 million yen in Q1." The target data entered by the user is immediately sent to the server and recorded in the database.

[0211] Data collection and cleansing

[0212] The server periodically collects target data submitted by users and stores it in a database. Since the collected data may include duplicates or inconsistent formats, the server cleanses this data. The cleansing process involves removing duplicate data, correcting inconsistent data, and eliminating noisy data.

[0213] Setting evaluation criteria

[0214] The server uses generative artificial intelligence to set evaluation criteria. The generative AI receives input such as the organization's past evaluation data, industry standards, and organizational policies. Based on this data, the generative AI performs analysis and automatically generates unified evaluation criteria. For example, the evaluation criteria for the sales department might include metrics such as sales targets, number of contracts, and customer satisfaction.

[0215] Evaluation of goal achievement

[0216] The server evaluates the user's achievement of their goals based on the set evaluation criteria. During the evaluation process, the generative artificial intelligence analyzes the user's goal data and calculates an achievement score. In addition to the score, the generative artificial intelligence also automatically generates feedback comments. For example, if a user achieves 4.5 million yen against a sales target of 5 million yen, a score of 90% achievement is calculated, and a comment such as "Although the target was slightly missed, the sales effort was remarkable" is generated.

[0217] Emotion recognition by an emotion engine

[0218] A distinctive feature of this invention is the addition of an emotion engine. The server inputs text data, voice data, facial expression data, etc., when the user enters goal data or receives feedback into the emotion engine. The emotion engine analyzes this data and recognizes the user's emotional state (for example, high motivation or signs of stress).

[0219] Generating and providing feedback

[0220] After the evaluation results are generated, the server generates feedback comments that reflect the emotional data obtained from the emotion engine. For example, if the user is feeling stressed, specific advice such as, "When setting goals next time, it would be good to be mindful of stress management," will be added. This feedback is sent to the user's device along with the evaluation score.

[0221] Specific example

[0222] Case Study A: Sato's Evaluation Process in the Sales Department

[0223] 1. Target Input: Sato inputs "Achieve a sales target of 5 million yen in Q1" into the terminal.

[0224] 2. Data Collection and Cleansing: The server collects the target data sent from Sato and cleanses away any unnecessary data.

[0225] 3. Setting Evaluation Criteria: The server uses generative artificial intelligence to set unified evaluation criteria based on past evaluation data and industry standards.

[0226] 4. Evaluation of Goal Achievement: The generative artificial intelligence analyzes Sato's sales performance (e.g., 4.5 million yen) and calculates an achievement score of 90%. It also generates feedback comments.

[0227] 5. Emotion Recognition: The server uses an emotion engine to recognize Sato's emotional state when receiving feedback. For example, if it determines that Sato is stressed, it adds appropriate advice.

[0228] 6. Providing Feedback: The server sends feedback comments reflecting the evaluation results and emotions to Sato's terminal, and Sato checks the results on his terminal.

[0229] This system not only ensures that evaluations are conducted based on objective criteria that eliminate subjectivity, but also provides personalized feedback that takes into account the user's emotional state, helping to maintain user motivation and manage stress.

[0230] The following describes the processing flow.

[0231] Step 1:

[0232] Users use a terminal to input their work objectives. Specifically, they input goals and numerical targets that must be achieved by the end of the period (for example, "Achieve a sales target of 5 million yen in Q1").

[0233] Step 2:

[0234] The terminal sends the entered target data to the server. A secure communication protocol is used for transmission, and the target data is immediately stored on the server.

[0235] Step 3:

[0236] The server records the received target data in a database. The database also stores metadata such as the date and time and user ID.

[0237] Step 4:

[0238] The server periodically collects all target data from the database and performs a cleansing process. Specifically, this involves removing duplicate data, correcting inconsistent data, and eliminating noisy data.

[0239] Step 5:

[0240] Based on the cleansed data, the server requests the generative artificial intelligence to set evaluation criteria. The server inputs industry standards, past evaluation data, and the organization's evaluation policies into the generative artificial intelligence.

[0241] Step 6:

[0242] Generative artificial intelligence analyzes input data and generates unified evaluation criteria for assessing goal achievement. The generated evaluation criteria are returned to the server and stored.

[0243] Step 7:

[0244] The server applies evaluation criteria generated by generative artificial intelligence to the cleansed target data to assess the user's degree of goal achievement. Specifically, it calculates a score by comparing the user's performance data (e.g., end-of-period sales performance) with the evaluation criteria.

[0245] Step 8:

[0246] Generative artificial intelligence automatically generates feedback comments in addition to achievement scores. For example, it might generate a comment such as, "Although the target was slightly missed, the sales efforts were commendable."

[0247] Step 9:

[0248] The server incorporates the user's emotional state, as analyzed by the emotion engine, into the feedback comments obtained from the generative artificial intelligence. For example, if the user is feeling stressed, this fact is added to the feedback comments.

[0249] Step 10:

[0250] The emotion engine analyzes text data, voice data, and facial expression data when the user enters goal data or receives feedback, and recognizes the user's emotional state. The recognized emotional data is then sent to the server.

[0251] Step 11:

[0252] The server sends the evaluation results and sentiment data to the user's device. A secure communication protocol is used for transmission.

[0253] Step 12:

[0254] Users use their devices to view evaluation results and feedback comments. For example, they might receive specific feedback such as, "You fell slightly short of your goal, but your sales efforts were commendable. When setting your next goal, it would be beneficial to focus on stress management."

[0255] (Example 2)

[0256] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0257] Conventional goal achievement evaluation systems are limited to objectively evaluating a user's goal achievement level and are unable to provide feedback that takes into account the user's emotional state. As a result, it has been difficult to properly manage the user's motivation and stress levels. This invention aims to solve these problems by not only evaluating the user's goal achievement level but also recognizing the user's emotional state using an emotion engine and providing feedback based on that.

[0258] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0259] In this invention, the server includes means for receiving target data from the user, means for collecting the target data and recording it in a database, means for cleansing the collected target data, means for setting evaluation criteria using generative artificial intelligence, means for evaluating the degree of achievement of the target data based on the evaluation criteria, means for generating feedback comments based on the evaluation results of the target data, means for recognizing the user's emotions using an emotion engine, means for adjusting the feedback comments based on the emotion data, and means for providing feedback to the user on the evaluation results of the target data and the feedback comments based on the emotion data. This makes it possible not only to objectively evaluate the user's degree of goal achievement but also to provide effective feedback that takes into account the user's emotional state.

[0260] "Target data" refers to data that users set as achievement goals on an annual, quarterly, or monthly basis.

[0261] A "user" refers to the entity that uses this system to set goals and receive feedback.

[0262] A "server" refers to a computer system that collects, cleanses, sets evaluation criteria, assesses goal achievement, recognizes emotions, and generates and provides feedback.

[0263] A "database" is a storage system for saving collected target data and cleansed data.

[0264] "Cleaning" refers to the process of correcting data duplication and inconsistencies and removing noisy data.

[0265] "Generative artificial intelligence" refers to an artificial intelligence system that automatically generates evaluation criteria based on input data, calculates scores, and creates feedback comments.

[0266] "Evaluation criteria" refers to a set of metrics set based on an organization's past evaluation data, industry standards, and organizational policies.

[0267] The "achievement score" is a numerical indicator that shows the degree to which a user has achieved their set goals.

[0268] A "feedback comment" is a comment created using generative artificial intelligence and an emotion engine, containing evaluation results and advice for the user.

[0269] An "emotion engine" refers to an analytical system that recognizes the user's emotional state and reflects it in the feedback comments.

[0270] "Emotional data" refers to data that indicates the emotional state of a user when they input goal data or receive feedback.

[0271] This invention combines a system in which the user inputs target data and the degree of goal achievement is objectively evaluated by a generative artificial intelligence system with an emotion engine to recognize the user's emotions and reflect them in the feedback. This allows for objective and fair evaluation, as well as more effective feedback that takes into account the user's emotional state. The following describes a specific embodiment of this system.

[0272] User goal input and recording

[0273] Users use work terminals to input annual, quarterly, and monthly target data. For example, a sales staff member might input a specific target such as "Achieve a sales target of 5 million yen in Q1." The entered target data is immediately sent to the server and recorded in the database.

[0274] Data collection and cleansing

[0275] The server periodically collects target data submitted by users and stores it in a database. Since the collected data may include duplicates or inconsistently formatted data, the server cleanses this data. During the cleansing process, Apache Spark is used to remove duplicate data, correct inconsistent data, and eliminate noise.

[0276] Setting evaluation criteria

[0277] The server uses generative artificial intelligence (for example, OpenAI®'s GPT-4®) to set evaluation criteria. The generative AI receives input such as the organization's past evaluation data, industry standards, and organizational policies. Based on this data, the generative AI performs analysis and automatically generates unified evaluation criteria. For example, evaluation criteria for the sales department might include metrics such as sales targets, number of contracts, and customer satisfaction.

[0278] Evaluation of goal achievement

[0279] The server evaluates the user's achievement of their goals based on the set evaluation criteria. During the evaluation process, the generative artificial intelligence analyzes the user's goal data and calculates an achievement score. In addition to the score, the generative AI also automatically generates feedback comments. For example, if a user achieves 4.5 million yen against a sales target of 5 million yen, a score of 90% achievement is calculated, and a comment such as "Although the target was slightly missed, the sales effort was remarkable" is generated.

[0280] Emotion Recognition by Emotion Engine

[0281] As a characteristic part of the present invention, an emotion engine is added. When the user inputs target data or receives feedback, the server inputs text data, voice data, expression data, etc. into the emotion engine. The emotion engine (for example, Tone Analyzer of IBM Watson (registered trademark)) analyzes these data and recognizes the user's emotional state (for example, the level of motivation or signs of stress).

[0282] Generation and Provision of Feedback

[0283] After the evaluation result is generated, the server generates feedback comments that reflect the emotion data obtained from the emotion engine. For example, when the user is feeling stressed, specific advice such as "It would be good to proceed with stress management in mind when setting goals next time" is added. This feedback is sent to the user's terminal together with the evaluation score. The user checks the feedback through the business terminal.

[0284] Specific Example

[0285] Case A: Evaluation Process for Staff in the Sales Department

[0286] 1. Goal Input: The staff in the sales department inputs "Achieve a sales target of 5 million yen in Q1" into the terminal.

[0287] 2. Data Collection and Cleansing: The server collects the input target data and uses Apache Spark to cleanse unnecessary data.

[0288] 3. Setting of Evaluation Criteria: The server uses generative artificial intelligence (GPT-4 of OpenAI) to set unified evaluation criteria based on past evaluation data and industry standards.

[0289] 4. Evaluation of Goal Achievement: The generative artificial intelligence analyzes the staff's sales performance (e.g., 4.5 million yen) and calculates an achievement score of 90%. It also generates feedback comments.

[0290] 5. Emotion Recognition: The server uses an emotion engine (IBM Watson's Tone Analyzer) to recognize the emotional state of staff members when they receive feedback. For example, if it is determined that a staff member is stressed, appropriate advice will be added.

[0291] 6. Providing Feedback: The server sends feedback comments reflecting the evaluation results and emotions to the staff member's terminal, and the staff member checks the results on their terminal.

[0292] This system not only ensures that evaluations are conducted based on objective criteria that eliminate subjectivity, but also provides personalized feedback that takes into account the user's emotional state, helping to maintain user motivation and manage stress.

[0293] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0294] Step 1: User goal input and recording

[0295] Users use their work terminals to input annual, quarterly, and monthly target data. For example, they might input a target such as "Achieve a sales target of 5 million yen in Q1."

[0296] The terminal immediately sends the input target data to the server. The input at this time is the user's target data, and the output is the data sent to the server.

[0297] The server records the received target data in the database. This ensures that the user's target data is securely stored.

[0298] Step 2: Data Collection and Cleansing

[0299] The server periodically collects unprocessed target data from the database. The input is raw data from the database, and the output is the collected target data.

[0300] The server uses Apache Spark to clean the collected data. Specifically, it performs duplicate data removal, inconsistent data correction, and noise data elimination. The input is the collected target data, and the output is the cleaned data.

[0301] Step 3: Setting of evaluation criteria

[0302] The server uses generative artificial intelligence (GPT-4 of OpenAI) to set evaluation criteria. The input is past evaluation data, industry standards, and organizational policies, and the output is the set evaluation criteria.

[0303] The server inputs these data into generative artificial intelligence for analysis. The generative artificial intelligence automatically generates unified evaluation criteria.

[0304] Step 4: Evaluation of goal achievement

[0305] The server evaluates the user's goal achievement based on the set evaluation criteria. The input is the user's target data and the evaluation criteria, and the output is the achievement score.

[0306] The generative artificial intelligence analyzes the user's target data and calculates the achievement score. In addition to the score, it also generates feedback comments. For example, it generates comments such as "It slightly missed the goal, but the sales efforts were remarkable."

[0307] Step 5: Emotion recognition

[0308] The server uses an emotion engine (IBM Watson's Tone Analyzer) to recognize the user's emotions. Inputs include text data, voice data, and facial expression data when the user enters target data or receives feedback, and output is emotion data.

[0309] The emotion engine analyzes this data to determine the user's motivation and signs of stress.

[0310] Step 6: Generating and providing feedback

[0311] The server generates feedback comments based on the evaluation results and sentiment data. The input is the evaluation results and sentiment data, and the output is the feedback comments.

[0312] The server adds specific advice such as, "Next time you set your goals, it would be a good idea to keep stress management in mind."

[0313] Step 7: Displaying user feedback

[0314] The server sends feedback comments and achievement scores to the user's device. The input is the generated feedback comments and achievement scores, and the output is the data sent to the user's device.

[0315] The device displays received feedback comments and achievement scores to the user. This allows the user to understand their progress toward their goals and areas for improvement.

[0316] (Application Example 2)

[0317] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0318] In evaluating the performance of factory robots, conventional methods are prone to subjective elements and have difficulty providing appropriate feedback that takes into account the robot's operating state and signs of internal stress. This can lead to problems such as decreased production efficiency and premature robot degradation.

[0319] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for receiving target data from the user, means for collecting the target data and recording it in a database, means for cleansing the collected target data, means for setting evaluation criteria using generative artificial intelligence, means for evaluating the degree of achievement of the target data based on the evaluation criteria, means for analyzing the evaluation results based on the evaluation criteria and the robot's operation data, and means for recognizing the emotional state using an emotion engine, and means for generating feedback that reflects the emotional data and providing it to the user. This makes it possible to objectively evaluate the performance of the factory robot and provide appropriate feedback.

[0320] "Target data" refers to data that shows specific numerical values ​​and action plans that users aim to achieve.

[0321] A "user" is an individual or organization that uses this system to set goals and has their achievement evaluated.

[0322] A "database" is a storage system where collected data is stored, enabling data management and retrieval.

[0323] "Data cleansing" is the process of removing duplicates and inconsistencies from collected data and organizing it.

[0324] "Generative artificial intelligence" is an AI technology that automatically generates new evaluation criteria based on past data and standards, and performs analysis.

[0325] "Evaluation criteria" are standards for objectively evaluating the user's degree of goal achievement, and are set by generative artificial intelligence.

[0326] "Achievement level" is a measure that indicates the actual degree to which results have been achieved in relation to the goals set by the user.

[0327] "Evaluation results" refer to data including the achievement score calculated by the generative artificial intelligence after analyzing the target data, and feedback comments.

[0328] An "emotion engine" is a technology that analyzes and recognizes a user's emotional state from text and audio data.

[0329] "Emotional data" refers to data that indicates the user's emotional state, as analyzed by the emotion engine.

[0330] "Feedback" refers to comments and advice provided to users based on evaluation results and sentiment data.

[0331] "Robot motion data" refers to detailed motion data collected while a factory robot is in operation, including error states and operational efficiency.

[0332] The system for realizing this invention includes the following hardware and software.

[0333] hardware

[0334] Factory robots: Robots used in production processes (e.g., typical articulated robots).

[0335] Server: A server that performs data processing, storage, and analysis.

[0336] Smartphone or tablet: A device used by the administrator for operation.

[0337] software

[0338] Generative AI model: AI software (e.g., OpenAI GPT-4) that automatically generates evaluation criteria from input data and produces achievement evaluations and feedback comments.

[0339] Emotion engine: Software that analyzes the emotional state of users or robots (e.g., IBM Watson Tone Analyzer).

[0340] Database: A database for storing target data and evaluation data (e.g., MySQL®).

[0341] Cleansing tool: A tool used to cleanse collected data (e.g., Apache NiFi).

[0342] System program

[0343] User goal input and recording

[0344] Users (administrators) input production targets for factory robots from their smartphones or tablets. For example, they input target data such as "produce 5,000 products per month," and this data is immediately sent to the server and recorded in the database.

[0345] Data collection and cleansing

[0346] The server collects real-time operation data transmitted from factory robots and stores it in a database. The collected data is then cleansed using a cleansing tool (Apache NiFi) to remove inconsistencies and duplicates, ensuring it is in a tidier state.

[0347] Setting evaluation criteria

[0348] The server uses a generative AI model (OpenAI GPT-4) to automatically generate evaluation criteria based on past evaluation data and industry standards. This ensures that unified evaluation criteria are established.

[0349] Evaluation of goal achievement

[0350] The server uses a generation AI model to analyze the input target data and actual data, and calculates an achievement score. Furthermore, it automatically generates feedback comments and compiles them into an evaluation result.

[0351] Emotion recognition by an emotion engine

[0352] The server uses an emotion engine (IBM Watson Tone Analyzer) to analyze the robot's motion data for signs of stress and errors, and recognizes its emotional state.

[0353] Generating and providing feedback

[0354] After the evaluation results are generated, the server generates feedback comments that reflect the emotional data obtained by the emotion engine. These feedback comments, along with the achievement score, are sent to the administrator's smartphone or tablet. The administrator can then review this feedback and consider measures to improve the robot's performance.

[0355] Specific example

[0356] If factory robot A is set to produce 5,000 products per month, but actually produces 4,800, the generating AI model will evaluate the achievement as 90% and generate a feedback comment. Additionally, the emotion engine analyzes the robot's operation data and incorporates any signs of stress or errors observed during operation into the feedback.

[0357] Example of a prompt

[0358] Factory robot A has a target of producing 5,000 products per month. It actually produced 4,800 products. Generate an evaluation of its achievement and feedback. Also, detect signs of stress and errors and provide feedback based on these.

[0359] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0360] Step 1:

[0361] The user uses a device (smartphone or tablet) to input the production target for the factory robot. For example, they might enter a specific number such as "produce 5,000 products per month." The entered target data is immediately sent to the server. Input: Production target data (e.g., 5,000 units), Output: Target data sent to the server.

[0362] Step 2:

[0363] The server records the target data submitted by the user in a database. The recorded data is structured and used for the following processing: Input: Submitted target data, Output: Target data stored in the database.

[0364] Step 3:

[0365] Factory robots transmit actual production data (performance data) to a server in real time. For example, they send data such as "4800 products were produced." Input: Robot performance data, Output: Performance data transmitted to the server.

[0366] Step 4:

[0367] The server collects historical data and uses a cleansing tool (Apache NiFi) to remove duplicates and inconsistencies. This improves the purity of the data. Input: Collected historical data, Output: Cleansed data.

[0368] Step 5:

[0369] The server uses a generated AI model (OpenAI GPT-4) to set evaluation criteria based on historical evaluation data and industry standards. This enables analysis based on these criteria. Input: Historical evaluation data, industry standard data; Output: Set evaluation criteria.

[0370] Step 6:

[0371] The server uses an AI model to analyze the input target and performance data and calculate an achievement score. Furthermore, it automatically generates feedback comments. Input: Evaluation criteria, target data, performance data; Output: Achievement score and feedback comments.

[0372] Step 7:

[0373] The server uses an emotion engine (IBM Watson Tone Analyzer) to detect signs of stress and errors from the robot's motion data and recognize its emotional state. Input: Robot motion data, Output: Recognized emotion data.

[0374] Step 8:

[0375] The server incorporates emotional data obtained from the emotion engine and generates feedback based on the achievement score. Specifically, if there are signs of stress, it adds advice such as, "It would be good to aim for more realistic numbers for your next goal." Input: Emotional data, achievement score, feedback comment; Output: Revised feedback comment.

[0376] Step 9:

[0377] The server sends the final feedback comments and achievement score to the administrator's device (smartphone or tablet). The administrator can review this and use it to improve the robot's performance. Input: Revised feedback comments, achievement score; Output: Feedback and score provided to the administrator's device.

[0378] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0379] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0380] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0381] [Second Embodiment]

[0382] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0383] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0384] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0385] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0386] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0387] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0388] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0389] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0390] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0391] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0392] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0393] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0394] This invention relates to a system that automates the evaluation of management by objectives (MBO) and ensures objectivity and fairness. The system performs a series of processes in which the user inputs goal data, a generative artificial intelligence evaluates the degree of goal achievement based on evaluation criteria, and provides feedback on the results.

[0395] User goal input and recording

[0396] Users input annual, quarterly, and monthly target data through their work terminals. For example, a sales staff member might input a specific target such as "Achieve a sales target of 5 million yen in Q1." The target data entered by the user is immediately sent to the server and recorded in the database.

[0397] Data collection and cleansing

[0398] The server periodically collects target data submitted by users and stores it in a database. Since the collected data may include duplicates or inconsistent formats, the server cleanses this data. The cleansing process involves removing duplicate data, correcting inconsistent data, and eliminating noisy data.

[0399] Setting evaluation criteria

[0400] The server uses generative artificial intelligence to set evaluation criteria. The generative AI receives input such as the organization's past evaluation data, industry standards, and organizational policies. Based on this data, the generative AI performs analysis and automatically generates unified evaluation criteria. For example, the evaluation criteria for the sales department might include metrics such as sales targets, number of contracts, and customer satisfaction.

[0401] Evaluation of goal achievement

[0402] The server evaluates the user's achievement of their goals based on the set evaluation criteria. During the evaluation process, the generative artificial intelligence analyzes the user's goal data and calculates an achievement score. In addition to the score, the generative artificial intelligence also automatically generates feedback comments. For example, if a user achieves 4.5 million yen against a sales target of 5 million yen, a score of 90% achievement is calculated, and a comment such as "Although the target was slightly missed, the sales effort was remarkable" is generated.

[0403] Provide feedback

[0404] After the evaluation results are generated, the server sends them to the user's device. The user can then view the evaluation score and feedback comments on their device. This feedback includes not only numerical data on achievement but also specific areas for improvement and advice for setting future goals.

[0405] Specific example

[0406] Case Study A: Sato's Evaluation Process in the Sales Department

[0407] 1. Target Input: Sato inputs "Achieve a sales target of 5 million yen in Q1" into the terminal.

[0408] 2. Data Collection and Cleansing: The server collects the target data sent from Sato and cleanses away any unnecessary data.

[0409] 3. Setting Evaluation Criteria: The server uses generative artificial intelligence to set unified evaluation criteria based on past evaluation data and industry standards.

[0410] 4. Evaluation of Goal Achievement: The generative artificial intelligence analyzes Sato's sales performance (e.g., 4.5 million yen) and calculates an achievement score of 90%. It also generates feedback comments.

[0411] 5. Providing feedback: The server sends the evaluation results and feedback comments to Sato's terminal, and Sato checks the results on his terminal.

[0412] This system ensures that evaluations are conducted based on objective criteria, eliminating subjectivity and resulting in fair and unbiased assessments. Furthermore, users receive specific feedback and guidance for setting future goals.

[0413] The following describes the processing flow.

[0414] Step 1:

[0415] Users use a terminal to input their work objectives. Specifically, they input goals and numerical targets that must be achieved by the end of the period (for example, "Achieve a sales target of 5 million yen in Q1").

[0416] Step 2:

[0417] The terminal sends the entered target data to the server. A secure communication protocol is used for transmission, and the target data is immediately stored on the server.

[0418] Step 3:

[0419] The server records the received target data in a database. The database also stores metadata such as the date and time and user ID.

[0420] Step 4:

[0421] The server periodically collects all target data from the database and performs a cleansing process. Specifically, this involves removing duplicate data, correcting inconsistent data, and eliminating noisy data.

[0422] Step 5:

[0423] Based on the cleansed data, the server requests the generative artificial intelligence to set evaluation criteria. The server inputs industry standards, past evaluation data, and the organization's evaluation policies into the generative artificial intelligence.

[0424] Step 6:

[0425] Generative artificial intelligence analyzes input data and generates unified evaluation criteria for assessing goal achievement. The generated evaluation criteria are returned to the server and stored.

[0426] Step 7:

[0427] The server applies evaluation criteria generated by generative artificial intelligence to the cleansed target data to assess the user's degree of goal achievement. Specifically, it calculates a score by comparing the user's performance data (e.g., end-of-period sales performance) with the evaluation criteria.

[0428] Step 8:

[0429] Generative artificial intelligence automatically generates feedback comments in addition to achievement scores. For example, it might generate a comment such as, "Although the target was slightly missed, the sales efforts were commendable."

[0430] Step 9:

[0431] The server sends the evaluation results and feedback comments to the user's device. A secure communication protocol is used for transmission.

[0432] Step 10:

[0433] Users use their devices to view evaluation results and feedback comments. This allows users to understand their own performance and gain specific guidance for setting future goals.

[0434] (Example 1)

[0435] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0436] Traditional management by objectives (MBO) systems suffer from problems such as subjectivity and lack of fairness in evaluations, and inconsistency in evaluation criteria. This can lead to a lack of appropriate feedback, hindering employee motivation and performance improvement. Furthermore, the evaluation process is complex and time-consuming, placing a significant burden on managers. This invention aims to solve these problems and provide a system that enables objective and efficient evaluation.

[0437] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0438] In this invention, the server includes means for receiving target data from a user, means for collecting the target data and recording it in a database, means for cleansing the collected target data, means for setting evaluation criteria using generative artificial intelligence, means for evaluating the degree of achievement of the target data based on the evaluation criteria, means for generating feedback comments based on the degree of achievement, and means for providing feedback to the user on the evaluation results and feedback comments of the target data. This ensures objectivity and fairness in the evaluation and enables an efficient evaluation process.

[0439] "Target data" refers to specific business goals that users enter on an annual, quarterly, or monthly basis.

[0440] A "user" refers to an employee of a company or organization who uses the system to input target data and receives evaluation results.

[0441] "Terminal" refers to computers, mobile devices, and other devices that users use to input target data or check evaluation results.

[0442] A "server" refers to a central computer system that collects and stores target data sent by users, performs data cleansing and analysis, sets evaluation criteria, assesses achievement, and generates feedback comments.

[0443] A "database" refers to a data storage system located on or outside a server, used to store target data, historical evaluation data, industry standards, organizational policies, and other similar information.

[0444] "Cleansing" refers to the data preparation process that corrects duplicates and format inconsistencies in the collected target data and eliminates noisy data.

[0445] "Generative artificial intelligence" refers to artificial intelligence technology that automatically generates evaluation criteria and creates evaluation scores and feedback comments based on an organization's past evaluation data, industry standards, and organizational policies.

[0446] "Evaluation criteria" refers to indicators set by generative artificial intelligence that serve as standards for objectively evaluating the degree of goal achievement.

[0447] "Achievement score" refers to a numerical representation of the degree to which a user has achieved their goals.

[0448] "Feedback comments" refer to comments automatically generated by a generative artificial intelligence system based on the user's achievement score, regarding their progress toward achieving their goals.

[0449] This invention relates to a system that automates the evaluation of management by objectives (MBO) and ensures objectivity and fairness. The system performs a series of processes in which the user inputs goal data from a work terminal, the data is collected and cleansed, evaluation criteria are set using generative artificial intelligence, the degree of goal achievement is evaluated, and the results are fed back to the user.

[0450] Users first use their work terminals to input specific target data on an annual, quarterly, or monthly basis. For example, a user in the sales department might input, "Achieve a sales target of 5 million yen in Q1." This target data is sent to the server in real time and recorded in the server's database. The server periodically collects target data from all users and performs data cleansing. This process removes duplicate data, corrects format inconsistencies, and eliminates noisy data.

[0451] Next, the server uses generative artificial intelligence to collect data such as past evaluation data, industry standards, and organizational policies in order to set evaluation criteria. Based on this data, the generative AI performs analysis and automatically generates unified evaluation criteria. In the sales department, indicators such as sales target achievement rate, number of contracts, and customer satisfaction are included in the evaluation criteria.

[0452] The server analyzes the user's target data and actual performance data based on the set evaluation criteria and calculates an achievement score. For example, if a user achieves 4.5 million yen against a sales target of 5 million yen, the achievement score would be calculated as 90%. Furthermore, the generative artificial intelligence automatically generates feedback comments based on this evaluation result. Specifically, comments such as "Although the target was slightly missed, the sales effort was remarkable" are generated.

[0453] After the evaluation results and feedback comments are generated, the server sends them to the user's device. The user can then review the received evaluation results and feedback comments on their device and receive specific advice for setting goals for the next time.

[0454] (Specific example)

[0455] Case Study A: Sato's Evaluation Process in the Sales Department

[0456] 1. Target Input: Sato inputs "Achieve a sales target of 5 million yen in Q1" into the terminal.

[0457] 2. Data Transmission: The terminal transmits target data from Sato to the server in real time. The server records this target data in its database.

[0458] 3. Data Collection and Cleansing: The server collects target data submitted by all users, including Sato, and corrects and removes duplicates, inconsistencies, and noise.

[0459] 4. Setting evaluation criteria: The server collects past evaluation data, industry standards, and organizational policies, and generates evaluation criteria using generative artificial intelligence.

[0460] 5. Evaluation of goal achievement: The generative artificial intelligence analyzes Sato's sales performance (e.g., 4.5 million yen), calculates an achievement score of 90%, and generates feedback comments.

[0461] 6. Providing feedback: The server sends the evaluation results and feedback comments to Sato's terminal, and Sato checks the results on his terminal.

[0462] (Example of a prompt message)

[0463] "Evaluate the achievement level of Sato from the Sales Department against the Q1 target of 5 million yen, and generate feedback comments. Sato's actual sales performance was 4.5 million yen."

[0464] This system eliminates subjectivity and uses objective criteria for evaluation, ensuring fair and unbiased assessments. Furthermore, users receive specific feedback and guidance for setting future goals.

[0465] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0466] Step 1:

[0467] Input and submission of target data

[0468] Users use their work terminals to input annual, quarterly, or monthly target data. For example, a user might input, "Achieve a sales target of 5 million yen in Q1." The entered target data is transmitted from the terminal to the server in real time.

[0469] Input: Target data entered by the user on the device.

[0470] Output: The transmitted target data has arrived at the server.

[0471] Specific operation: The terminal sends the target data entered by the user to the server, and the server verifies the received target data.

[0472] Step 2:

[0473] Recording target data

[0474] The server records the target data received from the terminal in its database. It then sends a response message to the terminal to confirm successful data reception.

[0475] Input: Target data that arrived at the server

[0476] Output: Target data stored in the database

[0477] Specific operation: The server saves the target data to the database and sends a response message to the terminal indicating that the data has been received and saved.

[0478] Step 3:

[0479] Data collection and cleansing

[0480] The server periodically collects target data submitted by all users and stores it in a database. It also performs data cleansing to eliminate duplicates, format inconsistencies, and noise from the collected data.

[0481] Input: Target data submitted by all users

[0482] Output: Cleansed target data

[0483] Specific operation: The server performs data collection tasks at regular intervals, such as at night, and cleanses the data to remove duplicates, inconsistencies, and noise.

[0484] Step 4:

[0485] Setting evaluation criteria

[0486] The server collects data such as past evaluation data, industry standards, and organizational policies, and sets evaluation criteria using generative artificial intelligence.

[0487] Input: Historical evaluation data, industry standards, organizational policy data

[0488] Output: Unified evaluation criteria

[0489] Specific operation: The server retrieves the necessary data from the database, provides it as input to the generative artificial intelligence, and has it perform analysis.

[0490] Step 5:

[0491] Evaluation of goal achievement

[0492] Based on the set evaluation criteria, the server uses generative artificial intelligence to analyze the user's target data and actual performance data, and calculates an achievement score. It also generates feedback comments.

[0493] Input: User's target data, performance data, and set evaluation criteria.

[0494] Output: Achievement score, feedback comments

[0495] Specific operation: The server passes target data and actual data to a generative artificial intelligence, which calculates an achievement score and generates feedback comments.

[0496] Step 6:

[0497] Provide feedback

[0498] The server sends the generated achievement score and feedback comments to the user's terminal. The user checks the received evaluation results and feedback comments on their work terminal.

[0499] Input: Achievement score, feedback comments

[0500] Output: Evaluation results and feedback comments displayed on the user's device.

[0501] Specific operation: The server sends the achievement score and feedback comments to the user's device, and the user reviews the evaluation.

[0502] These steps enable the system to automate the goal management system and ensure objectivity and fairness in evaluations.

[0503] (Application Example 1)

[0504] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0505] In current management by objectives (MBO) systems, the evaluation process is prone to subjectivity, resulting in a lack of objectivity and fairness. Furthermore, particularly in production systems, accurately and efficiently evaluating individual work performance is difficult, requiring significant effort and time for managers to provide appropriate feedback. Therefore, automation and improved accuracy of evaluations are essential.

[0506] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0507] In this invention, the server includes means for receiving target data from a user, means for collecting target data and recording it in a database, means for cleaning the collected target data, means for setting evaluation criteria using generative artificial intelligence, means for evaluating the degree of achievement of the target data based on the evaluation criteria, means for providing feedback on the evaluation results of the target data to the user, means for collecting and cleaning performance data of the production system, means for the generative artificial intelligence to automatically generate evaluation criteria based on the performance data of the production system, means for evaluating the degree of achievement of production targets in the production system and generating achievement scores and feedback comments, and means for providing the evaluation results and feedback comments to the production system administrator. This enables the automation of the evaluation process, realizes objective and fair evaluation, and allows administrators to provide feedback efficiently.

[0508] "Target data" refers to specific numerical values ​​or standards that users aim to achieve in their activities or tasks.

[0509] "Generative artificial intelligence" is an artificial intelligence technology that analyzes collected data and automatically generates evaluation criteria and feedback comments.

[0510] "Evaluation criteria" are standards set by generative artificial intelligence based on past data, industry standards, and organizational policies to evaluate the degree of goal achievement.

[0511] "Goal achievement" is a numerical metric that indicates how well a user or system has achieved the set goals.

[0512] "Feedback comments" are comments generated based on the evaluation results of goal achievement, and include suggestions for improvement and advice for setting future goals for the user.

[0513] A "production system" refers to automated equipment and mechanisms used in factories and manufacturing lines, and is a system that performs specific tasks or manufacturing processes.

[0514] "Performance data" refers to data such as the tasks performed by the production system, the quantities achieved, and the working hours.

[0515] "Cleansing" is the process of removing duplicate or incorrectly formatted data from collected data to improve its quality.

[0516] An "achievement score" is a numerical value that indicates the degree of achievement towards a goal, calculated based on established evaluation criteria.

[0517] A "manager" is a person responsible for monitoring the production system and the achievement of user goals, and for providing appropriate evaluations and feedback.

[0518] This invention relates to a system that automates management by objectives (MBO) and improves objectivity and fairness. This system performs the processes of inputting, collecting, and cleaning goal data, setting evaluation criteria, evaluating achievement, and providing feedback as follows.

[0519] Overall system configuration

[0520] The entire system consists mainly of the following components:

[0521] 1. User terminal

[0522] 2. Server

[0523] 3. Database

[0524] 4. Generative Artificial Intelligence

[0525] Program implementation overview

[0526] Input and recording of target data

[0527] Users input their daily production targets into their user terminals. For example, within the production system, an administrator might set a target of "assembling 1,000 units of parts today." This data is immediately sent to the server and recorded in the database.

[0528] Data collection and cleansing

[0529] The server collects performance data (e.g., number of completed tasks and working hours) from the production system in real time. It then cleanses the collected data, removing duplicates and erroneous entries. A data cleaner class is used for this cleansing.

[0530] Setting evaluation criteria

[0531] Generative artificial intelligence (AI) sets evaluation criteria based on past evaluation data, industry standards, and organizational policies. These established evaluation criteria include specific indicators for assessing the degree of goal achievement.

[0532] Evaluation of goal achievement

[0533] The server uses generative artificial intelligence to analyze production performance data and evaluate the degree of achievement. For example, if the set target is 1000 units and the actual result is 950 units, the achievement score will be calculated as 95%. Furthermore, the generative artificial intelligence also generates feedback comments based on the evaluation results.

[0534] Provide feedback

[0535] The evaluation results and feedback comments are sent from the server to the user's terminal. The user's terminal displays this feedback, which the administrator can use to identify areas for improvement and set goals for the future.

[0536] Hardware and software used

[0537] User terminal: A device used to input production targets and check feedback (e.g., PC, tablet).

[0538] Server: Hosts databases and generative artificial intelligence, performing aggregation, cleansing, evaluation, and feedback generation.

[0539] Database: SQL database, etc., used to store and manage target data and actual data.

[0540] Generative artificial intelligence: An AI system used to analyze past data and automatically generate evaluation criteria.

[0541] Specific examples and prompt statements

[0542] Specific example

[0543] Target data: The target is to assemble 1000 units of parts.

[0544] Performance data: Achieved 950 units.

[0545] Example of a prompt

[0546] "Robot ID 'robot_001' was set to achieve a production target of 1000 units today. Today's actual production is 950 units. Please generate a progress report and feedback based on this information."

[0547] As described above, the system automates the goal management system and provides objective and fair evaluations. Managers can efficiently receive feedback and use it to set future goals.

[0548] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0549] Step 1:

[0550] The user enters their production target into the terminal. For example, they might enter a specific target such as "assemble 1000 units of parts today" and send that data. The input is production target data, and the output is target data recorded by the server.

[0551] Step 2:

[0552] The server receives target data sent by the user and records it in the database. The input is the received target data, and the output is the target data stored in the database.

[0553] Step 3:

[0554] The server collects performance data from the production system in real time. This performance data includes the number of tasks completed, the time taken, and the accuracy of each task. The input is the collected performance data, and the output is the raw performance data.

[0555] Step 4:

[0556] The server cleanses the collected data. This process includes removing duplicate data, correcting erroneous data, and resolving format inconsistencies. Data cleansing improves the reliability of the data. The input is raw historical data, and the output is cleansed historical data.

[0557] Step 5:

[0558] The server uses generative artificial intelligence to set evaluation criteria. These criteria include numerical indicators based on data such as past evaluation data, industry standards, and organizational policies. The input is past evaluation data and industry standards, and the output is the set evaluation criteria.

[0559] Step 6:

[0560] The server uses generative artificial intelligence to analyze performance data based on predefined evaluation criteria. For example, if 950 units are achieved against a target of 1000 units, the achievement score is calculated as 95%. The input is cleansed performance data and evaluation criteria, and the output is the achievement score.

[0561] Step 7:

[0562] The server uses generative artificial intelligence to generate feedback comments. Based on the achievement score, it automatically generates comments that provide specific areas for improvement and help in setting future goals. For example, it might generate comments such as, "Achievement level 95%. The goal was not reached, but the work accuracy was high." The input is the achievement score, and the output is the feedback comment.

[0563] Step 8:

[0564] The server sends the evaluation results and feedback comments to the user's terminal. The administrator checks the results on the terminal and uses them to set goals for the next time and consider areas for improvement. The input is the evaluation results and feedback comments, and the output is the feedback information displayed on the user's terminal.

[0565] The above processing steps enable the automation of the evaluation process and ensure objective and fair evaluations. Managers can efficiently receive feedback and use it to set future goals.

[0566] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0567] This invention combines a system in which the user inputs target data and the degree of goal achievement is objectively evaluated by a generative artificial intelligence system with an emotion engine to recognize the user's emotions and reflect them in the feedback. This allows for objective and fair evaluation, as well as more effective feedback that takes into account the user's emotional state.

[0568] User goal input and recording

[0569] Users input annual, quarterly, and monthly target data through their work terminals. For example, a sales staff member might input a specific target such as "Achieve a sales target of 5 million yen in Q1." The target data entered by the user is immediately sent to the server and recorded in the database.

[0570] Data collection and cleansing

[0571] The server periodically collects target data submitted by users and stores it in a database. Since the collected data may include duplicates or inconsistent formats, the server cleanses this data. The cleansing process involves removing duplicate data, correcting inconsistent data, and eliminating noisy data.

[0572] Setting evaluation criteria

[0573] The server uses generative artificial intelligence to set evaluation criteria. The generative AI receives input such as the organization's past evaluation data, industry standards, and organizational policies. Based on this data, the generative AI performs analysis and automatically generates unified evaluation criteria. For example, the evaluation criteria for the sales department might include metrics such as sales targets, number of contracts, and customer satisfaction.

[0574] Evaluation of goal achievement

[0575] The server evaluates the user's achievement of their goals based on the set evaluation criteria. During the evaluation process, the generative artificial intelligence analyzes the user's goal data and calculates an achievement score. In addition to the score, the generative artificial intelligence also automatically generates feedback comments. For example, if a user achieves 4.5 million yen against a sales target of 5 million yen, a score of 90% achievement is calculated, and a comment such as "Although the target was slightly missed, the sales effort was remarkable" is generated.

[0576] Emotion recognition by an emotion engine

[0577] A distinctive feature of this invention is the addition of an emotion engine. The server inputs text data, voice data, facial expression data, etc., when the user enters goal data or receives feedback into the emotion engine. The emotion engine analyzes this data and recognizes the user's emotional state (for example, high motivation or signs of stress).

[0578] Generating and providing feedback

[0579] After the evaluation results are generated, the server generates feedback comments that reflect the emotional data obtained from the emotion engine. For example, if the user is feeling stressed, specific advice such as, "When setting goals next time, it would be good to be mindful of stress management," will be added. This feedback is sent to the user's device along with the evaluation score.

[0580] Specific example

[0581] Case Study A: Sato's Evaluation Process in the Sales Department

[0582] 1. Target Input: Sato inputs "Achieve a sales target of 5 million yen in Q1" into the terminal.

[0583] 2. Data Collection and Cleansing: The server collects the target data sent from Sato and cleanses away any unnecessary data.

[0584] 3. Setting Evaluation Criteria: The server uses generative artificial intelligence to set unified evaluation criteria based on past evaluation data and industry standards.

[0585] 4. Evaluation of Goal Achievement: The generative artificial intelligence analyzes Sato's sales performance (e.g., 4.5 million yen) and calculates an achievement score of 90%. It also generates feedback comments.

[0586] 5. Emotion Recognition: The server uses an emotion engine to recognize Sato's emotional state when receiving feedback. For example, if it determines that Sato is stressed, it adds appropriate advice.

[0587] 6. Providing Feedback: The server sends feedback comments reflecting the evaluation results and emotions to Sato's terminal, and Sato checks the results on his terminal.

[0588] This system not only ensures that evaluations are conducted based on objective criteria that eliminate subjectivity, but also provides personalized feedback that takes into account the user's emotional state, helping to maintain user motivation and manage stress.

[0589] The following describes the processing flow.

[0590] Step 1:

[0591] Users use a terminal to input their work objectives. Specifically, they input goals and numerical targets that must be achieved by the end of the period (for example, "Achieve a sales target of 5 million yen in Q1").

[0592] Step 2:

[0593] The terminal sends the entered target data to the server. A secure communication protocol is used for transmission, and the target data is immediately stored on the server.

[0594] Step 3:

[0595] The server records the received target data in a database. The database also stores metadata such as the date and time and user ID.

[0596] Step 4:

[0597] The server periodically collects all target data from the database and performs a cleansing process. Specifically, this involves removing duplicate data, correcting inconsistent data, and eliminating noisy data.

[0598] Step 5:

[0599] Based on the cleansed data, the server requests the generative artificial intelligence to set evaluation criteria. The server inputs industry standards, past evaluation data, and the organization's evaluation policies into the generative artificial intelligence.

[0600] Step 6:

[0601] Generative artificial intelligence analyzes input data and generates unified evaluation criteria for assessing goal achievement. The generated evaluation criteria are returned to the server and stored.

[0602] Step 7:

[0603] The server applies evaluation criteria generated by generative artificial intelligence to the cleansed target data to assess the user's degree of goal achievement. Specifically, it calculates a score by comparing the user's performance data (e.g., end-of-period sales performance) with the evaluation criteria.

[0604] Step 8:

[0605] Generative artificial intelligence automatically generates feedback comments in addition to achievement scores. For example, it might generate a comment such as, "Although the target was slightly missed, the sales efforts were commendable."

[0606] Step 9:

[0607] The server incorporates the user's emotional state, as analyzed by the emotion engine, into the feedback comments obtained from the generative artificial intelligence. For example, if the user is feeling stressed, this fact is added to the feedback comments.

[0608] Step 10:

[0609] The emotion engine analyzes text data, voice data, and facial expression data when the user enters goal data or receives feedback, and recognizes the user's emotional state. The recognized emotional data is then sent to the server.

[0610] Step 11:

[0611] The server sends the evaluation results and sentiment data to the user's device. A secure communication protocol is used for transmission.

[0612] Step 12:

[0613] Users use their devices to view evaluation results and feedback comments. For example, they might receive specific feedback such as, "You fell slightly short of your goal, but your sales efforts were commendable. When setting your next goal, it would be beneficial to focus on stress management."

[0614] (Example 2)

[0615] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0616] Conventional goal achievement evaluation systems are limited to objectively evaluating a user's goal achievement level and are unable to provide feedback that takes into account the user's emotional state. As a result, it has been difficult to properly manage the user's motivation and stress levels. This invention aims to solve these problems by not only evaluating the user's goal achievement level but also recognizing the user's emotional state using an emotion engine and providing feedback based on that.

[0617] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0618] In this invention, the server includes means for receiving target data from the user, means for collecting the target data and recording it in a database, means for cleansing the collected target data, means for setting evaluation criteria using generative artificial intelligence, means for evaluating the degree of achievement of the target data based on the evaluation criteria, means for generating feedback comments based on the evaluation results of the target data, means for recognizing the user's emotions using an emotion engine, means for adjusting the feedback comments based on the emotion data, and means for providing feedback to the user on the evaluation results of the target data and the feedback comments based on the emotion data. This makes it possible not only to objectively evaluate the user's degree of goal achievement but also to provide effective feedback that takes into account the user's emotional state.

[0619] "Target data" refers to data that users set as achievement goals on an annual, quarterly, or monthly basis.

[0620] A "user" refers to the entity that uses this system to set goals and receive feedback.

[0621] A "server" refers to a computer system that collects, cleanses, sets evaluation criteria, assesses goal achievement, recognizes emotions, and generates and provides feedback.

[0622] A "database" is a storage system for saving collected target data and cleansed data.

[0623] "Cleaning" refers to the process of correcting data duplication and inconsistencies and removing noisy data.

[0624] "Generative artificial intelligence" refers to an artificial intelligence system that automatically generates evaluation criteria based on input data, calculates scores, and creates feedback comments.

[0625] "Evaluation criteria" refers to a set of metrics set based on an organization's past evaluation data, industry standards, and organizational policies.

[0626] The "achievement score" is a numerical indicator that shows the degree to which a user has achieved their set goals.

[0627] A "feedback comment" is a comment created using generative artificial intelligence and an emotion engine, containing evaluation results and advice for the user.

[0628] An "emotion engine" refers to an analytical system that recognizes the user's emotional state and reflects it in the feedback comments.

[0629] "Emotional data" refers to data that indicates the emotional state of a user when they input goal data or receive feedback.

[0630] This invention combines a system in which the user inputs target data and the degree of goal achievement is objectively evaluated by a generative artificial intelligence system with an emotion engine to recognize the user's emotions and reflect them in the feedback. This allows for objective and fair evaluation, as well as more effective feedback that takes into account the user's emotional state. The following describes a specific embodiment of this system.

[0631] User goal input and recording

[0632] Users use work terminals to input annual, quarterly, and monthly target data. For example, a sales staff member might input a specific target such as "Achieve a sales target of 5 million yen in Q1." The entered target data is immediately sent to the server and recorded in the database.

[0633] Data collection and cleansing

[0634] The server periodically collects target data submitted by users and stores it in a database. Since the collected data may include duplicates or inconsistently formatted data, the server cleanses this data. During the cleansing process, Apache Spark is used to remove duplicate data, correct inconsistent data, and eliminate noise.

[0635] Setting evaluation criteria

[0636] The server uses generative artificial intelligence (for example, OpenAI's GPT-4) to set evaluation criteria. The generative AI receives input such as the organization's past evaluation data, industry standards, and organizational policies. Based on this data, the generative AI performs analysis and automatically generates unified evaluation criteria. For example, evaluation criteria for the sales department might include metrics such as sales targets, number of contracts, and customer satisfaction.

[0637] Evaluation of goal achievement

[0638] The server evaluates the user's achievement of their goals based on the set evaluation criteria. During the evaluation process, the generative artificial intelligence analyzes the user's goal data and calculates an achievement score. In addition to the score, the generative AI also automatically generates feedback comments. For example, if a user achieves 4.5 million yen against a sales target of 5 million yen, a score of 90% achievement is calculated, and a comment such as "Although the target was slightly missed, the sales effort was remarkable" is generated.

[0639] Emotion recognition by an emotion engine

[0640] A distinctive feature of this invention is the addition of an emotion engine. The server inputs text data, voice data, facial expression data, etc., when the user enters goal data or receives feedback into the emotion engine. The emotion engine (for example, IBM Watson's Tone Analyzer) analyzes this data and recognizes the user's emotional state (for example, high motivation or signs of stress).

[0641] Generating and providing feedback

[0642] After the evaluation results are generated, the server generates feedback comments that reflect the emotional data obtained from the emotion engine. For example, if the user is feeling stressed, specific advice such as, "When setting goals next time, it would be good to be mindful of stress management," will be added. This feedback, along with the evaluation score, is sent to the user's terminal. The user checks the feedback through their work terminal.

[0643] Specific example

[0644] Case Study A: Evaluation Process for Sales Department Staff

[0645] 1. Target Input: Sales staff enter "Achieve a sales target of 5 million yen in Q1" into the terminal.

[0646] 2. Data Collection and Cleansing: The server collects the input target data and cleanses unnecessary data using Apache Spark.

[0647] 3. Setting Evaluation Criteria: The server uses generative artificial intelligence (OpenAI's GPT-4) to set unified evaluation criteria based on past evaluation data and industry standards.

[0648] 4. Evaluation of Goal Achievement: The generative artificial intelligence analyzes the staff's sales performance (e.g., 4.5 million yen) and calculates an achievement score of 90%. It also generates feedback comments.

[0649] 5. Emotion Recognition: The server uses an emotion engine (IBM Watson's Tone Analyzer) to recognize the emotional state of staff members when they receive feedback. For example, if it is determined that a staff member is stressed, appropriate advice will be added.

[0650] 6. Providing Feedback: The server sends feedback comments reflecting the evaluation results and emotions to the staff member's terminal, and the staff member checks the results on their terminal.

[0651] This system not only ensures that evaluations are conducted based on objective criteria that eliminate subjectivity, but also provides personalized feedback that takes into account the user's emotional state, helping to maintain user motivation and manage stress.

[0652] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0653] Step 1: User goal input and recording

[0654] Users use their work terminals to input annual, quarterly, and monthly target data. For example, they might input a target such as "Achieve a sales target of 5 million yen in Q1."

[0655] The terminal immediately sends the input target data to the server. The input at this time is the user's target data, and the output is the data sent to the server.

[0656] The server records the received target data in the database. This ensures that the user's target data is securely stored.

[0657] Step 2: Data Collection and Cleansing

[0658] The server periodically collects raw target data from the database. The input is raw data from the database, and the output is the collected target data.

[0659] The server uses Apache Spark to cleanse the collected data. Specifically, it removes duplicate data, corrects inconsistent data, and eliminates noisy data. The input is the collected target data, and the output is the cleansed data.

[0660] Step 3: Setting evaluation criteria

[0661] The server uses generative artificial intelligence (OpenAI's GPT-4) to set evaluation criteria. The inputs are past evaluation data, industry standards, and organizational policies, and the output is the set evaluation criteria.

[0662] The server inputs this data into a generative artificial intelligence (AI) system for analysis. The AI ​​system automatically generates a unified evaluation standard.

[0663] Step 4: Evaluating the degree of goal achievement

[0664] The server evaluates the user's goal achievement level based on the configured evaluation criteria. The input is the user's goal data and evaluation criteria, and the output is the achievement score.

[0665] Generative artificial intelligence analyzes the user's goal data and calculates an achievement score. In addition to the score, it also generates feedback comments. For example, it might generate a comment such as, "You fell slightly short of your goal, but your sales efforts were commendable."

[0666] Step 5: Emotion Recognition

[0667] The server uses an emotion engine (IBM Watson's Tone Analyzer) to recognize the user's emotions. Inputs include text data, voice data, and facial expression data when the user enters target data or receives feedback, and output is emotion data.

[0668] The emotion engine analyzes this data to determine the user's motivation and signs of stress.

[0669] Step 6: Generating and providing feedback

[0670] The server generates feedback comments based on the evaluation results and sentiment data. The input is the evaluation results and sentiment data, and the output is the feedback comments.

[0671] The server adds specific advice such as, "Next time you set your goals, it would be a good idea to keep stress management in mind."

[0672] Step 7: Displaying user feedback

[0673] The server sends feedback comments and achievement scores to the user's device. The input is the generated feedback comments and achievement scores, and the output is the data sent to the user's device.

[0674] The device displays received feedback comments and achievement scores to the user. This allows the user to understand their progress toward their goals and areas for improvement.

[0675] (Application Example 2)

[0676] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0677] In evaluating the performance of factory robots, conventional methods are prone to subjective elements and have difficulty providing appropriate feedback that takes into account the robot's operating state and signs of internal stress. This can lead to problems such as decreased production efficiency and premature robot degradation.

[0678] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for receiving target data from the user, means for collecting the target data and recording it in a database, means for cleansing the collected target data, means for setting evaluation criteria using generative artificial intelligence, means for evaluating the degree of achievement of the target data based on the evaluation criteria, means for analyzing the evaluation results based on the evaluation criteria and the robot's operation data, and means for recognizing the emotional state using an emotion engine, and means for generating feedback that reflects the emotional data and providing it to the user. This makes it possible to objectively evaluate the performance of the factory robot and provide appropriate feedback.

[0679] "Target data" refers to data that shows specific numerical values ​​and action plans that users aim to achieve.

[0680] A "user" is an individual or organization that uses this system to set goals and has their achievement evaluated.

[0681] A "database" is a storage system where collected data is stored, enabling data management and retrieval.

[0682] "Data cleansing" is the process of removing duplicates and inconsistencies from collected data and organizing it.

[0683] "Generative artificial intelligence" is an AI technology that automatically generates new evaluation criteria based on past data and standards, and performs analysis.

[0684] "Evaluation criteria" are standards for objectively evaluating the user's degree of goal achievement, and are set by generative artificial intelligence.

[0685] "Achievement level" is a measure that indicates the actual degree to which results have been achieved in relation to the goals set by the user.

[0686] "Evaluation results" refer to data including the achievement score calculated by the generative artificial intelligence after analyzing the target data, and feedback comments.

[0687] An "emotion engine" is a technology that analyzes and recognizes a user's emotional state from text and audio data.

[0688] "Emotional data" refers to data that indicates the user's emotional state, as analyzed by the emotion engine.

[0689] "Feedback" refers to comments and advice provided to users based on evaluation results and sentiment data.

[0690] "Robot motion data" refers to detailed motion data collected while a factory robot is in operation, including error states and operational efficiency.

[0691] The system for realizing this invention includes the following hardware and software.

[0692] hardware

[0693] Factory robots: Robots used in production processes (e.g., typical articulated robots).

[0694] Server: A server that performs data processing, storage, and analysis.

[0695] Smartphone or tablet: A device used by the administrator for operation.

[0696] software

[0697] Generative AI model: AI software (e.g., OpenAI GPT-4) that automatically generates evaluation criteria from input data and produces achievement evaluations and feedback comments.

[0698] Emotion engine: Software that analyzes the emotional state of users or robots (e.g., IBM Watson Tone Analyzer).

[0699] Database: A database that stores target data and evaluation data (e.g., MySQL).

[0700] Cleansing tool: A tool used to cleanse collected data (e.g., Apache NiFi).

[0701] System program

[0702] User goal input and recording

[0703] Users (administrators) input production targets for factory robots from their smartphones or tablets. For example, they input target data such as "produce 5,000 products per month," and this data is immediately sent to the server and recorded in the database.

[0704] Data collection and cleansing

[0705] The server collects real-time operation data transmitted from factory robots and stores it in a database. The collected data is then cleansed using a cleansing tool (Apache NiFi) to remove inconsistencies and duplicates, ensuring it is in a tidier state.

[0706] Setting evaluation criteria

[0707] The server uses a generative AI model (OpenAI GPT-4) to automatically generate evaluation criteria based on past evaluation data and industry standards. This ensures that unified evaluation criteria are established.

[0708] Evaluation of goal achievement

[0709] The server uses a generation AI model to analyze the input target data and actual data, and calculates an achievement score. Furthermore, it automatically generates feedback comments and compiles them into an evaluation result.

[0710] Emotion recognition by an emotion engine

[0711] The server uses an emotion engine (IBM Watson Tone Analyzer) to analyze the robot's motion data for signs of stress and errors, and recognizes its emotional state.

[0712] Generating and providing feedback

[0713] After the evaluation results are generated, the server generates feedback comments that reflect the emotional data obtained by the emotion engine. These feedback comments, along with the achievement score, are sent to the administrator's smartphone or tablet. The administrator can then review this feedback and consider measures to improve the robot's performance.

[0714] Specific example

[0715] If factory robot A is set to produce 5,000 products per month, but actually produces 4,800, the generating AI model will evaluate the achievement as 90% and generate a feedback comment. Additionally, the emotion engine analyzes the robot's operation data and incorporates any signs of stress or errors observed during operation into the feedback.

[0716] Example of a prompt

[0717] Factory robot A has a target of producing 5,000 products per month. It actually produced 4,800 products. Generate an evaluation of its achievement and feedback. Also, detect signs of stress and errors and provide feedback based on these.

[0718] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0719] Step 1:

[0720] The user uses a device (smartphone or tablet) to input the production target for the factory robot. For example, they might enter a specific number such as "produce 5,000 products per month." The entered target data is immediately sent to the server. Input: Production target data (e.g., 5,000 units), Output: Target data sent to the server.

[0721] Step 2:

[0722] The server records the target data submitted by the user in a database. The recorded data is structured and used for the following processing: Input: Submitted target data, Output: Target data stored in the database.

[0723] Step 3:

[0724] Factory robots transmit actual production data (performance data) to a server in real time. For example, they send data such as "4800 products were produced." Input: Robot performance data, Output: Performance data transmitted to the server.

[0725] Step 4:

[0726] The server collects historical data and uses a cleansing tool (Apache NiFi) to remove duplicates and inconsistencies. This improves the purity of the data. Input: Collected historical data, Output: Cleansed data.

[0727] Step 5:

[0728] The server uses a generated AI model (OpenAI GPT-4) to set evaluation criteria based on historical evaluation data and industry standards. This enables analysis based on these criteria. Input: Historical evaluation data, industry standard data; Output: Set evaluation criteria.

[0729] Step 6:

[0730] The server uses an AI model to analyze the input target and performance data and calculate an achievement score. Furthermore, it automatically generates feedback comments. Input: Evaluation criteria, target data, performance data; Output: Achievement score and feedback comments.

[0731] Step 7:

[0732] The server uses an emotion engine (IBM Watson Tone Analyzer) to detect signs of stress and errors from the robot's motion data and recognize its emotional state. Input: Robot motion data, Output: Recognized emotion data.

[0733] Step 8:

[0734] The server incorporates emotional data obtained from the emotion engine and generates feedback based on the achievement score. Specifically, if there are signs of stress, it adds advice such as, "It would be good to aim for more realistic numbers for your next goal." Input: Emotional data, achievement score, feedback comment; Output: Revised feedback comment.

[0735] Step 9:

[0736] The server sends the final feedback comments and achievement score to the administrator's device (smartphone or tablet). The administrator can review this and use it to improve the robot's performance. Input: Revised feedback comments, achievement score; Output: Feedback and score provided to the administrator's device.

[0737] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0738] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0739] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0740] [Third Embodiment]

[0741] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0742] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0743] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0744] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0745] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0746] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0747] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0748] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0749] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0750] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0751] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0752] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0753] This invention relates to a system that automates the evaluation of management by objectives (MBO) and ensures objectivity and fairness. The system performs a series of processes in which the user inputs goal data, a generative artificial intelligence evaluates the degree of goal achievement based on evaluation criteria, and provides feedback on the results.

[0754] User goal input and recording

[0755] Users input annual, quarterly, and monthly target data through their work terminals. For example, a sales staff member might input a specific target such as "Achieve a sales target of 5 million yen in Q1." The target data entered by the user is immediately sent to the server and recorded in the database.

[0756] Data collection and cleansing

[0757] The server periodically collects target data submitted by users and stores it in a database. Since the collected data may include duplicates or inconsistent formats, the server cleanses this data. The cleansing process involves removing duplicate data, correcting inconsistent data, and eliminating noisy data.

[0758] Setting evaluation criteria

[0759] The server uses generative artificial intelligence to set evaluation criteria. The generative AI receives input such as the organization's past evaluation data, industry standards, and organizational policies. Based on this data, the generative AI performs analysis and automatically generates unified evaluation criteria. For example, the evaluation criteria for the sales department might include metrics such as sales targets, number of contracts, and customer satisfaction.

[0760] Evaluation of goal achievement

[0761] The server evaluates the user's achievement of their goals based on the set evaluation criteria. During the evaluation process, the generative artificial intelligence analyzes the user's goal data and calculates an achievement score. In addition to the score, the generative artificial intelligence also automatically generates feedback comments. For example, if a user achieves 4.5 million yen against a sales target of 5 million yen, a score of 90% achievement is calculated, and a comment such as "Although the target was slightly missed, the sales effort was remarkable" is generated.

[0762] Provide feedback

[0763] After the evaluation results are generated, the server sends them to the user's device. The user can then view the evaluation score and feedback comments on their device. This feedback includes not only numerical data on achievement but also specific areas for improvement and advice for setting future goals.

[0764] Specific example

[0765] Case Study A: Sato's Evaluation Process in the Sales Department

[0766] 1. Target Input: Sato inputs "Achieve a sales target of 5 million yen in Q1" into the terminal.

[0767] 2. Data Collection and Cleansing: The server collects the target data sent from Sato and cleanses away any unnecessary data.

[0768] 3. Setting Evaluation Criteria: The server uses generative artificial intelligence to set unified evaluation criteria based on past evaluation data and industry standards.

[0769] 4. Evaluation of Goal Achievement: The generative artificial intelligence analyzes Sato's sales performance (e.g., 4.5 million yen) and calculates an achievement score of 90%. It also generates feedback comments.

[0770] 5. Providing feedback: The server sends the evaluation results and feedback comments to Sato's terminal, and Sato checks the results on his terminal.

[0771] This system ensures that evaluations are conducted based on objective criteria, eliminating subjectivity and resulting in fair and unbiased assessments. Furthermore, users receive specific feedback and guidance for setting future goals.

[0772] The following describes the processing flow.

[0773] Step 1:

[0774] Users use a terminal to input their work objectives. Specifically, they input goals and numerical targets that must be achieved by the end of the period (for example, "Achieve a sales target of 5 million yen in Q1").

[0775] Step 2:

[0776] The terminal sends the entered target data to the server. A secure communication protocol is used for transmission, and the target data is immediately stored on the server.

[0777] Step 3:

[0778] The server records the received target data in a database. The database also stores metadata such as the date and time and user ID.

[0779] Step 4:

[0780] The server periodically collects all target data from the database and performs a cleansing process. Specifically, this involves removing duplicate data, correcting inconsistent data, and eliminating noisy data.

[0781] Step 5:

[0782] Based on the cleansed data, the server requests the generative artificial intelligence to set evaluation criteria. The server inputs industry standards, past evaluation data, and the organization's evaluation policies into the generative artificial intelligence.

[0783] Step 6:

[0784] Generative artificial intelligence analyzes input data and generates unified evaluation criteria for assessing goal achievement. The generated evaluation criteria are returned to the server and stored.

[0785] Step 7:

[0786] The server applies evaluation criteria generated by generative artificial intelligence to the cleansed target data to assess the user's degree of goal achievement. Specifically, it calculates a score by comparing the user's performance data (e.g., end-of-period sales performance) with the evaluation criteria.

[0787] Step 8:

[0788] Generative artificial intelligence automatically generates feedback comments in addition to achievement scores. For example, it might generate a comment such as, "Although the target was slightly missed, the sales efforts were commendable."

[0789] Step 9:

[0790] The server sends the evaluation results and feedback comments to the user's device. A secure communication protocol is used for transmission.

[0791] Step 10:

[0792] Users use their devices to view evaluation results and feedback comments. This allows users to understand their own performance and gain specific guidance for setting future goals.

[0793] (Example 1)

[0794] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0795] Traditional management by objectives (MBO) systems suffer from problems such as subjectivity and lack of fairness in evaluations, and inconsistency in evaluation criteria. This can lead to a lack of appropriate feedback, hindering employee motivation and performance improvement. Furthermore, the evaluation process is complex and time-consuming, placing a significant burden on managers. This invention aims to solve these problems and provide a system that enables objective and efficient evaluation.

[0796] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0797] In this invention, the server includes means for receiving target data from a user, means for collecting the target data and recording it in a database, means for cleansing the collected target data, means for setting evaluation criteria using generative artificial intelligence, means for evaluating the degree of achievement of the target data based on the evaluation criteria, means for generating feedback comments based on the degree of achievement, and means for providing feedback to the user on the evaluation results and feedback comments of the target data. This ensures objectivity and fairness in the evaluation and enables an efficient evaluation process.

[0798] "Target data" refers to specific business goals that users enter on an annual, quarterly, or monthly basis.

[0799] A "user" refers to an employee of a company or organization who uses the system to input target data and receives evaluation results.

[0800] "Terminal" refers to computers, mobile devices, and other devices that users use to input target data or check evaluation results.

[0801] A "server" refers to a central computer system that collects and stores target data sent by users, performs data cleansing and analysis, sets evaluation criteria, assesses achievement, and generates feedback comments.

[0802] A "database" refers to a data storage system located on or outside a server, used to store target data, historical evaluation data, industry standards, organizational policies, and other similar information.

[0803] "Cleansing" refers to the data preparation process that corrects duplicates and format inconsistencies in the collected target data and eliminates noisy data.

[0804] "Generative artificial intelligence" refers to artificial intelligence technology that automatically generates evaluation criteria and creates evaluation scores and feedback comments based on an organization's past evaluation data, industry standards, and organizational policies.

[0805] "Evaluation criteria" refers to indicators set by generative artificial intelligence that serve as standards for objectively evaluating the degree of goal achievement.

[0806] "Achievement score" refers to a numerical representation of the degree to which a user has achieved their goals.

[0807] "Feedback comments" refer to comments automatically generated by a generative artificial intelligence system based on the user's achievement score, regarding their progress toward achieving their goals.

[0808] This invention relates to a system that automates the evaluation of management by objectives (MBO) and ensures objectivity and fairness. The system performs a series of processes in which the user inputs goal data from a work terminal, the data is collected and cleansed, evaluation criteria are set using generative artificial intelligence, the degree of goal achievement is evaluated, and the results are fed back to the user.

[0809] Users first use their work terminals to input specific target data on an annual, quarterly, or monthly basis. For example, a user in the sales department might input, "Achieve a sales target of 5 million yen in Q1." This target data is sent to the server in real time and recorded in the server's database. The server periodically collects target data from all users and performs data cleansing. This process removes duplicate data, corrects format inconsistencies, and eliminates noisy data.

[0810] Next, the server uses generative artificial intelligence to collect data such as past evaluation data, industry standards, and organizational policies in order to set evaluation criteria. Based on this data, the generative AI performs analysis and automatically generates unified evaluation criteria. In the sales department, indicators such as sales target achievement rate, number of contracts, and customer satisfaction are included in the evaluation criteria.

[0811] The server analyzes the user's target data and actual performance data based on the set evaluation criteria and calculates an achievement score. For example, if a user achieves 4.5 million yen against a sales target of 5 million yen, the achievement score would be calculated as 90%. Furthermore, the generative artificial intelligence automatically generates feedback comments based on this evaluation result. Specifically, comments such as "Although the target was slightly missed, the sales effort was remarkable" are generated.

[0812] After the evaluation results and feedback comments are generated, the server sends them to the user's device. The user can then review the received evaluation results and feedback comments on their device and receive specific advice for setting goals for the next time.

[0813] (Specific example)

[0814] Case Study A: Sato's Evaluation Process in the Sales Department

[0815] 1. Target Input: Sato inputs "Achieve a sales target of 5 million yen in Q1" into the terminal.

[0816] 2. Data Transmission: The terminal transmits target data from Sato to the server in real time. The server records this target data in its database.

[0817] 3. Data Collection and Cleansing: The server collects target data submitted by all users, including Sato, and corrects and removes duplicates, inconsistencies, and noise.

[0818] 4. Setting evaluation criteria: The server collects past evaluation data, industry standards, and organizational policies, and generates evaluation criteria using generative artificial intelligence.

[0819] 5. Evaluation of goal achievement: The generative artificial intelligence analyzes Sato's sales performance (e.g., 4.5 million yen), calculates an achievement score of 90%, and generates feedback comments.

[0820] 6. Providing feedback: The server sends the evaluation results and feedback comments to Sato's terminal, and Sato checks the results on his terminal.

[0821] (Example of a prompt message)

[0822] "Evaluate the achievement level of Sato from the Sales Department against the Q1 target of 5 million yen, and generate feedback comments. Sato's actual sales performance was 4.5 million yen."

[0823] This system eliminates subjectivity and uses objective criteria for evaluation, ensuring fair and unbiased assessments. Furthermore, users receive specific feedback and guidance for setting future goals.

[0824] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0825] Step 1:

[0826] Input and submission of target data

[0827] Users use their work terminals to input annual, quarterly, or monthly target data. For example, a user might input, "Achieve a sales target of 5 million yen in Q1." The entered target data is transmitted from the terminal to the server in real time.

[0828] Input: Target data entered by the user on the device.

[0829] Output: The transmitted target data has arrived at the server.

[0830] Specific operation: The terminal sends the target data entered by the user to the server, and the server verifies the received target data.

[0831] Step 2:

[0832] Recording target data

[0833] The server records the target data received from the terminal in its database. It then sends a response message to the terminal to confirm successful data reception.

[0834] Input: Target data that arrived at the server

[0835] Output: Target data stored in the database

[0836] Specific operation: The server saves the target data to the database and sends a response message to the terminal indicating that the data has been received and saved.

[0837] Step 3:

[0838] Data collection and cleansing

[0839] The server periodically collects target data submitted by all users and stores it in a database. It also performs data cleansing to eliminate duplicates, format inconsistencies, and noise from the collected data.

[0840] Input: Target data submitted by all users

[0841] Output: Cleansed target data

[0842] Specific operation: The server performs data collection tasks at regular intervals, such as at night, and cleanses the data to remove duplicates, inconsistencies, and noise.

[0843] Step 4:

[0844] Setting evaluation criteria

[0845] The server collects data such as past evaluation data, industry standards, and organizational policies, and sets evaluation criteria using generative artificial intelligence.

[0846] Input: Historical evaluation data, industry standards, organizational policy data

[0847] Output: Unified evaluation criteria

[0848] Specific operation: The server retrieves the necessary data from the database, provides it as input to the generative artificial intelligence, and has it perform analysis.

[0849] Step 5:

[0850] Evaluation of goal achievement

[0851] Based on the set evaluation criteria, the server uses generative artificial intelligence to analyze the user's target data and actual performance data, and calculates an achievement score. It also generates feedback comments.

[0852] Input: User's target data, performance data, and set evaluation criteria.

[0853] Output: Achievement score, feedback comments

[0854] Specific operation: The server passes target data and actual data to a generative artificial intelligence, which calculates an achievement score and generates feedback comments.

[0855] Step 6:

[0856] Provide feedback

[0857] The server sends the generated achievement score and feedback comments to the user's terminal. The user checks the received evaluation results and feedback comments on their work terminal.

[0858] Input: Achievement score, feedback comments

[0859] Output: Evaluation results and feedback comments displayed on the user's device.

[0860] Specific operation: The server sends the achievement score and feedback comments to the user's device, and the user reviews the evaluation.

[0861] These steps enable the system to automate the goal management system and ensure objectivity and fairness in evaluations.

[0862] (Application Example 1)

[0863] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0864] In current management by objectives (MBO) systems, the evaluation process is prone to subjectivity, resulting in a lack of objectivity and fairness. Furthermore, particularly in production systems, accurately and efficiently evaluating individual work performance is difficult, requiring significant effort and time for managers to provide appropriate feedback. Therefore, automation and improved accuracy of evaluations are essential.

[0865] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0866] In this invention, the server includes means for receiving target data from a user, means for collecting target data and recording it in a database, means for cleaning the collected target data, means for setting evaluation criteria using generative artificial intelligence, means for evaluating the degree of achievement of the target data based on the evaluation criteria, means for providing feedback on the evaluation results of the target data to the user, means for collecting and cleaning performance data of the production system, means for the generative artificial intelligence to automatically generate evaluation criteria based on the performance data of the production system, means for evaluating the degree of achievement of production targets in the production system and generating achievement scores and feedback comments, and means for providing the evaluation results and feedback comments to the production system administrator. This enables the automation of the evaluation process, realizes objective and fair evaluation, and allows administrators to provide feedback efficiently.

[0867] "Target data" refers to specific numerical values ​​or standards that users aim to achieve in their activities or tasks.

[0868] "Generative artificial intelligence" is an artificial intelligence technology that analyzes collected data and automatically generates evaluation criteria and feedback comments.

[0869] "Evaluation criteria" are standards set by generative artificial intelligence based on past data, industry standards, and organizational policies to evaluate the degree of goal achievement.

[0870] "Goal achievement" is a numerical metric that indicates how well a user or system has achieved the set goals.

[0871] "Feedback comments" are comments generated based on the evaluation results of goal achievement, and include suggestions for improvement and advice for setting future goals for the user.

[0872] A "production system" refers to automated equipment and mechanisms used in factories and manufacturing lines, and is a system that performs specific tasks or manufacturing processes.

[0873] "Performance data" refers to data such as the tasks performed by the production system, the quantities achieved, and the working hours.

[0874] "Cleansing" is the process of removing duplicate or incorrectly formatted data from collected data to improve its quality.

[0875] An "achievement score" is a numerical value that indicates the degree of achievement towards a goal, calculated based on established evaluation criteria.

[0876] A "manager" is a person responsible for monitoring the production system and the achievement of user goals, and for providing appropriate evaluations and feedback.

[0877] This invention relates to a system that automates management by objectives (MBO) and improves objectivity and fairness. This system performs the processes of inputting, collecting, and cleaning goal data, setting evaluation criteria, evaluating achievement, and providing feedback as follows.

[0878] Overall system configuration

[0879] The entire system consists mainly of the following components:

[0880] 1. User terminal

[0881] 2. Server

[0882] 3. Database

[0883] 4. Generative Artificial Intelligence

[0884] Program implementation overview

[0885] Input and recording of target data

[0886] Users input their daily production targets into their user terminals. For example, within the production system, an administrator might set a target of "assembling 1,000 units of parts today." This data is immediately sent to the server and recorded in the database.

[0887] Data collection and cleansing

[0888] The server collects performance data (e.g., number of completed tasks and working hours) from the production system in real time. It then cleanses the collected data, removing duplicates and erroneous entries. A data cleaner class is used for this cleansing.

[0889] Setting evaluation criteria

[0890] Generative artificial intelligence (AI) sets evaluation criteria based on past evaluation data, industry standards, and organizational policies. These established evaluation criteria include specific indicators for assessing the degree of goal achievement.

[0891] Evaluation of goal achievement

[0892] The server uses generative artificial intelligence to analyze production performance data and evaluate the degree of achievement. For example, if the set target is 1000 units and the actual result is 950 units, the achievement score will be calculated as 95%. Furthermore, the generative artificial intelligence also generates feedback comments based on the evaluation results.

[0893] Provide feedback

[0894] The evaluation results and feedback comments are sent from the server to the user's terminal. The user's terminal displays this feedback, which the administrator can use to identify areas for improvement and set goals for the future.

[0895] Hardware and software used

[0896] User terminal: A device used to input production targets and check feedback (e.g., PC, tablet).

[0897] Server: Hosts databases and generative artificial intelligence, performing aggregation, cleansing, evaluation, and feedback generation.

[0898] Database: SQL database, etc., used to store and manage target data and actual data.

[0899] Generative artificial intelligence: An AI system used to analyze past data and automatically generate evaluation criteria.

[0900] Specific examples and prompt statements

[0901] Specific example

[0902] Target data: The target is to assemble 1000 units of parts.

[0903] Performance data: Achieved 950 units.

[0904] Example of a prompt

[0905] "Robot ID 'robot_001' was set to achieve a production target of 1000 units today. Today's actual production is 950 units. Please generate a progress report and feedback based on this information."

[0906] As described above, the system automates the goal management system and provides objective and fair evaluations. Managers can efficiently receive feedback and use it to set future goals.

[0907] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0908] Step 1:

[0909] The user enters their production target into the terminal. For example, they might enter a specific target such as "assemble 1000 units of parts today" and send that data. The input is production target data, and the output is target data recorded by the server.

[0910] Step 2:

[0911] The server receives target data sent by the user and records it in the database. The input is the received target data, and the output is the target data stored in the database.

[0912] Step 3:

[0913] The server collects performance data from the production system in real time. This performance data includes the number of tasks completed, the time taken, and the accuracy of each task. The input is the collected performance data, and the output is the raw performance data.

[0914] Step 4:

[0915] The server cleanses the collected data. This process includes removing duplicate data, correcting erroneous data, and resolving format inconsistencies. Data cleansing improves the reliability of the data. The input is raw historical data, and the output is cleansed historical data.

[0916] Step 5:

[0917] The server uses generative artificial intelligence to set evaluation criteria. These criteria include numerical indicators based on data such as past evaluation data, industry standards, and organizational policies. The input is past evaluation data and industry standards, and the output is the set evaluation criteria.

[0918] Step 6:

[0919] The server uses generative artificial intelligence to analyze performance data based on predefined evaluation criteria. For example, if 950 units are achieved against a target of 1000 units, the achievement score is calculated as 95%. The input is cleansed performance data and evaluation criteria, and the output is the achievement score.

[0920] Step 7:

[0921] The server uses generative artificial intelligence to generate feedback comments. Based on the achievement score, it automatically generates comments that provide specific areas for improvement and help in setting future goals. For example, it might generate comments such as, "Achievement level 95%. The goal was not reached, but the work accuracy was high." The input is the achievement score, and the output is the feedback comment.

[0922] Step 8:

[0923] The server sends the evaluation results and feedback comments to the user's terminal. The administrator checks the results on the terminal and uses them to set goals for the next time and consider areas for improvement. The input is the evaluation results and feedback comments, and the output is the feedback information displayed on the user's terminal.

[0924] The above processing steps enable the automation of the evaluation process and ensure objective and fair evaluations. Managers can efficiently receive feedback and use it to set future goals.

[0925] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0926] This invention combines a system in which the user inputs target data and the degree of goal achievement is objectively evaluated by a generative artificial intelligence system with an emotion engine to recognize the user's emotions and reflect them in the feedback. This allows for objective and fair evaluation, as well as more effective feedback that takes into account the user's emotional state.

[0927] User goal input and recording

[0928] Users input annual, quarterly, and monthly target data through their work terminals. For example, a sales staff member might input a specific target such as "Achieve a sales target of 5 million yen in Q1." The target data entered by the user is immediately sent to the server and recorded in the database.

[0929] Data collection and cleansing

[0930] The server periodically collects target data submitted by users and stores it in a database. Since the collected data may include duplicates or inconsistent formats, the server cleanses this data. The cleansing process involves removing duplicate data, correcting inconsistent data, and eliminating noisy data.

[0931] Setting evaluation criteria

[0932] The server uses generative artificial intelligence to set evaluation criteria. The generative AI receives input such as the organization's past evaluation data, industry standards, and organizational policies. Based on this data, the generative AI performs analysis and automatically generates unified evaluation criteria. For example, the evaluation criteria for the sales department might include metrics such as sales targets, number of contracts, and customer satisfaction.

[0933] Evaluation of goal achievement

[0934] The server evaluates the user's achievement of their goals based on the set evaluation criteria. During the evaluation process, the generative artificial intelligence analyzes the user's goal data and calculates an achievement score. In addition to the score, the generative artificial intelligence also automatically generates feedback comments. For example, if a user achieves 4.5 million yen against a sales target of 5 million yen, a score of 90% achievement is calculated, and a comment such as "Although the target was slightly missed, the sales effort was remarkable" is generated.

[0935] Emotion recognition by an emotion engine

[0936] A distinctive feature of this invention is the addition of an emotion engine. The server inputs text data, voice data, facial expression data, etc., when the user enters goal data or receives feedback into the emotion engine. The emotion engine analyzes this data and recognizes the user's emotional state (for example, high motivation or signs of stress).

[0937] Generating and providing feedback

[0938] After the evaluation results are generated, the server generates feedback comments that reflect the emotional data obtained from the emotion engine. For example, if the user is feeling stressed, specific advice such as, "When setting goals next time, it would be good to be mindful of stress management," will be added. This feedback is sent to the user's device along with the evaluation score.

[0939] Specific example

[0940] Case Study A: Sato's Evaluation Process in the Sales Department

[0941] 1. Target Input: Sato inputs "Achieve a sales target of 5 million yen in Q1" into the terminal.

[0942] 2. Data Collection and Cleansing: The server collects the target data sent from Sato and cleanses away any unnecessary data.

[0943] 3. Setting Evaluation Criteria: The server uses generative artificial intelligence to set unified evaluation criteria based on past evaluation data and industry standards.

[0944] 4. Evaluation of Goal Achievement: The generative artificial intelligence analyzes Sato's sales performance (e.g., 4.5 million yen) and calculates an achievement score of 90%. It also generates feedback comments.

[0945] 5. Emotion Recognition: The server uses an emotion engine to recognize Sato's emotional state when receiving feedback. For example, if it determines that Sato is stressed, it adds appropriate advice.

[0946] 6. Providing Feedback: The server sends feedback comments reflecting the evaluation results and emotions to Sato's terminal, and Sato checks the results on his terminal.

[0947] This system not only ensures that evaluations are conducted based on objective criteria that eliminate subjectivity, but also provides personalized feedback that takes into account the user's emotional state, helping to maintain user motivation and manage stress.

[0948] The following describes the processing flow.

[0949] Step 1:

[0950] Users use a terminal to input their work objectives. Specifically, they input goals and numerical targets that must be achieved by the end of the period (for example, "Achieve a sales target of 5 million yen in Q1").

[0951] Step 2:

[0952] The terminal sends the entered target data to the server. A secure communication protocol is used for transmission, and the target data is immediately stored on the server.

[0953] Step 3:

[0954] The server records the received target data in a database. The database also stores metadata such as the date and time and user ID.

[0955] Step 4:

[0956] The server periodically collects all target data from the database and performs a cleansing process. Specifically, this involves removing duplicate data, correcting inconsistent data, and eliminating noisy data.

[0957] Step 5:

[0958] Based on the cleansed data, the server requests the generative artificial intelligence to set evaluation criteria. The server inputs industry standards, past evaluation data, and the organization's evaluation policies into the generative artificial intelligence.

[0959] Step 6:

[0960] Generative artificial intelligence analyzes input data and generates unified evaluation criteria for assessing goal achievement. The generated evaluation criteria are returned to the server and stored.

[0961] Step 7:

[0962] The server applies evaluation criteria generated by generative artificial intelligence to the cleansed target data to assess the user's degree of goal achievement. Specifically, it calculates a score by comparing the user's performance data (e.g., end-of-period sales performance) with the evaluation criteria.

[0963] Step 8:

[0964] Generative artificial intelligence automatically generates feedback comments in addition to achievement scores. For example, it might generate a comment such as, "Although the target was slightly missed, the sales efforts were commendable."

[0965] Step 9:

[0966] The server incorporates the user's emotional state, as analyzed by the emotion engine, into the feedback comments obtained from the generative artificial intelligence. For example, if the user is feeling stressed, this fact is added to the feedback comments.

[0967] Step 10:

[0968] The emotion engine analyzes text data, voice data, and facial expression data when the user enters goal data or receives feedback, and recognizes the user's emotional state. The recognized emotional data is then sent to the server.

[0969] Step 11:

[0970] The server sends the evaluation results and sentiment data to the user's device. A secure communication protocol is used for transmission.

[0971] Step 12:

[0972] Users use their devices to view evaluation results and feedback comments. For example, they might receive specific feedback such as, "You fell slightly short of your goal, but your sales efforts were commendable. When setting your next goal, it would be beneficial to focus on stress management."

[0973] (Example 2)

[0974] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0975] Conventional goal achievement evaluation systems are limited to objectively evaluating a user's goal achievement level and are unable to provide feedback that takes into account the user's emotional state. As a result, it has been difficult to properly manage the user's motivation and stress levels. This invention aims to solve these problems by not only evaluating the user's goal achievement level but also recognizing the user's emotional state using an emotion engine and providing feedback based on that.

[0976] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0977] In this invention, the server includes means for receiving target data from the user, means for collecting the target data and recording it in a database, means for cleansing the collected target data, means for setting evaluation criteria using generative artificial intelligence, means for evaluating the degree of achievement of the target data based on the evaluation criteria, means for generating feedback comments based on the evaluation results of the target data, means for recognizing the user's emotions using an emotion engine, means for adjusting the feedback comments based on the emotion data, and means for providing feedback to the user on the evaluation results of the target data and the feedback comments based on the emotion data. This makes it possible not only to objectively evaluate the user's degree of goal achievement but also to provide effective feedback that takes into account the user's emotional state.

[0978] "Target data" refers to data that users set as achievement goals on an annual, quarterly, or monthly basis.

[0979] A "user" refers to the entity that uses this system to set goals and receive feedback.

[0980] A "server" refers to a computer system that collects, cleanses, sets evaluation criteria, assesses goal achievement, recognizes emotions, and generates and provides feedback.

[0981] A "database" is a storage system for saving collected target data and cleansed data.

[0982] "Cleaning" refers to the process of correcting data duplication and inconsistencies and removing noisy data.

[0983] "Generative artificial intelligence" refers to an artificial intelligence system that automatically generates evaluation criteria based on input data, calculates scores, and creates feedback comments.

[0984] "Evaluation criteria" refers to a set of metrics set based on an organization's past evaluation data, industry standards, and organizational policies.

[0985] The "achievement score" is a numerical indicator that shows the degree to which a user has achieved their set goals.

[0986] A "feedback comment" is a comment created using generative artificial intelligence and an emotion engine, containing evaluation results and advice for the user.

[0987] An "emotion engine" refers to an analytical system that recognizes the user's emotional state and reflects it in the feedback comments.

[0988] "Emotional data" refers to data that indicates the emotional state of a user when they input goal data or receive feedback.

[0989] This invention combines a system in which the user inputs target data and the degree of goal achievement is objectively evaluated by a generative artificial intelligence system with an emotion engine to recognize the user's emotions and reflect them in the feedback. This allows for objective and fair evaluation, as well as more effective feedback that takes into account the user's emotional state. The following describes a specific embodiment of this system.

[0990] User goal input and recording

[0991] Users use work terminals to input annual, quarterly, and monthly target data. For example, a sales staff member might input a specific target such as "Achieve a sales target of 5 million yen in Q1." The entered target data is immediately sent to the server and recorded in the database.

[0992] Data collection and cleansing

[0993] The server periodically collects target data submitted by users and stores it in a database. Since the collected data may include duplicates or inconsistently formatted data, the server cleanses this data. During the cleansing process, Apache Spark is used to remove duplicate data, correct inconsistent data, and eliminate noise.

[0994] Setting evaluation criteria

[0995] The server uses generative artificial intelligence (for example, OpenAI's GPT-4) to set evaluation criteria. The generative AI receives input such as the organization's past evaluation data, industry standards, and organizational policies. Based on this data, the generative AI performs analysis and automatically generates unified evaluation criteria. For example, evaluation criteria for the sales department might include metrics such as sales targets, number of contracts, and customer satisfaction.

[0996] Evaluation of goal achievement

[0997] The server evaluates the user's achievement of their goals based on the set evaluation criteria. During the evaluation process, the generative artificial intelligence analyzes the user's goal data and calculates an achievement score. In addition to the score, the generative AI also automatically generates feedback comments. For example, if a user achieves 4.5 million yen against a sales target of 5 million yen, a score of 90% achievement is calculated, and a comment such as "Although the target was slightly missed, the sales effort was remarkable" is generated.

[0998] Emotion recognition by an emotion engine

[0999] A distinctive feature of this invention is the addition of an emotion engine. The server inputs text data, voice data, facial expression data, etc., when the user enters goal data or receives feedback into the emotion engine. The emotion engine (for example, IBM Watson's Tone Analyzer) analyzes this data and recognizes the user's emotional state (for example, high motivation or signs of stress).

[1000] Generating and providing feedback

[1001] After the evaluation results are generated, the server generates feedback comments that reflect the emotional data obtained from the emotion engine. For example, if the user is feeling stressed, specific advice such as, "When setting goals next time, it would be good to be mindful of stress management," will be added. This feedback, along with the evaluation score, is sent to the user's terminal. The user checks the feedback through their work terminal.

[1002] Specific example

[1003] Case Study A: Evaluation Process for Sales Department Staff

[1004] 1. Target Input: Sales staff enter "Achieve a sales target of 5 million yen in Q1" into the terminal.

[1005] 2. Data Collection and Cleansing: The server collects the input target data and cleanses unnecessary data using Apache Spark.

[1006] 3. Setting Evaluation Criteria: The server uses generative artificial intelligence (OpenAI's GPT-4) to set unified evaluation criteria based on past evaluation data and industry standards.

[1007] 4. Evaluation of Goal Achievement: The generative artificial intelligence analyzes the staff's sales performance (e.g., 4.5 million yen) and calculates an achievement score of 90%. It also generates feedback comments.

[1008] 5. Emotion Recognition: The server uses an emotion engine (IBM Watson's Tone Analyzer) to recognize the emotional state of staff members when they receive feedback. For example, if it is determined that a staff member is stressed, appropriate advice will be added.

[1009] 6. Providing Feedback: The server sends feedback comments reflecting the evaluation results and emotions to the staff member's terminal, and the staff member checks the results on their terminal.

[1010] This system not only ensures that evaluations are conducted based on objective criteria that eliminate subjectivity, but also provides personalized feedback that takes into account the user's emotional state, helping to maintain user motivation and manage stress.

[1011] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1012] Step 1: User goal input and recording

[1013] Users use their work terminals to input annual, quarterly, and monthly target data. For example, they might input a target such as "Achieve a sales target of 5 million yen in Q1."

[1014] The terminal immediately sends the input target data to the server. The input at this time is the user's target data, and the output is the data sent to the server.

[1015] The server records the received target data in the database. This ensures that the user's target data is securely stored.

[1016] Step 2: Data Collection and Cleansing

[1017] The server periodically collects raw target data from the database. The input is raw data from the database, and the output is the collected target data.

[1018] The server uses Apache Spark to cleanse the collected data. Specifically, it removes duplicate data, corrects inconsistent data, and eliminates noisy data. The input is the collected target data, and the output is the cleansed data.

[1019] Step 3: Setting evaluation criteria

[1020] The server uses generative artificial intelligence (OpenAI's GPT-4) to set evaluation criteria. The inputs are past evaluation data, industry standards, and organizational policies, and the output is the set evaluation criteria.

[1021] The server inputs this data into a generative artificial intelligence (AI) system for analysis. The AI ​​system automatically generates a unified evaluation standard.

[1022] Step 4: Evaluating the degree of goal achievement

[1023] The server evaluates the user's goal achievement level based on the configured evaluation criteria. The input is the user's goal data and evaluation criteria, and the output is the achievement score.

[1024] Generative artificial intelligence analyzes the user's goal data and calculates an achievement score. In addition to the score, it also generates feedback comments. For example, it might generate a comment such as, "You fell slightly short of your goal, but your sales efforts were commendable."

[1025] Step 5: Emotion Recognition

[1026] The server uses an emotion engine (IBM Watson's Tone Analyzer) to recognize the user's emotions. Inputs include text data, voice data, and facial expression data when the user enters target data or receives feedback, and output is emotion data.

[1027] The emotion engine analyzes this data to determine the user's motivation and signs of stress.

[1028] Step 6: Generating and providing feedback

[1029] The server generates feedback comments based on the evaluation results and sentiment data. The input is the evaluation results and sentiment data, and the output is the feedback comments.

[1030] The server adds specific advice such as, "Next time you set your goals, it would be a good idea to keep stress management in mind."

[1031] Step 7: Displaying user feedback

[1032] The server sends feedback comments and achievement scores to the user's device. The input is the generated feedback comments and achievement scores, and the output is the data sent to the user's device.

[1033] The device displays received feedback comments and achievement scores to the user. This allows the user to understand their progress toward their goals and areas for improvement.

[1034] (Application Example 2)

[1035] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1036] In evaluating the performance of factory robots, conventional methods are prone to subjective elements and have difficulty providing appropriate feedback that takes into account the robot's operating state and signs of internal stress. This can lead to problems such as decreased production efficiency and premature robot degradation.

[1037] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for receiving target data from the user, means for collecting the target data and recording it in a database, means for cleansing the collected target data, means for setting evaluation criteria using generative artificial intelligence, means for evaluating the degree of achievement of the target data based on the evaluation criteria, means for analyzing the evaluation results based on the evaluation criteria and the robot's operation data, and means for recognizing the emotional state using an emotion engine, and means for generating feedback that reflects the emotional data and providing it to the user. This makes it possible to objectively evaluate the performance of the factory robot and provide appropriate feedback.

[1038] "Target data" refers to data that shows specific numerical values ​​and action plans that users aim to achieve.

[1039] A "user" is an individual or organization that uses this system to set goals and has their achievement evaluated.

[1040] A "database" is a storage system where collected data is stored, enabling data management and retrieval.

[1041] "Data cleansing" is the process of removing duplicates and inconsistencies from collected data and organizing it.

[1042] "Generative artificial intelligence" is an AI technology that automatically generates new evaluation criteria based on past data and standards, and performs analysis.

[1043] "Evaluation criteria" are standards for objectively evaluating the user's degree of goal achievement, and are set by generative artificial intelligence.

[1044] "Achievement level" is a measure that indicates the actual degree to which results have been achieved in relation to the goals set by the user.

[1045] "Evaluation results" refer to data including the achievement score calculated by the generative artificial intelligence after analyzing the target data, and feedback comments.

[1046] An "emotion engine" is a technology that analyzes and recognizes a user's emotional state from text and audio data.

[1047] "Emotional data" refers to data that indicates the user's emotional state, as analyzed by the emotion engine.

[1048] "Feedback" refers to comments and advice provided to users based on evaluation results and sentiment data.

[1049] "Robot motion data" refers to detailed motion data collected while a factory robot is in operation, including error states and operational efficiency.

[1050] The system for realizing this invention includes the following hardware and software.

[1051] hardware

[1052] Factory robots: Robots used in production processes (e.g., typical articulated robots).

[1053] Server: A server that performs data processing, storage, and analysis.

[1054] Smartphone or tablet: A device used by the administrator for operation.

[1055] software

[1056] Generative AI model: AI software (e.g., OpenAI GPT-4) that automatically generates evaluation criteria from input data and produces achievement evaluations and feedback comments.

[1057] Emotion engine: Software that analyzes the emotional state of users or robots (e.g., IBM Watson Tone Analyzer).

[1058] Database: A database that stores target data and evaluation data (e.g., MySQL).

[1059] Cleansing tool: A tool used to cleanse collected data (e.g., Apache NiFi).

[1060] System program

[1061] User goal input and recording

[1062] Users (administrators) input production targets for factory robots from their smartphones or tablets. For example, they input target data such as "produce 5,000 products per month," and this data is immediately sent to the server and recorded in the database.

[1063] Data collection and cleansing

[1064] The server collects real-time operation data transmitted from factory robots and stores it in a database. The collected data is then cleansed using a cleansing tool (Apache NiFi) to remove inconsistencies and duplicates, ensuring it is in a tidier state.

[1065] Setting evaluation criteria

[1066] The server uses a generative AI model (OpenAI GPT-4) to automatically generate evaluation criteria based on past evaluation data and industry standards. This ensures that unified evaluation criteria are established.

[1067] Evaluation of goal achievement

[1068] The server uses a generation AI model to analyze the input target data and actual data, and calculates an achievement score. Furthermore, it automatically generates feedback comments and compiles them into an evaluation result.

[1069] Emotion recognition by an emotion engine

[1070] The server uses an emotion engine (IBM Watson Tone Analyzer) to analyze the robot's motion data for signs of stress and errors, and recognizes its emotional state.

[1071] Generating and providing feedback

[1072] After the evaluation results are generated, the server generates feedback comments that reflect the emotional data obtained by the emotion engine. These feedback comments, along with the achievement score, are sent to the administrator's smartphone or tablet. The administrator can then review this feedback and consider measures to improve the robot's performance.

[1073] Specific example

[1074] If factory robot A is set to produce 5,000 products per month, but actually produces 4,800, the generating AI model will evaluate the achievement as 90% and generate a feedback comment. Additionally, the emotion engine analyzes the robot's operation data and incorporates any signs of stress or errors observed during operation into the feedback.

[1075] Example of a prompt

[1076] Factory robot A has a target of producing 5,000 products per month. It actually produced 4,800 products. Generate an evaluation of its achievement and feedback. Also, detect signs of stress and errors and provide feedback based on these.

[1077] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1078] Step 1:

[1079] The user uses a device (smartphone or tablet) to input the production target for the factory robot. For example, they might enter a specific number such as "produce 5,000 products per month." The entered target data is immediately sent to the server. Input: Production target data (e.g., 5,000 units), Output: Target data sent to the server.

[1080] Step 2:

[1081] The server records the target data submitted by the user in a database. The recorded data is structured and used for the following processing: Input: Submitted target data, Output: Target data stored in the database.

[1082] Step 3:

[1083] Factory robots transmit actual production data (performance data) to a server in real time. For example, they send data such as "4800 products were produced." Input: Robot performance data, Output: Performance data transmitted to the server.

[1084] Step 4:

[1085] The server collects historical data and uses a cleansing tool (Apache NiFi) to remove duplicates and inconsistencies. This improves the purity of the data. Input: Collected historical data, Output: Cleansed data.

[1086] Step 5:

[1087] The server uses a generated AI model (OpenAI GPT-4) to set evaluation criteria based on historical evaluation data and industry standards. This enables analysis based on these criteria. Input: Historical evaluation data, industry standard data; Output: Set evaluation criteria.

[1088] Step 6:

[1089] The server uses an AI model to analyze the input target and performance data and calculate an achievement score. Furthermore, it automatically generates feedback comments. Input: Evaluation criteria, target data, performance data; Output: Achievement score and feedback comments.

[1090] Step 7:

[1091] The server uses an emotion engine (IBM Watson Tone Analyzer) to detect signs of stress and errors from the robot's motion data and recognize its emotional state. Input: Robot motion data, Output: Recognized emotion data.

[1092] Step 8:

[1093] The server incorporates emotional data obtained from the emotion engine and generates feedback based on the achievement score. Specifically, if there are signs of stress, it adds advice such as, "It would be good to aim for more realistic numbers for your next goal." Input: Emotional data, achievement score, feedback comment; Output: Revised feedback comment.

[1094] Step 9:

[1095] The server sends the final feedback comments and achievement score to the administrator's device (smartphone or tablet). The administrator can review this and use it to improve the robot's performance. Input: Revised feedback comments, achievement score; Output: Feedback and score provided to the administrator's device.

[1096] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1097] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1098] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1099] [Fourth Embodiment]

[1100] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1101] As shown in Figure 7, the 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.

[1102] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1103] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1104] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1105] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1106] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1107] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1108] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1109] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[1110] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1111] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1112] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1113] This invention relates to a system that automates the evaluation of management by objectives (MBO) and ensures objectivity and fairness. The system performs a series of processes in which the user inputs goal data, a generative artificial intelligence evaluates the degree of goal achievement based on evaluation criteria, and provides feedback on the results.

[1114] User goal input and recording

[1115] Users input annual, quarterly, and monthly target data through their work terminals. For example, a sales staff member might input a specific target such as "Achieve a sales target of 5 million yen in Q1." The target data entered by the user is immediately sent to the server and recorded in the database.

[1116] Data collection and cleansing

[1117] The server periodically collects target data submitted by users and stores it in a database. Since the collected data may include duplicates or inconsistent formats, the server cleanses this data. The cleansing process involves removing duplicate data, correcting inconsistent data, and eliminating noisy data.

[1118] Setting evaluation criteria

[1119] The server uses generative artificial intelligence to set evaluation criteria. The generative AI receives input such as the organization's past evaluation data, industry standards, and organizational policies. Based on this data, the generative AI performs analysis and automatically generates unified evaluation criteria. For example, the evaluation criteria for the sales department might include metrics such as sales targets, number of contracts, and customer satisfaction.

[1120] Evaluation of goal achievement

[1121] The server evaluates the user's achievement of their goals based on the set evaluation criteria. During the evaluation process, the generative artificial intelligence analyzes the user's goal data and calculates an achievement score. In addition to the score, the generative artificial intelligence also automatically generates feedback comments. For example, if a user achieves 4.5 million yen against a sales target of 5 million yen, a score of 90% achievement is calculated, and a comment such as "Although the target was slightly missed, the sales effort was remarkable" is generated.

[1122] Provide feedback

[1123] After the evaluation results are generated, the server sends them to the user's device. The user can then view the evaluation score and feedback comments on their device. This feedback includes not only numerical data on achievement but also specific areas for improvement and advice for setting future goals.

[1124] Specific example

[1125] Case Study A: Sato's Evaluation Process in the Sales Department

[1126] 1. Target Input: Sato inputs "Achieve a sales target of 5 million yen in Q1" into the terminal.

[1127] 2. Data Collection and Cleansing: The server collects the target data sent from Sato and cleanses away any unnecessary data.

[1128] 3. Setting Evaluation Criteria: The server uses generative artificial intelligence to set unified evaluation criteria based on past evaluation data and industry standards.

[1129] 4. Evaluation of Goal Achievement: The generative artificial intelligence analyzes Sato's sales performance (e.g., 4.5 million yen) and calculates an achievement score of 90%. It also generates feedback comments.

[1130] 5. Providing feedback: The server sends the evaluation results and feedback comments to Sato's terminal, and Sato checks the results on his terminal.

[1131] This system ensures that evaluations are conducted based on objective criteria, eliminating subjectivity and resulting in fair and unbiased assessments. Furthermore, users receive specific feedback and guidance for setting future goals.

[1132] The following describes the processing flow.

[1133] Step 1:

[1134] Users use a terminal to input their work objectives. Specifically, they input goals and numerical targets that must be achieved by the end of the period (for example, "Achieve a sales target of 5 million yen in Q1").

[1135] Step 2:

[1136] The terminal sends the entered target data to the server. A secure communication protocol is used for transmission, and the target data is immediately stored on the server.

[1137] Step 3:

[1138] The server records the received target data in a database. The database also stores metadata such as the date and time and user ID.

[1139] Step 4:

[1140] The server periodically collects all target data from the database and performs a cleansing process. Specifically, this involves removing duplicate data, correcting inconsistent data, and eliminating noisy data.

[1141] Step 5:

[1142] Based on the cleansed data, the server requests the generative artificial intelligence to set evaluation criteria. The server inputs industry standards, past evaluation data, and the organization's evaluation policies into the generative artificial intelligence.

[1143] Step 6:

[1144] Generative artificial intelligence analyzes input data and generates unified evaluation criteria for assessing goal achievement. The generated evaluation criteria are returned to the server and stored.

[1145] Step 7:

[1146] The server applies evaluation criteria generated by generative artificial intelligence to the cleansed target data to assess the user's degree of goal achievement. Specifically, it calculates a score by comparing the user's performance data (e.g., end-of-period sales performance) with the evaluation criteria.

[1147] Step 8:

[1148] Generative artificial intelligence automatically generates feedback comments in addition to achievement scores. For example, it might generate a comment such as, "Although the target was slightly missed, the sales efforts were commendable."

[1149] Step 9:

[1150] The server sends the evaluation results and feedback comments to the user's device. A secure communication protocol is used for transmission.

[1151] Step 10:

[1152] Users use their devices to view evaluation results and feedback comments. This allows users to understand their own performance and gain specific guidance for setting future goals.

[1153] (Example 1)

[1154] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1155] Traditional management by objectives (MBO) systems suffer from problems such as subjectivity and lack of fairness in evaluations, and inconsistency in evaluation criteria. This can lead to a lack of appropriate feedback, hindering employee motivation and performance improvement. Furthermore, the evaluation process is complex and time-consuming, placing a significant burden on managers. This invention aims to solve these problems and provide a system that enables objective and efficient evaluation.

[1156] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1157] In this invention, the server includes means for receiving target data from a user, means for collecting the target data and recording it in a database, means for cleansing the collected target data, means for setting evaluation criteria using generative artificial intelligence, means for evaluating the degree of achievement of the target data based on the evaluation criteria, means for generating feedback comments based on the degree of achievement, and means for providing feedback to the user on the evaluation results and feedback comments of the target data. This ensures objectivity and fairness in the evaluation and enables an efficient evaluation process.

[1158] "Target data" refers to specific business goals that users enter on an annual, quarterly, or monthly basis.

[1159] A "user" refers to an employee of a company or organization who uses the system to input target data and receives evaluation results.

[1160] "Terminal" refers to computers, mobile devices, and other devices that users use to input target data or check evaluation results.

[1161] A "server" refers to a central computer system that collects and stores target data sent by users, performs data cleansing and analysis, sets evaluation criteria, assesses achievement, and generates feedback comments.

[1162] A "database" refers to a data storage system located on or outside a server, used to store target data, historical evaluation data, industry standards, organizational policies, and other similar information.

[1163] "Cleansing" refers to the data preparation process that corrects duplicates and format inconsistencies in the collected target data and eliminates noisy data.

[1164] "Generative artificial intelligence" refers to artificial intelligence technology that automatically generates evaluation criteria and creates evaluation scores and feedback comments based on an organization's past evaluation data, industry standards, and organizational policies.

[1165] "Evaluation criteria" refers to indicators set by generative artificial intelligence that serve as standards for objectively evaluating the degree of goal achievement.

[1166] "Achievement score" refers to a numerical representation of the degree to which a user has achieved their goals.

[1167] "Feedback comments" refer to comments automatically generated by a generative artificial intelligence system based on the user's achievement score, regarding their progress toward achieving their goals.

[1168] This invention relates to a system that automates the evaluation of management by objectives (MBO) and ensures objectivity and fairness. The system performs a series of processes in which the user inputs goal data from a work terminal, the data is collected and cleansed, evaluation criteria are set using generative artificial intelligence, the degree of goal achievement is evaluated, and the results are fed back to the user.

[1169] Users first use their work terminals to input specific target data on an annual, quarterly, or monthly basis. For example, a user in the sales department might input, "Achieve a sales target of 5 million yen in Q1." This target data is sent to the server in real time and recorded in the server's database. The server periodically collects target data from all users and performs data cleansing. This process removes duplicate data, corrects format inconsistencies, and eliminates noisy data.

[1170] Next, the server uses generative artificial intelligence to collect data such as past evaluation data, industry standards, and organizational policies in order to set evaluation criteria. Based on this data, the generative AI performs analysis and automatically generates unified evaluation criteria. In the sales department, indicators such as sales target achievement rate, number of contracts, and customer satisfaction are included in the evaluation criteria.

[1171] The server analyzes the user's target data and actual performance data based on the set evaluation criteria and calculates an achievement score. For example, if a user achieves 4.5 million yen against a sales target of 5 million yen, the achievement score would be calculated as 90%. Furthermore, the generative artificial intelligence automatically generates feedback comments based on this evaluation result. Specifically, comments such as "Although the target was slightly missed, the sales effort was remarkable" are generated.

[1172] After the evaluation results and feedback comments are generated, the server sends them to the user's device. The user can then review the received evaluation results and feedback comments on their device and receive specific advice for setting goals for the next time.

[1173] (Specific example)

[1174] Case Study A: Sato's Evaluation Process in the Sales Department

[1175] 1. Target Input: Sato inputs "Achieve a sales target of 5 million yen in Q1" into the terminal.

[1176] 2. Data Transmission: The terminal transmits target data from Sato to the server in real time. The server records this target data in its database.

[1177] 3. Data Collection and Cleansing: The server collects target data submitted by all users, including Sato, and corrects and removes duplicates, inconsistencies, and noise.

[1178] 4. Setting evaluation criteria: The server collects past evaluation data, industry standards, and organizational policies, and generates evaluation criteria using generative artificial intelligence.

[1179] 5. Evaluation of goal achievement: The generative artificial intelligence analyzes Sato's sales performance (e.g., 4.5 million yen), calculates an achievement score of 90%, and generates feedback comments.

[1180] 6. Providing feedback: The server sends the evaluation results and feedback comments to Sato's terminal, and Sato checks the results on his terminal.

[1181] (Example of a prompt message)

[1182] "Evaluate the achievement level of Sato from the Sales Department against the Q1 target of 5 million yen, and generate feedback comments. Sato's actual sales performance was 4.5 million yen."

[1183] This system eliminates subjectivity and uses objective criteria for evaluation, ensuring fair and unbiased assessments. Furthermore, users receive specific feedback and guidance for setting future goals.

[1184] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1185] Step 1:

[1186] Input and submission of target data

[1187] Users use their work terminals to input annual, quarterly, or monthly target data. For example, a user might input, "Achieve a sales target of 5 million yen in Q1." The entered target data is transmitted from the terminal to the server in real time.

[1188] Input: Target data entered by the user on the device.

[1189] Output: The transmitted target data has arrived at the server.

[1190] Specific operation: The terminal sends the target data entered by the user to the server, and the server verifies the received target data.

[1191] Step 2:

[1192] Recording target data

[1193] The server records the target data received from the terminal in its database. It then sends a response message to the terminal to confirm successful data reception.

[1194] Input: Target data that arrived at the server

[1195] Output: Target data stored in the database

[1196] Specific operation: The server saves the target data to the database and sends a response message to the terminal indicating that the data has been received and saved.

[1197] Step 3:

[1198] Data collection and cleansing

[1199] The server periodically collects target data submitted by all users and stores it in a database. It also performs data cleansing to eliminate duplicates, format inconsistencies, and noise from the collected data.

[1200] Input: Target data submitted by all users

[1201] Output: Cleansed target data

[1202] Specific operation: The server performs data collection tasks at regular intervals, such as at night, and cleanses the data to remove duplicates, inconsistencies, and noise.

[1203] Step 4:

[1204] Setting evaluation criteria

[1205] The server collects data such as past evaluation data, industry standards, and organizational policies, and sets evaluation criteria using generative artificial intelligence.

[1206] Input: Historical evaluation data, industry standards, organizational policy data

[1207] Output: Unified evaluation criteria

[1208] Specific operation: The server retrieves the necessary data from the database, provides it as input to the generative artificial intelligence, and has it perform analysis.

[1209] Step 5:

[1210] Evaluation of goal achievement

[1211] Based on the set evaluation criteria, the server uses generative artificial intelligence to analyze the user's target data and actual performance data, and calculates an achievement score. It also generates feedback comments.

[1212] Input: User's target data, performance data, and set evaluation criteria.

[1213] Output: Achievement score, feedback comments

[1214] Specific operation: The server passes target data and actual data to a generative artificial intelligence, which calculates an achievement score and generates feedback comments.

[1215] Step 6:

[1216] Provide feedback

[1217] The server sends the generated achievement score and feedback comments to the user's terminal. The user checks the received evaluation results and feedback comments on their work terminal.

[1218] Input: Achievement score, feedback comments

[1219] Output: Evaluation results and feedback comments displayed on the user's device.

[1220] Specific operation: The server sends the achievement score and feedback comments to the user's device, and the user reviews the evaluation.

[1221] These steps enable the system to automate the goal management system and ensure objectivity and fairness in evaluations.

[1222] (Application Example 1)

[1223] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1224] In current management by objectives (MBO) systems, the evaluation process is prone to subjectivity, resulting in a lack of objectivity and fairness. Furthermore, particularly in production systems, accurately and efficiently evaluating individual work performance is difficult, requiring significant effort and time for managers to provide appropriate feedback. Therefore, automation and improved accuracy of evaluations are essential.

[1225] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1226] In this invention, the server includes means for receiving target data from a user, means for collecting target data and recording it in a database, means for cleaning the collected target data, means for setting evaluation criteria using generative artificial intelligence, means for evaluating the degree of achievement of the target data based on the evaluation criteria, means for providing feedback on the evaluation results of the target data to the user, means for collecting and cleaning performance data of the production system, means for the generative artificial intelligence to automatically generate evaluation criteria based on the performance data of the production system, means for evaluating the degree of achievement of production targets in the production system and generating achievement scores and feedback comments, and means for providing the evaluation results and feedback comments to the production system administrator. This enables the automation of the evaluation process, realizes objective and fair evaluation, and allows administrators to provide feedback efficiently.

[1227] "Target data" refers to specific numerical values ​​or standards that users aim to achieve in their activities or tasks.

[1228] "Generative artificial intelligence" is an artificial intelligence technology that analyzes collected data and automatically generates evaluation criteria and feedback comments.

[1229] "Evaluation criteria" are standards set by generative artificial intelligence based on past data, industry standards, and organizational policies to evaluate the degree of goal achievement.

[1230] "Goal achievement" is a numerical metric that indicates how well a user or system has achieved the set goals.

[1231] "Feedback comments" are comments generated based on the evaluation results of goal achievement, and include suggestions for improvement and advice for setting future goals for the user.

[1232] A "production system" refers to automated equipment and mechanisms used in factories and manufacturing lines, and is a system that performs specific tasks or manufacturing processes.

[1233] "Performance data" refers to data such as the tasks performed by the production system, the quantities achieved, and the working hours.

[1234] "Cleansing" is the process of removing duplicate or incorrectly formatted data from collected data to improve its quality.

[1235] An "achievement score" is a numerical value that indicates the degree of achievement towards a goal, calculated based on established evaluation criteria.

[1236] A "manager" is a person responsible for monitoring the production system and the achievement of user goals, and for providing appropriate evaluations and feedback.

[1237] This invention relates to a system that automates management by objectives (MBO) and improves objectivity and fairness. This system performs the processes of inputting, collecting, and cleaning goal data, setting evaluation criteria, evaluating achievement, and providing feedback as follows.

[1238] Overall system configuration

[1239] The entire system consists mainly of the following components:

[1240] 1. User terminal

[1241] 2. Server

[1242] 3. Database

[1243] 4. Generative Artificial Intelligence

[1244] Program implementation overview

[1245] Input and recording of target data

[1246] Users input their daily production targets into their user terminals. For example, within the production system, an administrator might set a target of "assembling 1,000 units of parts today." This data is immediately sent to the server and recorded in the database.

[1247] Data collection and cleansing

[1248] The server collects performance data (e.g., number of completed tasks and working hours) from the production system in real time. It then cleanses the collected data, removing duplicates and erroneous entries. A data cleaner class is used for this cleansing.

[1249] Setting evaluation criteria

[1250] Generative artificial intelligence (AI) sets evaluation criteria based on past evaluation data, industry standards, and organizational policies. These established evaluation criteria include specific indicators for assessing the degree of goal achievement.

[1251] Evaluation of goal achievement

[1252] The server uses generative artificial intelligence to analyze production performance data and evaluate the degree of achievement. For example, if the set target is 1000 units and the actual result is 950 units, the achievement score will be calculated as 95%. Furthermore, the generative artificial intelligence also generates feedback comments based on the evaluation results.

[1253] Provide feedback

[1254] The evaluation results and feedback comments are sent from the server to the user's terminal. The user's terminal displays this feedback, which the administrator can use to identify areas for improvement and set goals for the future.

[1255] Hardware and software used

[1256] User terminal: A device used to input production targets and check feedback (e.g., PC, tablet).

[1257] Server: Hosts databases and generative artificial intelligence, performing aggregation, cleansing, evaluation, and feedback generation.

[1258] Database: SQL database, etc., used to store and manage target data and actual data.

[1259] Generative artificial intelligence: An AI system used to analyze past data and automatically generate evaluation criteria.

[1260] Specific examples and prompt statements

[1261] Specific example

[1262] Target data: The target is to assemble 1000 units of parts.

[1263] Performance data: Achieved 950 units.

[1264] Example of a prompt

[1265] "Robot ID 'robot_001' was set to achieve a production target of 1000 units today. Today's actual production is 950 units. Please generate a progress report and feedback based on this information."

[1266] As described above, the system automates the goal management system and provides objective and fair evaluations. Managers can efficiently receive feedback and use it to set future goals.

[1267] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1268] Step 1:

[1269] The user enters their production target into the terminal. For example, they might enter a specific target such as "assemble 1000 units of parts today" and send that data. The input is production target data, and the output is target data recorded by the server.

[1270] Step 2:

[1271] The server receives target data sent by the user and records it in the database. The input is the received target data, and the output is the target data stored in the database.

[1272] Step 3:

[1273] The server collects performance data from the production system in real time. This performance data includes the number of tasks completed, the time taken, and the accuracy of each task. The input is the collected performance data, and the output is the raw performance data.

[1274] Step 4:

[1275] The server cleanses the collected data. This process includes removing duplicate data, correcting erroneous data, and resolving format inconsistencies. Data cleansing improves the reliability of the data. The input is raw historical data, and the output is cleansed historical data.

[1276] Step 5:

[1277] The server uses generative artificial intelligence to set evaluation criteria. These criteria include numerical indicators based on data such as past evaluation data, industry standards, and organizational policies. The input is past evaluation data and industry standards, and the output is the set evaluation criteria.

[1278] Step 6:

[1279] The server uses generative artificial intelligence to analyze performance data based on predefined evaluation criteria. For example, if 950 units are achieved against a target of 1000 units, the achievement score is calculated as 95%. The input is cleansed performance data and evaluation criteria, and the output is the achievement score.

[1280] Step 7:

[1281] The server uses generative artificial intelligence to generate feedback comments. Based on the achievement score, it automatically generates comments that provide specific areas for improvement and help in setting future goals. For example, it might generate comments such as, "Achievement level 95%. The goal was not reached, but the work accuracy was high." The input is the achievement score, and the output is the feedback comment.

[1282] Step 8:

[1283] The server sends the evaluation results and feedback comments to the user's terminal. The administrator checks the results on the terminal and uses them to set goals for the next time and consider areas for improvement. The input is the evaluation results and feedback comments, and the output is the feedback information displayed on the user's terminal.

[1284] The above processing steps enable the automation of the evaluation process and ensure objective and fair evaluations. Managers can efficiently receive feedback and use it to set future goals.

[1285] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1286] This invention combines a system in which the user inputs target data and the degree of goal achievement is objectively evaluated by a generative artificial intelligence system with an emotion engine to recognize the user's emotions and reflect them in the feedback. This allows for objective and fair evaluation, as well as more effective feedback that takes into account the user's emotional state.

[1287] User goal input and recording

[1288] Users input annual, quarterly, and monthly target data through their work terminals. For example, a sales staff member might input a specific target such as "Achieve a sales target of 5 million yen in Q1." The target data entered by the user is immediately sent to the server and recorded in the database.

[1289] Data collection and cleansing

[1290] The server periodically collects target data submitted by users and stores it in a database. Since the collected data may include duplicates or inconsistent formats, the server cleanses this data. The cleansing process involves removing duplicate data, correcting inconsistent data, and eliminating noisy data.

[1291] Setting evaluation criteria

[1292] The server uses generative artificial intelligence to set evaluation criteria. The generative AI receives input such as the organization's past evaluation data, industry standards, and organizational policies. Based on this data, the generative AI performs analysis and automatically generates unified evaluation criteria. For example, the evaluation criteria for the sales department might include metrics such as sales targets, number of contracts, and customer satisfaction.

[1293] Evaluation of goal achievement

[1294] The server evaluates the user's achievement of their goals based on the set evaluation criteria. During the evaluation process, the generative artificial intelligence analyzes the user's goal data and calculates an achievement score. In addition to the score, the generative artificial intelligence also automatically generates feedback comments. For example, if a user achieves 4.5 million yen against a sales target of 5 million yen, a score of 90% achievement is calculated, and a comment such as "Although the target was slightly missed, the sales effort was remarkable" is generated.

[1295] Emotion recognition by an emotion engine

[1296] A distinctive feature of this invention is the addition of an emotion engine. The server inputs text data, voice data, facial expression data, etc., when the user enters goal data or receives feedback into the emotion engine. The emotion engine analyzes this data and recognizes the user's emotional state (for example, high motivation or signs of stress).

[1297] Generating and providing feedback

[1298] After the evaluation results are generated, the server generates feedback comments that reflect the emotional data obtained from the emotion engine. For example, if the user is feeling stressed, specific advice such as, "When setting goals next time, it would be good to be mindful of stress management," will be added. This feedback is sent to the user's device along with the evaluation score.

[1299] Specific example

[1300] Case Study A: Sato's Evaluation Process in the Sales Department

[1301] 1. Target Input: Sato inputs "Achieve a sales target of 5 million yen in Q1" into the terminal.

[1302] 2. Data Collection and Cleansing: The server collects the target data sent from Sato and cleanses away any unnecessary data.

[1303] 3. Setting Evaluation Criteria: The server uses generative artificial intelligence to set unified evaluation criteria based on past evaluation data and industry standards.

[1304] 4. Evaluation of Goal Achievement: The generative artificial intelligence analyzes Sato's sales performance (e.g., 4.5 million yen) and calculates an achievement score of 90%. It also generates feedback comments.

[1305] 5. Emotion Recognition: The server uses an emotion engine to recognize Sato's emotional state when receiving feedback. For example, if it determines that Sato is stressed, it adds appropriate advice.

[1306] 6. Providing Feedback: The server sends feedback comments reflecting the evaluation results and emotions to Sato's terminal, and Sato checks the results on his terminal.

[1307] This system not only ensures that evaluations are conducted based on objective criteria that eliminate subjectivity, but also provides personalized feedback that takes into account the user's emotional state, helping to maintain user motivation and manage stress.

[1308] The following describes the processing flow.

[1309] Step 1:

[1310] Users use a terminal to input their work objectives. Specifically, they input goals and numerical targets that must be achieved by the end of the period (for example, "Achieve a sales target of 5 million yen in Q1").

[1311] Step 2:

[1312] The terminal sends the entered target data to the server. A secure communication protocol is used for transmission, and the target data is immediately stored on the server.

[1313] Step 3:

[1314] The server records the received target data in a database. The database also stores metadata such as the date and time and user ID.

[1315] Step 4:

[1316] The server periodically collects all target data from the database and performs a cleansing process. Specifically, this involves removing duplicate data, correcting inconsistent data, and eliminating noisy data.

[1317] Step 5:

[1318] Based on the cleansed data, the server requests the generative artificial intelligence to set evaluation criteria. The server inputs industry standards, past evaluation data, and the organization's evaluation policies into the generative artificial intelligence.

[1319] Step 6:

[1320] Generative artificial intelligence analyzes input data and generates unified evaluation criteria for assessing goal achievement. The generated evaluation criteria are returned to the server and stored.

[1321] Step 7:

[1322] The server applies evaluation criteria generated by generative artificial intelligence to the cleansed target data to assess the user's degree of goal achievement. Specifically, it calculates a score by comparing the user's performance data (e.g., end-of-period sales performance) with the evaluation criteria.

[1323] Step 8:

[1324] Generative artificial intelligence automatically generates feedback comments in addition to achievement scores. For example, it might generate a comment such as, "Although the target was slightly missed, the sales efforts were commendable."

[1325] Step 9:

[1326] The server incorporates the user's emotional state, as analyzed by the emotion engine, into the feedback comments obtained from the generative artificial intelligence. For example, if the user is feeling stressed, this fact is added to the feedback comments.

[1327] Step 10:

[1328] The emotion engine analyzes text data, voice data, and facial expression data when the user enters goal data or receives feedback, and recognizes the user's emotional state. The recognized emotional data is then sent to the server.

[1329] Step 11:

[1330] The server sends the evaluation results and sentiment data to the user's device. A secure communication protocol is used for transmission.

[1331] Step 12:

[1332] Users use their devices to view evaluation results and feedback comments. For example, they might receive specific feedback such as, "You fell slightly short of your goal, but your sales efforts were commendable. When setting your next goal, it would be beneficial to focus on stress management."

[1333] (Example 2)

[1334] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1335] Conventional goal achievement evaluation systems are limited to objectively evaluating a user's goal achievement level and are unable to provide feedback that takes into account the user's emotional state. As a result, it has been difficult to properly manage the user's motivation and stress levels. This invention aims to solve these problems by not only evaluating the user's goal achievement level but also recognizing the user's emotional state using an emotion engine and providing feedback based on that.

[1336] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1337] In this invention, the server includes means for receiving target data from the user, means for collecting the target data and recording it in a database, means for cleansing the collected target data, means for setting evaluation criteria using generative artificial intelligence, means for evaluating the degree of achievement of the target data based on the evaluation criteria, means for generating feedback comments based on the evaluation results of the target data, means for recognizing the user's emotions using an emotion engine, means for adjusting the feedback comments based on the emotion data, and means for providing feedback to the user on the evaluation results of the target data and the feedback comments based on the emotion data. This makes it possible not only to objectively evaluate the user's degree of goal achievement but also to provide effective feedback that takes into account the user's emotional state.

[1338] "Target data" refers to data that users set as achievement goals on an annual, quarterly, or monthly basis.

[1339] A "user" refers to the entity that uses this system to set goals and receive feedback.

[1340] A "server" refers to a computer system that collects, cleanses, sets evaluation criteria, assesses goal achievement, recognizes emotions, and generates and provides feedback.

[1341] A "database" is a storage system for saving collected target data and cleansed data.

[1342] "Cleaning" refers to the process of correcting data duplication and inconsistencies and removing noisy data.

[1343] "Generative artificial intelligence" refers to an artificial intelligence system that automatically generates evaluation criteria based on input data, calculates scores, and creates feedback comments.

[1344] "Evaluation criteria" refers to a set of metrics set based on an organization's past evaluation data, industry standards, and organizational policies.

[1345] The "achievement score" is a numerical indicator that shows the degree to which a user has achieved their set goals.

[1346] A "feedback comment" is a comment created using generative artificial intelligence and an emotion engine, containing evaluation results and advice for the user.

[1347] An "emotion engine" refers to an analytical system that recognizes the user's emotional state and reflects it in the feedback comments.

[1348] "Emotional data" refers to data that indicates the emotional state of a user when they input goal data or receive feedback.

[1349] This invention combines a system in which the user inputs target data and the degree of goal achievement is objectively evaluated by a generative artificial intelligence system with an emotion engine to recognize the user's emotions and reflect them in the feedback. This allows for objective and fair evaluation, as well as more effective feedback that takes into account the user's emotional state. The following describes a specific embodiment of this system.

[1350] User goal input and recording

[1351] Users use work terminals to input annual, quarterly, and monthly target data. For example, a sales staff member might input a specific target such as "Achieve a sales target of 5 million yen in Q1." The entered target data is immediately sent to the server and recorded in the database.

[1352] Data collection and cleansing

[1353] The server periodically collects target data submitted by users and stores it in a database. Since the collected data may include duplicates or inconsistently formatted data, the server cleanses this data. During the cleansing process, Apache Spark is used to remove duplicate data, correct inconsistent data, and eliminate noise.

[1354] Setting evaluation criteria

[1355] The server uses generative artificial intelligence (for example, OpenAI's GPT-4) to set evaluation criteria. The generative AI receives input such as the organization's past evaluation data, industry standards, and organizational policies. Based on this data, the generative AI performs analysis and automatically generates unified evaluation criteria. For example, evaluation criteria for the sales department might include metrics such as sales targets, number of contracts, and customer satisfaction.

[1356] Evaluation of goal achievement

[1357] The server evaluates the user's achievement of their goals based on the set evaluation criteria. During the evaluation process, the generative artificial intelligence analyzes the user's goal data and calculates an achievement score. In addition to the score, the generative AI also automatically generates feedback comments. For example, if a user achieves 4.5 million yen against a sales target of 5 million yen, a score of 90% achievement is calculated, and a comment such as "Although the target was slightly missed, the sales effort was remarkable" is generated.

[1358] Emotion recognition by an emotion engine

[1359] A distinctive feature of this invention is the addition of an emotion engine. The server inputs text data, voice data, facial expression data, etc., when the user enters goal data or receives feedback into the emotion engine. The emotion engine (for example, IBM Watson's Tone Analyzer) analyzes this data and recognizes the user's emotional state (for example, high motivation or signs of stress).

[1360] Generating and providing feedback

[1361] After the evaluation results are generated, the server generates feedback comments that reflect the emotional data obtained from the emotion engine. For example, if the user is feeling stressed, specific advice such as, "When setting goals next time, it would be good to be mindful of stress management," will be added. This feedback, along with the evaluation score, is sent to the user's terminal. The user checks the feedback through their work terminal.

[1362] Specific example

[1363] Case Study A: Evaluation Process for Sales Department Staff

[1364] 1. Target Input: Sales staff enter "Achieve a sales target of 5 million yen in Q1" into the terminal.

[1365] 2. Data Collection and Cleansing: The server collects the input target data and cleanses unnecessary data using Apache Spark.

[1366] 3. Setting Evaluation Criteria: The server uses generative artificial intelligence (OpenAI's GPT-4) to set unified evaluation criteria based on past evaluation data and industry standards.

[1367] 4. Evaluation of Goal Achievement: The generative artificial intelligence analyzes the staff's sales performance (e.g., 4.5 million yen) and calculates an achievement score of 90%. It also generates feedback comments.

[1368] 5. Emotion Recognition: The server uses an emotion engine (IBM Watson's Tone Analyzer) to recognize the emotional state of staff members when they receive feedback. For example, if it is determined that a staff member is stressed, appropriate advice will be added.

[1369] 6. Providing Feedback: The server sends feedback comments reflecting the evaluation results and emotions to the staff member's terminal, and the staff member checks the results on their terminal.

[1370] This system not only ensures that evaluations are conducted based on objective criteria that eliminate subjectivity, but also provides personalized feedback that takes into account the user's emotional state, helping to maintain user motivation and manage stress.

[1371] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1372] Step 1: User goal input and recording

[1373] Users use their work terminals to input annual, quarterly, and monthly target data. For example, they might input a target such as "Achieve a sales target of 5 million yen in Q1."

[1374] The terminal immediately sends the input target data to the server. The input at this time is the user's target data, and the output is the data sent to the server.

[1375] The server records the received target data in the database. This ensures that the user's target data is securely stored.

[1376] Step 2: Data Collection and Cleansing

[1377] The server periodically collects raw target data from the database. The input is raw data from the database, and the output is the collected target data.

[1378] The server uses Apache Spark to cleanse the collected data. Specifically, it removes duplicate data, corrects inconsistent data, and eliminates noisy data. The input is the collected target data, and the output is the cleansed data.

[1379] Step 3: Setting evaluation criteria

[1380] The server uses generative artificial intelligence (OpenAI's GPT-4) to set evaluation criteria. The inputs are past evaluation data, industry standards, and organizational policies, and the output is the set evaluation criteria.

[1381] The server inputs this data into a generative artificial intelligence (AI) system for analysis. The AI ​​system automatically generates a unified evaluation standard.

[1382] Step 4: Evaluating the degree of goal achievement

[1383] The server evaluates the user's goal achievement level based on the configured evaluation criteria. The input is the user's goal data and evaluation criteria, and the output is the achievement score.

[1384] Generative artificial intelligence analyzes the user's goal data and calculates an achievement score. In addition to the score, it also generates feedback comments. For example, it might generate a comment such as, "You fell slightly short of your goal, but your sales efforts were commendable."

[1385] Step 5: Emotion Recognition

[1386] The server uses an emotion engine (IBM Watson's Tone Analyzer) to recognize the user's emotions. Inputs include text data, voice data, and facial expression data when the user enters target data or receives feedback, and output is emotion data.

[1387] The emotion engine analyzes this data to determine the user's motivation and signs of stress.

[1388] Step 6: Generating and providing feedback

[1389] The server generates feedback comments based on the evaluation results and sentiment data. The input is the evaluation results and sentiment data, and the output is the feedback comments.

[1390] The server adds specific advice such as, "Next time you set your goals, it would be a good idea to keep stress management in mind."

[1391] Step 7: Displaying user feedback

[1392] The server sends feedback comments and achievement scores to the user's device. The input is the generated feedback comments and achievement scores, and the output is the data sent to the user's device.

[1393] The device displays received feedback comments and achievement scores to the user. This allows the user to understand their progress toward their goals and areas for improvement.

[1394] (Application Example 2)

[1395] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1396] In evaluating the performance of factory robots, conventional methods are prone to subjective elements and have difficulty providing appropriate feedback that takes into account the robot's operating state and signs of internal stress. This can lead to problems such as decreased production efficiency and premature robot degradation.

[1397] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for receiving target data from the user, means for collecting the target data and recording it in a database, means for cleansing the collected target data, means for setting evaluation criteria using generative artificial intelligence, means for evaluating the degree of achievement of the target data based on the evaluation criteria, means for analyzing the evaluation results based on the evaluation criteria and the robot's operation data, and means for recognizing the emotional state using an emotion engine, and means for generating feedback that reflects the emotional data and providing it to the user. This makes it possible to objectively evaluate the performance of the factory robot and provide appropriate feedback.

[1398] "Target data" refers to data that shows specific numerical values ​​and action plans that users aim to achieve.

[1399] A "user" is an individual or organization that uses this system to set goals and has their achievement evaluated.

[1400] A "database" is a storage system where collected data is stored, enabling data management and retrieval.

[1401] "Data cleansing" is the process of removing duplicates and inconsistencies from collected data and organizing it.

[1402] "Generative artificial intelligence" is an AI technology that automatically generates new evaluation criteria based on past data and standards, and performs analysis.

[1403] "Evaluation criteria" are standards for objectively evaluating the user's degree of goal achievement, and are set by generative artificial intelligence.

[1404] "Achievement level" is a measure that indicates the actual degree to which results have been achieved in relation to the goals set by the user.

[1405] "Evaluation results" refer to data including the achievement score calculated by the generative artificial intelligence after analyzing the target data, and feedback comments.

[1406] An "emotion engine" is a technology that analyzes and recognizes a user's emotional state from text and audio data.

[1407] "Emotional data" refers to data that indicates the user's emotional state, as analyzed by the emotion engine.

[1408] "Feedback" refers to comments and advice provided to users based on evaluation results and sentiment data.

[1409] "Robot motion data" refers to detailed motion data collected while a factory robot is in operation, including error states and operational efficiency.

[1410] The system for realizing this invention includes the following hardware and software.

[1411] hardware

[1412] Factory robots: Robots used in production processes (e.g., typical articulated robots).

[1413] Server: A server that performs data processing, storage, and analysis.

[1414] Smartphone or tablet: A device used by the administrator for operation.

[1415] software

[1416] Generative AI model: AI software (e.g., OpenAI GPT-4) that automatically generates evaluation criteria from input data and produces achievement evaluations and feedback comments.

[1417] Emotion engine: Software that analyzes the emotional state of users or robots (e.g., IBM Watson Tone Analyzer).

[1418] Database: A database that stores target data and evaluation data (e.g., MySQL).

[1419] Cleansing tool: A tool used to cleanse collected data (e.g., Apache NiFi).

[1420] System program

[1421] User goal input and recording

[1422] Users (administrators) input production targets for factory robots from their smartphones or tablets. For example, they input target data such as "produce 5,000 products per month," and this data is immediately sent to the server and recorded in the database.

[1423] Data collection and cleansing

[1424] The server collects real-time operation data transmitted from factory robots and stores it in a database. The collected data is then cleansed using a cleansing tool (Apache NiFi) to remove inconsistencies and duplicates, ensuring it is in a tidier state.

[1425] Setting evaluation criteria

[1426] The server uses a generative AI model (OpenAI GPT-4) to automatically generate evaluation criteria based on past evaluation data and industry standards. This ensures that unified evaluation criteria are established.

[1427] Evaluation of goal achievement

[1428] The server uses a generation AI model to analyze the input target data and actual data, and calculates an achievement score. Furthermore, it automatically generates feedback comments and compiles them into an evaluation result.

[1429] Emotion recognition by an emotion engine

[1430] The server uses an emotion engine (IBM Watson Tone Analyzer) to analyze the robot's motion data for signs of stress and errors, and recognizes its emotional state.

[1431] Generating and providing feedback

[1432] After the evaluation results are generated, the server generates feedback comments that reflect the emotional data obtained by the emotion engine. These feedback comments, along with the achievement score, are sent to the administrator's smartphone or tablet. The administrator can then review this feedback and consider measures to improve the robot's performance.

[1433] Specific example

[1434] If factory robot A is set to produce 5,000 products per month, but actually produces 4,800, the generating AI model will evaluate the achievement as 90% and generate a feedback comment. Additionally, the emotion engine analyzes the robot's operation data and incorporates any signs of stress or errors observed during operation into the feedback.

[1435] Example of a prompt

[1436] Factory robot A has a target of producing 5,000 products per month. It actually produced 4,800 products. Generate an evaluation of its achievement and feedback. Also, detect signs of stress and errors and provide feedback based on these.

[1437] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1438] Step 1:

[1439] The user uses a device (smartphone or tablet) to input the production target for the factory robot. For example, they might enter a specific number such as "produce 5,000 products per month." The entered target data is immediately sent to the server. Input: Production target data (e.g., 5,000 units), Output: Target data sent to the server.

[1440] Step 2:

[1441] The server records the target data submitted by the user in a database. The recorded data is structured and used for the following processing: Input: Submitted target data, Output: Target data stored in the database.

[1442] Step 3:

[1443] Factory robots transmit actual production data (performance data) to a server in real time. For example, they send data such as "4800 products were produced." Input: Robot performance data, Output: Performance data transmitted to the server.

[1444] Step 4:

[1445] The server collects historical data and uses a cleansing tool (Apache NiFi) to remove duplicates and inconsistencies. This improves the purity of the data. Input: Collected historical data, Output: Cleansed data.

[1446] Step 5:

[1447] The server uses a generated AI model (OpenAI GPT-4) to set evaluation criteria based on historical evaluation data and industry standards. This enables analysis based on these criteria. Input: Historical evaluation data, industry standard data; Output: Set evaluation criteria.

[1448] Step 6:

[1449] The server uses an AI model to analyze the input target and performance data and calculate an achievement score. Furthermore, it automatically generates feedback comments. Input: Evaluation criteria, target data, performance data; Output: Achievement score and feedback comments.

[1450] Step 7:

[1451] The server uses an emotion engine (IBM Watson Tone Analyzer) to detect signs of stress and errors from the robot's motion data and recognize its emotional state. Input: Robot motion data, Output: Recognized emotion data.

[1452] Step 8:

[1453] The server incorporates emotional data obtained from the emotion engine and generates feedback based on the achievement score. Specifically, if there are signs of stress, it adds advice such as, "It would be good to aim for more realistic numbers for your next goal." Input: Emotional data, achievement score, feedback comment; Output: Revised feedback comment.

[1454] Step 9:

[1455] The server sends the final feedback comments and achievement score to the administrator's device (smartphone or tablet). The administrator can review this and use it to improve the robot's performance. Input: Revised feedback comments, achievement score; Output: Feedback and score provided to the administrator's device.

[1456] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1457] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1458] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1459] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1460] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1461] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1462] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1463] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1464] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1465] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1466] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1467] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1468] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1469] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1470] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1471] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1472] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1473] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1474] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1475] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1476] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[1477] The following is further disclosed regarding the embodiments described above.

[1478] (Claim 1)

[1479] A means of having users input target data,

[1480] A means for collecting the aforementioned target data and recording it in a database,

[1481] A means for cleansing the collected data of the aforementioned target data,

[1482] A means of setting evaluation criteria using generative artificial intelligence,

[1483] A means for evaluating the degree of achievement of the target data based on the aforementioned evaluation criteria,

[1484] A system including means for providing feedback to the user on the evaluation results of the aforementioned target data.

[1485] (Claim 2)

[1486] The system according to claim 1, wherein the evaluation criteria are set based on past evaluation data, industry standards, and organizational policies.

[1487] (Claim 3)

[1488] The system according to claim 1, wherein the generative artificial intelligence automatically generates evaluation criteria based on input data, calculates a score, and generates feedback comments.

[1489] "Example 1"

[1490] (Claim 1)

[1491] A means of having users input target data,

[1492] A means for collecting the aforementioned target data and recording it in a database,

[1493] A means for cleansing the collected data of the aforementioned target data,

[1494] A means of setting evaluation criteria using generative artificial intelligence,

[1495] A means for evaluating the degree of achievement of the target data based on the aforementioned evaluation criteria,

[1496] A means for generating feedback comments based on the aforementioned level of achievement,

[1497] A system including means for providing the user with feedback on the evaluation results of the target data and feedback comments.

[1498] (Claim 2)

[1499] The system according to claim 1, wherein the evaluation criteria are set based on past evaluation data, industry standards, and organizational policies.

[1500] (Claim 3)

[1501] The system according to claim 1, wherein the generative artificial intelligence automatically generates evaluation criteria based on input data, calculates a score, and generates feedback comments.

[1502] "Application Example 1"

[1503] (Claim 1)

[1504] A means of having users input target data,

[1505] A means for collecting the aforementioned target data and recording it in a database,

[1506] A means for cleansing the collected data of the aforementioned target data,

[1507] A means of setting evaluation criteria using generative artificial intelligence,

[1508] A means for evaluating the degree of achievement of the target data based on the aforementioned evaluation criteria,

[1509] A means for providing feedback to the user on the evaluation results of the aforementioned target data,

[1510] A means of collecting and cleansing performance data from the production system,

[1511] A means by which the generative artificial intelligence automatically generates evaluation criteria based on the performance data of the production system,

[1512] A means for evaluating the degree of achievement of production targets in the aforementioned production system and generating an achievement score and feedback comments,

[1513] A system including means for providing the aforementioned evaluation results and feedback comments to the manager of the production system.

[1514] (Claim 2)

[1515] The system according to claim 1, wherein the evaluation criteria are set based on past evaluation data, industry standards, and organizational policies.

[1516] (Claim 3)

[1517] The system according to claim 1, wherein the generative artificial intelligence automatically generates evaluation criteria based on input data, calculates a score, and generates feedback comments.

[1518] "Example 2 of combining an emotion engine"

[1519] (Claim 1)

[1520] A means of having users input target data,

[1521] A means for collecting the aforementioned target data and recording it in a database,

[1522] A means for cleansing the collected data of the aforementioned target data,

[1523] A means of setting evaluation criteria using generative artificial intelligence,

[1524] A means for evaluating the degree of achievement of the target data based on the aforementioned evaluation criteria,

[1525] A means for generating feedback comments based on the evaluation results of the aforementioned target data,

[1526] A means of recognizing a user's emotions using an emotion engine,

[1527] Means for adjusting feedback comments based on the aforementioned sentiment data,

[1528] A system including means for providing feedback to the user, such as feedback comments based on the evaluation results of the target data and sentiment data.

[1529] (Claim 2)

[1530] The system according to claim 1, wherein the evaluation criteria are set based on past evaluation data, industry standards, and organizational policies.

[1531] (Claim 3)

[1532] The system according to claim 1, wherein the generative artificial intelligence automatically generates evaluation criteria based on input data, calculates a score, and generates feedback comments.

[1533] "Application example 2 when combining with an emotional engine"

[1534] (Claim 1)

[1535] A means of having users input target data,

[1536] A means for collecting the aforementioned target data and recording it in a database,

[1537] A means for cleansing the collected data of the aforementioned target data,

[1538] A means of setting evaluation criteria using generative artificial intelligence,

[1539] A means for evaluating the degree of achievement of the target data based on the aforementioned evaluation criteria,

[1540] A means for analyzing evaluation results based on the aforementioned evaluation criteria and robot operation data, and for recognizing emotional states using an emotion engine,

[1541] A system including means for generating and providing feedback to the user that reflects the aforementioned emotional data.

[1542] (Claim 2)

[1543] The system according to claim 1, wherein the evaluation criteria are set based on past evaluation data, industry standards, and organizational policies.

[1544] (Claim 3)

[1545] The system according to claim 1, wherein the generative artificial intelligence automatically generates evaluation criteria based on input data, calculates a score, and generates feedback comments. [Explanation of Symbols]

[1546] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of having users input target data, A means for collecting the aforementioned target data and recording it in a database, A means for cleansing the collected data of the aforementioned target data, A means of setting evaluation criteria using generative artificial intelligence, A means for evaluating the degree of achievement of the target data based on the aforementioned evaluation criteria, A system including means for providing feedback to the user on the evaluation results of the aforementioned target data.

2. The system according to claim 1, wherein the evaluation criteria are set based on past evaluation data, industry standards, and organizational policies.

3. The system according to claim 1, wherein the generative artificial intelligence automatically generates evaluation criteria based on input data, calculates a score, and generates feedback comments.

Images