System

Abstract

A system is provided.SOLUTION: A system includes a means for acquiring evaluation data of an employee, a means for receiving input information from a manager, a means for generating a question for feedback and growth based on the evaluation data and the input information by using a generation model, and a means for notifying a terminal of the employee of the generated feedback and question.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In today's corporate environment, supporting employee growth and providing effective feedback is extremely important. However, the following challenges currently exist. First, young employees with a strong desire to grow want to accurately identify areas for improvement that will help them grow, but they have few opportunities to receive direct feedback from their superiors. Second, superiors often have many concerns about their subordinates' performance, but may refrain from providing feedback out of fear that repeatedly making detailed comments could damage the relationship. To address these challenges, there is a need to develop a method for providing optimized feedback to each employee while simultaneously reducing the burden on managers. [Means for solving the problem]

[0005] The present invention relates to a system that includes a means for acquiring employee evaluation data, a means for receiving input information from managers, a means for generating feedback and developmental questions based on the evaluation data and input information using a generative model, and a means for notifying employees of the generated feedback and questions via their devices. This system enables employees to receive individually optimized feedback and accurately identify areas for improvement needed for their own growth. Furthermore, by using this system, managers can reduce direct criticism and improve the quantity and quality of feedback while maintaining psychological safety. Furthermore, it provides a new communication channel that reduces the burden on managers and efficiently supports the growth of their subordinates.

[0006] "Employee evaluation data" is data that indicates information about an employee's performance or accomplishments.

[0007] "Input from management" refers to information provided by management such as feedback, instructions, and questions for employees.

[0008] A "generative model" is an algorithm or system that uses natural language processing to generate new sentences or information from data.

[0009] "Feedback" is information that provides evaluation and advice regarding an employee's behavior and performance.

[0010] "Questions for growth" are questions and instructions that encourage employees to grow and improve.

[0011] "Terminals" are devices such as computers, smartphones, and tablets used by employees and managers.

[0012] "Notification" is the act of sending certain information to a specific terminal and informing the recipient of that information. [Brief explanation of the drawings]

[0013] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0014] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0017] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0018] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0019] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0021] [First embodiment]

[0022] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0023] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0024] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0026] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0029] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0033] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0034] The system of the present invention is a platform that uses AI to individually support employee growth. This system acquires employee evaluation data and integrates it with input from managers. It then uses a generative model to generate feedback and questions for growth, and includes a series of processes that notify the employee's device.

[0035] 1. Obtaining evaluation data

[0036] The server first retrieves employee evaluation data from the company's internal evaluation database, which contains information about the employee's past performance and accomplishments.

[0037] 2. Receiving input from management

[0038] The server provides an interface for receiving input information from managers. Managers input and send questions and feedback points for each employee through their terminals. This input information is saved on the server.

[0039] 3. Generating feedback and questions

[0040] The server uses a generative model (such as a natural language generation model such as GPT-3) to generate feedback and questions for growth based on the acquired evaluation data and input information from managers. The generative model receives the evaluation data and input information as input and outputs appropriate feedback sentences and questions.

[0041] 4. Distribution of generated feedback

[0042] The server notifies the generated feedback and questions to the employee's terminal, which receives them and displays them to the user (employee). This notification is done as part of the employee's daily work.

[0043] Specific examples

[0044] Suppose a young employee at a company, Mr. A, is in charge of project management, but feels that there is room for improvement in his communication skills. His supervisor, Mr. B, uses his own device to type the question, "What are you having trouble communicating with your team members?" and sends it to the system. At the same time, evaluation data on Mr. A's recent projects is retrieved from the evaluation database. This data indicates that Mr. A's management skills are highly rated, but that there are some issues with communication.

[0045] Based on the evaluation data and the questions posed by Mr. B, the server uses a generative model to generate the following feedback and questions:

[0046] > "You've done a great job of managing project progress. But what are some of the challenges you face when communicating with your team members? Please give us some specific examples."

[0047] This feedback and question is sent as a notification to Mr. A's device, who can then check it on his own device and reply or self-evaluate.

[0048] The system of this invention makes it possible to provide effective feedback while individually supporting the growth of each employee and reducing the burden on supervisors, thereby increasing employees' motivation to grow and contributing to improving the performance of the entire company.

[0049] The processing flow will be explained below.

[0050] Step 1:

[0051] The user (supervisor) uses the terminal to enter the question they want to ask their subordinate and the feedback points they want to provide, and then clicks the send button. Specifically, they enter the "employee ID" and "question" into the input form and send it.

[0052] Step 2:

[0053] The server receives the data sent from the manager's device and receives a POST request through the API endpoint. The received data includes the employee ID and the question.

[0054] Step 3:

[0055] The server stores the received managerial input information in a database, which is then used for subsequent processing.

[0056] Step 4:

[0057] The server retrieves the evaluation data of the specified employee from the company's evaluation database, which includes information about the employee's performance and accomplishments.

[0058] Step 5:

[0059] The server creates a request to the generative model based on the acquired evaluation data and input information from the manager. The generative model receives the evaluation data and input information.

[0060] Step 6:

[0061] The server uses a generative model (such as GPT-3) to generate optimal feedback and questions for employees to help them grow. The generative model generates appropriate feedback sentences and questions based on the evaluation data and input information.

[0062] Step 7:

[0063] The server initiates a process for notifying the employee's terminal of the generated feedback and question, and sends the feedback and question using a notification service associated with the employee's terminal.

[0064] Step 8:

[0065] The terminal receives the feedback and questions sent from the server and displays them to the user (employee). The employee checks the feedback and questions on the terminal and uses them to reflect on their own behavior and work.

[0066] Step 9:

[0067] Users (employees) evaluate themselves based on the feedback and questions they receive, and reflect on their work and consider improvements as necessary. If employees want to add to or respond to the feedback, they are given the option to enter feedback again for their superiors or the system.

[0068] Example 1

[0069] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0070] Conventional feedback systems have had problems such as difficulty in effectively supporting the growth of individual employees and placing a heavy burden on managers. Furthermore, it was inefficient to integrate evaluation data with input from managers to provide appropriate feedback. This resulted in an insufficient quantity and quality of feedback, and insufficient consideration of psychological safety. Another issue was that feedback given to employees tended to be uniform, failing to address individual needs.

[0071] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0072] In this invention, the server includes means for acquiring employee evaluation data, means for extracting evaluation information for a specific employee from the evaluation database, means for receiving input information from managers, means for saving the input information and integrating it with the evaluation data, means for generating feedback and questions for growth based on the evaluation data and input information using a generative model, and means for notifying the generated feedback and questions to the employee's terminal. This enables individualized responses to each employee, improves the quantity and quality of feedback, maintains psychological safety, reduces the burden on managers, and contributes to improving the performance of the entire company.

[0073] "Employee evaluation data" means data containing information about an employee's performance or accomplishments.

[0074] An "evaluation database" is a data storage system in which employee evaluation data is stored.

[0075] "Input information from managers" refers to data collected from managers regarding feedback and questions given to employees.

[0076] A "generative model" is a machine learning model used to generate feedback and development questions based on assessment data and input information (e.g., a natural language generation model).

[0077] "Means of notification" refers to the functions and processes for sending generated feedback and questions to employees' devices.

[0078] "Employee devices" are devices such as computers and smartphones used by employees.

[0079] "Feedback" means providing specific evaluations and opinions to employees and giving advice for growth and improvement.

[0080] "Questioning" is a form of communication that includes specific questions or confirmations for employees.

[0081] "Storage and integration means" refers to the process by which input received from management is stored in a database or temporary file and combined with existing evaluation data.

[0082] An "API" is an interface that allows software applications to communicate with each other.

[0083] "Push Notification Service" means a cloud-based service for sending messages or notifications to specific devices in real time (e.g., Firebase Cloud Messaging).

[0084] The system of the present invention is a platform that uses AI to individually support employee growth. This system acquires employee evaluation data and integrates it with input from managers. It then uses a generative model to generate feedback and questions for growth, and sends them to the employee's device.

[0085] Specifically, the following hardware and software are used.

[0086] Obtaining evaluation data

[0087] The server first retrieves employee evaluation data from the company's internal evaluation database. The database management system used is, for example, MySQL or PostgreSQL. The server connects to this database and extracts the evaluation data for a specific employee (for example, employee ID "123").

[0088] Receiving input from management

[0089] The server provides a web interface to receive input from managers. This interface is built using a web application framework such as Django or Ruby on Rails. Users (managers) access the interface through their terminals, enter questions and feedback points for each employee, and send that information to the server.

[0090] Generate feedback and questions

[0091] The server generates feedback and questions for growth based on the acquired evaluation data and input information from managers using a natural language generation model (e.g., OpenAI's GPT-3). The generative model is called via an appropriate API and outputs the generated feedback sentences and questions based on the necessary input data.

[0092] For example, the following prompt sentence is input to the generative model:

[0093] Generate feedback to support employee growth. Here's the data:

[0094] Performance: Strong management skills

[0095] Challenge: Communication challenges

[0096] feedback:

[0097] Distribution of generated feedback

[0098] The server notifies the employee's device of the generated feedback and questions. Firebase Cloud Messaging (FCM) can be used as the push notification service. The device (employee's device) displays the received notification to the user. The user (employee) can check the notification and reply or self-evaluate as necessary.

[0099] Specific examples

[0100] Consider a case where a young employee, Mr. A, is in charge of project management and has room for improvement in his communication skills. His supervisor enters the question "What are you having trouble communicating with your team members?" into his own device and sends it to the system. At the same time, evaluation data on Mr. A's recent projects is retrieved from the evaluation database. Based on the evaluation data and the supervisor's question, the server uses a generative model to generate the following feedback and question:

[0101] You have been doing a great job of managing project progress, but what are some of the challenges you face when it comes to communicating with your team members? Please give us some specific examples.

[0102] This feedback and question is sent as a notification to Mr. A's device, who can then check it on his own device and reply or self-evaluate.

[0103] The system of this invention makes it possible to provide effective feedback while reducing the burden on managers and supporting the growth of each employee individually, thereby increasing employees' motivation to grow and contributing to improving the performance of the entire company.

[0104] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0105] Step 1:

[0106] The server retrieves employee evaluation data from the company's internal evaluation database. Specifically, it sends an SQL query to the database to extract evaluation data for a specific employee (e.g., "Employee ID 123"). It receives the employee ID as input and obtains evaluation data for that employee as output. This evaluation data includes the employee's performance and past evaluation history. The retrieved data is saved in internal memory or a temporary file.

[0107] Step 2:

[0108] The server provides a web interface for managers to input information. This interface is a screen where managers can enter feedback and questions for each employee. Users (managers) access this interface from their own devices and enter the necessary information. The input information includes questions such as, "What are you having trouble communicating with your team members?" This information is then sent to the server. The server stores the received input information in a database or temporary file.

[0109] Step 3:

[0110] The server integrates the acquired evaluation data with the input from the manager. Specifically, it performs data mapping and data merging processes to combine the evaluation data and the input into a single dataset. It receives the evaluation data and the input from the manager as input and obtains the integrated data as output. This integrated data is then ready to be input into the natural language generation model.

[0111] Step 4:

[0112] The server calls the API of a generative model (e.g., GPT-3) based on the integrated data. Specifically, it creates a prompt sentence and sends it to the generative model. The server converts the integrated data as input into a prompt sentence format and sends it to the generative model's API. This API outputs an appropriate feedback sentence and question.

[0113] Example prompt sentence:

[0114] Generate feedback to support employee growth. Here's the data:

[0115] Performance: Strong management skills

[0116] Challenge: Communication challenges

[0117] feedback:

[0118] Step 5:

[0119] The server notifies the employee's device of the generated feedback and questions. Specifically, it uses a push notification service such as Firebase Cloud Messaging (FCM) to send notifications to the employee's device. The server receives the feedback and questions output from the generative model as input and sends the contents to the employee's device as output.

[0120] Step 6:

[0121] The terminal (employee's device) displays the received notification to the user (employee). The user (employee) can check the notification and reply or self-evaluate as necessary. Specifically, the notification will be displayed as a pop-up, and the user can check the related feedback content from there.

[0122] The above are the specific processing steps of the program of this system.

[0123] (Application example 1)

[0124] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0125] Conventional employee growth support systems have had issues with the quality and quantity of feedback being insufficient, placing a heavy burden on managers. Furthermore, it has been difficult to provide effective feedback in certain work environments. In particular, in the operation management of autonomous vehicles, there has been a lack of feedback based on operation data, making it difficult to provide effective support for operation management.

[0126] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0127] In this invention, the server includes means for acquiring employee evaluation data, means for receiving input information from managers, means for generating feedback and questions for growth based on the evaluation data and the input information using a generative model, means for notifying the employee terminal of the generated feedback and questions, means for acquiring operation data, means for generating feedback and questions related to operation for the operator of the autonomous vehicle, and means for notifying the operator terminal of the generated feedback and questions. This makes it possible to provide individual feedback and questions not only to employees but also to the operator of the autonomous vehicle, thereby improving the quality of operation management.

[0128] An "employee" refers to an individual worker who works for an organization or company.

[0129] "Evaluation Data" refers to data that includes information about the performance and tasks of employees and autonomous vehicle operators.

[0130] A "management position" refers to a person in an organization or company who is in a position to manage and supervise subordinates or teams.

[0131] "Input information" refers to data such as feedback and questions sent by managers via their terminals.

[0132] A "generative model" refers to an algorithm or AI technology that automatically generates feedback and questions for growth based on evaluation data and input information.

[0133] "Employee devices" refers to devices such as computers, smartphones, and tablets used by employees for work.

[0134] An "autonomous vehicle" is a vehicle that can drive autonomously without the need for a human driver.

[0135] "Operation data" refers to data that includes information related to the operation of an autonomous vehicle, such as driving history, route information, traffic conditions, and weather conditions.

[0136] "Operator" refers to the person in charge of monitoring and managing the operation of autonomous vehicles.

[0137] An embodiment of this invention is a system that provides effective feedback and prompts for growth to employees and operators of autonomous vehicles. This system includes a series of processes that combines input information from managers based on employee evaluation data and autonomous vehicle operation data, generates appropriate feedback and prompts using a generative AI model, and notifies each terminal of the generated feedback and prompts.

[0138] The server collects employee evaluation data and autonomous vehicle operation data. The evaluation data includes information on past performance and achievements, while the operation data includes the autonomous vehicle's driving history, route information, traffic conditions, weather conditions, etc.

[0139] Managers use an interface to input specific feedback and development questions via their own devices, which are then stored on a server and integrated with evaluation and operational data.

[0140] The server uses a generative model (such as OpenAI's GPT-3) to generate appropriate feedback and questions for growth based on the acquired evaluation data, operational data, and input from managers. The generative model receives this data as input and outputs appropriate feedback sentences and questions.

[0141] The generated feedback and questions are sent to the devices of employees and autonomous vehicle operators, including PCs, smartphones, tablets, etc., and the information is displayed to the user.

[0142] As a concrete example, consider a case where an autonomous vehicle is in charge of operating a specific route, but needs feedback from a manager regarding the optimal routing to deal with traffic congestion and weather conditions at a specific time. The manager enters the question "Have you ever thought about how to deal with traffic congestion on Route A?" into his or her own device and sends it to the system. At the same time, the autonomous vehicle's operating data is retrieved from the evaluation database.

[0143] The server uses this information to generate feedback and prompts using a generative model, such as:

[0144] > "Recently, Route A has been operating appropriately in heavy traffic. However, what challenges do you face when weather conditions worsen? Please give specific examples."

[0145] This feedback and questions are sent as notifications to the autonomous vehicle operator's device, who can then view the feedback and provide feedback. This system provides individual feedback and questions to employees and autonomous vehicle operators, supporting their growth and reducing the burden on managers.

[0146] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0147] Step 1:

[0148] The server acquires employee evaluation data and autonomous vehicle operation data. The employee evaluation data includes information on past achievements and performance, while the autonomous vehicle operation data includes driving history, route information, traffic conditions, weather conditions, etc. The server acquires this data by accessing a database, with the input being the evaluation data and operation data and the output being data held within the server.

[0149] Step 2:

[0150] The user, a manager, uses the management interface through his / her own terminal to input feedback and questions for growth. This generates manager input information, which is sent to the server. The input is the feedback and questions from the manager, and the output is the input information stored on the server.

[0151] Step 3:

[0152] The server integrates the acquired evaluation data and operational data with input information from managers. Data processing involves appropriately formatting this data and preparing it as input data for the generative AI model. The inputs are evaluation data, operational data, and managerial input information, and the output is the integrated data to be input into the generative model.

[0153] Step 4:

[0154] The server uses a generative model (e.g., OpenAI's GPT-3) to generate feedback and questions for growth based on the integrated data. The data calculation performed here is to generate appropriate feedback sentences and questions from the evaluation data and managerial input information. The input is the integrated data, and the output is the generated feedback and questions.

[0155] Step 5:

[0156] The server notifies the generated feedback and questions to the terminals of employees and operators of autonomous vehicles. Notifications are sent in the form of push notifications, emails, etc. The input is the generated feedback and questions, and the output is the notification content displayed on the terminal.

[0157] Step 6:

[0158] The terminal displays the received feedback and questions to the user, who can then reply or provide feedback based on this information. The input is the notified feedback and questions, and the output is the user's feedback and self-evaluation.

[0159] As an example, use the following prompt:

[0160] > "Recently, Route A has been operating appropriately in heavy traffic. However, what challenges do you face when weather conditions worsen? Please give specific examples."

[0161] Through the above processing steps, the system will provide meaningful feedback and prompts for growth between the server, terminal, and user.

[0162] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0163] The system of the present invention is a platform that uses AI to individually support employee growth and provides more effective feedback by combining it with an emotion engine. This system acquires employee evaluation data and integrates it with input from managers. It then uses a generative model and emotion engine to generate feedback and questions for growth, and includes a series of processes that notify the employee's device.

[0164] 1. Acquisition of evaluation data and emotional information

[0165] The server first obtains employee evaluation data from the company's internal evaluation database. This evaluation data includes information about the employee's performance and achievements. It also uses an emotion engine to obtain the user's (employee's) emotional information. Emotional information is data that indicates how the employee is feeling. For example, voice analysis or facial expression analysis can be used.

[0166] 2. Receiving input from management

[0167] The server provides an interface for receiving input information from managers. Managers input and send questions and feedback points for each employee through their terminals. This input information is saved on the server.

[0168] 3. Generating feedback and questions

[0169] The server creates a request to the generative model based on the acquired evaluation data, emotion information, and input information from the manager.The generative model receives the evaluation data, emotion information, and input information.

[0170] The server uses a generative model (such as GPT-3) to generate optimal feedback and questions for employees to help them grow. The generative model generates appropriate feedback sentences and questions based on evaluation data, emotional information, and input information. The emotion engine provides feedback that takes into account the employee's emotional state.

[0171] 4. Distribution of generated feedback

[0172] The server notifies the generated feedback and questions to the employee's terminal, which receives them and displays them to the user (employee). This notification is done as part of the employee's daily work.

[0173] Specific examples

[0174] Suppose a young employee, Mr. A, is in charge of project management at a certain company, and in a recent evaluation, he was told that his communication skills could be improved. Mr. A seems to be feeling stressed during the progress of a recent project. His supervisor, Mr. B, types the question "What are you having trouble communicating with your team members?" into his own device and sends it to the system. At the same time, evaluation data on Mr. A's recent project is retrieved from the evaluation database.

[0175] The server uses a generative model to generate feedback and questions based on the evaluation data and the questions posed by boss B. In addition, the emotion engine recognizes that A is feeling stressed and adjusts the feedback accordingly. For example, the server generates the following feedback and questions:

[0176] "You've done a great job managing your project progress. However, you've been feeling a lot of stress lately. What are some of the areas you're having trouble communicating with your team members? Please give us some specific examples."

[0177] This feedback and question is sent as a notification to Mr. A's device, who can then check it on his own device and reply or self-evaluate.

[0178] The system of this invention enables the provision of effective feedback while individually supporting the growth of each employee, reducing the burden on managers and maintaining psychological safety. This increases employees' motivation to grow and contributes to improving the performance of the entire company. Furthermore, by combining it with an emotion engine, flexible feedback is provided that takes into account the employee's emotional state, realizing more advanced individual support.

[0179] The processing flow will be explained below.

[0180] Step 1:

[0181] The user (supervisor) uses the terminal to enter the question they want to ask their subordinate and the feedback points they want to provide, and then clicks the send button. Specifically, they enter the "employee ID" and "question" into the input form and send it.

[0182] Step 2:

[0183] The server receives the data sent from the manager's device and receives a POST request through the API endpoint. The received data includes the employee ID and the question.

[0184] Step 3:

[0185] The server stores the received managerial input information in a database, which is then used for subsequent processing.

[0186] Step 4:

[0187] The server retrieves the evaluation data of the specified employee from the company's evaluation database, which includes information about the employee's performance and accomplishments.

[0188] Step 5:

[0189] The server uses an emotion engine to acquire employee emotion data, which is acquired through voice analysis, facial expression analysis, etc. and indicates the employee's emotional state.

[0190] Step 6:

[0191] The server creates a request to the generative model based on the acquired evaluation data, emotion data, and input information from the manager. To do so, it organizes the evaluation data, emotion data, and input information and formats them as input to the generative model.

[0192] Step 7:

[0193] The server uses a generative model (such as GPT-3) to generate optimal feedback and questions for employee growth. The generative model creates feedback sentences and questions based on the input evaluation data, emotion data, and input information.

[0194] Step 8:

[0195] The server prepares to notify the generated feedback and questions to the employee's terminal, and starts the procedure for sending the feedback and questions using the notification service.

[0196] Step 9:

[0197] The terminal receives the feedback and questions sent from the server and displays them to the user (employee). The employee checks the feedback and questions on the terminal and uses them to reflect on their own behavior and work.

[0198] Step 10:

[0199] Users (employees) evaluate themselves based on the feedback and questions they receive, and reflect on their work and consider improvements as necessary. If employees want to add to or respond to the feedback, they are given the option to enter feedback again for their superiors or the system.

[0200] Example 2

[0201] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0202] Conventional employee evaluation systems did not take into account the emotional state or psychological factors of each employee, resulting in uniform and ineffective feedback. Furthermore, the burden on managers was heavy, leading to problems with insufficient feedback and support for growth. This could lead to a decline in employees' motivation to grow, hindering improvements in the company's overall performance. There was a need to solve these issues and effectively support the growth of each individual employee.

[0203] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0204] In this invention, the server includes means for acquiring employee evaluation data, means for receiving input information from managers, means for using an emotion engine to acquire emotional states, means for generating prompt sentences based on the evaluation data, emotional information, and input information, means for generating feedback and questions for growth using a generative model, and means for notifying the generated feedback and questions to the employee's terminal. This enables individual feedback that takes into account the employee's emotional state, allowing for the provision of high-quality feedback while maintaining psychological safety. Furthermore, by reducing the burden on managers and providing a new communication channel, support for employee growth can be effectively achieved.

[0205] The "means for obtaining employee evaluation data" refers to a server function for extracting information about employee performance and accomplishments from a database.

[0206] "Means for receiving input information from management" refers to the function by which the server receives feedback and questions from management as input via a web interface or API.

[0207] "Means of using an emotion engine to obtain emotional states" refers to a server function that uses technologies such as voice analysis and facial expression analysis to collect emotional information from employees and analyzes that data to understand their emotional states.

[0208] The "means for generating prompt sentences based on evaluation data, emotional information, and input information" is a function that creates appropriate prompt sentences based on the evaluation data, emotional information, and input information from the manager that the server has acquired.

[0209] The "means for generating feedback and questions for growth using a generative model" is a server function that inputs a prompt sentence into a generative model and generates feedback and questions for growth based on the results.

[0210] "Means for notifying employees of the generated feedback and questions on their devices" refers to a server function that sends and notifies employees of the generated feedback and questions via email or a dedicated application.

[0211] The system of the present invention is a platform for individually supporting employee growth, combining AI technology and an emotion engine to provide effective feedback. The main components of the system include a server, a terminal, and an emotion engine. Specific embodiments of the system of the present invention will be described below.

[0212] 1. Acquisition of rating data and emotional information

[0213] The server first connects to the company's internal evaluation database to obtain employee evaluation data. This evaluation data contains detailed information about each employee's performance, such as project progress, achievements, and behavioral evaluations. It then uses an emotion engine to obtain employee emotional information. Emotional information is obtained using technologies such as voice analysis and facial expression analysis. For example, the Alexa Voice Service can be used for voice analysis, and the Azure Face API can be used for facial expression analysis.

[0214] 2. Receiving input from management

[0215] The server provides a function to receive feedback and questions from managers through a web interface. Managers access the server from their own devices (PCs or tablets) and input feedback points and questions for specific employees. This input information is sent to the server and stored in a database.

[0216] 3. Generating feedback and questions

[0217] The server combines the acquired evaluation data, emotional information, and input from managers to generate prompts. Using advanced AI technologies such as GPT-3 as a generative model, it generates optimal feedback and questions for employee growth. Based on the emotional information acquired by the emotion engine, the content of the feedback is tailored to the emotional state of each individual employee.

[0218] For example, the following prompt statement is generated:

[0219] > Evaluation data: Mr. A's recent performance evaluation indicated that his communication skills have room for improvement.

[0220] > Emotional information: Person A is feeling stressed during the project.

[0221] > Management input: What are the communication challenges you have with your team members?

[0222] Based on this prompt, the generative model generates appropriate feedback and questions.

[0223] 4. Distribution of generated feedback

[0224] The server notifies the employee's device of the generated feedback and questions. The employee's device receives the notification and displays it to the user (employee). Notification methods include email and a dedicated application, and employees can check the received feedback and reply or self-evaluate as necessary. This ensures that the feedback process proceeds smoothly as part of their daily work.

[0225] For example, the feedback and prompt might look like this:

[0226] "You've done a great job managing your project progress. However, you've been feeling a lot of stress lately. What are some of the areas you're having trouble communicating with your team members? Please give us some specific examples."

[0227] In this way, this system can provide individual support for the growth of each employee, providing effective feedback while reducing the burden on managers. Furthermore, by using an emotion engine, flexible feedback is provided that takes into account the employee's emotional state, enabling more advanced individual support.

[0228] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0229] Step 1:

[0230] The server executes a query to retrieve employee evaluation data from the company's internal evaluation database. The evaluation data includes project progress, performance, and behavioral evaluations. Executing this query imports the evaluation data into the server. Next, an emotion engine is used to obtain the employee's emotional information. Emotional information is obtained using voice analysis and facial expression analysis, for example, using the Alexa Voice Service or Azure Face API. The voice data and facial expression data are processed as input, and then quantified emotional data is output.

[0231] input:

[0232] Employee evaluation database

[0233] Employee voice data and facial expression data

[0234] output:

[0235] Evaluation Data

[0236] Emotional Data

[0237] Specific behavior:

[0238] The server periodically queries the reputation database to obtain the latest reputation data.

[0239] The server passes the voice and facial expression data to the emotion engine and acquires the emotion data.

[0240] Step 2:

[0241] The server provides a web interface for receiving feedback and questions from managers. Managers can use their terminals to send input information for specific employees. The server receives this input information and stores it in a database. Feedback points and specific questions are entered as input information, and the received data is stored in the database within the server.

[0242] input:

[0243] Feedback and inquiries sent from the manager's terminal

[0244] output:

[0245] Management input stored in a database

[0246] Specific behavior:

[0247] Managers enter their feedback into a dedicated web form and click the submit button.

[0248] The server stores the data received via the API in a database.

[0249] Step 3:

[0250] The server combines the evaluation data, emotion data, and input from managers to create prompts to be input into the generative model. These prompts include the employee's evaluation results, emotional state, and questions from managers. The data is formatted using Python scripts and passed to the generative model "GPT-3." The generative model then uses this data to generate feedback and questions for growth.

[0251] input:

[0252] Evaluation Data

[0253] Emotional Data

[0254] Management input

[0255] output:

[0256] Prompt sentence to input to the generative model

[0257] Feedback and Prompts

[0258] Specific behavior:

[0259] The server retrieves the required information from the database using a query.

[0260] The server converts the data into prompt statements using a Python script and sends them to the Generative Model API.

[0261] Step 4:

[0262] A generative model is used to generate feedback and questions for growth. The generative model generates the optimal sentence based on the input prompt. This creates individual feedback tailored to the employee. The feedback and questions returned by the generative model are stored on the server.

[0263] input:

[0264] Prompt statement

[0265] output:

[0266] Feedback Statement

[0267] Question

[0268] Specific behavior:

[0269] The server sends the prompt text to the Generative Model API via a POST request.

[0270] The server receives the response from the generative model and stores its contents.

[0271] Step 5:

[0272] The server notifies the employee's device of the generated feedback and questions. Notification methods include email and a dedicated application. The employee's device displays the received notification on its screen. The employee (user) can check the notification content and reply or self-evaluate as necessary.

[0273] input:

[0274] Feedback and questions obtained from the generative model

[0275] output:

[0276] Feedback notification delivered to employee devices

[0277] Specific behavior:

[0278] The server sends the notification using a mail server or push notification service.

[0279] The employee's device receives the notification and displays the contents.

[0280] (Application example 2)

[0281] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0282] Conventional feedback systems provide uniform feedback without considering evaluation data or emotional information, which means that they are unable to adequately support the individual growth of workers or manage their stress. In particular, in work environments such as factories, where improved work efficiency and real-time feedback are required, providing appropriate support is difficult. Furthermore, it is difficult for busy managers to efficiently support their subordinates while maintaining the quality of feedback.

[0283] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring evaluation data and emotion information, means for receiving input information from managers, means for generating feedback and questions for growth based on the evaluation data, emotion information, and input information using a generative model, means for notifying the terminal of the generated feedback and questions, and means for adjusting the feedback content using an emotion engine. This enables improved work efficiency and stress management. It also reduces the burden on managers and provides a new communication channel for supporting the growth of individual workers.

[0284] "Evaluation data" is information that indicates the achievements, performance, efficiency, etc. of workers or employees.

[0285] "Emotional information" is data that indicates the emotional state and psychological condition of workers or employees, and is obtained through voice analysis, facial expression analysis, etc.

[0286] A "generative model" is an algorithmic model that generates appropriate feedback or questions based on given data. A representative example is GPT-3.

[0287] The "emotion engine" is a system that analyzes the user's emotional state and adjusts the feedback content to match the user's emotions.

[0288] "Feedback" refers to advice or guidance provided to workers or employees based on evaluation data and emotional information.

[0289] "Questions" are questions or prompts generated by the generative model to encourage the growth of workers or employees.

[0290] "Terminals" are external devices used by workers or employees, including smartphones, smart glasses, head-mounted displays, robots, etc.

[0291] "Notification" refers to the act of sending the generated feedback or question to the terminal and displaying it to the user.

[0292] "Work efficiency" refers to the efficiency with which a worker performs work within a certain period of time, and refers to the speed and accuracy of the work.

[0293] "Stress management" refers to methods and means for appropriately controlling the stress that workers feel during work and maintaining a comfortable working environment.

[0294] "Psychological safety" refers to a state in which workers and employees feel free to express their opinions and feelings without feeling any psychological pressure when receiving feedback or evaluations.

[0295] "Communication channels" refer to the means and methods for exchanging information and data between management and workers or employees.

[0296] The system of the present invention is configured by combining multiple technical elements to provide individual feedback and growth support to workers in a factory. Specific embodiments are described below.

[0297] System Configuration

[0298] This system uses the following hardware and software:

[0299] Hardware: smart glasses, servers, sensors for voice and facial expression analysis

[0300] Software: reputation database, managerial interface, generative models (e.g., GPT-3), sentiment engine, notification system

[0301] Program processing description

[0302] The system provides workers with appropriate feedback and development support by taking the following steps:

[0303] 1. Acquisition of rating data and emotional information

[0304] The smart glasses worn by the workers are equipped with built-in sensors for voice and facial expression analysis. These sensors collect the worker's voice and facial expression information in real time and send it to a server.

[0305] The server retrieves worker evaluation data from the company's internal evaluation database, including information on achievements, performance, and efficiency.

[0306] 2. Receiving input from management

[0307] Managers enter feedback and questions for each worker through a dedicated web interface, and this information is stored on a server.

[0308] 3. Generating feedback and questions

[0309] The server uses a generative model (such as GPT-3) to generate optimal feedback and questions based on the acquired evaluation data, emotional information, and input from managers.

[0310] Additionally, the emotion engine adjusts this feedback content to match the worker's emotional state.

[0311] 4. Distribution of generated feedback

[0312] The server notifies the smart glasses of the generated feedback and questions, which then display the feedback and questions to the worker in real time.

[0313] Specific examples

[0314] A real-life example is a young factory worker named Mr. A. He was recently promoted to manager of a new product line, but evaluation data shows he has issues with efficiency and stress management. Mr. A wears smart glasses while working.

[0315] Boss B inputs the question, "What situations at work cause you particular stress?" into the system and sends it. At the same time, recent performance data for Person A is retrieved from the evaluation database, and sensors in the smart glasses collect facial expressions and voice information from Person A.

[0316] The server uses a generative model (such as GPT-3) based on the acquired data to generate feedback and questions like the following:

[0317] > "Your recent work on your new product line has been great, but I'd like to find ways to reduce the stress you're experiencing. What tasks in particular stress you out? Please be specific."

[0318] This feedback is displayed in real time on Mr. A's smart glasses, and Mr. A can read it and enter his own opinions as needed. Through this activity, Mr. A receives support from his supervisor for his own stress management and receives specific feedback for his growth.

[0319] Example prompt for a generative AI model:

[0320] "Based on the worker's evaluation data, emotional state, and managerial feedback, develop feedback and questions such as the following. Evaluation data includes worker efficiency and stress levels."

[0321] This system allows for individual feedback and support for each worker, reducing the burden on managers while maintaining psychological safety for workers.

[0322] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0323] Step 1: Obtaining rating data and emotional information

[0324] Input: The smart glasses have built-in voice and facial expression analysis sensors that collect the worker's voice and facial expression information in real time. The server also retrieves the worker's evaluation data from the company's internal evaluation database.

[0325] Specific operation: The sensor collects voice and facial expression data and transmits them to the server via the smart glasses. The server accesses the evaluation database and obtains the necessary evaluation data.

[0326] Output: The server receives the worker's voice, facial expression data, and evaluation data.

[0327] Step 2: Receiving input from management

[0328] Input: Managers input feedback and questions for each worker through a dedicated web interface.

[0329] Specific actions: Managers access the web interface, enter feedback or questions in text format, and send it to the server.

[0330] Output: The server receives and stores feedback and questions from managers.

[0331] Step 3: Generate feedback and questions

[0332] Input: appraisal data, emotional information, and managerial input

[0333] Specific operation: The server integrates these data and inputs them into a generative model (e.g., GPT-3). The generative model generates appropriate feedback and questions based on the prompt. Furthermore, an emotion engine analyzes the worker's emotional state and adjusts the feedback appropriately.

[0334] Output: The server retrieves the feedback and questions obtained from the generative model.

[0335] Step 4: Distributing generated feedback

[0336] Input: Generated feedback and questions

[0337] Specific operation: The server notifies the smart glasses of the generated feedback and questions. The smart glasses, upon receiving the notification, display the feedback and questions to the worker.

[0338] Output: Feedback and prompts are displayed on the worker's smart glasses.

[0339] At each step, servers, smart glasses, sensors, and other devices work together to quickly and accurately acquire, process, generate, and distribute data, providing effective feedback and support for worker development.

[0340] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0341] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0342] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0343] [Second embodiment]

[0344] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0345] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0346] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0347] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0348] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0349] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0350] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0351] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0352] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0353] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0354] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0355] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0356] The system of the present invention is a platform that uses AI to individually support employee growth. This system acquires employee evaluation data and integrates it with input from managers. It then uses a generative model to generate feedback and questions for growth, and includes a series of processes that notify the employee's device.

[0357] 1. Obtaining evaluation data

[0358] The server first retrieves employee evaluation data from the company's internal evaluation database, which contains information about the employee's past performance and accomplishments.

[0359] 2. Receiving input from management

[0360] The server provides an interface for receiving input information from managers. Managers input and send questions and feedback points for each employee through their terminals. This input information is saved on the server.

[0361] 3. Generating feedback and questions

[0362] The server uses a generative model (such as a natural language generation model such as GPT-3) to generate feedback and questions for growth based on the acquired evaluation data and input information from managers. The generative model receives the evaluation data and input information as input and outputs appropriate feedback sentences and questions.

[0363] 4. Distribution of generated feedback

[0364] The server notifies the generated feedback and questions to the employee's terminal, which receives them and displays them to the user (employee). This notification is done as part of the employee's daily work.

[0365] Specific examples

[0366] Suppose a young employee at a company, Mr. A, is in charge of project management, but feels that there is room for improvement in his communication skills. His supervisor, Mr. B, uses his own device to type the question, "What are you having trouble communicating with your team members?" and sends it to the system. At the same time, evaluation data on Mr. A's recent projects is retrieved from the evaluation database. This data indicates that Mr. A's management skills are highly rated, but that there are some issues with communication.

[0367] Based on the evaluation data and the questions posed by Mr. B, the server uses a generative model to generate the following feedback and questions:

[0368] > "You've done a great job of managing project progress. But what are some of the challenges you face when communicating with your team members? Please give us some specific examples."

[0369] This feedback and question is sent as a notification to Mr. A's device, who can then check it on his own device and reply or self-evaluate.

[0370] The system of this invention makes it possible to provide effective feedback while individually supporting the growth of each employee and reducing the burden on supervisors, thereby increasing employees' motivation to grow and contributing to improving the performance of the entire company.

[0371] The processing flow will be explained below.

[0372] Step 1:

[0373] The user (supervisor) uses the terminal to enter the question they want to ask their subordinate and the feedback points they want to provide, and then clicks the send button. Specifically, they enter the "employee ID" and "question" into the input form and send it.

[0374] Step 2:

[0375] The server receives the data sent from the manager's device and receives a POST request through the API endpoint. The received data includes the employee ID and the question.

[0376] Step 3:

[0377] The server stores the received managerial input information in a database, which is then used for subsequent processing.

[0378] Step 4:

[0379] The server retrieves the evaluation data of the specified employee from the company's evaluation database, which includes information about the employee's performance and accomplishments.

[0380] Step 5:

[0381] The server creates a request to the generative model based on the acquired evaluation data and input information from the manager. The generative model receives the evaluation data and input information.

[0382] Step 6:

[0383] The server uses a generative model (such as GPT-3) to generate optimal feedback and questions for employees to help them grow. The generative model generates appropriate feedback sentences and questions based on the evaluation data and input information.

[0384] Step 7:

[0385] The server initiates a process for notifying the employee's terminal of the generated feedback and question, and sends the feedback and question using a notification service associated with the employee's terminal.

[0386] Step 8:

[0387] The terminal receives the feedback and questions sent from the server and displays them to the user (employee). The employee checks the feedback and questions on the terminal and uses them to reflect on their own behavior and work.

[0388] Step 9:

[0389] Users (employees) evaluate themselves based on the feedback and questions they receive, and reflect on their work and consider improvements as necessary. If employees want to add to or respond to the feedback, they are given the option to enter feedback again for their superiors or the system.

[0390] Example 1

[0391] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0392] Conventional feedback systems have had problems such as difficulty in effectively supporting the growth of individual employees and placing a heavy burden on managers. Furthermore, it was inefficient to integrate evaluation data with input from managers to provide appropriate feedback. This resulted in an insufficient quantity and quality of feedback, and insufficient consideration of psychological safety. Another issue was that feedback given to employees tended to be uniform, failing to address individual needs.

[0393] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0394] In this invention, the server includes means for acquiring employee evaluation data, means for extracting evaluation information for a specific employee from the evaluation database, means for receiving input information from managers, means for saving the input information and integrating it with the evaluation data, means for generating feedback and questions for growth based on the evaluation data and input information using a generative model, and means for notifying the generated feedback and questions to the employee's terminal. This enables individualized responses to each employee, improves the quantity and quality of feedback, maintains psychological safety, reduces the burden on managers, and contributes to improving the performance of the entire company.

[0395] "Employee evaluation data" means data containing information about an employee's performance or accomplishments.

[0396] An "evaluation database" is a data storage system in which employee evaluation data is stored.

[0397] "Input information from managers" refers to data collected from managers regarding feedback and questions given to employees.

[0398] A "generative model" is a machine learning model used to generate feedback and development questions based on assessment data and input information (e.g., a natural language generation model).

[0399] "Means of notification" refers to the functions and processes for sending generated feedback and questions to employees' devices.

[0400] "Employee devices" are devices such as computers and smartphones used by employees.

[0401] "Feedback" means providing specific evaluations and opinions to employees and giving advice for growth and improvement.

[0402] "Questioning" is a form of communication that includes specific questions or confirmations for employees.

[0403] "Storage and integration means" refers to the process by which input received from management is stored in a database or temporary file and combined with existing evaluation data.

[0404] An "API" is an interface that allows software applications to communicate with each other.

[0405] "Push Notification Service" means a cloud-based service for sending messages or notifications to specific devices in real time (e.g., Firebase Cloud Messaging).

[0406] The system of the present invention is a platform that uses AI to individually support employee growth. This system acquires employee evaluation data and integrates it with input from managers. It then uses a generative model to generate feedback and questions for growth, and sends them to the employee's device.

[0407] Specifically, the following hardware and software are used.

[0408] Obtaining evaluation data

[0409] The server first retrieves employee evaluation data from the company's internal evaluation database. The database management system used is, for example, MySQL or PostgreSQL. The server connects to this database and extracts the evaluation data for a specific employee (for example, employee ID "123").

[0410] Receiving input from management

[0411] The server provides a web interface to receive input from managers. This interface is built using a web application framework such as Django or Ruby on Rails. Users (managers) access the interface through their terminals, enter questions and feedback points for each employee, and send that information to the server.

[0412] Generate feedback and questions

[0413] The server generates feedback and questions for growth based on the acquired evaluation data and input information from managers using a natural language generation model (e.g., OpenAI's GPT-3). The generative model is called via an appropriate API and outputs the generated feedback sentences and questions based on the necessary input data.

[0414] For example, the following prompt sentence is input to the generative model:

[0415] Generate feedback to support employee growth. Here's the data:

[0416] Performance: Strong management skills

[0417] Challenge: Communication challenges

[0418] feedback:

[0419] Distribution of generated feedback

[0420] The server notifies the employee's device of the generated feedback and questions. Firebase Cloud Messaging (FCM) can be used as the push notification service. The device (employee's device) displays the received notification to the user. The user (employee) can check the notification and reply or self-evaluate as necessary.

[0421] Specific examples

[0422] Consider a case where a young employee, Mr. A, is in charge of project management and has room for improvement in his communication skills. His supervisor enters the question "What are you having trouble communicating with your team members?" into his own device and sends it to the system. At the same time, evaluation data on Mr. A's recent projects is retrieved from the evaluation database. Based on the evaluation data and the supervisor's question, the server uses a generative model to generate the following feedback and question:

[0423] You have been doing a great job of managing project progress, but what are some of the challenges you face when it comes to communicating with your team members? Please give us some specific examples.

[0424] This feedback and question is sent as a notification to Mr. A's device, who can then check it on his own device and reply or self-evaluate.

[0425] The system of this invention makes it possible to provide effective feedback while reducing the burden on managers and supporting the growth of each employee individually, thereby increasing employees' motivation to grow and contributing to improving the performance of the entire company.

[0426] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0427] Step 1:

[0428] The server retrieves employee evaluation data from the company's internal evaluation database. Specifically, it sends an SQL query to the database to extract evaluation data for a specific employee (e.g., "Employee ID 123"). It receives the employee ID as input and obtains evaluation data for that employee as output. This evaluation data includes the employee's performance and past evaluation history. The retrieved data is saved in internal memory or a temporary file.

[0429] Step 2:

[0430] The server provides a web interface for managers to input information. This interface is a screen where managers can enter feedback and questions for each employee. Users (managers) access this interface from their own devices and enter the necessary information. The input information includes questions such as, "What are you having trouble communicating with your team members?" This information is then sent to the server. The server stores the received input information in a database or temporary file.

[0431] Step 3:

[0432] The server integrates the acquired evaluation data with the input from the manager. Specifically, it performs data mapping and data merging processes to combine the evaluation data and the input into a single dataset. It receives the evaluation data and the input from the manager as input and obtains the integrated data as output. This integrated data is then ready to be input into the natural language generation model.

[0433] Step 4:

[0434] The server calls the API of a generative model (e.g., GPT-3) based on the integrated data. Specifically, it creates a prompt sentence and sends it to the generative model. The server converts the integrated data as input into a prompt sentence format and sends it to the generative model's API. This API outputs an appropriate feedback sentence and question.

[0435] Example prompt sentence:

[0436] Generate feedback to support employee growth. Here's the data:

[0437] Performance: Strong management skills

[0438] Challenge: Communication challenges

[0439] feedback:

[0440] Step 5:

[0441] The server notifies the employee's device of the generated feedback and questions. Specifically, it uses a push notification service such as Firebase Cloud Messaging (FCM) to send notifications to the employee's device. The server receives the feedback and questions output from the generative model as input and sends the contents to the employee's device as output.

[0442] Step 6:

[0443] The terminal (employee's device) displays the received notification to the user (employee). The user (employee) can check the notification and reply or self-evaluate as necessary. Specifically, the notification will be displayed as a pop-up, and the user can check the related feedback content from there.

[0444] The above are the specific processing steps of the program of this system.

[0445] (Application example 1)

[0446] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0447] Conventional employee growth support systems have had issues with the quality and quantity of feedback being insufficient, placing a heavy burden on managers. Furthermore, it has been difficult to provide effective feedback in certain work environments. In particular, in the operation management of autonomous vehicles, there has been a lack of feedback based on operation data, making it difficult to provide effective support for operation management.

[0448] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0449] In this invention, the server includes means for acquiring employee evaluation data, means for receiving input information from managers, means for generating feedback and questions for growth based on the evaluation data and the input information using a generative model, means for notifying the employee terminal of the generated feedback and questions, means for acquiring operation data, means for generating feedback and questions related to operation for the operator of the autonomous vehicle, and means for notifying the operator terminal of the generated feedback and questions. This makes it possible to provide individual feedback and questions not only to employees but also to the operator of the autonomous vehicle, thereby improving the quality of operation management.

[0450] An "employee" refers to an individual worker who works for an organization or company.

[0451] "Evaluation Data" refers to data that includes information about the performance and tasks of employees and autonomous vehicle operators.

[0452] A "management position" refers to a person in an organization or company who is in a position to manage and supervise subordinates or teams.

[0453] "Input information" refers to data such as feedback and questions sent by managers via their terminals.

[0454] A "generative model" refers to an algorithm or AI technology that automatically generates feedback and questions for growth based on evaluation data and input information.

[0455] "Employee devices" refers to devices such as computers, smartphones, and tablets used by employees for work.

[0456] An "autonomous vehicle" is a vehicle that can drive autonomously without the need for a human driver.

[0457] "Operation data" refers to data that includes information related to the operation of an autonomous vehicle, such as driving history, route information, traffic conditions, and weather conditions.

[0458] "Operator" refers to the person in charge of monitoring and managing the operation of autonomous vehicles.

[0459] An embodiment of this invention is a system that provides effective feedback and prompts for growth to employees and operators of autonomous vehicles. This system includes a series of processes that combines input information from managers based on employee evaluation data and autonomous vehicle operation data, generates appropriate feedback and prompts using a generative AI model, and notifies each terminal of the generated feedback and prompts.

[0460] The server collects employee evaluation data and autonomous vehicle operation data. The evaluation data includes information on past performance and achievements, while the operation data includes the autonomous vehicle's driving history, route information, traffic conditions, weather conditions, etc.

[0461] Managers use an interface to input specific feedback and development questions via their own devices, which are then stored on a server and integrated with evaluation and operational data.

[0462] The server uses a generative model (such as OpenAI's GPT-3) to generate appropriate feedback and questions for growth based on the acquired evaluation data, operational data, and input from managers. The generative model receives this data as input and outputs appropriate feedback sentences and questions.

[0463] The generated feedback and questions are sent to the devices of employees and autonomous vehicle operators, including PCs, smartphones, tablets, etc., and the information is displayed to the user.

[0464] As a concrete example, consider a case where an autonomous vehicle is in charge of operating a specific route, but needs feedback from a manager regarding the optimal routing to deal with traffic congestion and weather conditions at a specific time. The manager enters the question "Have you ever thought about how to deal with traffic congestion on Route A?" into his or her own device and sends it to the system. At the same time, the autonomous vehicle's operating data is retrieved from the evaluation database.

[0465] The server uses this information to generate feedback and prompts using a generative model, such as:

[0466] > "Recently, Route A has been operating appropriately in heavy traffic. However, what challenges do you face when weather conditions worsen? Please give specific examples."

[0467] This feedback and questions are sent as notifications to the autonomous vehicle operator's device, who can then view the feedback and provide feedback. This system provides individual feedback and questions to employees and autonomous vehicle operators, supporting their growth and reducing the burden on managers.

[0468] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0469] Step 1:

[0470] The server acquires employee evaluation data and autonomous vehicle operation data. The employee evaluation data includes information on past achievements and performance, while the autonomous vehicle operation data includes driving history, route information, traffic conditions, weather conditions, etc. The server acquires this data by accessing a database, with the input being the evaluation data and operation data and the output being data held within the server.

[0471] Step 2:

[0472] The user, a manager, uses the management interface through his / her own terminal to input feedback and questions for growth. This generates manager input information, which is sent to the server. The input is the feedback and questions from the manager, and the output is the input information stored on the server.

[0473] Step 3:

[0474] The server integrates the acquired evaluation data and operational data with input information from managers. Data processing involves appropriately formatting this data and preparing it as input data for the generative AI model. The inputs are evaluation data, operational data, and managerial input information, and the output is the integrated data to be input into the generative model.

[0475] Step 4:

[0476] The server uses a generative model (e.g., OpenAI's GPT-3) to generate feedback and questions for growth based on the integrated data. The data calculation performed here is to generate appropriate feedback sentences and questions from the evaluation data and managerial input information. The input is the integrated data, and the output is the generated feedback and questions.

[0477] Step 5:

[0478] The server notifies the generated feedback and questions to the terminals of employees and operators of autonomous vehicles. Notifications are sent in the form of push notifications, emails, etc. The input is the generated feedback and questions, and the output is the notification content displayed on the terminal.

[0479] Step 6:

[0480] The terminal displays the received feedback and questions to the user, who can then reply or provide feedback based on this information. The input is the notified feedback and questions, and the output is the user's feedback and self-evaluation.

[0481] As an example, use the following prompt:

[0482] > "Recently, Route A has been operating appropriately in heavy traffic. However, what challenges do you face when weather conditions worsen? Please give specific examples."

[0483] Through the above processing steps, the system will provide meaningful feedback and prompts for growth between the server, terminal, and user.

[0484] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0485] The system of the present invention is a platform that uses AI to individually support employee growth and provides more effective feedback by combining it with an emotion engine. This system acquires employee evaluation data and integrates it with input from managers. It then uses a generative model and emotion engine to generate feedback and questions for growth, and includes a series of processes that notify the employee's device.

[0486] 1. Acquisition of evaluation data and emotional information

[0487] The server first obtains employee evaluation data from the company's internal evaluation database. This evaluation data includes information about the employee's performance and achievements. It also uses an emotion engine to obtain the user's (employee's) emotional information. Emotional information is data that indicates how the employee is feeling. For example, voice analysis or facial expression analysis can be used.

[0488] 2. Receiving input from management

[0489] The server provides an interface for receiving input information from managers. Managers input and send questions and feedback points for each employee through their terminals. This input information is saved on the server.

[0490] 3. Generating feedback and questions

[0491] The server creates a request to the generative model based on the acquired evaluation data, emotion information, and input information from the manager.The generative model receives the evaluation data, emotion information, and input information.

[0492] The server uses a generative model (such as GPT-3) to generate optimal feedback and questions for employees to help them grow. The generative model generates appropriate feedback sentences and questions based on evaluation data, emotional information, and input information. The emotion engine provides feedback that takes into account the employee's emotional state.

[0493] 4. Distribution of generated feedback

[0494] The server notifies the generated feedback and questions to the employee's terminal, which receives them and displays them to the user (employee). This notification is done as part of the employee's daily work.

[0495] Specific examples

[0496] Suppose a young employee, Mr. A, is in charge of project management at a certain company, and in a recent evaluation, he was told that his communication skills could be improved. Mr. A seems to be feeling stressed during the progress of a recent project. His supervisor, Mr. B, types the question "What are you having trouble communicating with your team members?" into his own device and sends it to the system. At the same time, evaluation data on Mr. A's recent project is retrieved from the evaluation database.

[0497] The server uses a generative model to generate feedback and questions based on the evaluation data and the questions posed by boss B. In addition, the emotion engine recognizes that A is feeling stressed and adjusts the feedback accordingly. For example, the server generates the following feedback and questions:

[0498] "You've done a great job managing your project progress. However, you've been feeling a lot of stress lately. What are some of the areas you're having trouble communicating with your team members? Please give us some specific examples."

[0499] This feedback and question is sent as a notification to Mr. A's device, who can then check it on his own device and reply or self-evaluate.

[0500] The system of this invention enables the provision of effective feedback while individually supporting the growth of each employee, reducing the burden on managers and maintaining psychological safety. This increases employees' motivation to grow and contributes to improving the performance of the entire company. Furthermore, by combining it with an emotion engine, flexible feedback is provided that takes into account the employee's emotional state, realizing more advanced individual support.

[0501] The processing flow will be explained below.

[0502] Step 1:

[0503] The user (supervisor) uses the terminal to enter the question they want to ask their subordinate and the feedback points they want to provide, and then clicks the send button. Specifically, they enter the "employee ID" and "question" into the input form and send it.

[0504] Step 2:

[0505] The server receives the data sent from the manager's device and receives a POST request through the API endpoint. The received data includes the employee ID and the question.

[0506] Step 3:

[0507] The server stores the received managerial input information in a database, which is then used for subsequent processing.

[0508] Step 4:

[0509] The server retrieves the evaluation data of the specified employee from the company's evaluation database, which includes information about the employee's performance and accomplishments.

[0510] Step 5:

[0511] The server uses an emotion engine to acquire employee emotion data, which is acquired through voice analysis, facial expression analysis, etc. and indicates the employee's emotional state.

[0512] Step 6:

[0513] The server creates a request to the generative model based on the acquired evaluation data, emotion data, and input information from the manager. To do so, it organizes the evaluation data, emotion data, and input information and formats them as input to the generative model.

[0514] Step 7:

[0515] The server uses a generative model (such as GPT-3) to generate optimal feedback and questions for employee growth. The generative model creates feedback sentences and questions based on the input evaluation data, emotion data, and input information.

[0516] Step 8:

[0517] The server prepares to notify the generated feedback and questions to the employee's terminal, and starts the procedure for sending the feedback and questions using the notification service.

[0518] Step 9:

[0519] The terminal receives the feedback and questions sent from the server and displays them to the user (employee). The employee checks the feedback and questions on the terminal and uses them to reflect on their own behavior and work.

[0520] Step 10:

[0521] Users (employees) evaluate themselves based on the feedback and questions they receive, and reflect on their work and consider improvements as necessary. If employees want to add to or respond to the feedback, they are given the option to enter feedback again for their superiors or the system.

[0522] Example 2

[0523] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0524] Conventional employee evaluation systems did not take into account the emotional state or psychological factors of each employee, resulting in uniform and ineffective feedback. Furthermore, the burden on managers was heavy, leading to problems with insufficient feedback and support for growth. This could lead to a decline in employees' motivation to grow, hindering improvements in the company's overall performance. There was a need to solve these issues and effectively support the growth of each individual employee.

[0525] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0526] In this invention, the server includes means for acquiring employee evaluation data, means for receiving input information from managers, means for using an emotion engine to acquire emotional states, means for generating prompt sentences based on the evaluation data, emotional information, and input information, means for generating feedback and questions for growth using a generative model, and means for notifying the generated feedback and questions to the employee's terminal. This enables individual feedback that takes into account the employee's emotional state, allowing for the provision of high-quality feedback while maintaining psychological safety. Furthermore, by reducing the burden on managers and providing a new communication channel, support for employee growth can be effectively achieved.

[0527] The "means for obtaining employee evaluation data" refers to a server function for extracting information about employee performance and accomplishments from a database.

[0528] "Means for receiving input information from management" refers to the function by which the server receives feedback and questions from management as input via a web interface or API.

[0529] "Means of using an emotion engine to obtain emotional states" refers to a server function that uses technologies such as voice analysis and facial expression analysis to collect emotional information from employees and analyzes that data to understand their emotional states.

[0530] The "means for generating prompt sentences based on evaluation data, emotional information, and input information" is a function that creates appropriate prompt sentences based on the evaluation data, emotional information, and input information from the manager that the server has acquired.

[0531] The "means for generating feedback and questions for growth using a generative model" is a server function that inputs a prompt sentence into a generative model and generates feedback and questions for growth based on the results.

[0532] "Means for notifying employees of the generated feedback and questions on their devices" refers to a server function that sends and notifies employees of the generated feedback and questions via email or a dedicated application.

[0533] The system of the present invention is a platform for individually supporting employee growth, combining AI technology and an emotion engine to provide effective feedback. The main components of the system include a server, a terminal, and an emotion engine. Specific embodiments of the system of the present invention will be described below.

[0534] 1. Acquisition of rating data and emotional information

[0535] The server first connects to the company's internal evaluation database to obtain employee evaluation data. This evaluation data contains detailed information about each employee's performance, such as project progress, achievements, and behavioral evaluations. It then uses an emotion engine to obtain employee emotional information. Emotional information is obtained using technologies such as voice analysis and facial expression analysis. For example, the Alexa Voice Service can be used for voice analysis, and the Azure Face API can be used for facial expression analysis.

[0536] 2. Receiving input from management

[0537] The server provides a function to receive feedback and questions from managers through a web interface. Managers access the server from their own devices (PCs or tablets) and input feedback points and questions for specific employees. This input information is sent to the server and stored in a database.

[0538] 3. Generating feedback and questions

[0539] The server combines the acquired evaluation data, emotional information, and input from managers to generate prompts. Using advanced AI technologies such as GPT-3 as a generative model, it generates optimal feedback and questions for employee growth. Based on the emotional information acquired by the emotion engine, the content of the feedback is tailored to the emotional state of each individual employee.

[0540] For example, the following prompt statement is generated:

[0541] > Evaluation data: Mr. A's recent performance evaluation indicated that his communication skills have room for improvement.

[0542] > Emotional information: Person A is feeling stressed during the project.

[0543] > Management input: What are the communication challenges you have with your team members?

[0544] Based on this prompt, the generative model generates appropriate feedback and questions.

[0545] 4. Distribution of generated feedback

[0546] The server notifies the employee's device of the generated feedback and questions. The employee's device receives the notification and displays it to the user (employee). Notification methods include email and a dedicated application, and employees can check the received feedback and reply or self-evaluate as necessary. This ensures that the feedback process proceeds smoothly as part of their daily work.

[0547] For example, the feedback and prompt might look like this:

[0548] "You've done a great job managing your project progress. However, you've been feeling a lot of stress lately. What are some of the areas you're having trouble communicating with your team members? Please give us some specific examples."

[0549] In this way, this system can provide individual support for the growth of each employee, providing effective feedback while reducing the burden on managers. Furthermore, by using an emotion engine, flexible feedback is provided that takes into account the employee's emotional state, enabling more advanced individual support.

[0550] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0551] Step 1:

[0552] The server executes a query to retrieve employee evaluation data from the company's internal evaluation database. The evaluation data includes project progress, performance, and behavioral evaluations. Executing this query imports the evaluation data into the server. Next, an emotion engine is used to obtain the employee's emotional information. Emotional information is obtained using voice analysis and facial expression analysis, for example, using the Alexa Voice Service or Azure Face API. The voice data and facial expression data are processed as input, and then quantified emotional data is output.

[0553] input:

[0554] Employee evaluation database

[0555] Employee voice data and facial expression data

[0556] output:

[0557] Evaluation Data

[0558] Emotional Data

[0559] Specific behavior:

[0560] The server periodically queries the reputation database to obtain the latest reputation data.

[0561] The server passes the voice and facial expression data to the emotion engine and acquires the emotion data.

[0562] Step 2:

[0563] The server provides a web interface for receiving feedback and questions from managers. Managers can use their terminals to send input information for specific employees. The server receives this input information and stores it in a database. Feedback points and specific questions are entered as input information, and the received data is stored in the database within the server.

[0564] input:

[0565] Feedback and inquiries sent from the manager's terminal

[0566] output:

[0567] Management input stored in a database

[0568] Specific behavior:

[0569] Managers enter their feedback into a dedicated web form and click the submit button.

[0570] The server stores the data received via the API in a database.

[0571] Step 3:

[0572] The server combines the evaluation data, emotion data, and input from managers to create prompts to be input into the generative model. These prompts include the employee's evaluation results, emotional state, and questions from managers. The data is formatted using Python scripts and passed to the generative model "GPT-3." The generative model then uses this data to generate feedback and questions for growth.

[0573] input:

[0574] Evaluation Data

[0575] Emotional Data

[0576] Management input

[0577] output:

[0578] Prompt sentence to input to the generative model

[0579] Feedback and Prompts

[0580] Specific behavior:

[0581] The server retrieves the required information from the database using a query.

[0582] The server converts the data into prompt statements using a Python script and sends them to the Generative Model API.

[0583] Step 4:

[0584] A generative model is used to generate feedback and questions for growth. The generative model generates the optimal sentence based on the input prompt. This creates individual feedback tailored to the employee. The feedback and questions returned by the generative model are stored on the server.

[0585] input:

[0586] Prompt statement

[0587] output:

[0588] Feedback Statement

[0589] Question

[0590] Specific behavior:

[0591] The server sends the prompt text to the Generative Model API via a POST request.

[0592] The server receives the response from the generative model and stores its contents.

[0593] Step 5:

[0594] The server notifies the employee's device of the generated feedback and questions. Notification methods include email and a dedicated application. The employee's device displays the received notification on its screen. The employee (user) can check the notification content and reply or self-evaluate as necessary.

[0595] input:

[0596] Feedback and questions obtained from the generative model

[0597] output:

[0598] Feedback notification delivered to employee devices

[0599] Specific behavior:

[0600] The server sends the notification using a mail server or push notification service.

[0601] The employee's device receives the notification and displays the contents.

[0602] (Application example 2)

[0603] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0604] Conventional feedback systems provide uniform feedback without considering evaluation data or emotional information, which means that they are unable to adequately support the individual growth of workers or manage their stress. In particular, in work environments such as factories, where improved work efficiency and real-time feedback are required, providing appropriate support is difficult. Furthermore, it is difficult for busy managers to efficiently support their subordinates while maintaining the quality of feedback.

[0605] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring evaluation data and emotion information, means for receiving input information from managers, means for generating feedback and questions for growth based on the evaluation data, emotion information, and input information using a generative model, means for notifying the terminal of the generated feedback and questions, and means for adjusting the feedback content using an emotion engine. This enables improved work efficiency and stress management. It also reduces the burden on managers and provides a new communication channel for supporting the growth of individual workers.

[0606] "Evaluation data" is information that indicates the achievements, performance, efficiency, etc. of workers or employees.

[0607] "Emotional information" is data that indicates the emotional state and psychological condition of workers or employees, and is obtained through voice analysis, facial expression analysis, etc.

[0608] A "generative model" is an algorithmic model that generates appropriate feedback or questions based on given data. A representative example is GPT-3.

[0609] The "emotion engine" is a system that analyzes the user's emotional state and adjusts the feedback content to match the user's emotions.

[0610] "Feedback" refers to advice or guidance provided to workers or employees based on evaluation data and emotional information.

[0611] "Questions" are questions or prompts generated by the generative model to encourage the growth of workers or employees.

[0612] "Terminals" are external devices used by workers or employees, including smartphones, smart glasses, head-mounted displays, robots, etc.

[0613] "Notification" refers to the act of sending the generated feedback or question to the terminal and displaying it to the user.

[0614] "Work efficiency" refers to the efficiency with which a worker performs work within a certain period of time, and refers to the speed and accuracy of the work.

[0615] "Stress management" refers to methods and means for appropriately controlling the stress that workers feel during work and maintaining a comfortable working environment.

[0616] "Psychological safety" refers to a state in which workers and employees feel free to express their opinions and feelings without feeling any psychological pressure when receiving feedback or evaluations.

[0617] "Communication channels" refer to the means and methods for exchanging information and data between management and workers or employees.

[0618] The system of the present invention is configured by combining multiple technical elements to provide individual feedback and growth support to workers in a factory. Specific embodiments are described below.

[0619] System Configuration

[0620] This system uses the following hardware and software:

[0621] Hardware: smart glasses, servers, sensors for voice and facial expression analysis

[0622] Software: reputation database, managerial interface, generative models (e.g., GPT-3), sentiment engine, notification system

[0623] Program processing description

[0624] The system provides workers with appropriate feedback and development support by taking the following steps:

[0625] 1. Acquisition of rating data and emotional information

[0626] The smart glasses worn by the workers are equipped with built-in sensors for voice and facial expression analysis. These sensors collect the worker's voice and facial expression information in real time and send it to a server.

[0627] The server retrieves worker evaluation data from the company's internal evaluation database, including information on achievements, performance, and efficiency.

[0628] 2. Receiving input from management

[0629] Managers enter feedback and questions for each worker through a dedicated web interface, and this information is stored on a server.

[0630] 3. Generating feedback and questions

[0631] The server uses a generative model (such as GPT-3) to generate optimal feedback and questions based on the acquired evaluation data, emotional information, and input from managers.

[0632] Additionally, the emotion engine adjusts this feedback content to match the worker's emotional state.

[0633] 4. Distribution of generated feedback

[0634] The server notifies the smart glasses of the generated feedback and questions, which then display the feedback and questions to the worker in real time.

[0635] Specific examples

[0636] A real-life example is a young factory worker named Mr. A. He was recently promoted to manager of a new product line, but evaluation data shows he has issues with efficiency and stress management. Mr. A wears smart glasses while working.

[0637] Boss B inputs the question, "What situations at work cause you particular stress?" into the system and sends it. At the same time, recent performance data for Person A is retrieved from the evaluation database, and sensors in the smart glasses collect facial expressions and voice information from Person A.

[0638] The server uses a generative model (such as GPT-3) based on the acquired data to generate feedback and questions like the following:

[0639] > "Your recent work on your new product line has been great, but I'd like to find ways to reduce the stress you're experiencing. What tasks in particular stress you out? Please be specific."

[0640] This feedback is displayed in real time on Mr. A's smart glasses, and Mr. A can read it and enter his own opinions as needed. Through this activity, Mr. A receives support from his supervisor for his own stress management and receives specific feedback for his growth.

[0641] Example prompt for a generative AI model:

[0642] "Based on the worker's evaluation data, emotional state, and managerial feedback, develop feedback and questions such as the following. Evaluation data includes worker efficiency and stress levels."

[0643] This system allows for individual feedback and support for each worker, reducing the burden on managers while maintaining psychological safety for workers.

[0644] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0645] Step 1: Obtaining rating data and emotional information

[0646] Input: The smart glasses have built-in voice and facial expression analysis sensors that collect the worker's voice and facial expression information in real time. The server also retrieves the worker's evaluation data from the company's internal evaluation database.

[0647] Specific operation: The sensor collects voice and facial expression data and transmits them to the server via the smart glasses. The server accesses the evaluation database and obtains the necessary evaluation data.

[0648] Output: The server receives the worker's voice, facial expression data, and evaluation data.

[0649] Step 2: Receiving input from management

[0650] Input: Managers input feedback and questions for each worker through a dedicated web interface.

[0651] Specific actions: Managers access the web interface, enter feedback or questions in text format, and send it to the server.

[0652] Output: The server receives and stores feedback and questions from managers.

[0653] Step 3: Generate feedback and questions

[0654] Input: appraisal data, emotional information, and managerial input

[0655] Specific operation: The server integrates these data and inputs them into a generative model (e.g., GPT-3). The generative model generates appropriate feedback and questions based on the prompt. Furthermore, an emotion engine analyzes the worker's emotional state and adjusts the feedback appropriately.

[0656] Output: The server retrieves the feedback and questions obtained from the generative model.

[0657] Step 4: Distributing generated feedback

[0658] Input: Generated feedback and questions

[0659] Specific operation: The server notifies the smart glasses of the generated feedback and questions. The smart glasses, upon receiving the notification, display the feedback and questions to the worker.

[0660] Output: Feedback and prompts are displayed on the worker's smart glasses.

[0661] At each step, servers, smart glasses, sensors, and other devices work together to quickly and accurately acquire, process, generate, and distribute data, providing effective feedback and support for worker development.

[0662] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0663] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0664] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0665] [Third embodiment]

[0666] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0667] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0668] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0669] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0670] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0671] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0672] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0673] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0674] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0675] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0676] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0677] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0678] The system of the present invention is a platform that uses AI to individually support employee growth. This system acquires employee evaluation data and integrates it with input from managers. It then uses a generative model to generate feedback and questions for growth, and includes a series of processes that notify the employee's device.

[0679] 1. Obtaining evaluation data

[0680] The server first retrieves employee evaluation data from the company's internal evaluation database, which contains information about the employee's past performance and accomplishments.

[0681] 2. Receiving input from management

[0682] The server provides an interface for receiving input information from managers. Managers input and send questions and feedback points for each employee through their terminals. This input information is saved on the server.

[0683] 3. Generating feedback and questions

[0684] The server uses a generative model (such as a natural language generation model such as GPT-3) to generate feedback and questions for growth based on the acquired evaluation data and input information from managers. The generative model receives the evaluation data and input information as input and outputs appropriate feedback sentences and questions.

[0685] 4. Distribution of generated feedback

[0686] The server notifies the generated feedback and questions to the employee's terminal, which receives them and displays them to the user (employee). This notification is done as part of the employee's daily work.

[0687] Specific examples

[0688] Suppose a young employee at a company, Mr. A, is in charge of project management, but feels that there is room for improvement in his communication skills. His supervisor, Mr. B, uses his own device to type the question, "What are you having trouble communicating with your team members?" and sends it to the system. At the same time, evaluation data on Mr. A's recent projects is retrieved from the evaluation database. This data indicates that Mr. A's management skills are highly rated, but that there are some issues with communication.

[0689] Based on the evaluation data and the questions posed by Mr. B, the server uses a generative model to generate the following feedback and questions:

[0690] > "You've done a great job of managing project progress. But what are some of the challenges you face when communicating with your team members? Please give us some specific examples."

[0691] This feedback and question is sent as a notification to Mr. A's device, who can then check it on his own device and reply or self-evaluate.

[0692] The system of this invention makes it possible to provide effective feedback while individually supporting the growth of each employee and reducing the burden on supervisors, thereby increasing employees' motivation to grow and contributing to improving the performance of the entire company.

[0693] The processing flow will be explained below.

[0694] Step 1:

[0695] The user (supervisor) uses the terminal to enter the question they want to ask their subordinate and the feedback points they want to provide, and then clicks the send button. Specifically, they enter the "employee ID" and "question" into the input form and send it.

[0696] Step 2:

[0697] The server receives the data sent from the manager's device and receives a POST request through the API endpoint. The received data includes the employee ID and the question.

[0698] Step 3:

[0699] The server stores the received managerial input information in a database, which is then used for subsequent processing.

[0700] Step 4:

[0701] The server retrieves the evaluation data of the specified employee from the company's evaluation database, which includes information about the employee's performance and accomplishments.

[0702] Step 5:

[0703] The server creates a request to the generative model based on the acquired evaluation data and input information from the manager. The generative model receives the evaluation data and input information.

[0704] Step 6:

[0705] The server uses a generative model (such as GPT-3) to generate optimal feedback and questions for employees to help them grow. The generative model generates appropriate feedback sentences and questions based on the evaluation data and input information.

[0706] Step 7:

[0707] The server initiates a process for notifying the employee's terminal of the generated feedback and question, and sends the feedback and question using a notification service associated with the employee's terminal.

[0708] Step 8:

[0709] The terminal receives the feedback and questions sent from the server and displays them to the user (employee). The employee checks the feedback and questions on the terminal and uses them to reflect on their own behavior and work.

[0710] Step 9:

[0711] Users (employees) evaluate themselves based on the feedback and questions they receive, and reflect on their work and consider improvements as necessary. If employees want to add to or respond to the feedback, they are given the option to enter feedback again for their superiors or the system.

[0712] Example 1

[0713] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0714] Conventional feedback systems have had problems such as difficulty in effectively supporting the growth of individual employees and placing a heavy burden on managers. Furthermore, it was inefficient to integrate evaluation data with input from managers to provide appropriate feedback. This resulted in an insufficient quantity and quality of feedback, and insufficient consideration of psychological safety. Another issue was that feedback given to employees tended to be uniform, failing to address individual needs.

[0715] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0716] In this invention, the server includes means for acquiring employee evaluation data, means for extracting evaluation information for a specific employee from the evaluation database, means for receiving input information from managers, means for saving the input information and integrating it with the evaluation data, means for generating feedback and questions for growth based on the evaluation data and input information using a generative model, and means for notifying the generated feedback and questions to the employee's terminal. This enables individualized responses to each employee, improves the quantity and quality of feedback, maintains psychological safety, reduces the burden on managers, and contributes to improving the performance of the entire company.

[0717] "Employee evaluation data" means data containing information about an employee's performance or accomplishments.

[0718] An "evaluation database" is a data storage system in which employee evaluation data is stored.

[0719] "Input information from managers" refers to data collected from managers regarding feedback and questions given to employees.

[0720] A "generative model" is a machine learning model used to generate feedback and development questions based on assessment data and input information (e.g., a natural language generation model).

[0721] "Means of notification" refers to the functions and processes for sending generated feedback and questions to employees' devices.

[0722] "Employee devices" are devices such as computers and smartphones used by employees.

[0723] "Feedback" means providing specific evaluations and opinions to employees and giving advice for growth and improvement.

[0724] "Questioning" is a form of communication that includes specific questions or confirmations for employees.

[0725] "Storage and integration means" refers to the process by which input received from management is stored in a database or temporary file and combined with existing evaluation data.

[0726] An "API" is an interface that allows software applications to communicate with each other.

[0727] "Push Notification Service" means a cloud-based service for sending messages or notifications to specific devices in real time (e.g., Firebase Cloud Messaging).

[0728] The system of the present invention is a platform that uses AI to individually support employee growth. This system acquires employee evaluation data and integrates it with input from managers. It then uses a generative model to generate feedback and questions for growth, and sends them to the employee's device.

[0729] Specifically, the following hardware and software are used.

[0730] Obtaining evaluation data

[0731] The server first retrieves employee evaluation data from the company's internal evaluation database. The database management system used is, for example, MySQL or PostgreSQL. The server connects to this database and extracts the evaluation data for a specific employee (for example, employee ID "123").

[0732] Receiving input from management

[0733] The server provides a web interface to receive input from managers. This interface is built using a web application framework such as Django or Ruby on Rails. Users (managers) access the interface through their terminals, enter questions and feedback points for each employee, and send that information to the server.

[0734] Generate feedback and questions

[0735] The server generates feedback and questions for growth based on the acquired evaluation data and input information from managers using a natural language generation model (e.g., OpenAI's GPT-3). The generative model is called via an appropriate API and outputs the generated feedback sentences and questions based on the necessary input data.

[0736] For example, the following prompt sentence is input to the generative model:

[0737] Generate feedback to support employee growth. Here's the data:

[0738] Performance: Strong management skills

[0739] Challenge: Communication challenges

[0740] feedback:

[0741] Distribution of generated feedback

[0742] The server notifies the employee's device of the generated feedback and questions. Firebase Cloud Messaging (FCM) can be used as the push notification service. The device (employee's device) displays the received notification to the user. The user (employee) can check the notification and reply or self-evaluate as necessary.

[0743] Specific examples

[0744] Consider a case where a young employee, Mr. A, is in charge of project management and has room for improvement in his communication skills. His supervisor enters the question "What are you having trouble communicating with your team members?" into his own device and sends it to the system. At the same time, evaluation data on Mr. A's recent projects is retrieved from the evaluation database. Based on the evaluation data and the supervisor's question, the server uses a generative model to generate the following feedback and question:

[0745] You have been doing a great job of managing project progress, but what are some of the challenges you face when it comes to communicating with your team members? Please give us some specific examples.

[0746] This feedback and question is sent as a notification to Mr. A's device, who can then check it on his own device and reply or self-evaluate.

[0747] The system of this invention makes it possible to provide effective feedback while reducing the burden on managers and supporting the growth of each employee individually, thereby increasing employees' motivation to grow and contributing to improving the performance of the entire company.

[0748] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0749] Step 1:

[0750] The server retrieves employee evaluation data from the company's internal evaluation database. Specifically, it sends an SQL query to the database to extract evaluation data for a specific employee (e.g., "Employee ID 123"). It receives the employee ID as input and obtains evaluation data for that employee as output. This evaluation data includes the employee's performance and past evaluation history. The retrieved data is saved in internal memory or a temporary file.

[0751] Step 2:

[0752] The server provides a web interface for managers to input information. This interface is a screen where managers can enter feedback and questions for each employee. Users (managers) access this interface from their own devices and enter the necessary information. The input information includes questions such as, "What are you having trouble communicating with your team members?" This information is then sent to the server. The server stores the received input information in a database or temporary file.

[0753] Step 3:

[0754] The server integrates the acquired evaluation data with the input from the manager. Specifically, it performs data mapping and data merging processes to combine the evaluation data and the input into a single dataset. It receives the evaluation data and the input from the manager as input and obtains the integrated data as output. This integrated data is then ready to be input into the natural language generation model.

[0755] Step 4:

[0756] The server calls the API of a generative model (e.g., GPT-3) based on the integrated data. Specifically, it creates a prompt sentence and sends it to the generative model. The server converts the integrated data as input into a prompt sentence format and sends it to the generative model's API. This API outputs an appropriate feedback sentence and question.

[0757] Example prompt sentence:

[0758] Generate feedback to support employee growth. Here's the data:

[0759] Performance: Strong management skills

[0760] Challenge: Communication challenges

[0761] feedback:

[0762] Step 5:

[0763] The server notifies the employee's device of the generated feedback and questions. Specifically, it uses a push notification service such as Firebase Cloud Messaging (FCM) to send notifications to the employee's device. The server receives the feedback and questions output from the generative model as input and sends the contents to the employee's device as output.

[0764] Step 6:

[0765] The terminal (employee's device) displays the received notification to the user (employee). The user (employee) can check the notification and reply or self-evaluate as necessary. Specifically, the notification will be displayed as a pop-up, and the user can check the related feedback content from there.

[0766] The above are the specific processing steps of the program of this system.

[0767] (Application example 1)

[0768] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0769] Conventional employee growth support systems have had issues with the quality and quantity of feedback being insufficient, placing a heavy burden on managers. Furthermore, it has been difficult to provide effective feedback in certain work environments. In particular, in the operation management of autonomous vehicles, there has been a lack of feedback based on operation data, making it difficult to provide effective support for operation management.

[0770] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0771] In this invention, the server includes means for acquiring employee evaluation data, means for receiving input information from managers, means for generating feedback and questions for growth based on the evaluation data and the input information using a generative model, means for notifying the employee terminal of the generated feedback and questions, means for acquiring operation data, means for generating feedback and questions related to operation for the operator of the autonomous vehicle, and means for notifying the operator terminal of the generated feedback and questions. This makes it possible to provide individual feedback and questions not only to employees but also to the operator of the autonomous vehicle, thereby improving the quality of operation management.

[0772] An "employee" refers to an individual worker who works for an organization or company.

[0773] "Evaluation Data" refers to data that includes information about the performance and tasks of employees and autonomous vehicle operators.

[0774] A "management position" refers to a person in an organization or company who is in a position to manage and supervise subordinates or teams.

[0775] "Input information" refers to data such as feedback and questions sent by managers via their terminals.

[0776] A "generative model" refers to an algorithm or AI technology that automatically generates feedback and questions for growth based on evaluation data and input information.

[0777] "Employee devices" refers to devices such as computers, smartphones, and tablets used by employees for work.

[0778] An "autonomous vehicle" is a vehicle that can drive autonomously without the need for a human driver.

[0779] "Operation data" refers to data that includes information related to the operation of an autonomous vehicle, such as driving history, route information, traffic conditions, and weather conditions.

[0780] "Operator" refers to the person in charge of monitoring and managing the operation of autonomous vehicles.

[0781] An embodiment of this invention is a system that provides effective feedback and prompts for growth to employees and operators of autonomous vehicles. This system includes a series of processes that combines input information from managers based on employee evaluation data and autonomous vehicle operation data, generates appropriate feedback and prompts using a generative AI model, and notifies each terminal of the generated feedback and prompts.

[0782] The server collects employee evaluation data and autonomous vehicle operation data. The evaluation data includes information on past performance and achievements, while the operation data includes the autonomous vehicle's driving history, route information, traffic conditions, weather conditions, etc.

[0783] Managers use an interface to input specific feedback and development questions via their own devices, which are then stored on a server and integrated with evaluation and operational data.

[0784] The server uses a generative model (such as OpenAI's GPT-3) to generate appropriate feedback and questions for growth based on the acquired evaluation data, operational data, and input from managers. The generative model receives this data as input and outputs appropriate feedback sentences and questions.

[0785] The generated feedback and questions are sent to the devices of employees and autonomous vehicle operators, including PCs, smartphones, tablets, etc., and the information is displayed to the user.

[0786] As a concrete example, consider a case where an autonomous vehicle is in charge of operating a specific route, but needs feedback from a manager regarding the optimal routing to deal with traffic congestion and weather conditions at a specific time. The manager enters the question "Have you ever thought about how to deal with traffic congestion on Route A?" into his or her own device and sends it to the system. At the same time, the autonomous vehicle's operating data is retrieved from the evaluation database.

[0787] The server uses this information to generate feedback and prompts using a generative model, such as:

[0788] > "Recently, Route A has been operating appropriately in heavy traffic. However, what challenges do you face when weather conditions worsen? Please give specific examples."

[0789] This feedback and questions are sent as notifications to the autonomous vehicle operator's device, who can then view the feedback and provide feedback. This system provides individual feedback and questions to employees and autonomous vehicle operators, supporting their growth and reducing the burden on managers.

[0790] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0791] Step 1:

[0792] The server acquires employee evaluation data and autonomous vehicle operation data. The employee evaluation data includes information on past achievements and performance, while the autonomous vehicle operation data includes driving history, route information, traffic conditions, weather conditions, etc. The server acquires this data by accessing a database, with the input being the evaluation data and operation data and the output being data held within the server.

[0793] Step 2:

[0794] The user, a manager, uses the management interface through his / her own terminal to input feedback and questions for growth. This generates manager input information, which is sent to the server. The input is the feedback and questions from the manager, and the output is the input information stored on the server.

[0795] Step 3:

[0796] The server integrates the acquired evaluation data and operational data with input information from managers. Data processing involves appropriately formatting this data and preparing it as input data for the generative AI model. The inputs are evaluation data, operational data, and managerial input information, and the output is the integrated data to be input into the generative model.

[0797] Step 4:

[0798] The server uses a generative model (e.g., OpenAI's GPT-3) to generate feedback and questions for growth based on the integrated data. The data calculation performed here is to generate appropriate feedback sentences and questions from the evaluation data and managerial input information. The input is the integrated data, and the output is the generated feedback and questions.

[0799] Step 5:

[0800] The server notifies the generated feedback and questions to the terminals of employees and operators of autonomous vehicles. Notifications are sent in the form of push notifications, emails, etc. The input is the generated feedback and questions, and the output is the notification content displayed on the terminal.

[0801] Step 6:

[0802] The terminal displays the received feedback and questions to the user, who can then reply or provide feedback based on this information. The input is the notified feedback and questions, and the output is the user's feedback and self-evaluation.

[0803] As an example, use the following prompt:

[0804] > "Recently, Route A has been operating appropriately in heavy traffic. However, what challenges do you face when weather conditions worsen? Please give specific examples."

[0805] Through the above processing steps, the system will provide meaningful feedback and prompts for growth between the server, terminal, and user.

[0806] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0807] The system of the present invention is a platform that uses AI to individually support employee growth and provides more effective feedback by combining it with an emotion engine. This system acquires employee evaluation data and integrates it with input from managers. It then uses a generative model and emotion engine to generate feedback and questions for growth, and includes a series of processes that notify the employee's device.

[0808] 1. Acquisition of evaluation data and emotional information

[0809] The server first obtains employee evaluation data from the company's internal evaluation database. This evaluation data includes information about the employee's performance and achievements. It also uses an emotion engine to obtain the user's (employee's) emotional information. Emotional information is data that indicates how the employee is feeling. For example, voice analysis or facial expression analysis can be used.

[0810] 2. Receiving input from management

[0811] The server provides an interface for receiving input information from managers. Managers input and send questions and feedback points for each employee through their terminals. This input information is saved on the server.

[0812] 3. Generating feedback and questions

[0813] The server creates a request to the generative model based on the acquired evaluation data, emotion information, and input information from the manager.The generative model receives the evaluation data, emotion information, and input information.

[0814] The server uses a generative model (such as GPT-3) to generate optimal feedback and questions for employees to help them grow. The generative model generates appropriate feedback sentences and questions based on evaluation data, emotional information, and input information. The emotion engine provides feedback that takes into account the employee's emotional state.

[0815] 4. Distribution of generated feedback

[0816] The server notifies the generated feedback and questions to the employee's terminal, which receives them and displays them to the user (employee). This notification is done as part of the employee's daily work.

[0817] Specific examples

[0818] Suppose a young employee, Mr. A, is in charge of project management at a certain company, and in a recent evaluation, he was told that his communication skills could be improved. Mr. A seems to be feeling stressed during the progress of a recent project. His supervisor, Mr. B, types the question "What are you having trouble communicating with your team members?" into his own device and sends it to the system. At the same time, evaluation data on Mr. A's recent project is retrieved from the evaluation database.

[0819] The server uses a generative model to generate feedback and questions based on the evaluation data and the questions posed by boss B. In addition, the emotion engine recognizes that A is feeling stressed and adjusts the feedback accordingly. For example, the server generates the following feedback and questions:

[0820] "You've done a great job managing your project progress. However, you've been feeling a lot of stress lately. What are some of the areas you're having trouble communicating with your team members? Please give us some specific examples."

[0821] This feedback and question is sent as a notification to Mr. A's device, who can then check it on his own device and reply or self-evaluate.

[0822] The system of this invention enables the provision of effective feedback while individually supporting the growth of each employee, reducing the burden on managers and maintaining psychological safety. This increases employees' motivation to grow and contributes to improving the performance of the entire company. Furthermore, by combining it with an emotion engine, flexible feedback is provided that takes into account the employee's emotional state, realizing more advanced individual support.

[0823] The processing flow will be explained below.

[0824] Step 1:

[0825] The user (supervisor) uses the terminal to enter the question they want to ask their subordinate and the feedback points they want to provide, and then clicks the send button. Specifically, they enter the "employee ID" and "question" into the input form and send it.

[0826] Step 2:

[0827] The server receives the data sent from the manager's device and receives a POST request through the API endpoint. The received data includes the employee ID and the question.

[0828] Step 3:

[0829] The server stores the received managerial input information in a database, which is then used for subsequent processing.

[0830] Step 4:

[0831] The server retrieves the evaluation data of the specified employee from the company's evaluation database, which includes information about the employee's performance and accomplishments.

[0832] Step 5:

[0833] The server uses an emotion engine to acquire employee emotion data, which is acquired through voice analysis, facial expression analysis, etc. and indicates the employee's emotional state.

[0834] Step 6:

[0835] The server creates a request to the generative model based on the acquired evaluation data, emotion data, and input information from the manager. To do so, it organizes the evaluation data, emotion data, and input information and formats them as input to the generative model.

[0836] Step 7:

[0837] The server uses a generative model (such as GPT-3) to generate optimal feedback and questions for employee growth. The generative model creates feedback sentences and questions based on the input evaluation data, emotion data, and input information.

[0838] Step 8:

[0839] The server prepares to notify the generated feedback and questions to the employee's terminal, and starts the procedure for sending the feedback and questions using the notification service.

[0840] Step 9:

[0841] The terminal receives the feedback and questions sent from the server and displays them to the user (employee). The employee checks the feedback and questions on the terminal and uses them to reflect on their own behavior and work.

[0842] Step 10:

[0843] Users (employees) evaluate themselves based on the feedback and questions they receive, and reflect on their work and consider improvements as necessary. If employees want to add to or respond to the feedback, they are given the option to enter feedback again for their superiors or the system.

[0844] Example 2

[0845] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0846] Conventional employee evaluation systems did not take into account the emotional state or psychological factors of each employee, resulting in uniform and ineffective feedback. Furthermore, the burden on managers was heavy, leading to problems with insufficient feedback and support for growth. This could lead to a decline in employees' motivation to grow, hindering improvements in the company's overall performance. There was a need to solve these issues and effectively support the growth of each individual employee.

[0847] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0848] In this invention, the server includes means for acquiring employee evaluation data, means for receiving input information from managers, means for using an emotion engine to acquire emotional states, means for generating prompt sentences based on the evaluation data, emotional information, and input information, means for generating feedback and questions for growth using a generative model, and means for notifying the generated feedback and questions to the employee's terminal. This enables individual feedback that takes into account the employee's emotional state, allowing for the provision of high-quality feedback while maintaining psychological safety. Furthermore, by reducing the burden on managers and providing a new communication channel, support for employee growth can be effectively achieved.

[0849] The "means for obtaining employee evaluation data" refers to a server function for extracting information about employee performance and accomplishments from a database.

[0850] "Means for receiving input information from management" refers to the function by which the server receives feedback and questions from management as input via a web interface or API.

[0851] "Means of using an emotion engine to obtain emotional states" refers to a server function that uses technologies such as voice analysis and facial expression analysis to collect emotional information from employees and analyzes that data to understand their emotional states.

[0852] The "means for generating prompt sentences based on evaluation data, emotional information, and input information" is a function that creates appropriate prompt sentences based on the evaluation data, emotional information, and input information from the manager that the server has acquired.

[0853] The "means for generating feedback and questions for growth using a generative model" is a server function that inputs a prompt sentence into a generative model and generates feedback and questions for growth based on the results.

[0854] "Means for notifying employees of the generated feedback and questions on their devices" refers to a server function that sends and notifies employees of the generated feedback and questions via email or a dedicated application.

[0855] The system of the present invention is a platform for individually supporting employee growth, combining AI technology and an emotion engine to provide effective feedback. The main components of the system include a server, a terminal, and an emotion engine. Specific embodiments of the system of the present invention will be described below.

[0856] 1. Acquisition of rating data and emotional information

[0857] The server first connects to the company's internal evaluation database to obtain employee evaluation data. This evaluation data contains detailed information about each employee's performance, such as project progress, achievements, and behavioral evaluations. It then uses an emotion engine to obtain employee emotional information. Emotional information is obtained using technologies such as voice analysis and facial expression analysis. For example, the Alexa Voice Service can be used for voice analysis, and the Azure Face API can be used for facial expression analysis.

[0858] 2. Receiving input from management

[0859] The server provides a function to receive feedback and questions from managers through a web interface. Managers access the server from their own devices (PCs or tablets) and input feedback points and questions for specific employees. This input information is sent to the server and stored in a database.

[0860] 3. Generating feedback and questions

[0861] The server combines the acquired evaluation data, emotional information, and input from managers to generate prompts. Using advanced AI technologies such as GPT-3 as a generative model, it generates optimal feedback and questions for employee growth. Based on the emotional information acquired by the emotion engine, the content of the feedback is tailored to the emotional state of each individual employee.

[0862] For example, the following prompt statement is generated:

[0863] > Evaluation data: Mr. A's recent performance evaluation indicated that his communication skills have room for improvement.

[0864] > Emotional information: Person A is feeling stressed during the project.

[0865] > Management input: What are the communication challenges you have with your team members?

[0866] Based on this prompt, the generative model generates appropriate feedback and questions.

[0867] 4. Distribution of generated feedback

[0868] The server notifies the employee's device of the generated feedback and questions. The employee's device receives the notification and displays it to the user (employee). Notification methods include email and a dedicated application, and employees can check the received feedback and reply or self-evaluate as necessary. This ensures that the feedback process proceeds smoothly as part of their daily work.

[0869] For example, the feedback and prompt might look like this:

[0870] "You've done a great job managing your project progress. However, you've been feeling a lot of stress lately. What are some of the areas you're having trouble communicating with your team members? Please give us some specific examples."

[0871] In this way, this system can provide individual support for the growth of each employee, providing effective feedback while reducing the burden on managers. Furthermore, by using an emotion engine, flexible feedback is provided that takes into account the employee's emotional state, enabling more advanced individual support.

[0872] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0873] Step 1:

[0874] The server executes a query to retrieve employee evaluation data from the company's internal evaluation database. The evaluation data includes project progress, performance, and behavioral evaluations. Executing this query imports the evaluation data into the server. Next, an emotion engine is used to obtain the employee's emotional information. Emotional information is obtained using voice analysis and facial expression analysis, for example, using the Alexa Voice Service or Azure Face API. The voice data and facial expression data are processed as input, and then quantified emotional data is output.

[0875] input:

[0876] Employee evaluation database

[0877] Employee voice data and facial expression data

[0878] output:

[0879] Evaluation Data

[0880] Emotional Data

[0881] Specific behavior:

[0882] The server periodically queries the reputation database to obtain the latest reputation data.

[0883] The server passes the voice and facial expression data to the emotion engine and acquires the emotion data.

[0884] Step 2:

[0885] The server provides a web interface for receiving feedback and questions from managers. Managers can use their terminals to send input information for specific employees. The server receives this input information and stores it in a database. Feedback points and specific questions are entered as input information, and the received data is stored in the database within the server.

[0886] input:

[0887] Feedback and inquiries sent from the manager's terminal

[0888] output:

[0889] Management input stored in a database

[0890] Specific behavior:

[0891] Managers enter their feedback into a dedicated web form and click the submit button.

[0892] The server stores the data received via the API in a database.

[0893] Step 3:

[0894] The server combines the evaluation data, emotion data, and input from managers to create prompts to be input into the generative model. These prompts include the employee's evaluation results, emotional state, and questions from managers. The data is formatted using Python scripts and passed to the generative model "GPT-3." The generative model then uses this data to generate feedback and questions for growth.

[0895] input:

[0896] Evaluation Data

[0897] Emotional Data

[0898] Management input

[0899] output:

[0900] Prompt sentence to input to the generative model

[0901] Feedback and Prompts

[0902] Specific behavior:

[0903] The server retrieves the required information from the database using a query.

[0904] The server converts the data into prompt statements using a Python script and sends them to the Generative Model API.

[0905] Step 4:

[0906] A generative model is used to generate feedback and questions for growth. The generative model generates the optimal sentence based on the input prompt. This creates individual feedback tailored to the employee. The feedback and questions returned by the generative model are stored on the server.

[0907] input:

[0908] Prompt statement

[0909] output:

[0910] Feedback Statement

[0911] Question

[0912] Specific behavior:

[0913] The server sends the prompt text to the Generative Model API via a POST request.

[0914] The server receives the response from the generative model and stores its contents.

[0915] Step 5:

[0916] The server notifies the employee's device of the generated feedback and questions. Notification methods include email and a dedicated application. The employee's device displays the received notification on its screen. The employee (user) can check the notification content and reply or self-evaluate as necessary.

[0917] input:

[0918] Feedback and questions obtained from the generative model

[0919] output:

[0920] Feedback notification delivered to employee devices

[0921] Specific behavior:

[0922] The server sends the notification using a mail server or push notification service.

[0923] The employee's device receives the notification and displays the contents.

[0924] (Application example 2)

[0925] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0926] Conventional feedback systems provide uniform feedback without considering evaluation data or emotional information, which means that they are unable to adequately support the individual growth of workers or manage their stress. In particular, in work environments such as factories, where improved work efficiency and real-time feedback are required, providing appropriate support is difficult. Furthermore, it is difficult for busy managers to efficiently support their subordinates while maintaining the quality of feedback.

[0927] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring evaluation data and emotion information, means for receiving input information from managers, means for generating feedback and questions for growth based on the evaluation data, emotion information, and input information using a generative model, means for notifying the terminal of the generated feedback and questions, and means for adjusting the feedback content using an emotion engine. This enables improved work efficiency and stress management. It also reduces the burden on managers and provides a new communication channel for supporting the growth of individual workers.

[0928] "Evaluation data" is information that indicates the achievements, performance, efficiency, etc. of workers or employees.

[0929] "Emotional information" is data that indicates the emotional state and psychological condition of workers or employees, and is obtained through voice analysis, facial expression analysis, etc.

[0930] A "generative model" is an algorithmic model that generates appropriate feedback or questions based on given data. A representative example is GPT-3.

[0931] The "emotion engine" is a system that analyzes the user's emotional state and adjusts the feedback content to match the user's emotions.

[0932] "Feedback" refers to advice or guidance provided to workers or employees based on evaluation data and emotional information.

[0933] "Questions" are questions or prompts generated by the generative model to encourage the growth of workers or employees.

[0934] "Terminals" are external devices used by workers or employees, including smartphones, smart glasses, head-mounted displays, robots, etc.

[0935] "Notification" refers to the act of sending the generated feedback or question to the terminal and displaying it to the user.

[0936] "Work efficiency" refers to the efficiency with which a worker performs work within a certain period of time, and refers to the speed and accuracy of the work.

[0937] "Stress management" refers to methods and means for appropriately controlling the stress that workers feel during work and maintaining a comfortable working environment.

[0938] "Psychological safety" refers to a state in which workers and employees feel free to express their opinions and feelings without feeling any psychological pressure when receiving feedback or evaluations.

[0939] "Communication channels" refer to the means and methods for exchanging information and data between management and workers or employees.

[0940] The system of the present invention is configured by combining multiple technical elements to provide individual feedback and growth support to workers in a factory. Specific embodiments are described below.

[0941] System Configuration

[0942] This system uses the following hardware and software:

[0943] Hardware: smart glasses, servers, sensors for voice and facial expression analysis

[0944] Software: reputation database, managerial interface, generative models (e.g., GPT-3), sentiment engine, notification system

[0945] Program processing description

[0946] The system provides workers with appropriate feedback and development support by taking the following steps:

[0947] 1. Acquisition of rating data and emotional information

[0948] The smart glasses worn by the workers are equipped with built-in sensors for voice and facial expression analysis. These sensors collect the worker's voice and facial expression information in real time and send it to a server.

[0949] The server retrieves worker evaluation data from the company's internal evaluation database, including information on achievements, performance, and efficiency.

[0950] 2. Receiving input from management

[0951] Managers enter feedback and questions for each worker through a dedicated web interface, and this information is stored on a server.

[0952] 3. Generating feedback and questions

[0953] The server uses a generative model (such as GPT-3) to generate optimal feedback and questions based on the acquired evaluation data, emotional information, and input from managers.

[0954] Additionally, the emotion engine adjusts this feedback content to match the worker's emotional state.

[0955] 4. Distribution of generated feedback

[0956] The server notifies the smart glasses of the generated feedback and questions, which then display the feedback and questions to the worker in real time.

[0957] Specific examples

[0958] A real-life example is a young factory worker named Mr. A. He was recently promoted to manager of a new product line, but evaluation data shows he has issues with efficiency and stress management. Mr. A wears smart glasses while working.

[0959] Boss B inputs the question, "What situations at work cause you particular stress?" into the system and sends it. At the same time, recent performance data for Person A is retrieved from the evaluation database, and sensors in the smart glasses collect facial expressions and voice information from Person A.

[0960] The server uses a generative model (such as GPT-3) based on the acquired data to generate feedback and questions like the following:

[0961] > "Your recent work on your new product line has been great, but I'd like to find ways to reduce the stress you're experiencing. What tasks in particular stress you out? Please be specific."

[0962] This feedback is displayed in real time on Mr. A's smart glasses, and Mr. A can read it and enter his own opinions as needed. Through this activity, Mr. A receives support from his supervisor for his own stress management and receives specific feedback for his growth.

[0963] Example prompt for a generative AI model:

[0964] "Based on the worker's evaluation data, emotional state, and managerial feedback, develop feedback and questions such as the following. Evaluation data includes worker efficiency and stress levels."

[0965] This system allows for individual feedback and support for each worker, reducing the burden on managers while maintaining psychological safety for workers.

[0966] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0967] Step 1: Obtaining rating data and emotional information

[0968] Input: The smart glasses have built-in voice and facial expression analysis sensors that collect the worker's voice and facial expression information in real time. The server also retrieves the worker's evaluation data from the company's internal evaluation database.

[0969] Specific operation: The sensor collects voice and facial expression data and transmits them to the server via the smart glasses. The server accesses the evaluation database and obtains the necessary evaluation data.

[0970] Output: The server receives the worker's voice, facial expression data, and evaluation data.

[0971] Step 2: Receiving input from management

[0972] Input: Managers input feedback and questions for each worker through a dedicated web interface.

[0973] Specific actions: Managers access the web interface, enter feedback or questions in text format, and send it to the server.

[0974] Output: The server receives and stores feedback and questions from managers.

[0975] Step 3: Generate feedback and questions

[0976] Input: appraisal data, emotional information, and managerial input

[0977] Specific operation: The server integrates these data and inputs them into a generative model (e.g., GPT-3). The generative model generates appropriate feedback and questions based on the prompt. Furthermore, an emotion engine analyzes the worker's emotional state and adjusts the feedback appropriately.

[0978] Output: The server retrieves the feedback and questions obtained from the generative model.

[0979] Step 4: Distributing generated feedback

[0980] Input: Generated feedback and questions

[0981] Specific operation: The server notifies the smart glasses of the generated feedback and questions. The smart glasses, upon receiving the notification, display the feedback and questions to the worker.

[0982] Output: Feedback and prompts are displayed on the worker's smart glasses.

[0983] At each step, servers, smart glasses, sensors, and other devices work together to quickly and accurately acquire, process, generate, and distribute data, providing effective feedback and support for worker development.

[0984] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0985] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0986] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[0987] [Fourth embodiment]

[0988] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0989] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0990] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0991] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0992] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0993] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0994] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0995] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0996] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0997] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0998] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0999] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1000] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1001] The system of the present invention is a platform that uses AI to individually support employee growth. This system acquires employee evaluation data and integrates it with input from managers. It then uses a generative model to generate feedback and questions for growth, and includes a series of processes that notify the employee's device.

[1002] 1. Obtaining evaluation data

[1003] The server first retrieves employee evaluation data from the company's internal evaluation database, which contains information about the employee's past performance and accomplishments.

[1004] 2. Receiving input from management

[1005] The server provides an interface for receiving input information from managers. Managers input and send questions and feedback points for each employee through their terminals. This input information is saved on the server.

[1006] 3. Generating feedback and questions

[1007] The server uses a generative model (such as a natural language generation model such as GPT-3) to generate feedback and questions for growth based on the acquired evaluation data and input information from managers. The generative model receives the evaluation data and input information as input and outputs appropriate feedback sentences and questions.

[1008] 4. Distribution of generated feedback

[1009] The server notifies the generated feedback and questions to the employee's terminal, which receives them and displays them to the user (employee). This notification is done as part of the employee's daily work.

[1010] Specific examples

[1011] Suppose a young employee at a company, Mr. A, is in charge of project management, but feels that there is room for improvement in his communication skills. His supervisor, Mr. B, uses his own device to type the question, "What are you having trouble communicating with your team members?" and sends it to the system. At the same time, evaluation data on Mr. A's recent projects is retrieved from the evaluation database. This data indicates that Mr. A's management skills are highly rated, but that there are some issues with communication.

[1012] Based on the evaluation data and the questions posed by Mr. B, the server uses a generative model to generate the following feedback and questions:

[1013] > "You've done a great job of managing project progress. But what are some of the challenges you face when communicating with your team members? Please give us some specific examples."

[1014] This feedback and question is sent as a notification to Mr. A's device, who can then check it on his own device and reply or self-evaluate.

[1015] The system of this invention makes it possible to provide effective feedback while individually supporting the growth of each employee and reducing the burden on supervisors, thereby increasing employees' motivation to grow and contributing to improving the performance of the entire company.

[1016] The processing flow will be explained below.

[1017] Step 1:

[1018] The user (supervisor) uses the terminal to enter the question they want to ask their subordinate and the feedback points they want to provide, and then clicks the send button. Specifically, they enter the "employee ID" and "question" into the input form and send it.

[1019] Step 2:

[1020] The server receives the data sent from the manager's device and receives a POST request through the API endpoint. The received data includes the employee ID and the question.

[1021] Step 3:

[1022] The server stores the received managerial input information in a database, which is then used for subsequent processing.

[1023] Step 4:

[1024] The server retrieves the evaluation data of the specified employee from the company's evaluation database, which includes information about the employee's performance and accomplishments.

[1025] Step 5:

[1026] The server creates a request to the generative model based on the acquired evaluation data and input information from the manager. The generative model receives the evaluation data and input information.

[1027] Step 6:

[1028] The server uses a generative model (such as GPT-3) to generate optimal feedback and questions for employees to help them grow. The generative model generates appropriate feedback sentences and questions based on the evaluation data and input information.

[1029] Step 7:

[1030] The server initiates a process for notifying the employee's terminal of the generated feedback and question, and sends the feedback and question using a notification service associated with the employee's terminal.

[1031] Step 8:

[1032] The terminal receives the feedback and questions sent from the server and displays them to the user (employee). The employee checks the feedback and questions on the terminal and uses them to reflect on their own behavior and work.

[1033] Step 9:

[1034] Users (employees) evaluate themselves based on the feedback and questions they receive, and reflect on their work and consider improvements as necessary. If employees want to add to or respond to the feedback, they are given the option to enter feedback again for their superiors or the system.

[1035] Example 1

[1036] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1037] Conventional feedback systems have had problems such as difficulty in effectively supporting the growth of individual employees and placing a heavy burden on managers. Furthermore, it was inefficient to integrate evaluation data with input from managers to provide appropriate feedback. This resulted in an insufficient quantity and quality of feedback, and insufficient consideration of psychological safety. Another issue was that feedback given to employees tended to be uniform, failing to address individual needs.

[1038] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1039] In this invention, the server includes means for acquiring employee evaluation data, means for extracting evaluation information for a specific employee from the evaluation database, means for receiving input information from managers, means for saving the input information and integrating it with the evaluation data, means for generating feedback and questions for growth based on the evaluation data and input information using a generative model, and means for notifying the generated feedback and questions to the employee's terminal. This enables individualized responses to each employee, improves the quantity and quality of feedback, maintains psychological safety, reduces the burden on managers, and contributes to improving the performance of the entire company.

[1040] "Employee evaluation data" means data containing information about an employee's performance or accomplishments.

[1041] An "evaluation database" is a data storage system in which employee evaluation data is stored.

[1042] "Input information from managers" refers to data collected from managers regarding feedback and questions given to employees.

[1043] A "generative model" is a machine learning model used to generate feedback and development questions based on assessment data and input information (e.g., a natural language generation model).

[1044] "Means of notification" refers to the functions and processes for sending generated feedback and questions to employees' devices.

[1045] "Employee devices" are devices such as computers and smartphones used by employees.

[1046] "Feedback" means providing specific evaluations and opinions to employees and giving advice for growth and improvement.

[1047] "Questioning" is a form of communication that includes specific questions or confirmations for employees.

[1048] "Storage and integration means" refers to the process by which input received from management is stored in a database or temporary file and combined with existing evaluation data.

[1049] An "API" is an interface that allows software applications to communicate with each other.

[1050] "Push Notification Service" means a cloud-based service for sending messages or notifications to specific devices in real time (e.g., Firebase Cloud Messaging).

[1051] The system of the present invention is a platform that uses AI to individually support employee growth. This system acquires employee evaluation data and integrates it with input from managers. It then uses a generative model to generate feedback and questions for growth, and sends them to the employee's device.

[1052] Specifically, the following hardware and software are used.

[1053] Obtaining evaluation data

[1054] The server first retrieves employee evaluation data from the company's internal evaluation database. The database management system used is, for example, MySQL or PostgreSQL. The server connects to this database and extracts the evaluation data for a specific employee (for example, employee ID "123").

[1055] Receiving input from management

[1056] The server provides a web interface to receive input from managers. This interface is built using a web application framework such as Django or Ruby on Rails. Users (managers) access the interface through their terminals, enter questions and feedback points for each employee, and send that information to the server.

[1057] Generate feedback and questions

[1058] The server generates feedback and questions for growth based on the acquired evaluation data and input information from managers using a natural language generation model (e.g., OpenAI's GPT-3). The generative model is called via an appropriate API and outputs the generated feedback sentences and questions based on the necessary input data.

[1059] For example, the following prompt sentence is input to the generative model:

[1060] Generate feedback to support employee growth. Here's the data:

[1061] Performance: Strong management skills

[1062] Challenge: Communication challenges

[1063] feedback:

[1064] Distribution of generated feedback

[1065] The server notifies the employee's device of the generated feedback and questions. Firebase Cloud Messaging (FCM) can be used as the push notification service. The device (employee's device) displays the received notification to the user. The user (employee) can check the notification and reply or self-evaluate as necessary.

[1066] Specific examples

[1067] Consider a case where a young employee, Mr. A, is in charge of project management and has room for improvement in his communication skills. His supervisor enters the question "What are you having trouble communicating with your team members?" into his own device and sends it to the system. At the same time, evaluation data on Mr. A's recent projects is retrieved from the evaluation database. Based on the evaluation data and the supervisor's question, the server uses a generative model to generate the following feedback and question:

[1068] You have been doing a great job of managing project progress, but what are some of the challenges you face when it comes to communicating with your team members? Please give us some specific examples.

[1069] This feedback and question is sent as a notification to Mr. A's device, who can then check it on his own device and reply or self-evaluate.

[1070] The system of this invention makes it possible to provide effective feedback while reducing the burden on managers and supporting the growth of each employee individually, thereby increasing employees' motivation to grow and contributing to improving the performance of the entire company.

[1071] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1072] Step 1:

[1073] The server retrieves employee evaluation data from the company's internal evaluation database. Specifically, it sends an SQL query to the database to extract evaluation data for a specific employee (e.g., "Employee ID 123"). It receives the employee ID as input and obtains evaluation data for that employee as output. This evaluation data includes the employee's performance and past evaluation history. The retrieved data is saved in internal memory or a temporary file.

[1074] Step 2:

[1075] The server provides a web interface for managers to input information. This interface is a screen where managers can enter feedback and questions for each employee. Users (managers) access this interface from their own devices and enter the necessary information. The input information includes questions such as, "What are you having trouble communicating with your team members?" This information is then sent to the server. The server stores the received input information in a database or temporary file.

[1076] Step 3:

[1077] The server integrates the acquired evaluation data with the input from the manager. Specifically, it performs data mapping and data merging processes to combine the evaluation data and the input into a single dataset. It receives the evaluation data and the input from the manager as input and obtains the integrated data as output. This integrated data is then ready to be input into the natural language generation model.

[1078] Step 4:

[1079] The server calls the API of a generative model (e.g., GPT-3) based on the integrated data. Specifically, it creates a prompt sentence and sends it to the generative model. The server converts the integrated data as input into a prompt sentence format and sends it to the generative model's API. This API outputs an appropriate feedback sentence and question.

[1080] Example prompt sentence:

[1081] Generate feedback to support employee growth. Here's the data:

[1082] Performance: Strong management skills

[1083] Challenge: Communication challenges

[1084] feedback:

[1085] Step 5:

[1086] The server notifies the employee's device of the generated feedback and questions. Specifically, it uses a push notification service such as Firebase Cloud Messaging (FCM) to send notifications to the employee's device. The server receives the feedback and questions output from the generative model as input and sends the contents to the employee's device as output.

[1087] Step 6:

[1088] The terminal (employee's device) displays the received notification to the user (employee). The user (employee) can check the notification and reply or self-evaluate as necessary. Specifically, the notification will be displayed as a pop-up, and the user can check the related feedback content from there.

[1089] The above are the specific processing steps of the program of this system.

[1090] (Application example 1)

[1091] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1092] Conventional employee growth support systems have had issues with the quality and quantity of feedback being insufficient, placing a heavy burden on managers. Furthermore, it has been difficult to provide effective feedback in certain work environments. In particular, in the operation management of autonomous vehicles, there has been a lack of feedback based on operation data, making it difficult to provide effective support for operation management.

[1093] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1094] In this invention, the server includes means for acquiring employee evaluation data, means for receiving input information from managers, means for generating feedback and questions for growth based on the evaluation data and the input information using a generative model, means for notifying the employee terminal of the generated feedback and questions, means for acquiring operation data, means for generating feedback and questions related to operation for the operator of the autonomous vehicle, and means for notifying the operator terminal of the generated feedback and questions. This makes it possible to provide individual feedback and questions not only to employees but also to the operator of the autonomous vehicle, thereby improving the quality of operation management.

[1095] An "employee" refers to an individual worker who works for an organization or company.

[1096] "Evaluation Data" refers to data that includes information about the performance and tasks of employees and autonomous vehicle operators.

[1097] A "management position" refers to a person in an organization or company who is in a position to manage and supervise subordinates or teams.

[1098] "Input information" refers to data such as feedback and questions sent by managers via their terminals.

[1099] A "generative model" refers to an algorithm or AI technology that automatically generates feedback and questions for growth based on evaluation data and input information.

[1100] "Employee devices" refers to devices such as computers, smartphones, and tablets used by employees for work.

[1101] An "autonomous vehicle" is a vehicle that can drive autonomously without the need for a human driver.

[1102] "Operation data" refers to data that includes information related to the operation of an autonomous vehicle, such as driving history, route information, traffic conditions, and weather conditions.

[1103] "Operator" refers to the person in charge of monitoring and managing the operation of autonomous vehicles.

[1104] An embodiment of this invention is a system that provides effective feedback and prompts for growth to employees and operators of autonomous vehicles. This system includes a series of processes that combines input information from managers based on employee evaluation data and autonomous vehicle operation data, generates appropriate feedback and prompts using a generative AI model, and notifies each terminal of the generated feedback and prompts.

[1105] The server collects employee evaluation data and autonomous vehicle operation data. The evaluation data includes information on past performance and achievements, while the operation data includes the autonomous vehicle's driving history, route information, traffic conditions, weather conditions, etc.

[1106] Managers use an interface to input specific feedback and development questions via their own devices, which are then stored on a server and integrated with evaluation and operational data.

[1107] The server uses a generative model (such as OpenAI's GPT-3) to generate appropriate feedback and questions for growth based on the acquired evaluation data, operational data, and input from managers. The generative model receives this data as input and outputs appropriate feedback sentences and questions.

[1108] The generated feedback and questions are sent to the devices of employees and autonomous vehicle operators, including PCs, smartphones, tablets, etc., and the information is displayed to the user.

[1109] As a concrete example, consider a case where an autonomous vehicle is in charge of operating a specific route, but needs feedback from a manager regarding the optimal routing to deal with traffic congestion and weather conditions at a specific time. The manager enters the question "Have you ever thought about how to deal with traffic congestion on Route A?" into his or her own device and sends it to the system. At the same time, the autonomous vehicle's operating data is retrieved from the evaluation database.

[1110] The server uses this information to generate feedback and prompts using a generative model, such as:

[1111] > "Recently, Route A has been operating appropriately in heavy traffic. However, what challenges do you face when weather conditions worsen? Please give specific examples."

[1112] This feedback and questions are sent as notifications to the autonomous vehicle operator's device, who can then view the feedback and provide feedback. This system provides individual feedback and questions to employees and autonomous vehicle operators, supporting their growth and reducing the burden on managers.

[1113] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1114] Step 1:

[1115] The server acquires employee evaluation data and autonomous vehicle operation data. The employee evaluation data includes information on past achievements and performance, while the autonomous vehicle operation data includes driving history, route information, traffic conditions, weather conditions, etc. The server acquires this data by accessing a database, with the input being the evaluation data and operation data and the output being data held within the server.

[1116] Step 2:

[1117] The user, a manager, uses the management interface through his / her own terminal to input feedback and questions for growth. This generates manager input information, which is sent to the server. The input is the feedback and questions from the manager, and the output is the input information stored on the server.

[1118] Step 3:

[1119] The server integrates the acquired evaluation data and operational data with input information from managers. Data processing involves appropriately formatting this data and preparing it as input data for the generative AI model. The inputs are evaluation data, operational data, and managerial input information, and the output is the integrated data to be input into the generative model.

[1120] Step 4:

[1121] The server uses a generative model (e.g., OpenAI's GPT-3) to generate feedback and questions for growth based on the integrated data. The data calculation performed here is to generate appropriate feedback sentences and questions from the evaluation data and managerial input information. The input is the integrated data, and the output is the generated feedback and questions.

[1122] Step 5:

[1123] The server notifies the generated feedback and questions to the terminals of employees and operators of autonomous vehicles. Notifications are sent in the form of push notifications, emails, etc. The input is the generated feedback and questions, and the output is the notification content displayed on the terminal.

[1124] Step 6:

[1125] The terminal displays the received feedback and questions to the user, who can then reply or provide feedback based on this information. The input is the notified feedback and questions, and the output is the user's feedback and self-evaluation.

[1126] As an example, use the following prompt:

[1127] > "Recently, Route A has been operating appropriately in heavy traffic. However, what challenges do you face when weather conditions worsen? Please give specific examples."

[1128] Through the above processing steps, the system will provide meaningful feedback and prompts for growth between the server, terminal, and user.

[1129] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1130] The system of the present invention is a platform that uses AI to individually support employee growth and provides more effective feedback by combining it with an emotion engine. This system acquires employee evaluation data and integrates it with input from managers. It then uses a generative model and emotion engine to generate feedback and questions for growth, and includes a series of processes that notify the employee's device.

[1131] 1. Acquisition of evaluation data and emotional information

[1132] The server first obtains employee evaluation data from the company's internal evaluation database. This evaluation data includes information about the employee's performance and achievements. It also uses an emotion engine to obtain the user's (employee's) emotional information. Emotional information is data that indicates how the employee is feeling. For example, voice analysis or facial expression analysis can be used.

[1133] 2. Receiving input from management

[1134] The server provides an interface for receiving input information from managers. Managers input and send questions and feedback points for each employee through their terminals. This input information is saved on the server.

[1135] 3. Generating feedback and questions

[1136] The server creates a request to the generative model based on the acquired evaluation data, emotion information, and input information from the manager.The generative model receives the evaluation data, emotion information, and input information.

[1137] The server uses a generative model (such as GPT-3) to generate optimal feedback and questions for employees to help them grow. The generative model generates appropriate feedback sentences and questions based on evaluation data, emotional information, and input information. The emotion engine provides feedback that takes into account the employee's emotional state.

[1138] 4. Distribution of generated feedback

[1139] The server notifies the generated feedback and questions to the employee's terminal, which receives them and displays them to the user (employee). This notification is done as part of the employee's daily work.

[1140] Specific examples

[1141] Suppose a young employee, Mr. A, is in charge of project management at a certain company, and in a recent evaluation, he was told that his communication skills could be improved. Mr. A seems to be feeling stressed during the progress of a recent project. His supervisor, Mr. B, types the question "What are you having trouble communicating with your team members?" into his own device and sends it to the system. At the same time, evaluation data on Mr. A's recent project is retrieved from the evaluation database.

[1142] The server uses a generative model to generate feedback and questions based on the evaluation data and the questions posed by boss B. In addition, the emotion engine recognizes that A is feeling stressed and adjusts the feedback accordingly. For example, the server generates the following feedback and questions:

[1143] "You've done a great job managing your project progress. However, you've been feeling a lot of stress lately. What are some of the areas you're having trouble communicating with your team members? Please give us some specific examples."

[1144] This feedback and question is sent as a notification to Mr. A's device, who can then check it on his own device and reply or self-evaluate.

[1145] The system of this invention enables the provision of effective feedback while individually supporting the growth of each employee, reducing the burden on managers and maintaining psychological safety. This increases employees' motivation to grow and contributes to improving the performance of the entire company. Furthermore, by combining it with an emotion engine, flexible feedback is provided that takes into account the employee's emotional state, realizing more advanced individual support.

[1146] The processing flow will be explained below.

[1147] Step 1:

[1148] The user (supervisor) uses the terminal to enter the question they want to ask their subordinate and the feedback points they want to provide, and then clicks the send button. Specifically, they enter the "employee ID" and "question" into the input form and send it.

[1149] Step 2:

[1150] The server receives the data sent from the manager's device and receives a POST request through the API endpoint. The received data includes the employee ID and the question.

[1151] Step 3:

[1152] The server stores the received managerial input information in a database, which is then used for subsequent processing.

[1153] Step 4:

[1154] The server retrieves the evaluation data of the specified employee from the company's evaluation database, which includes information about the employee's performance and accomplishments.

[1155] Step 5:

[1156] The server uses an emotion engine to acquire employee emotion data, which is acquired through voice analysis, facial expression analysis, etc. and indicates the employee's emotional state.

[1157] Step 6:

[1158] The server creates a request to the generative model based on the acquired evaluation data, emotion data, and input information from the manager. To do so, it organizes the evaluation data, emotion data, and input information and formats them as input to the generative model.

[1159] Step 7:

[1160] The server uses a generative model (such as GPT-3) to generate optimal feedback and questions for employee growth. The generative model creates feedback sentences and questions based on the input evaluation data, emotion data, and input information.

[1161] Step 8:

[1162] The server prepares to notify the generated feedback and questions to the employee's terminal, and starts the procedure for sending the feedback and questions using the notification service.

[1163] Step 9:

[1164] The terminal receives the feedback and questions sent from the server and displays them to the user (employee). The employee checks the feedback and questions on the terminal and uses them to reflect on their own behavior and work.

[1165] Step 10:

[1166] Users (employees) evaluate themselves based on the feedback and questions they receive, and reflect on their work and consider improvements as necessary. If employees want to add to or respond to the feedback, they are given the option to enter feedback again for their superiors or the system.

[1167] Example 2

[1168] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1169] Conventional employee evaluation systems did not take into account the emotional state or psychological factors of each employee, resulting in uniform and ineffective feedback. Furthermore, the burden on managers was heavy, leading to problems with insufficient feedback and support for growth. This could lead to a decline in employees' motivation to grow, hindering improvements in the company's overall performance. There was a need to solve these issues and effectively support the growth of each individual employee.

[1170] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1171] In this invention, the server includes means for acquiring employee evaluation data, means for receiving input information from managers, means for using an emotion engine to acquire emotional states, means for generating prompt sentences based on the evaluation data, emotional information, and input information, means for generating feedback and questions for growth using a generative model, and means for notifying the generated feedback and questions to the employee's terminal. This enables individual feedback that takes into account the employee's emotional state, allowing for the provision of high-quality feedback while maintaining psychological safety. Furthermore, by reducing the burden on managers and providing a new communication channel, support for employee growth can be effectively achieved.

[1172] The "means for obtaining employee evaluation data" refers to a server function for extracting information about employee performance and accomplishments from a database.

[1173] "Means for receiving input information from management" refers to the function by which the server receives feedback and questions from management as input via a web interface or API.

[1174] "Means of using an emotion engine to obtain emotional states" refers to a server function that uses technologies such as voice analysis and facial expression analysis to collect emotional information from employees and analyzes that data to understand their emotional states.

[1175] The "means for generating prompt sentences based on evaluation data, emotional information, and input information" is a function that creates appropriate prompt sentences based on the evaluation data, emotional information, and input information from the manager that the server has acquired.

[1176] The "means for generating feedback and questions for growth using a generative model" is a server function that inputs a prompt sentence into a generative model and generates feedback and questions for growth based on the results.

[1177] "Means for notifying employees of the generated feedback and questions on their devices" refers to a server function that sends and notifies employees of the generated feedback and questions via email or a dedicated application.

[1178] The system of the present invention is a platform for individually supporting employee growth, combining AI technology and an emotion engine to provide effective feedback. The main components of the system include a server, a terminal, and an emotion engine. Specific embodiments of the system of the present invention will be described below.

[1179] 1. Acquisition of rating data and emotional information

[1180] The server first connects to the company's internal evaluation database to obtain employee evaluation data. This evaluation data contains detailed information about each employee's performance, such as project progress, achievements, and behavioral evaluations. It then uses an emotion engine to obtain employee emotional information. Emotional information is obtained using technologies such as voice analysis and facial expression analysis. For example, the Alexa Voice Service can be used for voice analysis, and the Azure Face API can be used for facial expression analysis.

[1181] 2. Receiving input from management

[1182] The server provides a function to receive feedback and questions from managers through a web interface. Managers access the server from their own devices (PCs or tablets) and input feedback points and questions for specific employees. This input information is sent to the server and stored in a database.

[1183] 3. Generating feedback and questions

[1184] The server combines the acquired evaluation data, emotional information, and input from managers to generate prompts. Using advanced AI technologies such as GPT-3 as a generative model, it generates optimal feedback and questions for employee growth. Based on the emotional information acquired by the emotion engine, the content of the feedback is tailored to the emotional state of each individual employee.

[1185] For example, the following prompt statement is generated:

[1186] > Evaluation data: Mr. A's recent performance evaluation indicated that his communication skills have room for improvement.

[1187] > Emotional information: Person A is feeling stressed during the project.

[1188] > Management input: What are the communication challenges you have with your team members?

[1189] Based on this prompt, the generative model generates appropriate feedback and questions.

[1190] 4. Distribution of generated feedback

[1191] The server notifies the employee's device of the generated feedback and questions. The employee's device receives the notification and displays it to the user (employee). Notification methods include email and a dedicated application, and employees can check the received feedback and reply or self-evaluate as necessary. This ensures that the feedback process proceeds smoothly as part of their daily work.

[1192] For example, the feedback and prompt might look like this:

[1193] "You've done a great job managing your project progress. However, you've been feeling a lot of stress lately. What are some of the areas you're having trouble communicating with your team members? Please give us some specific examples."

[1194] In this way, this system can provide individual support for the growth of each employee, providing effective feedback while reducing the burden on managers. Furthermore, by using an emotion engine, flexible feedback is provided that takes into account the employee's emotional state, enabling more advanced individual support.

[1195] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1196] Step 1:

[1197] The server executes a query to retrieve employee evaluation data from the company's internal evaluation database. The evaluation data includes project progress, performance, and behavioral evaluations. Executing this query imports the evaluation data into the server. Next, an emotion engine is used to obtain the employee's emotional information. Emotional information is obtained using voice analysis and facial expression analysis, for example, using the Alexa Voice Service or Azure Face API. The voice data and facial expression data are processed as input, and then quantified emotional data is output.

[1198] input:

[1199] Employee evaluation database

[1200] Employee voice data and facial expression data

[1201] output:

[1202] Evaluation Data

[1203] Emotional Data

[1204] Specific behavior:

[1205] The server periodically queries the reputation database to obtain the latest reputation data.

[1206] The server passes the voice and facial expression data to the emotion engine and acquires the emotion data.

[1207] Step 2:

[1208] The server provides a web interface for receiving feedback and questions from managers. Managers can use their terminals to send input information for specific employees. The server receives this input information and stores it in a database. Feedback points and specific questions are entered as input information, and the received data is stored in the database within the server.

[1209] input:

[1210] Feedback and inquiries sent from the manager's terminal

[1211] output:

[1212] Management input stored in a database

[1213] Specific behavior:

[1214] Managers enter their feedback into a dedicated web form and click the submit button.

[1215] The server stores the data received via the API in a database.

[1216] Step 3:

[1217] The server combines the evaluation data, emotion data, and input from managers to create prompts to be input into the generative model. These prompts include the employee's evaluation results, emotional state, and questions from managers. The data is formatted using Python scripts and passed to the generative model "GPT-3." The generative model then uses this data to generate feedback and questions for growth.

[1218] input:

[1219] Evaluation Data

[1220] Emotional Data

[1221] Management input

[1222] output:

[1223] Prompt sentence to input to the generative model

[1224] Feedback and Prompts

[1225] Specific behavior:

[1226] The server retrieves the required information from the database using a query.

[1227] The server converts the data into prompt statements using a Python script and sends them to the Generative Model API.

[1228] Step 4:

[1229] A generative model is used to generate feedback and questions for growth. The generative model generates the optimal sentence based on the input prompt. This creates individual feedback tailored to the employee. The feedback and questions returned by the generative model are stored on the server.

[1230] input:

[1231] Prompt statement

[1232] output:

[1233] Feedback Statement

[1234] Question

[1235] Specific behavior:

[1236] The server sends the prompt text to the Generative Model API via a POST request.

[1237] The server receives the response from the generative model and stores its contents.

[1238] Step 5:

[1239] The server notifies the employee's device of the generated feedback and questions. Notification methods include email and a dedicated application. The employee's device displays the received notification on its screen. The employee (user) can check the notification content and reply or self-evaluate as necessary.

[1240] input:

[1241] Feedback and questions obtained from the generative model

[1242] output:

[1243] Feedback notification delivered to employee devices

[1244] Specific behavior:

[1245] The server sends the notification using a mail server or push notification service.

[1246] The employee's device receives the notification and displays the contents.

[1247] (Application example 2)

[1248] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1249] Conventional feedback systems provide uniform feedback without considering evaluation data or emotional information, which means that they are unable to adequately support the individual growth of workers or manage their stress. In particular, in work environments such as factories, where improved work efficiency and real-time feedback are required, providing appropriate support is difficult. Furthermore, it is difficult for busy managers to efficiently support their subordinates while maintaining the quality of feedback.

[1250] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring evaluation data and emotion information, means for receiving input information from managers, means for generating feedback and questions for growth based on the evaluation data, emotion information, and input information using a generative model, means for notifying the terminal of the generated feedback and questions, and means for adjusting the feedback content using an emotion engine. This enables improved work efficiency and stress management. It also reduces the burden on managers and provides a new communication channel for supporting the growth of individual workers.

[1251] "Evaluation data" is information that indicates the achievements, performance, efficiency, etc. of workers or employees.

[1252] "Emotional information" is data that indicates the emotional state and psychological condition of workers or employees, and is obtained through voice analysis, facial expression analysis, etc.

[1253] A "generative model" is an algorithmic model that generates appropriate feedback or questions based on given data. A representative example is GPT-3.

[1254] The "emotion engine" is a system that analyzes the user's emotional state and adjusts the feedback content to match the user's emotions.

[1255] "Feedback" refers to advice or guidance provided to workers or employees based on evaluation data and emotional information.

[1256] "Questions" are questions or prompts generated by the generative model to encourage the growth of workers or employees.

[1257] "Terminals" are external devices used by workers or employees, including smartphones, smart glasses, head-mounted displays, robots, etc.

[1258] "Notification" refers to the act of sending the generated feedback or question to the terminal and displaying it to the user.

[1259] "Work efficiency" refers to the efficiency with which a worker performs work within a certain period of time, and refers to the speed and accuracy of the work.

[1260] "Stress management" refers to methods and means for appropriately controlling the stress that workers feel during work and maintaining a comfortable working environment.

[1261] "Psychological safety" refers to a state in which workers and employees feel free to express their opinions and feelings without feeling any psychological pressure when receiving feedback or evaluations.

[1262] "Communication channels" refer to the means and methods for exchanging information and data between management and workers or employees.

[1263] The system of the present invention is configured by combining multiple technical elements to provide individual feedback and growth support to workers in a factory. Specific embodiments are described below.

[1264] System Configuration

[1265] This system uses the following hardware and software:

[1266] Hardware: smart glasses, servers, sensors for voice and facial expression analysis

[1267] Software: reputation database, managerial interface, generative models (e.g., GPT-3), sentiment engine, notification system

[1268] Program processing description

[1269] The system provides workers with appropriate feedback and development support by taking the following steps:

[1270] 1. Acquisition of rating data and emotional information

[1271] The smart glasses worn by the workers are equipped with built-in sensors for voice and facial expression analysis. These sensors collect the worker's voice and facial expression information in real time and send it to a server.

[1272] The server retrieves worker evaluation data from the company's internal evaluation database, including information on achievements, performance, and efficiency.

[1273] 2. Receiving input from management

[1274] Managers enter feedback and questions for each worker through a dedicated web interface, and this information is stored on a server.

[1275] 3. Generating feedback and questions

[1276] The server uses a generative model (such as GPT-3) to generate optimal feedback and questions based on the acquired evaluation data, emotional information, and input from managers.

[1277] Additionally, the emotion engine adjusts this feedback content to match the worker's emotional state.

[1278] 4. Distribution of generated feedback

[1279] The server notifies the smart glasses of the generated feedback and questions, which then display the feedback and questions to the worker in real time.

[1280] Specific examples

[1281] A real-life example is a young factory worker named Mr. A. He was recently promoted to manager of a new product line, but evaluation data shows he has issues with efficiency and stress management. Mr. A wears smart glasses while working.

[1282] Boss B inputs the question, "What situations at work cause you particular stress?" into the system and sends it. At the same time, recent performance data for Person A is retrieved from the evaluation database, and sensors in the smart glasses collect facial expressions and voice information from Person A.

[1283] The server uses a generative model (such as GPT-3) based on the acquired data to generate feedback and questions like the following:

[1284] > "Your recent work on your new product line has been great, but I'd like to find ways to reduce the stress you're experiencing. What tasks in particular stress you out? Please be specific."

[1285] This feedback is displayed in real time on Mr. A's smart glasses, and Mr. A can read it and enter his own opinions as needed. Through this activity, Mr. A receives support from his supervisor for his own stress management and receives specific feedback for his growth.

[1286] Example prompt for a generative AI model:

[1287] "Based on the worker's evaluation data, emotional state, and managerial feedback, develop feedback and questions such as the following. Evaluation data includes worker efficiency and stress levels."

[1288] This system allows for individual feedback and support for each worker, reducing the burden on managers while maintaining psychological safety for workers.

[1289] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1290] Step 1: Obtaining rating data and emotional information

[1291] Input: The smart glasses have built-in voice and facial expression analysis sensors that collect the worker's voice and facial expression information in real time. The server also retrieves the worker's evaluation data from the company's internal evaluation database.

[1292] Specific operation: The sensor collects voice and facial expression data and transmits them to the server via the smart glasses. The server accesses the evaluation database and obtains the necessary evaluation data.

[1293] Output: The server receives the worker's voice, facial expression data, and evaluation data.

[1294] Step 2: Receiving input from management

[1295] Input: Managers input feedback and questions for each worker through a dedicated web interface.

[1296] Specific actions: Managers access the web interface, enter feedback or questions in text format, and send it to the server.

[1297] Output: The server receives and stores feedback and questions from managers.

[1298] Step 3: Generate feedback and questions

[1299] Input: appraisal data, emotional information, and managerial input

[1300] Specific operation: The server integrates these data and inputs them into a generative model (e.g., GPT-3). The generative model generates appropriate feedback and questions based on the prompt. Furthermore, an emotion engine analyzes the worker's emotional state and adjusts the feedback appropriately.

[1301] Output: The server retrieves the feedback and questions obtained from the generative model.

[1302] Step 4: Distributing generated feedback

[1303] Input: Generated feedback and questions

[1304] Specific operation: The server notifies the smart glasses of the generated feedback and questions. The smart glasses, upon receiving the notification, display the feedback and questions to the worker.

[1305] Output: Feedback and prompts are displayed on the worker's smart glasses.

[1306] At each step, servers, smart glasses, sensors, and other devices work together to quickly and accurately acquire, process, generate, and distribute data, providing effective feedback and support for worker development.

[1307] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1308] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1309] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1310] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1311] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1312] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1313] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1314] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1315] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1316] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1317] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1318] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1319] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1320] 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.

[1321] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1322] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1323] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1324] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1325] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1326] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1327] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1328] The following is further disclosed regarding the above embodiment.

[1329] (Claim 1)

[1330] A means of obtaining employee evaluation data;

[1331] a means for receiving input from management;

[1332] a means for generating feedback and development questions based on the assessment data and input information using a generative model;

[1333] A means for notifying the generated feedback and questions to the employee's terminal;

[1334] A system including:

[1335] (Claim 2)

[1336] 10. The system of claim 1, further comprising means for increasing the quantity and quality of feedback while maintaining psychological safety.

[1337] (Claim 3)

[1338] 2. The system according to claim 1, further comprising means for reducing the burden on managers and providing new communication channels to support the growth of subordinates.

[1339] "Example 1"

[1340] (Claim 1)

[1341] A means of obtaining employee evaluation data;

[1342] A means for extracting evaluation information of a specific employee from the evaluation database;

[1343] a means for receiving input from management;

[1344] means for storing and integrating the input information with the assessment data;

[1345] a means for generating feedback and development questions based on the assessment data and input information using a generative model;

[1346] A means for notifying the generated feedback and questions to the employee's terminal;

[1347] A system including:

[1348] (Claim 2)

[1349] 10. The system of claim 1, further comprising means for increasing the quantity and quality of feedback while maintaining psychological safety.

[1350] (Claim 3)

[1351] 2. The system according to claim 1, further comprising means for reducing the burden on managers and providing new communication channels to support the growth of subordinates.

[1352] "Application Example 1"

[1353] (Claim 1)

[1354] A means of obtaining employee evaluation data;

[1355] a means for receiving input from management;

[1356] a means for generating feedback and development questions based on the assessment data and input information using a generative model;

[1357] A means for notifying the generated feedback and questions to the employee's terminal;

[1358] A means for acquiring operational data;

[1359] means for generating feedback and operational queries for an operator of the automated vehicle;

[1360] means for notifying an operator terminal of the generated feedback and questions;

[1361] A system including:

[1362] (Claim 2)

[1363] 10. The system of claim 1, further comprising means for increasing the quantity and quality of feedback while maintaining psychological safety.

[1364] (Claim 3)

[1365] 2. The system according to claim 1, further comprising means for reducing the burden on managers and providing new communication channels to support the growth of subordinates.

[1366] "Example 2: Combining Emotion Engines"

[1367] (Claim 1)

[1368] A means of obtaining employee evaluation data;

[1369] a means for receiving input from management;

[1370] means for using an emotion engine to obtain an emotional state;

[1371] a means for generating a prompt sentence based on the evaluation data, emotion information, and input information;

[1372] A means of generating feedback and growth questions using generative models;

[1373] A means for notifying the generated feedback and questions to the employee's terminal;

[1374] A system including:

[1375] (Claim 2)

[1376] 10. The system of claim 1, further comprising means for increasing the quantity and quality of feedback while maintaining psychological safety.

[1377] (Claim 3)

[1378] 2. The system according to claim 1, further comprising means for reducing the burden on managers and providing new communication channels to support the growth of subordinates.

[1379] "Application example 2 when combining emotion engines"

[1380] (Claim 1)

[1381] means for obtaining rating data and emotion information;

[1382] a means for receiving input from management;

[1383] a means for generating feedback and questions for growth based on evaluation data, emotional information, and input information using a generative model;

[1384] means for notifying the terminal of the generated feedback and questions;

[1385] a means for adjusting the feedback content using an emotion engine;

[1386] A system including:

[1387] (Claim 2)

[1388] 2. The system of claim 1, further comprising means for improving the quantity and quality of feedback while maintaining psychological safety, and means for supporting work efficiency improvement and stress management.

[1389] (Claim 3)

[1390] 10. The system of claim 1, further comprising means for reducing the burden on management and providing new communication channels to support the development of individual workers. [Explanation of symbols]

[1391] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of obtaining employee evaluation data; a means for receiving input from management; a means for generating feedback and development questions based on the assessment data and input information using a generative model; A means for notifying the generated feedback and questions to the employee's terminal; A system including:

2. The system of claim 1, further comprising means for increasing the quantity and quality of feedback while maintaining psychological safety.

3. 2. The system according to claim 1, further comprising means for reducing the burden on managers and providing new communication channels to support the growth of subordinates.

Images