System

Abstract

To provide a system.SOLUTION: A system includes: means for collecting operation logs and input data generated in response to an operation for a business tool or a system; means for identifying the contents of the business carried out using the business tool or the system by analyzing the collected operation logs and input data; and means for generating a daily report on the basis of the identified contents of the business.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] When creating daily work reports for sales and planning, it is difficult to input all the details of the day's work, and it is also difficult for superiors to review all the reports. As a result, there is a lack of effort to reflect on, review, and improve upon work, which leads to issues with inefficient reviews. [Means for solving the problem]

[0005] To solve this problem, we offer an automated recording system for work content and work activities that utilizes generative AI. This system evaluates the records of work content and work activities generated by generative AI, and provides points for reflection, reflection, and improvement based on that evaluation. This enables many reviews and feedback to be provided in a short amount of time, resulting in efficient work improvement. [Brief explanation of the drawings]

[0006] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [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. 2 is a sequence diagram showing a flow of processing in the data processing system according to the first embodiment of the first form example. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Embodiment 1. [Figure 13] FIG. 10 is a sequence diagram showing a processing flow of a data processing system in a second embodiment of the second form example. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Embodiment Example 2. [Figure 15]FIG. 10 is a sequence diagram showing the flow of processing in a data processing system according to a third embodiment of the third embodiment. [Figure 16] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Embodiment 3. [Figure 17] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the first embodiment of the first form example when an emotion engine is combined. [Figure 18] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Form Example 1 when an emotion engine is combined. [Figure 19] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the second embodiment of the second form example when an emotion engine is combined. [Figure 20] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Form Example 2 when an emotion engine is combined. [Figure 21] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the third embodiment of the third form example when an emotion engine is combined. [Figure 22] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Form Example 3 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0007] 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.

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

[0009] 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, the 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), an APU (Accelerated Processing Unit), or a TPU (TENSOR PROCESSING UNIT (registered trademark)).

[0010] 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.

[0011] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0012] In the following embodiments, a communication I / F (Interface) with a 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.

[0013] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. 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."

[0014] [First embodiment]

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

[0016] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0017] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0018] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0019] The reception device 38 includes a touch panel 38A, 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.

[0020] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (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.

[0021] 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.

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

[0023] 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.

[0024] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0025] In the smart device 14, the processor 46 performs the reception output 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.

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

[0027] "Example 1"

[0028] In one embodiment of the present invention, generative AI automatically records the work activities performed by business personnel and generates the records as daily reports. Specifically, it works in conjunction with the business tools and systems used by business personnel, understands the work content based on the operation logs and input data, and formats the results into daily reports.

[0029] "Example 2"

[0030] The evaluation means evaluates the daily reports generated by the generative AI. Specifically, it automatically extracts the degree of achievement and problems of work based on the contents of the daily reports and outputs the evaluation results. For example, it compares the work goals with the actual results and calculates the degree of achievement. It also extracts problems and areas for improvement from the work content.

[0031] "Example 3"

[0032] The feedback method provides points for reflection, reflection, and improvement based on the evaluation method. Specifically, specific improvement suggestions are made based on the evaluation results and feedback is provided to the worker. For example, if the level of achievement of a task is low, the problem that caused it and improvement suggestions are presented to the worker.

[0033] The processing flow of each embodiment will be described below.

[0034] "Example 1"

[0035] Step 1: The worker operates the business tools and systems.

[0036] Step 2: Generative AI collects operation logs and input data from business tools and systems.

[0037] Step 3: Based on the data collected by the generative AI, the work content is understood and formatted into a daily report.

[0038] "Example 2"

[0039] Step 1: Generative AI generates daily reports.

[0040] Step 2: The evaluation tool automatically extracts the degree of achievement and problems of the work based on the contents of the generated daily report.

[0041] Step 3: The evaluation means outputs the evaluation result.

[0042] "Example 3"

[0043] Step 1: The evaluation means outputs the evaluation result.

[0044] Step 2: The feedback mechanism makes specific improvement suggestions based on the evaluation results.

[0045] Step 3: The feedback mechanism provides feedback to the operator.

[0046] Example 1

[0047] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0048] Conventional business record systems require employees to manually record their work, which takes time and effort, and often results in inaccuracies and inconsistencies in the records. Furthermore, because evaluations of work and feedback on areas for improvement are also done manually, this is inefficient and can delay business improvements. There is a need for a system that can solve these problems, automate business records, and provide efficient feedback.

[0049] 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.

[0050] In this invention, the server includes generative AI means for automatically recording work content and work activities, evaluation means for evaluating the records of work content and work activities generated by the generative AI, feedback means for providing points for reflection, review, and improvement based on the evaluation means, data collection means for collecting operation logs and input data from work tools and systems, data analysis means for analyzing the collected data and understanding the work content, daily report generation means for generating daily reports based on the analysis results, and daily report distribution means for distributing the generated daily reports to users. This enables automation of work records and efficient feedback.

[0051] "Generative AI means" refers to artificial intelligence technology that automatically records work content and activities and formats them into daily reports and other formats.

[0052] "Evaluation means" refers to the function for analyzing the work content and records of work activities generated by generative AI and evaluating their content.

[0053] "Feedback means" refers to a function for providing points for reflection, review, and improvement based on the evaluation results obtained by the evaluation means.

[0054] "Data collection means" refers to the function for collecting operation logs and input data from business tools and systems.

[0055] "Data analysis means" refers to the function for analyzing collected data and understanding business operations.

[0056] The "daily report generation means" refers to a function for generating a daily report based on the analysis results obtained by the data analysis means.

[0057] The "daily report distribution means" refers to a function for distributing the generated daily report to the user.

[0058] The present invention relates to a system for automatically recording work content and work activities and generating a daily report. A specific embodiment of this system will be described below.

[0059] Server Roles

[0060] The server executes a generative AI means that automatically records business content and business activities. This generative AI works in conjunction with business tools and systems to collect their operation logs and input data. Specifically, the server acquires data from systems such as MICROSOFT (registered trademark) EXCEL (registered trademark), Google (registered trademark) Docs, Salesforce, and SAP via API. The collected data is analyzed by a data analysis means within the server, and the business content is identified. Based on the analysis results, the server generates a daily report using a daily report generation means. The generated daily report is distributed to the user via a daily report distribution means. For example, the server sends the generated daily report to the user's email address.

[0061] Device Role

[0062] A terminal generates an operation log when a user operates a business tool or system. Specifically, the terminal monitors user operations in real time and records the details of the operation in a log file. For example, when a user enters data into Microsoft Excel, the terminal records the details of the input as a log. The generated operation log and input data are sent from the terminal to a server. The terminal periodically communicates with the server and uploads the collected data.

[0063] User Roles

[0064] Users use business tools and systems on a daily basis to carry out their work activities. Specifically, they perform operations such as data entry and information updates. For example, a user updates customer information and adds a new contact in Salesforce. A daily report is automatically generated by the user simply by performing their daily work activities without any special operations. The generated daily report is distributed from the server, and the user can check the received daily report via email or chat tools.

[0065] Specific examples

[0066] Example 1: Recording sales activities

[0067] The server uses the Salesforce API to retrieve the log of customer information updated by the user. The server analyzes the operation log "Updated customer A's contact information" and identifies the updated content. The server generates a daily report stating "Today, customer A's information was updated and a new contact was added" and sends it to the user's email address.

[0068] Example 2: Recording Data Entry

[0069] When a user inputs data into Microsoft Excel, the device records the input as a log. The device sends the collected operation logs to the server every hour. The server receives the operation logs sent from the device, analyzes the operation log "Enter sales data," and identifies the sales data that was input. The server generates a daily report stating, "Today, sales data was entered and total sales amounted to XX yen," and sends it to the user's email address.

[0070] Prompt Sentence Examples

[0071] "Please generate a daily report based on the operation log when a business user updates customer information in Salesforce."

[0072] "Generate a daily report based on sales data entered in Microsoft Excel."

[0073] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0074] Step 1:

[0075] The server collects operation logs and input data from business tools and systems. Specifically, the server obtains data from systems such as Microsoft Excel, Google Docs, Salesforce, and SAP via API. As input, it receives operation logs and input data from business tools and systems, and as output, it stores the collected data in an internal database.

[0076] Step 2:

[0077] The server analyzes the collected data. Specifically, it uses natural language processing (NLP) technology to extract important information from operation logs and input data. As input, it receives operation logs and input data stored in an internal database, and as output, it generates analysis results. For example, the server analyzes the operation log "Update customer A's contact information" and identifies the updated content.

[0078] Step 3:

[0079] The server generates a daily report based on the analysis results. Specifically, the server uses a generative AI model to format the extracted information in natural language. It receives the analysis results as input and generates a daily report as output. For example, the server generates a daily report stating, "Today, customer A's information was updated and a new contact was added."

[0080] Step 4:

[0081] The server distributes the generated daily report to the user. Specifically, the server sends the daily report via email or a chat tool (for example, Slack or MICROSOFT TEAMS (registered trademark)). The server receives the generated daily report as input and sends the daily report to the user's email address or chat tool as output. For example, the server sends the generated daily report to the user's email address.

[0082] Step 5:

[0083] A terminal generates an operation log when a user operates a business tool or system. Specifically, the terminal monitors user operations in real time and records the operation details in a log file. It receives user operations as input and generates an operation log as output. For example, when a user enters data into Microsoft Excel, the terminal records the input details as a log.

[0084] Step 6:

[0085] The terminal sends the generated operation logs and input data to the server. Specifically, the terminal periodically communicates with the server and uploads the collected data. It receives the generated operation logs and input data as input and sends data to the server as output. For example, the terminal sends the collected operation logs to the server every hour.

[0086] Step 7:

[0087] Users use business tools and systems on a daily basis to perform business activities. Specifically, users perform operations such as data entry and information updates. As input, they use business tools and systems, and as output, they generate operation logs and input data. For example, a user updates customer information and adds a new contact in Salesforce.

[0088] Step 8:

[0089] The user checks the daily report delivered from the server. Specifically, the user views the daily report received via email or chat tool. The user receives the daily report delivered from the server as input, and checks the contents of the daily report as output. For example, the user opens the daily report received by email and checks the work content.

[0090] (Application example 1)

[0091] Next, a description will be given of Application Example 1 of Embodiment 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."

[0092] In the past, work records in factories were often done manually, which placed a heavy burden on workers and was prone to errors and omissions. Furthermore, work evaluations and feedback on areas for improvement were not properly conducted, making it difficult to improve operations efficiently. Furthermore, the process of formatting work details into daily reports was time-consuming and labor-intensive.

[0093] 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.

[0094] In this invention, the server includes a generative AI means for automatically recording work content and work activities, an evaluation means for evaluating the records of work content and work activities generated by the generative AI, a feedback means for providing points for reflection, review, and improvement based on the evaluation means, a means for automatically recording the work content of machines operating in the factory and generating the results as a daily report, and a means for saving the daily report. This enables automated and accurate recording of work records, reduces the burden on workers, and enables efficient work improvement. Furthermore, the automatic generation of daily reports enables quick understanding and evaluation of work content.

[0095] "Generative AI methods" are artificial intelligence technologies that automatically record work content and activities and generate documents such as daily reports based on those records.

[0096] "Evaluation means" refers to technology for analyzing the work content and records of work activities generated by generative AI means and evaluating their content.

[0097] "Feedback means" refers to a technique for providing points for reflection, review, and improvement based on the evaluation results obtained by the evaluation means.

[0098] "Machines operating in factories" refer to automated devices and robots used to perform manufacturing, assembly, and other tasks in factories.

[0099] "Means for automatically recording work content" refers to technology for automatically recording the operation and work content of machines operating in a factory.

[0100] The "means for generating a daily report" is a technology for automatically generating a document in daily report format based on the recorded work content.

[0101] The "means for storing the daily report" is a technology for storing the generated daily report in a digital format.

[0102] A system for carrying out the present invention is for automatically recording the work details of machines operating in a factory and generating a daily report. A specific embodiment of this system will be described below.

[0103] System Configuration

[0104] The system includes the following main hardware and software:

[0105] Hardware: Factory robots (e.g., general-purpose robots), servers, data storage devices

[0106] Software: Python, generative AI models (e.g., GPT-3 (registered trademark)), database management system

[0107] Program processing

[0108] The server receives and records data on the work content sent by the factory robots. Specifically, it saves the robot's movements and work content as a log with a timestamp. Next, it uses a generative AI model to analyze the recorded data and format it as a daily report. The generated daily report is stored in a database and can be accessed as needed.

[0109] Specific examples

[0110] For example, when a factory robot performs tasks such as "starting the assembly line," "checking product quality," and "packing products into boxes," each task is recorded with a timestamp. A generative AI model analyzes this data and formats it into a daily report.

[0111] Prompt Sentence Examples

[0112] Please generate a daily report based on the work log below.

[0113] 1. 2023-10-01T09:00:00 - Start of assembly line

[0114] 2. 2023-10-01T10:00:00 - Check the quality of the product

[0115] 3. 2023-10-01T11:00:00 - Packing the products into boxes

[0116] The format of the report is as follows:

[0117] Date: YYYY-MM-DD

[0118] What you'll do:

[0119] Task 1: Task Details

[0120] Task 2: Task Details

[0121] Task 3: Task Details

[0122] In this way, a system is realized that automatically records the work content of factory robots and generates it as a daily report. This system enables automated and accurate recording of work records, reduces the burden on workers, and enables efficient business improvement. In addition, the automatic generation of daily reports makes it possible to quickly understand and evaluate work content.

[0123] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0124] Step 1:

[0125] The server receives data on the work content sent from the factory robot.

[0126] Input: Task data from factory robots (e.g., "Start the assembly line," "Check the quality of the product," etc.)

[0127] Output: A time-stamped log of work

[0128] Specific operation: The server receives data on the work content sent from the factory robots in real time, assigns a timestamp to each task, and saves it as a log.

[0129] Step 2:

[0130] The server stores the received work log in a database.

[0131] Input: Timestamp work log

[0132] Output: Work logs stored in a database

[0133] Specific operation: The server sends a time-stamped work log to the database management system and stores it in the database.

[0134] Step 3:

[0135] The server uses a generative AI model to analyze the saved work logs and format them into a daily report.

[0136] Input: Work logs stored in the database

[0137] Output: Formatted daily report

[0138] Specific operation: The server calls a generative AI model (e.g., GPT-3) and provides the saved work log as input. The generative AI model analyzes the work log and generates a document in the form of a daily report.

[0139] Step 4:

[0140] The server stores the generated daily report in a database.

[0141] Input: Formatted daily report

[0142] Output: Daily reports stored in a database

[0143] Specific operation: The server sends the generated daily report to the database management system and stores it in the database.

[0144] Step 5:

[0145] The user can obtain and view the daily report from the database as needed.

[0146] Input: User request

[0147] Output: Daily report provided to the user

[0148] Specific operation: The user sends a request for a daily report to the server. The server retrieves the relevant daily report from the database and provides it to the user.

[0149] Example 2

[0150] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0151] Conventional work evaluation systems required manual recording of work content and work activities, making the evaluation and feedback process cumbersome and time-consuming. Furthermore, the evaluations often lacked accuracy and consistency, making it difficult to identify specific areas for improvement. This led to the issue of insufficient work efficiency and improvement.

[0152] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: a generative AI means for automatically recording work content and work activities; an evaluation means for evaluating the records of work content and work activities generated by the generative AI; a feedback means for providing points for reflection, review, and improvement based on the evaluation means; an input means for a user to input a daily report; a transmission means for transmitting the input daily report data to the server; an analysis means for the server to receive the daily report data and input a prompt sentence to the generative AI model; a generation means for receiving the analysis results from the generative AI model and generating an evaluation report; a transmission means for transmitting the generated evaluation report to a terminal; and a confirmation means for a user to check the evaluation report. This automates the process from recording work content and work activities to evaluation and feedback, improves the accuracy and consistency of evaluation, and enables specific areas for improvement to be quickly identified.

[0153] "Generative AI means" refers to artificial intelligence technology for automatically recording work content and work activities.

[0154] "Evaluation means" refers to a function that analyzes the work content and work activity records generated by generative AI and evaluates the degree of work achievement and problems.

[0155] "Feedback means" refers to a function for providing points for reflection, reflection, and improvement based on evaluation means.

[0156] "Input means" refers to an interface for a user to input a daily report.

[0157] "Transmission means" refers to a function for transmitting input daily report data to a server.

[0158] "Analysis means" refers to the function that allows the server to receive daily report data and input prompt sentences into the generative AI model.

[0159] "Generation means" refers to the function for receiving the analysis results from the generative AI model and generating an evaluation report.

[0160] The "verification means" refers to an interface for the user to verify the evaluation report.

[0161] The present invention relates to a system for automatically recording work content and work activities and providing evaluations and feedback. Specific embodiments of this system will be described below.

[0162] System configuration

[0163] The system consists of the following major components:

[0164] 1. Generative AI means:

[0165] Generative AI uses artificial intelligence technology to automatically record work content and work activities. Specifically, it uses natural language processing technology to analyze daily reports entered by users and automatically record work content.

[0166] 2. Evaluation method:

[0167] The evaluation means analyzes the work content and work activity records generated by the generative AI and evaluates the degree of work achievement and problems. The evaluation means analyzes the content of the daily report using a generative AI model (for example, GPT-4 (registered trademark) by OpenAI (registered trademark)).

[0168] 3. Feedback methods:

[0169] The feedback method provides points for reflection, reflection, and improvement based on the evaluation method. Specifically, specific improvement proposals are made based on the evaluation results.

[0170] 4. Input method:

[0171] This is an interface for users to input daily reports. This is realized using devices such as PCs and smartphones.

[0172] 5. Means of transmission:

[0173] This function allows the terminal to send the daily report data entered to the server. The data is encrypted using SSL / TLS before being sent.

[0174] 6. Analysis methods:

[0175] This function allows the server to receive daily report data and input prompt sentences into the generative AI model. The prompt sentences are generated based on the contents of the daily report.

[0176] 7. Generation means:

[0177] This function allows the server to receive the analysis results from the generated AI model and generate an evaluation report that lists the degree of task achievement, specific problems, and areas for improvement.

[0178] 8. Verification Method:

[0179] This is an interface for the user to check the evaluation report. The evaluation report is provided to the user via the terminal.

[0180] System Operation

[0181] The operation of this system is as follows.

[0182] 1. Enter your daily report:

[0183] After work, the user uses the terminal to enter a daily report. For example, the user might enter, "Today's sales target was 1 million yen, but the actual result was 900,000 yen. It took too long to respond to customers."

[0184] 2. Data transmission:

[0185] The terminal sends the entered daily report data to the server. The data is encrypted before transmission, ensuring security.

[0186] 3. Data Analysis:

[0187] The server inputs the received daily report data into the generative AI model. An example of a prompt sentence is, "Analyze the following daily report and extract the degree of achievement and problems of the work. Daily report: 'Today's sales target was 1 million yen, and the actual result was 900,000 yen. It took too long to respond to customers.'"

[0188] 4. Generate the assessment report:

[0189] The server generates an evaluation report based on the analysis results from the generative AI model, which details the level of achievement, specific problems, and areas for improvement.

[0190] 5. Review the evaluation report:

[0191] Users can check the evaluation report through their terminal and use it to consider next steps to improve their business operations.

[0192] In this way, the process from recording work content and work activities to evaluation and feedback can be automated, improving the accuracy and consistency of evaluations and enabling specific areas for improvement to be quickly identified.

[0193] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0194] Step 1:

[0195] The user inputs a daily report.

[0196] After work, the user uses the device to enter a daily report. Specifically, the user opens a dedicated application and enters, "Today's sales target was 1 million yen, but the actual result was 900,000 yen. It took too long to respond to customers." The entered data is saved on the device as daily report data.

[0197] Step 2:

[0198] The terminal transmits the daily report data to the server.

[0199] The terminal sends the daily report data entered by the user to the server by pressing the "Send" button. When sent, the data is encrypted using SSL / TLS. The input is the daily report data, and the output is the encrypted daily report data.

[0200] Step 3:

[0201] The server receives the daily report data.

[0202] The server receives the encrypted daily report data sent from the terminal and decrypts it. The decrypted daily report data is stored in a database. The input is the encrypted daily report data, and the output is the decrypted daily report data.

[0203] Step 4:

[0204] The server inputs a prompt sentence into the generative AI model.

[0205] The server generates a prompt sentence based on the received daily report data. For example, a prompt sentence such as "Analyze the following daily report and extract the degree of achievement and problems of the work. Daily report: 'Today's sales target was 1 million yen, and the actual result was 900,000 yen. It took too long to respond to customers.'" is input into the generative AI model. The input is the daily report data, and the output is the prompt sentence.

[0206] Step 5:

[0207] The server receives the analysis results from the generative AI model.

[0208] The server receives analysis results from a generative AI model (e.g., OpenAI's GPT-4). The analysis results include the task's achievement level, problems, and areas for improvement. The input is a prompt, and the output is the analysis results.

[0209] Step 6:

[0210] The server generates the analysis results as an evaluation report.

[0211] The server generates an evaluation report based on the analysis results received from the generative AI model. The evaluation report details the level of achievement, specific problems, and areas for improvement. The input is the analysis results, and the output is the evaluation report.

[0212] Step 7:

[0213] The server sends the evaluation report to the terminal.

[0214] The server sends the generated evaluation report to the terminal and notifies the user. During transmission, data integrity and security are ensured. The input is the evaluation report, and the output is the evaluation report sent to the terminal.

[0215] Step 8:

[0216] The user checks the evaluation report.

[0217] The user receives a notification, opens the application, and checks the evaluation report, which states, "Achievement: 90%; Issue: Customer response time was too long." The input is the evaluation report, and the output is the user's confirmation.

[0218] In this way, a system is realized in which the server, terminals, and users work together to evaluate daily reports.

[0219] (Application example 2)

[0220] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0221] Conventional business record systems require manual recording of work content and activities, which takes time and effort. Evaluation and feedback are also done manually, which often results in inefficiency and inaccuracy. Furthermore, there is no way to check evaluation results in real time, which can lead to missed opportunities for business improvement. To solve these problems, there is a need for a system that automates business records, evaluations, and feedback, and also allows evaluation results to be checked in real time.

[0222] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0223] In this invention, the server includes generative AI means for automatically recording work content and work activities, evaluation means for evaluating the records of work content and work activities generated by the generative AI, feedback means for providing points for reflection, review, and improvement based on the evaluation means, and display means for displaying the evaluation results on a smartphone. This enables automation of work recording, evaluation, and feedback, and also allows the evaluation results to be checked in real time.

[0224] "Generative AI means" refers to artificial intelligence technology for automatically recording work content and work activities.

[0225] "Evaluation means" refers to the function for evaluating the work content and records of work activities generated by generative AI.

[0226] "Feedback means" refers to a function for providing points for reflection, reflection, and improvement based on evaluation means.

[0227] "Display means" refers to the function for displaying the evaluation results on a smartphone.

[0228] The system for carrying out this invention includes generative AI means, evaluation means, feedback means, and display means. Specific embodiments of each means will be described below.

[0229] First, generative AI means use artificial intelligence technology to automatically record work content and work activities. Specifically, it receives data on work content and work activities as input and automatically generates it in the form of a daily report. The generated daily report is saved as text data.

[0230] Next, the evaluation means has the function of evaluating the daily reports generated by the generative AI means. This evaluation means uses OpenAI's API to automatically extract the degree of achievement, problems, and areas for improvement based on the contents of the daily reports. The evaluation means generates the contents of the daily reports as prompt sentences and sends them to OpenAI's API to obtain the evaluation results.

[0231] The feedback method provides points for reflection, reflection, and improvement based on the evaluation results obtained by the evaluation method. This feedback includes specific suggestions for improvement, and contributes to improving the efficiency and quality of work.

[0232] The display function has the function of displaying the evaluation results on a smartphone. The evaluation results can be checked in real time through the smartphone application, allowing users to immediately grasp the progress of their work and areas for improvement.

[0233] For example, you can use the following prompt to evaluate daily reports:

[0234] Example prompt sentence:

[0235] Please rate the following daily report.

[0236] Daily report contents:

[0237] Robot A had a goal of assembling 100 parts during an 8-hour shift.

[0238] In fact, it was made up of 90 parts.

[0239] There was a delay in parts supply midway through, which caused work to be temporarily halted.

[0240] Evaluation content:

[0241] 1. Task accomplishment

[0242] 2. Problems

[0243] 3. Improvements

[0244] This prompt is used to ask the generative AI model to evaluate the daily report. The evaluation results are output from three perspectives: the degree of accomplishment, problems, and areas for improvement.

[0245] The hardware used is a smartphone, and the software uses Python and OpenAI API. For data processing, the contents of the daily reports are generated as prompt sentences, and for data calculation, OpenAI API is used to generate evaluations.

[0246] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0247] Step 1:

[0248] The server receives data on work content and work activities. The input data includes information such as the progress of work, work content, and time. The server passes this data to a generative AI means, which automatically generates a daily report. The generated daily report is saved as text data.

[0249] Step 2:

[0250] The server passes the generated daily report to the evaluation means. The evaluation means generates a prompt sentence from the content of the daily report. Specifically, it converts the content of the daily report into the following format:

[0251] Please rate the following daily report.

[0252] Daily report contents:

[0253] [Daily report contents]

[0254] Evaluation content:

[0255] 1. Task accomplishment

[0256] 2. Problems

[0257] 3. Improvements

[0258] By generating this prompt sentence, the evaluation means prepares to evaluate the contents of the daily report.

[0259] Step 3:

[0260] The server sends the generated prompt to OpenAI's API. The input data is the prompt, and the output data is the evaluation result. OpenAI's API automatically extracts the task achievement level, problems, and areas for improvement based on the prompt, and returns the evaluation result.

[0261] Step 4:

[0262] The server receives the evaluation results returned from the OpenAI API and passes them to the feedback mechanism. The feedback mechanism provides points for reflection, reflection, and improvement based on the evaluation results. Specifically, it analyzes the evaluation results and generates specific improvement proposals.

[0263] Step 5:

[0264] The server passes the improvement suggestions obtained from the feedback means to the display means. The display means displays the evaluation results and improvement suggestions on the smartphone. The user can check the evaluation results and improvement suggestions in real time via the smartphone.

[0265] Step 6:

[0266] Users can check the evaluation results and improvement suggestions displayed on their smartphones and make improvements to their work as needed, thereby improving work efficiency and quality.

[0267] Example 3

[0268] Next, a description will be given of a third embodiment of the third embodiment. 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."

[0269] Conventional work evaluation systems have difficulty not only evaluating the level of work performance of employees but also providing specific suggestions for improvement. In addition, feedback based on evaluation results is often abstract, and it is often unclear how employees should specifically improve. This has led to the issue of not being able to fully improve employees' work efficiency.

[0270] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0271] In this invention, the server includes generative artificial intelligence means for automatically recording work content and work activities, evaluation means for evaluating the records of work content and work activities generated by the generative artificial intelligence, feedback means for providing points for reflection, review, and improvement based on the evaluation means, generative artificial intelligence model means for generating specific improvement proposals based on the evaluation results by the feedback means, prompt sentence generation means for inputting the evaluation results to the generative artificial intelligence model means, and notification means for providing feedback obtained from the generative artificial intelligence model means to the worker. This makes it possible to provide specific and practical improvement proposals to the worker.

[0272] "Generative artificial intelligence means" refers to artificial intelligence technology for automatically recording work content and work activities.

[0273] "Evaluation means" refers to technology for analyzing the work content and work activity records generated by the generative artificial intelligence means and evaluating the degree of work achievement.

[0274] "Feedback measures" refer to techniques for providing points for reflection, reflection, and improvement based on evaluation measures.

[0275] "Generative artificial intelligence model means" refers to artificial intelligence technology for generating specific improvement proposals based on evaluation results.

[0276] The "prompt sentence generation means" refers to a technique for generating a prompt sentence for inputting the evaluation result to the generation artificial intelligence model means.

[0277] "Notification means" refers to a technology for providing feedback obtained from the generative artificial intelligence model means to a business operator.

[0278] This invention is a system for evaluating the degree of work performance of an employee and providing specific suggestions for improvement. The program processing of this system will be specifically described below.

[0279] The server uses a generative artificial intelligence means to automatically record the work content and work activities of the worker. This generative artificial intelligence means collects data from the terminal used by the worker and records the work content and work activities. For example, it collects task completion information entered by the worker into a task management application and data from a time tracking tool that records work hours.

[0280] The server then analyzes the collected data using an evaluation tool. Specifically, it uses Scikit-learn, a Python machine learning library, to evaluate the worker's level of work achievement. The evaluation tool quantifies the level of work achievement and identifies the cause of low achievement. For example, it quantifies the level of work achievement based on the number of tasks an employee completes in a week and the time required to complete them. If achievement is low, the server identifies issues with task prioritization and time management.

[0281] The server then generates specific improvement suggestions based on the evaluation results. This process uses OpenAI's GPT-4, a generative AI model. The server inputs the evaluation results into the generative AI model as a prompt sentence, generating feedback for the worker. For example, the following prompt sentence could be input into the generative AI model:

[0282] "Worker A's performance is 50% and their main issue is improper task prioritization. Please provide specific suggestions for improving this issue."

[0283] When this prompt sentence is fed into a generative AI model, the model generates the following feedback:

[0284] "Employee A, we have confirmed that your work completion rate is 50%. The main problem is that you are not prioritizing your tasks properly. To improve this, it is important to first classify your daily tasks based on importance and urgency, and clarify their priorities. We also recommend that you regularly check your progress and re-prioritize your tasks as necessary."

[0285] Finally, the server notifies the worker of the generated feedback to their device. For example, it sends a notification to the worker's smartphone saying, "We recommend that you review the prioritization of your tasks and classify them based on importance and urgency."

[0286] In this way, the server can generate specific improvement proposals based on the evaluation results and provide feedback to the business operator. This system allows the business operator to receive specific and practical improvement proposals, thereby improving business efficiency. The flow of the identification process in Example 3 will be described with reference to Figure 15.

[0287] Step 1:

[0288] The server collects data on work content and work activities from the workers' devices. Specifically, it collects task completion information entered by workers into a task management application and data from a time tracking tool that records work time. Input data includes task names, completion dates and times, and required time. This data is sent to the server and saved as a record of work content and work activities.

[0289] Step 2:

[0290] The server analyzes the collected data using evaluation methods. Specifically, it uses Scikit-learn, a Python machine learning library, to evaluate the worker's level of work achievement. The input data is the records of work content and work activities collected in Step 1. The server uses this data to quantify the level of work achievement and identify the causes of low achievement. For example, it identifies problems with task prioritization and time management.

[0291] Step 3:

[0292] The server generates specific improvement proposals based on the evaluation results. A generative AI model is used in this process. The input data is the evaluation results obtained in step 2. The server inputs the evaluation results into the generative AI model as a prompt sentence, and generates feedback for the worker. For example, it generates a prompt sentence such as, "Worker A's task achievement rate is 50%, and the main problem is that the prioritization of tasks is inappropriate. Please provide specific proposals to improve this problem."

[0293] Step 4:

[0294] The server notifies the worker's device of the feedback obtained from the generative AI model. The input data is the feedback generated in step 3. The server sends a notification to the worker's smartphone saying, "We recommend that you review your task prioritization and classify them based on importance and urgency." The worker can use this feedback to improve their work.

[0295] In this way, the server can generate specific improvement suggestions based on the evaluation results and provide feedback to the operator.

[0296] (Application example 3)

[0297] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0298] Traditionally, evaluation of work efficiency and accuracy in factories has relied on human monitoring and manual recording, making it difficult to provide efficient feedback and suggest improvements. Furthermore, as work becomes increasingly automated, there is a need for a method to evaluate the performance of machinery in real time and quickly provide feedback on specific areas for improvement.

[0299] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means. In this invention, the server includes generative AI means for automatically recording work content and work activities, evaluation means for evaluating the records of work content and work activities generated by the generative AI, feedback means for providing points for reflection, review, and improvements based on the evaluation means, and means for evaluating the work efficiency and accuracy of machinery performing work in a factory and providing feedback on areas for improvement. This makes it possible to evaluate the work efficiency and accuracy of machinery in real time and quickly provide feedback on specific improvement suggestions.

[0300] "Generative AI means" refers to artificial intelligence technology for automatically recording work content and work activities.

[0301] "Evaluation means" refers to the means for evaluating the work content and work activity records generated by generative AI.

[0302] "Feedback measures" refer to measures for providing points for reflection, reflection, and improvement based on evaluation measures.

[0303] "Machinery" refers to automated devices and robots used to perform work within a factory.

[0304] "Work efficiency" refers to an index that indicates how much work a machine or device can complete within a certain amount of time.

[0305] "Precision" refers to an indicator of the accuracy and smallness of error when a machine or device performs its work.

[0306] "Areas for improvement" refers to specific methods and means proposed based on the evaluation results to improve work efficiency and accuracy.

[0307] A system for implementing this invention includes a generative AI means for automatically recording work content and work activities, an evaluation means for evaluating the generated records of work content and work activities, a feedback means for providing points for reflection, review, and improvement based on the evaluation means, and a means for evaluating the work efficiency and accuracy of machinery and equipment used in work within a factory and providing feedback on points for improvement.

[0308] The server automatically records work content and work activities using generative AI means. The generative AI means monitors the progress of work and work content in real time and collects data. The collected data is analyzed by evaluation means, and work efficiency and accuracy are evaluated.

[0309] The evaluation means calculates performance indicators such as work time and error rate based on the collected data, thereby quantifying the work efficiency and accuracy of the machine and obtaining evaluation results.

[0310] The feedback mechanism generates specific improvement suggestions based on the evaluation results. For example, if a task takes a long time, it suggests optimizing the motion path or calibrating the tool. If the error rate is high, it identifies the cause of the error and suggests how to correct it.

[0311] As a concrete example, feedback can be obtained by inputting the following prompt sentences into a generative AI model:

[0312] Example prompt sentence:

[0313] A factory robot performed a part assembly task. The task took 15 seconds and resulted in two errors. Please rate its performance and provide feedback on areas for improvement.

[0314] In response to this prompt, the generative AI model provides the following feedback:

[0315] Examples of feedback generated:

[0316] Performance Score: 50

[0317] Improvement Needed:

[0318] Reduce task time. Consider optimizing the movement path.

[0319] Reduce errors. Check the calibration of the tools.

[0320] The system is implemented using Python programming. The hardware used includes factory robots and sensors, and the software includes Python and an evaluation system. This makes it possible to evaluate the work efficiency and accuracy of machinery in real time and quickly provide feedback on specific improvement suggestions.

[0321] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0322] Step 1:

[0323] The server automatically records work content and activities using generative AI methods. Specifically, it collects work data (such as work time and number of errors) from factory robots in real time and stores it in a database. The input is sensor data from the factory robots, and the output is work records stored in the database.

[0324] Step 2:

[0325] The server analyzes the collected data using the evaluation tools. Specifically, it calculates performance indicators such as work time and number of errors, and evaluates work efficiency and accuracy. The input is the work records stored in the database, and the output is the evaluation results (performance scores, etc.).

[0326] Step 3:

[0327] The server generates specific improvement suggestions using feedback means based on the evaluation results. Specifically, it analyzes the evaluation results and suggests optimizing the operation path if the task time is long, or suggests tool calibration if the error rate is high. The input is the evaluation results, and the output is feedback including improvement suggestions.

[0328] Step 4:

[0329] The server sends the generated feedback to the factory robot's management system. Specifically, it generates the feedback content in text format and notifies the management system. The input is the feedback including the improvement suggestions, and the output is the feedback notification sent to the management system.

[0330] Step 5:

[0331] The user checks the feedback through the management system and makes any necessary improvements. Specifically, the user checks the feedback and optimizes the motion path or calibrates the tool. The input is the feedback displayed on the management system, and the output is improved work efficiency and accuracy.

[0332] 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.

[0333] "Example 1"

[0334] One embodiment of the present invention provides a system including an emotion engine that recognizes the emotions of workers. In this system, a generative AI not only automatically records the work content and work activities of workers, but also simultaneously records the worker's emotional state. The emotion engine estimates the worker's emotional state from the worker's tone of voice, facial expression, choice of words, etc. Specifically, the emotion engine estimates the worker's emotional state from the worker's tone of voice when operating business tools, facial expressions during video conferences, choice of words in chat tools, etc.

[0335] "Example 2"

[0336] Furthermore, the generative AI reflects the emotional state of the worker estimated by the emotion engine in the daily report. Specifically, the emotional state of the worker on that day, such as when the worker is feeling happy, when they are facing difficulties, when they are feeling stressed, etc., is recorded in the daily report. This allows the worker and their superiors to understand not only the work content but also the emotional state of the worker. "Example 3"

[0337] Furthermore, the feedback means provides feedback based not only on the evaluation results of the work content by the evaluation means, but also on the estimation results of the emotional state by the emotion engine. Specifically, when the worker is feeling stressed, advice on how to reduce stress is provided. Also, when the worker is feeling joy, the source of that joy is analyzed and advice on how to achieve the same joy is provided. This enables more appropriate feedback that takes into account the worker's emotional state.

[0338] The processing flow of each embodiment will be described below.

[0339] "Example 1"

[0340] Step 1: The worker interacts with the tools they use. This interaction may reflect their emotional state, such as tone of voice, facial expression, and choice of words.

[0341] Step 2: The emotion engine estimates the worker's emotional state from factors such as the worker's tone of voice, facial expressions, and choice of words.

[0342] Step 3: The generative AI automatically records the worker's work content and activities, along with the worker's emotional state estimated by the emotion engine.

[0343] "Example 2"

[0344] Step 1: Generative AI automatically records the work content and work activities of employees.

[0345] Step 2: The emotion engine estimates the worker's emotional state.

[0346] Step 3: The generative AI reflects the emotional state of the employee estimated by the emotion engine in the daily report.

[0347] "Example 3"

[0348] Step 1: The evaluation instrument evaluates the job content.

[0349] Step 2: The emotion engine estimates the worker's emotional state.

[0350] Step 3: The feedback means provides feedback based on the evaluation results of the work content by the evaluation means and the estimation results of the emotional state by the emotion engine.

[0351] Example 1

[0352] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0353] Conventional business record systems could automatically record the work content and activities of employees, but were unable to simultaneously record their emotional state. This made it difficult to provide feedback or suggest improvements that took into account the employee's psychological state. Furthermore, work content records were rarely automatically generated as daily reports, placing a heavy burden on employees. To solve these issues, a system that simultaneously records work content and emotional state and automatically generates daily reports is needed.

[0354] 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.

[0355] In this invention, the server includes generative AI means for automatically recording work content and work activities, evaluation means for evaluating the records of work content and work activities generated by the generative AI, feedback means for providing points for reflection, review, and improvement based on the evaluation means, emotion engine means for estimating the emotional state of the worker, and means for recording the emotional state estimated by the emotion engine means. This makes it possible to simultaneously record work content and emotional state and automatically generate a daily report.

[0356] "Generative AI methods" are artificial intelligence methods that automatically record work content and work activities and generate them as daily reports.

[0357] "Evaluation means" refers to a means for evaluating the work content and work activity records generated by generative AI.

[0358] "Feedback measures" are means for providing points for reflection, reflection, and improvement based on evaluation measures.

[0359] The "emotion engine means" is a means for estimating the emotional state of a worker.

[0360] The "recording means" is a means for recording the emotional state estimated by the emotion engine means.

[0361] MODE FOR CARRYING OUT THE INVENTION

[0362] This invention is a system that automatically records the work content and work activities of employees and generates a daily report. Furthermore, by estimating and recording the employee's emotional state, it is possible to provide more detailed feedback. This system includes elements such as a server, a terminal, and a user.

[0363] 1. Program Generation

[0364] The server automatically records the work activities of employees and generates a program to generate daily reports. This program works in conjunction with business tools and systems, understands the work content based on operation logs and input data, and formats the data into daily reports.

[0365] 2. Program processing explanation

[0366] The server connects to the business tools (e.g., office suites, cloud services) and systems (e.g., customer management systems, ERP systems) used by employees. It collects operation logs and input data when employees use these tools to understand the content of their work. It also simultaneously records the employee's emotional state using an emotion engine. The emotion engine analyzes the employee's tone of voice, facial expressions, choice of words, and other factors. For example, it analyzes the video and audio during a video conference and infers the employee's emotional state from their facial expressions and tone of voice.

[0367] 3. Examples of concrete examples and prompts

[0368] Let's say a user is holding a meeting using a video conferencing system. At this time, the server analyzes the video and audio of the video conference and estimates the worker's emotional state from their facial expressions and tone of voice. It also collects documents used during the meeting and chat content to understand the work content. Based on this data, the server generates a daily report.

[0369] As a concrete example, the following prompt sentence is input to the generative AI model:

[0370] "Please record today's work. Use a video conferencing system, and include what was said during the meeting and any chat conversations. Also, record the worker's emotional state."

[0371] Based on this prompt, the generative AI model generates a daily report like this:

[0372] "Today's business:

[0373] 10:00 AM - 11:00 AM: Project meeting via video conferencing system

[0374] What was said: Project progress report, confirmation of next steps

[0375] Chat content: Sharing materials, Q&A

[0376] Emotional state: The tone of voice during the meeting indicated that the workers were generally calm, with occasional bouts of tension. Their facial expressions also indicated that they were focused.

[0377] In this way, the server records the worker's work activities and emotional state in detail and formats them into a daily report, which makes it possible to provide feedback and suggest improvements that take into account the worker's psychological state.

[0378] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0379] Program processing flow

[0380] Step 1: Integration with business tools and systems

[0381] The server connects to the business tools and systems used by business personnel. Specifically, it uses APIs and plug-ins to obtain data from business tools (e.g., office suites, cloud services) and systems (e.g., customer management systems, ERP systems).

[0382] Input: API keys and authentication information for business tools and systems

[0383] Output: Data access permissions from business tools and systems

[0384] Specific operation: The server uses the API key to access the data of the business tool and obtains operation logs and input data.

[0385] Step 2: Collect operation logs and input data

[0386] The server collects operation logs and input data in real time when business personnel operate business tools.

[0387] Input: Operation logs and input data obtained from business tools and systems

[0388] Output: Save collected operation logs and input data

[0389] Specific operation: The server records the operation history when a worker enters data into Excel or updates customer information in a customer management system.

[0390] Step 3: Estimating emotional state

[0391] The server uses an emotion engine to estimate the emotional state of the worker, which analyzes the worker's tone of voice, facial expressions, choice of words, etc.

[0392] Input: Video and audio from video conferences, chat content

[0393] Output: Estimated emotional state data

[0394] Specific operation: The server analyzes the facial expressions of workers during video conferences and detects changes in their expressions, such as smiling or furrowing their brows. It also analyzes the tone of their voices to estimate whether the workers are tense or relaxed.

[0395] Step 4: Analyze data and generate daily reports

[0396] The server analyzes the collected operation logs, input data, and emotional state to understand the work content, and generates daily reports using a generative AI model based on this data.

[0397] Input: Operation log, input data, emotional state data

[0398] Output: Generated daily report

[0399] Specific operation: The server generates a daily report including the tasks performed by the worker, their progress, and their emotional state. For example, it generates the following daily report:

[0400] "Today's business:

[0401] 10:00 AM - 11:00 AM: Project meeting via video conferencing system

[0402] What was said: Project progress report, confirmation of next steps

[0403] Chat content: Sharing materials, Q&A

[0404] Emotional state: The tone of voice during the meeting indicated that the workers were generally calm, with occasional bouts of tension. Their facial expressions also indicated that they were focused.

[0405] Step 5: Provide daily reports

[0406] The server provides the generated daily reports to the workers, who can then view them on a dedicated dashboard or send them to their terminals via email.

[0407] Input: Generated daily report

[0408] Output: Daily report provided to the worker

[0409] Specific operation: The server sends the generated daily report to the employee's email address. It also displays the daily report on a dedicated dashboard so that the employee can view it at any time.

[0410] (Application example 1)

[0411] Next, a description will be given of Application Example 1 of Embodiment 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."

[0412] In conventional business record systems, recording of work content and work activities is often done manually, which is inefficient. Furthermore, feedback that takes into account the emotional state of the worker is not provided, so improvements in work efficiency and safety are not sufficiently achieved. This can easily lead to the accumulation of stress and fatigue among workers, resulting in decreased productivity and increased errors.

[0413] 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.

[0414] In this invention, the server includes generative AI means for automatically recording work content and work activities, evaluation means for evaluating the records of work content and work activities generated by the generative AI, feedback means for providing points for reflection, review, and improvement based on the evaluation means, emotion engine means for recognizing the emotional state of the worker, and means for providing appropriate feedback to the worker based on the emotion engine means. This enables efficient recording and evaluation of work content and work activities, and further enables improvement of work efficiency and safety by providing feedback that takes into account the emotional state of the worker.

[0415] "Generative AI means" is an artificial intelligence technology that automatically records work content and activities and generates those records as daily reports.

[0416] "Evaluation methods" are technologies for analyzing the work content and records of work activities generated by generative AI and evaluating their content.

[0417] "Feedback methods" are techniques for providing points for reflection, reflection, and improvement based on evaluation methods.

[0418] "Emotion engine means" is a technology for estimating and recognizing a worker's emotional state from their tone of voice, facial expressions, choice of words, etc.

[0419] The "means for providing appropriate feedback" is a technology that takes into consideration the emotional state of the worker based on the emotion engine means and provides feedback to improve work efficiency and safety.

[0420] A system for carrying out this invention has the following configuration: A server includes generative AI means for automatically recording work content and work activities, evaluation means for evaluating the records of work content and work activities generated by the generative AI, feedback means for providing points for reflection, review, and improvement based on the evaluation means, emotion engine means for recognizing the emotional state of a worker, and means for providing appropriate feedback to the worker based on the emotion engine means.

[0421] Hardware and software used

[0422] Hardware:

[0423] Factory robots

[0424] Microphone (voice data collection)

[0425] Camera (video data collection)

[0426] Computer (data processing)

[0427] software:

[0428] Python

[0429] EmotionEngine (emotion recognition engine)

[0430] WorkLog (work record management)

[0431] Data processing and calculation

[0432] 1. Record your work:

[0433] The server uses the WorkLog class to record work content. It receives work data (e.g., work content, work time) as input and adds it to the log.

[0434] 2. Recognition of emotional states:

[0435] The server uses the EmotionEngine class to estimate the emotional state from audio, video, and text data, and outputs the emotional state (e.g., stress level, fatigue level).

[0436] 3. Providing Feedback:

[0437] The server provides appropriate feedback to the worker based on their emotional state, for example, sending a notification to take a break if their stress level is high.

[0438] Specific examples

[0439] Record your work:

[0440] If a worker does "assembly work" for two hours, record the details.

[0441] Emotional state recognition:

[0442] Recognizes the emotional state of a worker when they look tired during a video conference.

[0443] Providing feedback:

[0444] If a worker is tired, a notification will be sent saying, "We recommend you take a break."

[0445] Prompt Sentence Examples

[0446] Design a system in which a factory robot records its work, recognizes the worker's emotional state, and provides feedback. To record work, use operation logs and input data from work tools and systems, and to recognize the worker's emotional state, use tone of voice, facial expressions, and choice of words. Include specific examples of feedback.

[0447] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0448] Step 1:

[0449] The server receives work data (e.g., work content, work time) as input to record the work content of the worker. Specifically, if a worker performs "assembly work" for two hours, the content is added to the WorkLog class. The input data is the worker's operation log and input data, and the output is the recorded work content.

[0450] Step 2:

[0451] The server collects audio, video, and text data to recognize the worker's emotional state. Specifically, audio data collected by a microphone, video data collected by a camera, and text data from a chat tool are input into the EmotionEngine class. The input data are audio, video, and text data, and the output is an estimated emotional state (e.g., stress level, fatigue level).

[0452] Step 3:

[0453] The server uses the EmotionEngine class to estimate the worker's emotional state from the collected data. Specifically, it analyzes the tone of voice, facial expressions, and word choice to evaluate the worker's emotional state. The input data is audio, video, and text data, and the output is the evaluation result of the worker's emotional state.

[0454] Step 4:

[0455] The server uses evaluation tools to analyze the work content and work activity records generated by the generative AI. Specifically, it evaluates the efficiency and accuracy of the work content and identifies areas for improvement. The input data is the recorded work content, and the output is the evaluation results.

[0456] Step 5:

[0457] The server provides appropriate feedback to the worker based on the evaluation results and emotional state. Specifically, if the stress level is high, the server sends a notification encouraging the worker to take a break. The input data are the evaluation results and emotional state, and the output is the feedback content.

[0458] Step 6:

[0459] The server sends a notification to the worker using the feedback means. Specifically, it displays a message on the worker's terminal saying, "We recommend you take a break." The input data is the feedback content, and the output is the notification to the worker.

[0460] Example 2

[0461] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0462] In conventional business record systems, recording of work content and work activities is often done manually, resulting in inefficiency. Furthermore, because the evaluation of work achievements and problems is also done manually, it tends to rely on subjective judgment. Furthermore, because evaluations and feedback do not take into account the emotional state of the worker, it is difficult to properly grasp the worker's psychological burden and stress. To solve these problems, there is a need for a system that automates the recording of work content and work activities and provides objective evaluations and feedback.

[0463] 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.

[0464] In this invention, the server includes a generative AI means for automatically recording work content and work activities, an evaluation means for evaluating the records of work content and work activities generated by the generative AI, a feedback means for providing points for reflection, review, and improvement based on the evaluation means, an emotion engine means for estimating the emotional state of the worker, and a means for reflecting the emotional state estimated by the emotion engine means in the records of work content and work activities. This makes it possible to automate the recording of work content and work activities and provide objective evaluation and feedback. Furthermore, by providing evaluation and feedback that takes the worker's emotional state into consideration, it is possible to appropriately understand and improve the worker's psychological burden and stress.

[0465] "Generative AI means" refers to artificial intelligence technology that automatically records work content and activities and generates them in the form of daily reports, etc.

[0466] "Evaluation means" refers to a device or program that has the function of analyzing the work content and work activity records generated by the generative AI means and automatically extracting the degree of work achievement and problems.

[0467] "Feedback means" refers to a device or program that has the function of providing points for reflection, review, and improvement based on the evaluation results obtained by the evaluation means.

[0468] "Emotion engine means" refers to artificial intelligence technology for estimating the emotional state of workers, and has the function of analyzing the joy, difficulties, stress, etc. that workers are feeling.

[0469] The "means for reflecting the emotional state in the record of work content or work activity" refers to a device or program having a function of adding the emotional state estimated by the emotion engine means to the generated record of work content or work activity.

[0470] MODE FOR CARRYING OUT THE INVENTION

[0471] The present invention relates to a system for automatically recording work content and work activities and providing evaluations and feedback. Specific embodiments of this system will be described below.

[0472] Hardware and software used

[0473] Hardware: Servers, terminals

[0474] Software: Generative AI model, emotion engine

[0475] System Overview

[0476] In this system, users input data on their work content and work activities after completing their work, and a generative AI model generates a daily report based on that data. The generated daily report is analyzed by an evaluation means, and the degree of work achievement and problems are extracted. Furthermore, an emotion engine means estimates the worker's emotional state, and this emotional state is reflected in the daily report. The final daily report is then provided with feedback means to provide points for reflection, reflection, and improvement, and is displayed on a terminal for the user and their supervisor to view.

[0477] Program processing

[0478] 1. The user enters the daily report data

[0479] Users use a dedicated application on their device to input information about the day's work, results, and impressions.

[0480] Specifically, you enter the number of visits, number of successful transactions, main business activities, and emotions felt.

[0481] 2. The device sends the data to the server

[0482] The terminal transmits the input data to the server in real time.

[0483] Specifically, data is sent to the server using an HTTP request.

[0484] 3. The server generates a daily report using the generative AI model

[0485] The server inputs the received data into a generative AI model to generate an initial version of the daily report.

[0486] Specifically, a prompt sentence is input into the generative AI model to generate the text of the daily report.

[0487] 4. The server passes the daily report to the evaluation tool

[0488] The server passes the generated daily report to the evaluation means.

[0489] Specifically, the evaluation means' API is called to send daily report data.

[0490] 5. The server extracts the degree of accomplishment and problems of the business.

[0491] The server analyzes the data returned from the evaluation means and extracts the degree of accomplishment of the work and any problems.

[0492] Specifically, it compares work goals with actual results and calculates the degree of achievement. It also extracts problems and areas for improvement from the contents of daily reports.

[0493] 6. The server uses the emotion engine to estimate the emotional state.

[0494] The server uses an emotion engine to estimate the emotional state of the worker.

[0495] Specifically, the text data of the daily report is input into an emotion engine to estimate the emotional state.

[0496] 7. The server reflects the emotional state in the daily report

[0497] The server reflects the estimated emotional state in the daily report.

[0498] Specifically, emotional states are added to the text of daily reports.

[0499] 8. The server generates the final daily report and sends it to the device.

[0500] The server generates the final daily report and sends it to the terminal.

[0501] Specifically, the final daily report data is sent to the terminal in JSON format.

[0502] 9. The device displays the daily report to the user.

[0503] The terminal displays the received daily report to the user.

[0504] Specifically, daily reports are displayed on the UI of a dedicated application.

[0505] Specific examples

[0506] For example, a sales representative enters the following data:

[0507] Number of visits: 5

[0508] Number of successful transactions: 2

[0509] Main duties: Developing new customers and following up with existing customers

[0510] Emotions felt: Stress

[0511] Example prompt sentence:

[0512] Today I made five visits and closed two deals. I developed new clients and followed up with existing clients. I felt stressed.

[0513] Based on this data, the server uses a generative AI model to generate a daily report like this:

[0514] Today, there were five visits and two successful sales. We developed new clients and followed up with existing clients. Our work is only 40% accomplished, meaning we have not yet reached our target number of successful sales. There is room for improvement in our approach to developing new clients. Additionally, we need additional suggestions to improve customer satisfaction when following up with existing clients. Our staff is finding it difficult to develop new clients and is feeling stressed.

[0515] In this way, a daily report is generated that includes the work content and emotional state.

[0516] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0517] Program processing flow

[0518] Step 1:

[0519] The user enters the daily report data.

[0520] Input: The user uses a dedicated application on the device to input information about the day's work, results, and feelings.

[0521] Specific behavior: The user fills out an input form with information such as the number of visits, number of successful transactions, main tasks, and feelings.

[0522] Output: Input data is saved to the terminal.

[0523] Step 2:

[0524] The device sends the data to the server

[0525] Input: User input data stored on the device.

[0526] Specific operation: The device uses an HTTP request to send input data to the server.

[0527] Output: The user input data is sent to the server.

[0528] Step 3:

[0529] The server generates daily reports using the generative AI model

[0530] Input: User input data sent to the server.

[0531] Specific operation: The server inputs a prompt sentence into the generative AI model to generate an initial version of the daily report.

[0532] Output: The initial version of the daily report text is generated.

[0533] Step 4:

[0534] The server passes the daily report to the evaluation means

[0535] Input: The initial version of the generated daily report text.

[0536] Specific operation: The server calls the evaluation means API and sends the daily report data.

[0537] Output: Daily report data is passed to the evaluation means.

[0538] Step 5:

[0539] The server extracts the degree of accomplishment and problems of the work

[0540] Input: The evaluation data returned by the evaluation instrument.

[0541] Specific operation: The server compares the business goals and actual results, calculates the degree of achievement, and extracts problems and areas for improvement from the contents of the daily report.

[0542] Output: The degree of accomplishment, problems, and areas for improvement of the work are extracted.

[0543] Step 6:

[0544] The server uses an emotion engine to estimate the emotional state.

[0545] Input: The initial version of the daily report text.

[0546] Specific operation: The server inputs the text data of the daily report into the emotion engine and estimates the emotional state.

[0547] Output: The worker's emotional state is estimated.

[0548] Step 7:

[0549] The server reflects the emotional state in the daily report.

[0550] Input: Estimated emotional state and initial version of daily report text.

[0551] Specific behavior: The server adds the emotional state to the text of the daily report.

[0552] Output: A final version of the daily report reflecting the emotional state is generated.

[0553] Step 8:

[0554] The server generates the final daily report and sends it to the device.

[0555] Input: Final version of daily report reflecting emotional state.

[0556] Specific operation: The server sends the final daily report data in JSON format to the terminal.

[0557] Output: The final daily report data is sent to the terminal.

[0558] Step 9:

[0559] The device displays the daily report to the user.

[0560] Input: Final daily report data sent from the server.

[0561] Specific operation: The device displays the daily report on the UI of a dedicated application.

[0562] Output: The user can view the final daily report.

[0563] (Application example 2)

[0564] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0565] In conventional business record systems, recording of work content and work activities is often done manually, which is time-consuming and labor-intensive, and can lead to a lack of accuracy and consistency in the records. In addition, evaluations and feedback do not take into account the emotional state of employees, so there is a risk that employee stress or a decline in motivation may be overlooked. This leads to the issue of insufficient efforts to improve and streamline work.

[0566] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0567] In this invention, the server includes generative AI means for automatically recording work content and work activities, evaluation means for evaluating the records of work content and work activities generated by the generative AI, feedback means for providing points for reflection, review, and improvement based on the evaluation means, emotion estimation means for estimating and recording the emotional state of the worker using an emotion engine, and daily report generation means for reflecting the emotional state estimated by the emotion estimation means in the daily report. This not only automates the recording of work content and work activities and enables accurate and consistent recording, but also provides evaluations and feedback that take the emotional state of the worker into consideration, thereby improving and streamlining work and preventing stress and a decline in motivation among workers.

[0568] "Generative AI means" refers to artificial intelligence technology that automatically records work content and activities and generates documents such as daily reports.

[0569] "Evaluation methods" are technologies for evaluating the work content and records of work activities generated by generative AI and extracting the level of achievement and problems.

[0570] "Feedback methods" are techniques for providing points for reflection, reflection, and improvement based on evaluation methods.

[0571] The "emotion estimation means" is a technology for estimating and recording the emotional state of a worker using an emotion engine.

[0572] The "daily report generation means" is a technology for reflecting the emotional state estimated by the emotion estimation means in the daily report.

[0573] A system for carrying out this invention is configured as follows: A server includes generative AI means for automatically recording work content and work activities, evaluation means for evaluating the records of work content and work activities generated by the generative AI, feedback means for providing points for reflection, review, and improvement based on the evaluation means, emotion estimation means for estimating and recording the emotional state of the worker using an emotion engine, and daily report generation means for reflecting the emotional state estimated by the emotion estimation means in a daily report.

[0574] Hardware and software used

[0575] Hardware: Factory robots, sensors (temperature, humidity, vibration, etc.)

[0576] Software: Python, OpenAI API, sentiment analysis library (e.g., sentiment_analysis)

[0577] Data processing and calculation

[0578] 1. Work data acquisition: Factory robots record their daily work, for example, collecting data that indicates that work A has been completed and work B has not yet been completed.

[0579] 2. Acquisition of emotional data: The emotion engine estimates the emotional state of the worker based on sensor information. For example, it collects data on whether the worker is feeling stressed.

[0580] 3. Daily report generation: Using a generative AI model (OpenAI API), a daily report is generated based on task data and emotion data. Instructions are given to the generative AI using prompt statements.

[0581] 4. Daily report evaluation: Evaluate the generated daily reports and identify achievements and problems. Based on the evaluation results, make specific improvement proposals.

[0582] Specific examples

[0583] For example, suppose a factory robot has the following task and emotion data:

[0584] Operation data: Operation A is completed, and operation B is incomplete.

[0585] Emotional data: Workers are feeling stressed.

[0586] Based on this data, the generative AI model is given the following prompt:

[0587] Please generate a daily report based on the following work data:

[0588] Task data: Task A: Completed, Task B: Incomplete

[0589] Emotional data: workers are stressed

[0590] The generative AI model generates a daily report based on this prompt, and the evaluation means evaluates the daily report. Based on the evaluation results, the feedback means provides specific suggestions for improvement. This not only automates the recording of work content and work activities, enabling accurate and consistent recording, but also provides evaluations and feedback that take into account the worker's emotional state, thereby improving and streamlining work and preventing worker stress and a decline in motivation.

[0591] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0592] Step 1:

[0593] The server acquires work data from the factory robots. Specifically, the factory robots record their daily work and send that data to the server. The input is the work data, and the output is the work data saved on the server. For example, data such as "Task A: Completed, Task B: Incomplete" is acquired.

[0594] Step 2:

[0595] The server uses an emotion engine to estimate the worker's emotional state based on sensor information. Specifically, it analyzes sensor information such as temperature, humidity, and vibration to estimate the worker's emotional state. The input is sensor information, and the output is estimated emotional data. For example, data such as "the worker is feeling stressed" can be obtained.

[0596] Step 3:

[0597] The server generates daily reports using a generative AI model. Specifically, a prompt sentence is created based on task data and emotion data and input into the generative AI model. The input is task data and emotion data, and the output is the generated daily report. An example of a prompt sentence is "Please generate a daily report based on the following task data. Task data: Task A: Completed, Task B: Incomplete. Emotion data: The worker is feeling stressed."

[0598] Step 4:

[0599] The server evaluates the generated daily reports. Specifically, it analyzes the contents of the daily reports and extracts the degree of achievement and problems of the work. The input is the generated daily report, and the output is the evaluation result. For example, the evaluation result may be "Achievement: Low, Problem: Task B is incomplete."

[0600] Step 5:

[0601] The server provides feedback based on the evaluation results. Specifically, it analyzes the evaluation results and presents points for reflection, reflection, and improvement. The input is the evaluation results, and the output is the feedback content. For example, a specific improvement suggestion such as "Check the progress of task B and provide any necessary support" is provided.

[0602] Step 6:

[0603] The server saves the generated daily report and feedback content, and notifies the user as necessary. Specifically, it saves the daily report and feedback content in a database and makes them accessible to the user. The input is the generated daily report and feedback content, and the output is the saved data and notification. For example, a notification such as "The daily report and feedback have been saved. Please check them" is sent to the user.

[0604] Example 3

[0605] Next, a description will be given of a third embodiment of the third embodiment. 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."

[0606] Conventional performance evaluation systems not only evaluate the work content and records of work activities, but also have difficulty providing feedback that takes into account the emotional state of the worker. Furthermore, there is a lack of means to generate feedback in natural language, making it difficult to provide specific and appropriate improvement suggestions to the worker. This has led to the issue of insufficient improvements in the worker's work efficiency and emotional state.

[0607] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0608] In this invention, the server includes generative AI means for automatically recording work content and work activities, evaluation means for evaluating the records of work content and work activities generated by the generative AI, feedback means for providing points for reflection, review, and improvement based on the evaluation means, means for the feedback means to provide feedback based on the emotional state estimation result by the emotion engine, and means for the feedback means to generate feedback content in natural language using a generative AI model. This makes it possible to comprehensively evaluate the work content and emotional state of the worker and provide specific and appropriate feedback.

[0609] "Generative AI means" refers to artificial intelligence technology for automatically recording work content and work activities.

[0610] "Evaluation means" refers to the means for analyzing the work content and work activity records generated by generative AI means and identifying the degree of work achievement and problems.

[0611] "Feedback measures" refer to measures for providing points for reflection, reflection, and improvement based on evaluation measures.

[0612] "Emotion engine" refers to software or algorithms for estimating the emotional state of a worker.

[0613] "Generative AI model" refers to an artificial intelligence model that generates feedback content in natural language.

[0614] "Natural language generation" refers to the technology of using artificial intelligence to generate sentences in language that humans can understand.

[0615] MODE FOR CARRYING OUT THE INVENTION

[0616] The present invention relates to a system for automatically recording, evaluating, and providing feedback on work content and work activities. Specific embodiments of this system will be described below.

[0617] Hardware and software used

[0618] Server: A central server for processing data and generating evaluation results.

[0619] Devices: PCs and smartphones used by business personnel

[0620] Emotion Engine: Software for estimating the emotional state of workers

[0621] Generative AI model: An AI model for generating feedback content in natural language

[0622] Program processing procedure

[0623] 1. Data Collection

[0624] The server collects data on the work of the workers, including the progress of the work, deliverables, and working hours.

[0625] Specific operation: The server retrieves data from business management systems and project management tools (e.g., JIRA, Trello) via API.

[0626] 2. Job Evaluation

[0627] The server evaluates the work of the workers based on the collected data, and identifies the degree of achievement and problems of the work using the evaluation means.

[0628] Specific operation: The server executes the evaluation algorithm to calculate the progress rate of the work and the completion status of the task. For example, if the progress rate is less than 50%, it is determined to be late.

[0629] 3. Emotional State Estimation

[0630] The server uses an emotion engine to estimate the emotional state of the worker, determining whether the worker is feeling stressed or happy.

[0631] Specific operation: The server analyzes the employee's input data (e.g., daily reports and feedback forms) and biometric data (e.g., heart rate and facial expression recognition) to estimate their emotional state.

[0632] 4. Feedback Generation

[0633] The server generates specific feedback based on the evaluation results and the estimated emotional state, using a generative AI model to generate the feedback content in natural language.

[0634] Specific operation: The server inputs the following prompt sentence into the generative AI model.

[0635] Employee evaluation results: The project is behind schedule due to insufficient task prioritization.

[0636] Worker emotional state: High stress levels.

[0637] Generate feedback content.

[0638] The generative AI model generates appropriate feedback based on this prompt.

[0639] 5. Send Feedback

[0640] The server transmits the generated feedback to the business operator's terminal.

[0641] Specific operation: The server sends feedback via the employee's email address or chat tool (e.g., Slack, Microsoft Teams).

[0642] 6. Receiving and Using Feedback

[0643] Workers receive feedback through the device, which helps them improve their work and manage their emotional state.

[0644] Specific Actions: The worker reviews the feedback received and implements the suggested improvements and advice, such as reevaluating task priorities and taking short breaks to reduce stress.

[0645] Specific examples

[0646] For example, suppose a worker reports on the progress of a project. The server collects this report data and analyzes it using an evaluation tool. As a result of the analysis, it is determined that the project is behind schedule. At the same time, if the emotion engine estimates that the worker's stress level is high, the server generates the following feedback:

[0647] Feedback based on the evaluation: "The project is not progressing smoothly because we haven't prioritized the tasks properly. Let's reevaluate the tasks at our next meeting."

[0648] Feedback based on emotional state: "You seem to be stressed out by your work lately. I suggest you take a short break to reduce your stress."

[0649] In this way, the worker can receive specific and appropriate feedback, which can be used to improve the work and manage the emotional state. The flow of the identification process in the third embodiment will be described with reference to FIG.

[0650] Step 1:

[0651] Data collection

[0652] The server collects data relating to the business activities of business operators.

[0653] Input: Business data from business management systems and project management tools (e.g., JIRA, Trello).

[0654] Specific operation: The server obtains data such as work progress, deliverables, and working hours through the API.

[0655] Output: Collected business data.

[0656] Step 2:

[0657] Business evaluation

[0658] The server evaluates the work of the employee based on the collected data.

[0659] Input: Business data collected in step 1.

[0660] Specific operation: The server executes an evaluation algorithm to calculate the progress rate and task completion status. For example, if the progress rate is less than 50%, it is considered to be late.

[0661] Output: Evaluation results showing the degree of accomplishment and problems of the work.

[0662] Step 3:

[0663] Emotional state estimation

[0664] The server uses an emotion engine to estimate the emotional state of the worker.

[0665] Input: Employee input data (e.g., daily reports and feedback forms) and biometric data (e.g., heart rate, facial expression recognition).

[0666] Specific operation: The server analyzes these data and determines whether the worker is feeling stressed or happy.

[0667] Output: Estimation of the worker's emotional state.

[0668] Step 4:

[0669] Feedback Generation

[0670] The server generates specific feedback based on the evaluation results and the estimated emotional state.

[0671] Input: Evaluation results from step 2 and estimation results of emotional state from step 3.

[0672] Specific operation: The server inputs the following prompt sentence into the generative AI model.

[0673] Employee evaluation results: The project is behind schedule due to insufficient task prioritization.

[0674] Worker emotional state: High stress levels.

[0675] Generate feedback content.

[0676] The generative AI model generates appropriate feedback based on this prompt.

[0677] Output: Generated feedback in natural language.

[0678] Step 5:

[0679] Send Feedback

[0680] The server transmits the generated feedback to the business operator's terminal.

[0681] Input: The feedback generated in step 4.

[0682] Specific operation: The server sends feedback via the employee's email address or chat tool (e.g., Slack, Microsoft Teams).

[0683] Output: Feedback sent to the worker's device.

[0684] Step 6:

[0685] Receiving and using feedback

[0686] Workers receive feedback through the device, which helps them improve their work and manage their emotional state.

[0687] Input: Feedback submitted in step 5.

[0688] Specific Actions: The worker reviews the feedback received and implements the suggested improvements and advice, such as reevaluating task priorities and taking short breaks to reduce stress.

[0689] Output: Improved work performance and controlled emotional state.

[0690] (Application example 3)

[0691] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0692] Conventional work evaluation systems have difficulty comprehensively evaluating workers' work efficiency and emotional state and providing appropriate feedback. Furthermore, while there is a need for real-time detection of declines in work efficiency and overload conditions, particularly for factory robots, and appropriate improvement proposals, there has been a lack of concrete methods for achieving this. As a result, improvements in robot work efficiency and reductions in overload conditions have not been fully achieved.

[0693] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0694] In this invention, the server includes generative AI means for automatically recording work content and work activities, evaluation means for evaluating the records of work content and work activities generated by the generative AI, feedback means for providing points for reflection, review, and improvement based on the evaluation means, means for collecting robot work data and sensor information and evaluating work efficiency, means for estimating the emotional state based on the sensor information of the robot, and means for providing specific improvement suggestions and feedback based on the evaluation results and the emotional state, thereby making it possible to improve the robot's work efficiency and reduce overload.

[0695] "Generative AI methods" are artificial intelligence methods that automatically record work content and work activities and generate data.

[0696] "Evaluation means" refers to a means for evaluating the work content and work activity records generated by generative AI.

[0697] "Feedback measures" are means for providing points for reflection, reflection, and improvement based on evaluation measures.

[0698] "Task data" refers to data related to the work performed by the robot, and includes information on the movements, time, efficiency, etc.

[0699] "Sensor information" refers to information obtained from sensors mounted on the robot, and includes data such as temperature, pressure, and operating status.

[0700] "Means for evaluating work efficiency" refers to a means for evaluating work efficiency based on robot work data and sensor information.

[0701] The "means for estimating emotional state" is a means for estimating the emotional state of the robot (for example, an overloaded state or a normal state) based on the sensor information of the robot.

[0702] "Means for providing specific improvement suggestions and feedback" refers to means for providing specific improvement suggestions and feedback based on the evaluation results and emotional state.

[0703] A system for carrying out this invention is configured as follows: The server includes generative AI means for automatically recording work content and work activities, evaluation means for evaluating the generated records of work content and work activities, feedback means for providing points for reflection, review, and improvement based on the evaluation means, means for collecting robot work data and sensor information and evaluating work efficiency, means for estimating the emotional state based on the robot's sensor information, and means for providing specific improvement suggestions and feedback based on the evaluation results and the emotional state.

[0704] Hardware and Software Configuration

[0705] Hardware:

[0706] Robot body

[0707] Sensors (temperature, pressure, motion sensors, etc.)

[0708] server

[0709] software:

[0710] Generative AI Model

[0711] Evaluation Module

[0712] Emotion Engine

[0713] Data Collection Module

[0714] Data processing and calculation

[0715] The server collects data in real time from sensors installed on the robot body. The collected data is processed by the data collection module and input into the generative AI model. The generative AI model generates records of work content and work activities and passes them to the evaluation module. The evaluation module evaluates work efficiency based on the generated records, and the emotion engine estimates the robot's emotional state based on sensor information.

[0716] The evaluation results and the emotional state are passed to a feedback system, which generates specific suggestions for improvement and feedback. For example, if work efficiency is low, feedback such as "Please review your work procedures" is provided, and if the emotional state is stressed, advice such as "Please take a break" is provided.

[0717] Specific examples

[0718] For example, if a robot's efficiency drops while working in a factory, the server will provide feedback such as "Please review your work procedures." If the robot is overloaded, the server will provide advice such as "Please take a break."

[0719] Prompt Sentence Examples

[0720] An example of a prompt for the generative AI model is as follows:

[0721] Create a program that evaluates the robot's work efficiency and emotional state based on its work data and sensor information, and provides specific suggestions for improvement and feedback. If the evaluation result is low, provide feedback such as "Please review your work procedures," and if the robot's emotional state is stressed, provide feedback such as "Please take a break."

[0722] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0723] Step 1:

[0724] The server collects data in real time from sensors installed on the robot body. The input is sensor information, and the output is the collected raw data. Specifically, it acquires data such as temperature, pressure, and operating status from the sensors and sends it to the data collection module.

[0725] Step 2:

[0726] The server preprocesses the raw data collected using the data collection module. The input is the collected raw data, and the output is the preprocessed data. Specifically, it performs noise removal and data normalization, and converts the data into a format suitable for generative AI models.

[0727] Step 3:

[0728] The server inputs the preprocessed data into a generative AI model to generate records of work content and activities. The input is the preprocessed data, and the output is the generated work record. Specifically, the generative AI model analyzes the data and generates details of work content and activities in text format.

[0729] Step 4:

[0730] The server passes the generated business records to the evaluation module to evaluate the work efficiency. The input is the generated business records, and the output is the evaluation result of the work efficiency. Specifically, the evaluation module analyzes the business records and quantifies the work efficiency.

[0731] Step 5:

[0732] The server inputs sensor information into the emotion engine to estimate the robot's emotional state. The input is sensor information, and the output is the estimated emotional state. Specifically, the emotion engine analyzes the sensor information and determines whether the robot is in an overloaded state or a normal state.

[0733] Step 6:

[0734] The server passes the evaluation results and the estimated emotional state results to the feedback means, which then generates specific improvement suggestions and feedback. The input is the evaluation results of work efficiency and the estimated emotional state results, and the output is specific improvement suggestions and feedback. Specifically, the feedback means generates appropriate improvement suggestions and advice based on the evaluation results and the emotional state.

[0735] Step 7:

[0736] The server sends the generated feedback to the robot, which then modifies its behavior based on it. The input is specific improvement suggestions or feedback, and the output is the robot's behavior modification. Specific actions include the robot receiving the feedback and reviewing its work procedures or taking a break.

[0737] 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.

[0738] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ) 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.

[0739] Another example of generative AI is Gemini (registered trademark) (Internet search engine). <url: https: gemini.google.com ?hl="ja">) are mentioned.

[0740] 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.

[0741] [Second embodiment]

[0742] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0743] 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.

[0744] 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).

[0745] 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.

[0746] 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.

[0747] 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).

[0748] 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. 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.

[0749] 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.

[0750] 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.

[0751] 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.

[0752] 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.

[0753] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0754] "Example 1"

[0755] In one embodiment of the present invention, generative AI automatically records the work activities performed by business personnel and generates the records as daily reports. Specifically, it works in conjunction with the business tools and systems used by business personnel, understands the work content based on the operation logs and input data, and formats the results into daily reports.

[0756] "Example 2"

[0757] The evaluation means evaluates the daily reports generated by the generative AI. Specifically, it automatically extracts the degree of achievement and problems of work based on the contents of the daily reports and outputs the evaluation results. For example, it compares the work goals with the actual results and calculates the degree of achievement. It also extracts problems and areas for improvement from the work content.

[0758] "Example 3"

[0759] The feedback method provides points for reflection, reflection, and improvement based on the evaluation method. Specifically, specific improvement suggestions are made based on the evaluation results and feedback is provided to the worker. For example, if the level of achievement of a task is low, the problem that caused it and improvement suggestions are presented to the worker.

[0760] The processing flow of each embodiment will be described below.

[0761] "Example 1"

[0762] Step 1: The worker operates the business tools and systems.

[0763] Step 2: Generative AI collects operation logs and input data from business tools and systems.

[0764] Step 3: Based on the data collected by the generative AI, the work content is understood and formatted into a daily report.

[0765] "Example 2"

[0766] Step 1: Generative AI generates daily reports.

[0767] Step 2: The evaluation tool automatically extracts the degree of achievement and problems of the work based on the contents of the generated daily report.

[0768] Step 3: The evaluation means outputs the evaluation result.

[0769] "Example 3"

[0770] Step 1: The evaluation means outputs the evaluation result.

[0771] Step 2: The feedback mechanism makes specific improvement suggestions based on the evaluation results.

[0772] Step 3: The feedback mechanism provides feedback to the operator.

[0773] Example 1

[0774] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0775] Conventional business record systems require employees to manually record their work, which takes time and effort, and often results in inaccuracies and inconsistencies in the records. Furthermore, because evaluations of work and feedback on areas for improvement are also done manually, this is inefficient and can delay business improvements. There is a need for a system that can solve these problems, automate business records, and provide efficient feedback.

[0776] 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.

[0777] In this invention, the server includes generative AI means for automatically recording work content and work activities, evaluation means for evaluating the records of work content and work activities generated by the generative AI, feedback means for providing points for reflection, review, and improvement based on the evaluation means, data collection means for collecting operation logs and input data from work tools and systems, data analysis means for analyzing the collected data and understanding the work content, daily report generation means for generating daily reports based on the analysis results, and daily report distribution means for distributing the generated daily reports to users. This enables automation of work records and efficient feedback.

[0778] "Generative AI means" refers to artificial intelligence technology that automatically records work content and activities and formats them into daily reports and other formats.

[0779] "Evaluation means" refers to the function for analyzing the work content and records of work activities generated by generative AI and evaluating their content.

[0780] "Feedback means" refers to a function for providing points for reflection, review, and improvement based on the evaluation results obtained by the evaluation means.

[0781] "Data collection means" refers to the function for collecting operation logs and input data from business tools and systems.

[0782] "Data analysis means" refers to the function for analyzing collected data and understanding business operations.

[0783] The "daily report generation means" refers to a function for generating a daily report based on the analysis results obtained by the data analysis means.

[0784] The "daily report distribution means" refers to a function for distributing the generated daily report to the user.

[0785] The present invention relates to a system for automatically recording work content and work activities and generating a daily report. A specific embodiment of this system will be described below.

[0786] Server Roles

[0787] The server runs a generative AI means that automatically records business content and business activities. This generative AI works in conjunction with business tools and systems to collect their operation logs and input data. Specifically, the server obtains data from systems such as Microsoft Excel, Google Docs, Salesforce, and SAP via API. The collected data is analyzed by a data analysis means within the server, and the business content is identified. Based on the analysis results, the server generates a daily report using a daily report generation means. The generated daily report is distributed to the user via a daily report distribution means. For example, the server sends the generated daily report to the user's email address.

[0788] Device Role

[0789] A terminal generates an operation log when a user operates a business tool or system. Specifically, the terminal monitors user operations in real time and records the details of the operation in a log file. For example, when a user enters data into Microsoft Excel, the terminal records the details of the input as a log. The generated operation log and input data are sent from the terminal to a server. The terminal periodically communicates with the server and uploads the collected data.

[0790] User Roles

[0791] Users use business tools and systems on a daily basis to carry out their work activities. Specifically, they perform operations such as data entry and information updates. For example, a user updates customer information and adds a new contact in Salesforce. A daily report is automatically generated by the user simply by performing their daily work activities without any special operations. The generated daily report is distributed from the server, and the user can check the received daily report via email or chat tools.

[0792] Specific examples

[0793] Example 1: Recording sales activities

[0794] The server uses the Salesforce API to retrieve the log of customer information updated by the user. The server analyzes the operation log "Updated customer A's contact information" and identifies the updated content. The server generates a daily report stating "Today, customer A's information was updated and a new contact was added" and sends it to the user's email address.

[0795] Example 2: Recording Data Entry

[0796] When a user inputs data into Microsoft Excel, the device records the input as a log. The device sends the collected operation logs to the server every hour. The server receives the operation logs sent from the device, analyzes the operation log "Enter sales data," and identifies the sales data that was input. The server generates a daily report stating, "Today, sales data was entered and total sales amounted to XX yen," and sends it to the user's email address.

[0797] Prompt Sentence Examples

[0798] "Please generate a daily report based on the operation log when a business user updates customer information in Salesforce."

[0799] "Generate a daily report based on sales data entered in Microsoft Excel."

[0800] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0801] Step 1:

[0802] The server collects operation logs and input data from business tools and systems. Specifically, the server obtains data from systems such as Microsoft Excel, Google Docs, Salesforce, and SAP via API. As input, it receives operation logs and input data from business tools and systems, and as output, it stores the collected data in an internal database.

[0803] Step 2:

[0804] The server analyzes the collected data. Specifically, it uses natural language processing (NLP) technology to extract important information from operation logs and input data. As input, it receives operation logs and input data stored in an internal database, and as output, it generates analysis results. For example, the server analyzes the operation log "Update customer A's contact information" and identifies the updated content.

[0805] Step 3:

[0806] The server generates a daily report based on the analysis results. Specifically, the server uses a generative AI model to format the extracted information in natural language. It receives the analysis results as input and generates a daily report as output. For example, the server generates a daily report stating, "Today, customer A's information was updated and a new contact was added."

[0807] Step 4:

[0808] The server distributes the generated daily report to the user. Specifically, the server sends the daily report via email or a chat tool (for example, Slack or Microsoft Teams). The server receives the generated daily report as input and sends the daily report to the user's email address or chat tool as output. For example, the server sends the generated daily report to the user's email address.

[0809] Step 5:

[0810] A terminal generates an operation log when a user operates a business tool or system. Specifically, the terminal monitors user operations in real time and records the operation details in a log file. It receives user operations as input and generates an operation log as output. For example, when a user enters data into Microsoft Excel, the terminal records the input details as a log.

[0811] Step 6:

[0812] The terminal sends the generated operation logs and input data to the server. Specifically, the terminal periodically communicates with the server and uploads the collected data. It receives the generated operation logs and input data as input and sends data to the server as output. For example, the terminal sends the collected operation logs to the server every hour.

[0813] Step 7:

[0814] Users use business tools and systems on a daily basis to perform business activities. Specifically, users perform operations such as data entry and information updates. As input, they use business tools and systems, and as output, they generate operation logs and input data. For example, a user updates customer information and adds a new contact in Salesforce.

[0815] Step 8:

[0816] The user checks the daily report delivered from the server. Specifically, the user views the daily report received via email or chat tool. The user receives the daily report delivered from the server as input, and checks the contents of the daily report as output. For example, the user opens the daily report received by email and checks the work content.

[0817] (Application example 1)

[0818] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0819] In the past, work records in factories were often done manually, which placed a heavy burden on workers and was prone to errors and omissions. Furthermore, work evaluations and feedback on areas for improvement were not properly conducted, making it difficult to improve operations efficiently. Furthermore, the process of formatting work details into daily reports was time-consuming and labor-intensive.

[0820] 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.

[0821] In this invention, the server includes a generative AI means for automatically recording work content and work activities, an evaluation means for evaluating the records of work content and work activities generated by the generative AI, a feedback means for providing points for reflection, review, and improvement based on the evaluation means, a means for automatically recording the work content of machines operating in the factory and generating the results as a daily report, and a means for saving the daily report. This enables automated and accurate recording of work records, reduces the burden on workers, and enables efficient work improvement. Furthermore, the automatic generation of daily reports enables quick understanding and evaluation of work content.

[0822] "Generative AI methods" are artificial intelligence technologies that automatically record work content and activities and generate documents such as daily reports based on those records.

[0823] "Evaluation means" refers to technology for analyzing the work content and records of work activities generated by generative AI means and evaluating their content.

[0824] "Feedback means" refers to a technique for providing points for reflection, review, and improvement based on the evaluation results obtained by the evaluation means.

[0825] "Machines operating in factories" refer to automated devices and robots used to perform manufacturing, assembly, and other tasks in factories.

[0826] "Means for automatically recording work content" refers to technology for automatically recording the operation and work content of machines operating in a factory.

[0827] The "means for generating a daily report" is a technology for automatically generating a document in daily report format based on the recorded work content.

[0828] The "means for storing the daily report" is a technology for storing the generated daily report in a digital format.

[0829] A system for carrying out the present invention is for automatically recording the work details of machines operating in a factory and generating a daily report. A specific embodiment of this system will be described below.

[0830] System Configuration

[0831] The system includes the following main hardware and software:

[0832] Hardware: Factory robots (e.g., general-purpose robots), servers, data storage devices

[0833] Software: Python, generative AI models (e.g., GPT-3), database management system

[0834] Program processing

[0835] The server receives and records data on the work content sent by the factory robots. Specifically, it saves the robot's movements and work content as a log with a timestamp. Next, it uses a generative AI model to analyze the recorded data and format it as a daily report. The generated daily report is stored in a database and can be accessed as needed.

[0836] Specific examples

[0837] For example, when a factory robot performs tasks such as "starting the assembly line," "checking product quality," and "packing products into boxes," each task is recorded with a timestamp. A generative AI model analyzes this data and formats it into a daily report.

[0838] Prompt Sentence Examples

[0839] Please generate a daily report based on the work log below.

[0840] 1. 2023-10-01T09:00:00 - Start of assembly line

[0841] 2. 2023-10-01T10:00:00 - Check the quality of the product

[0842] 3. 2023-10-01T11:00:00 - Packing the products into boxes

[0843] The format of the report is as follows:

[0844] Date: YYYY-MM-DD

[0845] What you'll do:

[0846] Task 1: Task Details

[0847] Task 2: Task Details

[0848] Task 3: Task Details

[0849] In this way, a system is realized that automatically records the work content of factory robots and generates it as a daily report. This system enables automated and accurate recording of work records, reduces the burden on workers, and enables efficient business improvement. In addition, the automatic generation of daily reports makes it possible to quickly understand and evaluate work content.

[0850] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0851] Step 1:

[0852] The server receives data on the work content sent from the factory robot.

[0853] Input: Task data from factory robots (e.g., "Start the assembly line," "Check the quality of the product," etc.)

[0854] Output: A time-stamped log of work

[0855] Specific operation: The server receives data on the work content sent from the factory robots in real time, assigns a timestamp to each task, and saves it as a log.

[0856] Step 2:

[0857] The server stores the received work log in a database.

[0858] Input: Timestamp work log

[0859] Output: Work logs stored in a database

[0860] Specific operation: The server sends a time-stamped work log to the database management system and stores it in the database.

[0861] Step 3:

[0862] The server uses a generative AI model to analyze the saved work logs and format them into a daily report.

[0863] Input: Work logs stored in the database

[0864] Output: Formatted daily report

[0865] Specific operation: The server calls a generative AI model (e.g., GPT-3) and provides the saved work log as input. The generative AI model analyzes the work log and generates a document in the form of a daily report.

[0866] Step 4:

[0867] The server stores the generated daily report in a database.

[0868] Input: Formatted daily report

[0869] Output: Daily reports stored in a database

[0870] Specific operation: The server sends the generated daily report to the database management system and stores it in the database.

[0871] Step 5:

[0872] The user can obtain and view the daily report from the database as needed.

[0873] Input: User request

[0874] Output: Daily report provided to the user

[0875] Specific operation: The user sends a request for a daily report to the server. The server retrieves the relevant daily report from the database and provides it to the user.

[0876] Example 2

[0877] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0878] Conventional work evaluation systems required manual recording of work content and work activities, making the evaluation and feedback process cumbersome and time-consuming. Furthermore, the evaluations often lacked accuracy and consistency, making it difficult to identify specific areas for improvement. This led to the issue of insufficient work efficiency and improvement.

[0879] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: a generative AI means for automatically recording work content and work activities; an evaluation means for evaluating the records of work content and work activities generated by the generative AI; a feedback means for providing points for reflection, review, and improvement based on the evaluation means; an input means for a user to input a daily report; a transmission means for transmitting the input daily report data to the server; an analysis means for the server to receive the daily report data and input a prompt sentence to the generative AI model; a generation means for receiving the analysis results from the generative AI model and generating an evaluation report; a transmission means for transmitting the generated evaluation report to a terminal; and a confirmation means for a user to check the evaluation report. This automates the process from recording work content and work activities to evaluation and feedback, improves the accuracy and consistency of evaluation, and enables specific areas for improvement to be quickly identified.

[0880] "Generative AI means" refers to artificial intelligence technology for automatically recording work content and work activities.

[0881] "Evaluation means" refers to a function that analyzes the work content and work activity records generated by generative AI and evaluates the degree of work achievement and problems.

[0882] "Feedback means" refers to a function for providing points for reflection, reflection, and improvement based on evaluation means.

[0883] "Input means" refers to an interface for a user to input a daily report.

[0884] "Transmission means" refers to a function for transmitting input daily report data to a server.

[0885] "Analysis means" refers to the function that allows the server to receive daily report data and input prompt sentences into the generative AI model.

[0886] "Generation means" refers to the function for receiving the analysis results from the generative AI model and generating an evaluation report.

[0887] The "verification means" refers to an interface for the user to verify the evaluation report.

[0888] The present invention relates to a system for automatically recording work content and work activities and providing evaluations and feedback. Specific embodiments of this system will be described below.

[0889] System configuration

[0890] The system consists of the following major components:

[0891] 1. Generative AI means:

[0892] Generative AI uses artificial intelligence technology to automatically record work content and work activities. Specifically, it uses natural language processing technology to analyze daily reports entered by users and automatically record work content.

[0893] 2. Evaluation method:

[0894] The evaluation means analyzes the work content and work activity records generated by the generative AI and evaluates the degree of work achievement and problems. The evaluation means analyzes the contents of the daily report using a generative AI model (e.g., OpenAI's GPT-4).

[0895] 3. Feedback methods:

[0896] The feedback method provides points for reflection, reflection, and improvement based on the evaluation method. Specifically, specific improvement proposals are made based on the evaluation results.

[0897] 4. Input method:

[0898] This is an interface for users to input daily reports. This is realized using devices such as PCs and smartphones.

[0899] 5. Means of transmission:

[0900] This function allows the terminal to send the daily report data entered to the server. The data is encrypted using SSL / TLS before being sent.

[0901] 6. Analysis methods:

[0902] This function allows the server to receive daily report data and input prompt sentences into the generative AI model. The prompt sentences are generated based on the contents of the daily report.

[0903] 7. Generation means:

[0904] This function allows the server to receive the analysis results from the generated AI model and generate an evaluation report that lists the degree of task achievement, specific problems, and areas for improvement.

[0905] 8. Verification Method:

[0906] This is an interface for the user to check the evaluation report. The evaluation report is provided to the user via the terminal.

[0907] System Operation

[0908] The operation of this system is as follows.

[0909] 1. Enter your daily report:

[0910] After work, the user uses the terminal to enter a daily report. For example, the user might enter, "Today's sales target was 1 million yen, but the actual result was 900,000 yen. It took too long to respond to customers."

[0911] 2. Data transmission:

[0912] The terminal sends the entered daily report data to the server. The data is encrypted before transmission, ensuring security.

[0913] 3. Data Analysis:

[0914] The server inputs the received daily report data into the generative AI model. An example of a prompt sentence is, "Analyze the following daily report and extract the degree of achievement and problems of the work. Daily report: 'Today's sales target was 1 million yen, and the actual result was 900,000 yen. It took too long to respond to customers.'"

[0915] 4. Generate the assessment report:

[0916] The server generates an evaluation report based on the analysis results from the generative AI model, which details the level of achievement, specific problems, and areas for improvement.

[0917] 5. Review the evaluation report:

[0918] Users can check the evaluation report through their terminal and use it to consider next steps to improve their business operations.

[0919] In this way, the process from recording work content and work activities to evaluation and feedback can be automated, improving the accuracy and consistency of evaluations and enabling specific areas for improvement to be quickly identified.

[0920] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0921] Step 1:

[0922] The user inputs a daily report.

[0923] After work, the user uses the device to enter a daily report. Specifically, the user opens a dedicated application and enters, "Today's sales target was 1 million yen, but the actual result was 900,000 yen. It took too long to respond to customers." The entered data is saved on the device as daily report data.

[0924] Step 2:

[0925] The terminal transmits the daily report data to the server.

[0926] The terminal sends the daily report data entered by the user to the server by pressing the "Send" button. When sent, the data is encrypted using SSL / TLS. The input is the daily report data, and the output is the encrypted daily report data.

[0927] Step 3:

[0928] The server receives the daily report data.

[0929] The server receives the encrypted daily report data sent from the terminal and decrypts it. The decrypted daily report data is stored in a database. The input is the encrypted daily report data, and the output is the decrypted daily report data.

[0930] Step 4:

[0931] The server inputs a prompt sentence into the generative AI model.

[0932] The server generates a prompt sentence based on the received daily report data. For example, a prompt sentence such as "Analyze the following daily report and extract the degree of achievement and problems of the work. Daily report: 'Today's sales target was 1 million yen, and the actual result was 900,000 yen. It took too long to respond to customers.'" is input into the generative AI model. The input is the daily report data, and the output is the prompt sentence.

[0933] Step 5:

[0934] The server receives the analysis results from the generative AI model.

[0935] The server receives analysis results from a generative AI model (e.g., OpenAI's GPT-4). The analysis results include the task's achievement level, problems, and areas for improvement. The input is a prompt, and the output is the analysis results.

[0936] Step 6:

[0937] The server generates the analysis results as an evaluation report.

[0938] The server generates an evaluation report based on the analysis results received from the generative AI model. The evaluation report details the level of achievement, specific problems, and areas for improvement. The input is the analysis results, and the output is the evaluation report.

[0939] Step 7:

[0940] The server sends the evaluation report to the terminal.

[0941] The server sends the generated evaluation report to the terminal and notifies the user. During transmission, data integrity and security are ensured. The input is the evaluation report, and the output is the evaluation report sent to the terminal.

[0942] Step 8:

[0943] The user checks the evaluation report.

[0944] The user receives a notification, opens the application, and checks the evaluation report, which states, "Achievement: 90%; Issue: Customer response time was too long." The input is the evaluation report, and the output is the user's confirmation.

[0945] In this way, a system is realized in which the server, terminals, and users work together to evaluate daily reports.

[0946] (Application example 2)

[0947] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0948] Conventional business record systems require manual recording of work content and activities, which takes time and effort. Evaluation and feedback are also done manually, which often results in inefficiency and inaccuracy. Furthermore, there is no way to check evaluation results in real time, which can lead to missed opportunities for business improvement. To solve these problems, there is a need for a system that automates business records, evaluations, and feedback, and also allows evaluation results to be checked in real time.

[0949] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0950] In this invention, the server includes generative AI means for automatically recording work content and work activities, evaluation means for evaluating the records of work content and work activities generated by the generative AI, feedback means for providing points for reflection, review, and improvement based on the evaluation means, and display means for displaying the evaluation results on a smartphone. This enables automation of work recording, evaluation, and feedback, and also allows the evaluation results to be checked in real time.

[0951] "Generative AI means" refers to artificial intelligence technology for automatically recording work content and work activities.

[0952] "Evaluation means" refers to the function for evaluating the work content and records of work activities generated by generative AI.

[0953] "Feedback means" refers to a function for providing points for reflection, reflection, and improvement based on evaluation means.

[0954] "Display means" refers to the function for displaying the evaluation results on a smartphone.

[0955] The system for carrying out this invention includes generative AI means, evaluation means, feedback means, and display means. Specific embodiments of each means will be described below.

[0956] First, generative AI means use artificial intelligence technology to automatically record work content and work activities. Specifically, it receives data on work content and work activities as input and automatically generates it in the form of a daily report. The generated daily report is saved as text data.

[0957] Next, the evaluation means has the function of evaluating the daily reports generated by the generative AI means. This evaluation means uses OpenAI's API to automatically extract the degree of achievement, problems, and areas for improvement based on the contents of the daily reports. The evaluation means generates the contents of the daily reports as prompt sentences and sends them to OpenAI's API to obtain the evaluation results.

[0958] The feedback method provides points for reflection, reflection, and improvement based on the evaluation results obtained by the evaluation method. This feedback includes specific suggestions for improvement, and contributes to improving the efficiency and quality of work.

[0959] The display function has the function of displaying the evaluation results on a smartphone. The evaluation results can be checked in real time through the smartphone application, allowing users to immediately grasp the progress of their work and areas for improvement.

[0960] For example, you can use the following prompt to evaluate daily reports:

[0961] Example prompt sentence:

[0962] Please rate the following daily report.

[0963] Daily report contents:

[0964] Robot A had a goal of assembling 100 parts during an 8-hour shift.

[0965] In fact, it was made up of 90 parts.

[0966] There was a delay in parts supply midway through, which caused work to be temporarily halted.

[0967] Evaluation content:

[0968] 1. Task accomplishment

[0969] 2. Problems

[0970] 3. Improvements

[0971] This prompt is used to ask the generative AI model to evaluate the daily report. The evaluation results are output from three perspectives: the degree of accomplishment, problems, and areas for improvement.

[0972] The hardware used is a smartphone, and the software uses Python and OpenAI API. For data processing, the contents of the daily reports are generated as prompt sentences, and for data calculation, OpenAI API is used to generate evaluations.

[0973] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0974] Step 1:

[0975] The server receives data on work content and work activities. The input data includes information such as the progress of work, work content, and time. The server passes this data to a generative AI means, which automatically generates a daily report. The generated daily report is saved as text data.

[0976] Step 2:

[0977] The server passes the generated daily report to the evaluation means. The evaluation means generates a prompt sentence from the content of the daily report. Specifically, it converts the content of the daily report into the following format:

[0978] Please rate the following daily report.

[0979] Daily report contents:

[0980] [Daily report contents]

[0981] Evaluation content:

[0982] 1. Task accomplishment

[0983] 2. Problems

[0984] 3. Improvements

[0985] By generating this prompt sentence, the evaluation means prepares to evaluate the contents of the daily report.

[0986] Step 3:

[0987] The server sends the generated prompt to OpenAI's API. The input data is the prompt, and the output data is the evaluation result. OpenAI's API automatically extracts the task achievement level, problems, and areas for improvement based on the prompt, and returns the evaluation result.

[0988] Step 4:

[0989] The server receives the evaluation results returned from the OpenAI API and passes them to the feedback mechanism. The feedback mechanism provides points for reflection, reflection, and improvement based on the evaluation results. Specifically, it analyzes the evaluation results and generates specific improvement proposals.

[0990] Step 5:

[0991] The server passes the improvement suggestions obtained from the feedback means to the display means. The display means displays the evaluation results and improvement suggestions on the smartphone. The user can check the evaluation results and improvement suggestions in real time via the smartphone.

[0992] Step 6:

[0993] Users can check the evaluation results and improvement suggestions displayed on their smartphones and make improvements to their work as needed, thereby improving work efficiency and quality.

[0994] Example 3

[0995] Next, a description will be given of Example 3 of Form Example 3. 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."

[0996] Conventional work evaluation systems have difficulty not only evaluating the level of work performance of employees but also providing specific suggestions for improvement. In addition, feedback based on evaluation results is often abstract, and it is often unclear how employees should specifically improve. This has led to the issue of not being able to fully improve employees' work efficiency.

[0997] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0998] In this invention, the server includes generative artificial intelligence means for automatically recording work content and work activities, evaluation means for evaluating the records of work content and work activities generated by the generative artificial intelligence, feedback means for providing points for reflection, review, and improvement based on the evaluation means, generative artificial intelligence model means for generating specific improvement proposals based on the evaluation results by the feedback means, prompt sentence generation means for inputting the evaluation results to the generative artificial intelligence model means, and notification means for providing feedback obtained from the generative artificial intelligence model means to the worker. This makes it possible to provide specific and practical improvement proposals to the worker.

[0999] "Generative artificial intelligence means" refers to artificial intelligence technology for automatically recording work content and work activities.

[1000] "Evaluation means" refers to technology for analyzing the work content and work activity records generated by the generative artificial intelligence means and evaluating the degree of work achievement.

[1001] "Feedback measures" refer to techniques for providing points for reflection, reflection, and improvement based on evaluation measures.

[1002] "Generative artificial intelligence model means" refers to artificial intelligence technology for generating specific improvement proposals based on evaluation results.

[1003] The "prompt sentence generation means" refers to a technique for generating a prompt sentence for inputting the evaluation result to the generation artificial intelligence model means.

[1004] "Notification means" refers to a technology for providing feedback obtained from the generative artificial intelligence model means to a business operator.

[1005] This invention is a system for evaluating the degree of work performance of an employee and providing specific suggestions for improvement. The program processing of this system will be specifically described below.

[1006] The server uses a generative artificial intelligence means to automatically record the work content and work activities of the worker. This generative artificial intelligence means collects data from the terminal used by the worker and records the work content and work activities. For example, it collects task completion information entered by the worker into a task management application and data from a time tracking tool that records work hours.

[1007] The server then analyzes the collected data using an evaluation tool. Specifically, it uses Scikit-learn, a Python machine learning library, to evaluate the worker's level of work achievement. The evaluation tool quantifies the level of work achievement and identifies the cause of low achievement. For example, it quantifies the level of work achievement based on the number of tasks an employee completes in a week and the time required to complete them. If achievement is low, the server identifies issues with task prioritization and time management.

[1008] The server then generates specific improvement suggestions based on the evaluation results. This process uses OpenAI's GPT-4, a generative AI model. The server inputs the evaluation results into the generative AI model as a prompt sentence, generating feedback for the worker. For example, the following prompt sentence could be input into the generative AI model:

[1009] "Worker A's performance is 50% and their main issue is improper task prioritization. Please provide specific suggestions for improving this issue."

[1010] When this prompt sentence is fed into a generative AI model, the model generates the following feedback:

[1011] "Employee A, we have confirmed that your work completion rate is 50%. The main problem is that you are not prioritizing your tasks properly. To improve this, it is important to first classify your daily tasks based on importance and urgency, and clarify their priorities. We also recommend that you regularly check your progress and re-prioritize your tasks as necessary."

[1012] Finally, the server notifies the worker of the generated feedback to their device. For example, it sends a notification to the worker's smartphone saying, "We recommend that you review the prioritization of your tasks and classify them based on importance and urgency."

[1013] In this way, the server can generate specific improvement proposals based on the evaluation results and provide feedback to the business operator. This system allows the business operator to receive specific and practical improvement proposals, thereby improving business efficiency. The flow of the identification process in Example 3 will be described with reference to Figure 15.

[1014] Step 1:

[1015] The server collects data on work content and work activities from the workers' devices. Specifically, it collects task completion information entered by workers into a task management application and data from a time tracking tool that records work time. Input data includes task names, completion dates and times, and required time. This data is sent to the server and saved as a record of work content and work activities.

[1016] Step 2:

[1017] The server analyzes the collected data using evaluation methods. Specifically, it uses Scikit-learn, a Python machine learning library, to evaluate the worker's level of work achievement. The input data is the records of work content and work activities collected in Step 1. The server uses this data to quantify the level of work achievement and identify the causes of low achievement. For example, it identifies problems with task prioritization and time management.

[1018] Step 3:

[1019] The server generates specific improvement proposals based on the evaluation results. A generative AI model is used in this process. The input data is the evaluation results obtained in step 2. The server inputs the evaluation results into the generative AI model as a prompt sentence, and generates feedback for the worker. For example, it generates a prompt sentence such as, "Worker A's task achievement rate is 50%, and the main problem is that the prioritization of tasks is inappropriate. Please provide specific proposals to improve this problem."

[1020] Step 4:

[1021] The server notifies the worker's device of the feedback obtained from the generative AI model. The input data is the feedback generated in step 3. The server sends a notification to the worker's smartphone saying, "We recommend that you review your task prioritization and classify them based on importance and urgency." The worker can use this feedback to improve their work.

[1022] In this way, the server can generate specific improvement suggestions based on the evaluation results and provide feedback to the operator.

[1023] (Application example 3)

[1024] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1025] Traditionally, evaluation of work efficiency and accuracy in factories has relied on human monitoring and manual recording, making it difficult to provide efficient feedback and suggest improvements. Furthermore, as work becomes increasingly automated, there is a need for a method to evaluate the performance of machinery in real time and quickly provide feedback on specific areas for improvement.

[1026] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means. In this invention, the server includes generative AI means for automatically recording work content and work activities, evaluation means for evaluating the records of work content and work activities generated by the generative AI, feedback means for providing points for reflection, review, and improvements based on the evaluation means, and means for evaluating the work efficiency and accuracy of machinery performing work in a factory and providing feedback on areas for improvement. This makes it possible to evaluate the work efficiency and accuracy of machinery in real time and quickly provide feedback on specific improvement suggestions.

[1027] "Generative AI means" refers to artificial intelligence technology for automatically recording work content and work activities.

[1028] "Evaluation means" refers to the means for evaluating the work content and work activity records generated by generative AI.

[1029] "Feedback measures" refer to measures for providing points for reflection, reflection, and improvement based on evaluation measures.

[1030] "Machinery" refers to automated devices and robots used to perform work within a factory.

[1031] "Work efficiency" refers to an index that indicates how much work a machine or device can complete within a certain amount of time.

[1032] "Precision" refers to an indicator of the accuracy and smallness of error when a machine or device performs its work.

[1033] "Areas for improvement" refers to specific methods and means proposed based on the evaluation results to improve work efficiency and accuracy.

[1034] A system for implementing this invention includes a generative AI means for automatically recording work content and work activities, an evaluation means for evaluating the generated records of work content and work activities, a feedback means for providing points for reflection, review, and improvement based on the evaluation means, and a means for evaluating the work efficiency and accuracy of machinery and equipment used in work within a factory and providing feedback on points for improvement.

[1035] The server automatically records work content and work activities using generative AI means. The generative AI means monitors the progress of work and work content in real time and collects data. The collected data is analyzed by evaluation means, and work efficiency and accuracy are evaluated.

[1036] The evaluation means calculates performance indicators such as work time and error rate based on the collected data, thereby quantifying the work efficiency and accuracy of the machine and obtaining evaluation results.

[1037] The feedback mechanism generates specific improvement suggestions based on the evaluation results. For example, if a task takes a long time, it suggests optimizing the motion path or calibrating the tool. If the error rate is high, it identifies the cause of the error and suggests how to correct it.

[1038] As a concrete example, feedback can be obtained by inputting the following prompt sentences into a generative AI model:

[1039] Example prompt sentence:

[1040] A factory robot performed a part assembly task. The task took 15 seconds and resulted in two errors. Please rate its performance and provide feedback on areas for improvement.

[1041] In response to this prompt, the generative AI model provides the following feedback:

[1042] Examples of feedback generated:

[1043] Performance Score: 50

[1044] Improvement Needed:

[1045] Reduce task time. Consider optimizing the movement path.

[1046] Reduce errors. Check the calibration of the tools.

[1047] The system is implemented using Python programming. The hardware used includes factory robots and sensors, and the software includes Python and an evaluation system. This makes it possible to evaluate the work efficiency and accuracy of machinery in real time and quickly provide feedback on specific improvement suggestions.

[1048] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1049] Step 1:

[1050] The server automatically records work content and activities using generative AI methods. Specifically, it collects work data (such as work time and number of errors) from factory robots in real time and stores it in a database. The input is sensor data from the factory robots, and the output is work records stored in the database.

[1051] Step 2:

[1052] The server analyzes the collected data using the evaluation tools. Specifically, it calculates performance indicators such as work time and number of errors, and evaluates work efficiency and accuracy. The input is the work records stored in the database, and the output is the evaluation results (performance scores, etc.).

[1053] Step 3:

[1054] The server generates specific improvement suggestions using feedback means based on the evaluation results. Specifically, it analyzes the evaluation results and suggests optimizing the operation path if the task time is long, or suggests tool calibration if the error rate is high. The input is the evaluation results, and the output is feedback including improvement suggestions.

[1055] Step 4:

[1056] The server sends the generated feedback to the factory robot's management system. Specifically, it generates the feedback content in text format and notifies the management system. The input is the feedback including the improvement suggestions, and the output is the feedback notification sent to the management system.

[1057] Step 5:

[1058] The user checks the feedback through the management system and makes any necessary improvements. Specifically, the user checks the feedback and optimizes the motion path or calibrates the tool. The input is the feedback displayed on the management system, and the output is improved work efficiency and accuracy.

[1059] 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.

[1060] "Example 1"

[1061] One embodiment of the present invention provides a system including an emotion engine that recognizes the emotions of workers. In this system, a generative AI not only automatically records the work content and work activities of workers, but also simultaneously records the worker's emotional state. The emotion engine estimates the worker's emotional state from the worker's tone of voice, facial expression, choice of words, etc. Specifically, the emotion engine estimates the worker's emotional state from the worker's tone of voice when operating business tools, facial expressions during video conferences, choice of words in chat tools, etc.

[1062] "Example 2"

[1063] Furthermore, the generative AI reflects the emotional state of the worker estimated by the emotion engine in the daily report. Specifically, the emotional state of the worker on that day, such as when the worker is feeling happy, when they are facing difficulties, when they are feeling stressed, etc., is recorded in the daily report. This allows the worker and their superiors to understand not only the work content but also the emotional state of the worker. "Example 3"

[1064] Furthermore, the feedback means provides feedback based not only on the evaluation results of the work content by the evaluation means, but also on the estimation results of the emotional state by the emotion engine. Specifically, when the worker is feeling stressed, advice on how to reduce stress is provided. Also, when the worker is feeling joy, the source of that joy is analyzed and advice on how to achieve the same joy is provided. This enables more appropriate feedback that takes into account the worker's emotional state.

[1065] The processing flow of each embodiment will be described below.

[1066] "Example 1"

[1067] Step 1: The worker interacts with the tools they use. This interaction may reflect their emotional state, such as tone of voice, facial expression, and choice of words.

[1068] Step 2: The emotion engine estimates the worker's emotional state from factors such as the worker's tone of voice, facial expressions, and choice of words.

[1069] Step 3: The generative AI automatically records the worker's work content and activities, along with the worker's emotional state estimated by the emotion engine.

[1070] "Example 2"

[1071] Step 1: Generative AI automatically records the work content and work activities of employees.

[1072] Step 2: The emotion engine estimates the worker's emotional state.

[1073] Step 3: The generative AI reflects the emotional state of the employee estimated by the emotion engine in the daily report.

[1074] "Example 3"

[1075] Step 1: The evaluation instrument evaluates the job content.

[1076] Step 2: The emotion engine estimates the worker's emotional state.

[1077] Step 3: The feedback means provides feedback based on the evaluation results of the work content by the evaluation means and the estimation results of the emotional state by the emotion engine.

[1078] Example 1

[1079] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1080] Conventional business record systems could automatically record the work content and activities of employees, but were unable to simultaneously record their emotional state. This made it difficult to provide feedback or suggest improvements that took into account the employee's psychological state. Furthermore, work content records were rarely automatically generated as daily reports, placing a heavy burden on employees. To solve these issues, a system that simultaneously records work content and emotional state and automatically generates daily reports is needed.

[1081] 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.

[1082] In this invention, the server includes generative AI means for automatically recording work content and work activities, evaluation means for evaluating the records of work content and work activities generated by the generative AI, feedback means for providing points for reflection, review, and improvement based on the evaluation means, emotion engine means for estimating the emotional state of the worker, and means for recording the emotional state estimated by the emotion engine means. This makes it possible to simultaneously record work content and emotional state and automatically generate a daily report.

[1083] "Generative AI methods" are artificial intelligence methods that automatically record work content and work activities and generate them as daily reports.

[1084] "Evaluation means" refers to a means for evaluating the work content and work activity records generated by generative AI.

[1085] "Feedback measures" are means for providing points for reflection, reflection, and improvement based on evaluation measures.

[1086] The "emotion engine means" is a means for estimating the emotional state of a worker.

[1087] The "recording means" is a means for recording the emotional state estimated by the emotion engine means.

[1088] MODE FOR CARRYING OUT THE INVENTION

[1089] This invention is a system that automatically records the work content and work activities of employees and generates a daily report. Furthermore, by estimating and recording the employee's emotional state, it is possible to provide more detailed feedback. This system includes elements such as a server, a terminal, and a user.

[1090] 1. Program Generation

[1091] The server automatically records the work activities of employees and generates a program to generate daily reports. This program works in conjunction with business tools and systems, understands the work content based on operation logs and input data, and formats the data into daily reports.

[1092] 2. Program processing explanation

[1093] The server connects to the business tools (e.g., office suites, cloud services) and systems (e.g., customer management systems, ERP systems) used by employees. It collects operation logs and input data when employees use these tools to understand the content of their work. It also simultaneously records the employee's emotional state using an emotion engine. The emotion engine analyzes the employee's tone of voice, facial expressions, choice of words, and other factors. For example, it analyzes the video and audio during a video conference and infers the employee's emotional state from their facial expressions and tone of voice.

[1094] 3. Examples of concrete examples and prompts

[1095] Let's say a user is holding a meeting using a video conferencing system. At this time, the server analyzes the video and audio of the video conference and estimates the worker's emotional state from their facial expressions and tone of voice. It also collects documents used during the meeting and chat content to understand the work content. Based on this data, the server generates a daily report.

[1096] As a concrete example, the following prompt sentence is input to the generative AI model:

[1097] "Please record today's work. Use a video conferencing system, and include what was said during the meeting and any chat conversations. Also, record the worker's emotional state."

[1098] Based on this prompt, the generative AI model generates a daily report like this:

[1099] "Today's business:

[1100] 10:00 AM - 11:00 AM: Project meeting via video conferencing system

[1101] What was said: Project progress report, confirmation of next steps

[1102] Chat content: Sharing materials, Q&A

[1103] Emotional state: The tone of voice during the meeting indicated that the workers were generally calm, with occasional bouts of tension. Their facial expressions also indicated that they were focused.

[1104] In this way, the server records the worker's work activities and emotional state in detail and formats them into a daily report, which makes it possible to provide feedback and suggest improvements that take into account the worker's psychological state.

[1105] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1106] Program processing flow

[1107] Step 1: Integration with business tools and systems

[1108] The server connects to the business tools and systems used by business personnel. Specifically, it uses APIs and plug-ins to obtain data from business tools (e.g., office suites, cloud services) and systems (e.g., customer management systems, ERP systems).

[1109] Input: API keys and authentication information for business tools and systems

[1110] Output: Data access permissions from business tools and systems

[1111] Specific operation: The server uses the API key to access the data of the business tool and obtains operation logs and input data.

[1112] Step 2: Collect operation logs and input data

[1113] The server collects operation logs and input data in real time when business personnel operate business tools.

[1114] Input: Operation logs and input data obtained from business tools and systems

[1115] Output: Save collected operation logs and input data

[1116] Specific operation: The server records the operation history when a worker enters data into Excel or updates customer information in a customer management system.

[1117] Step 3: Estimating emotional state

[1118] The server uses an emotion engine to estimate the emotional state of the worker, which analyzes the worker's tone of voice, facial expressions, choice of words, etc.

[1119] Input: Video and audio from video conferences, chat content

[1120] Output: Estimated emotional state data

[1121] Specific operation: The server analyzes the facial expressions of workers during video conferences and detects changes in their expressions, such as smiling or furrowing their brows. It also analyzes the tone of their voices to estimate whether the workers are tense or relaxed.

[1122] Step 4: Analyze data and generate daily reports

[1123] The server analyzes the collected operation logs, input data, and emotional state to understand the work content, and generates daily reports using a generative AI model based on this data.

[1124] Input: Operation log, input data, emotional state data

[1125] Output: Generated daily report

[1126] Specific operation: The server generates a daily report including the tasks performed by the worker, their progress, and their emotional state. For example, it generates the following daily report:

[1127] "Today's business:

[1128] 10:00 AM - 11:00 AM: Project meeting via video conferencing system

[1129] What was said: Project progress report, confirmation of next steps

[1130] Chat content: Sharing materials, Q&A

[1131] Emotional state: The tone of voice during the meeting indicated that the workers were generally calm, with occasional bouts of tension. Their facial expressions also indicated that they were focused.

[1132] Step 5: Provide daily reports

[1133] The server provides the generated daily reports to the workers, who can then view them on a dedicated dashboard or send them to their terminals via email.

[1134] Input: Generated daily report

[1135] Output: Daily report provided to the worker

[1136] Specific operation: The server sends the generated daily report to the employee's email address. It also displays the daily report on a dedicated dashboard so that the employee can view it at any time.

[1137] (Application example 1)

[1138] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1139] In conventional business record systems, recording of work content and work activities is often done manually, which is inefficient. Furthermore, feedback that takes into account the emotional state of the worker is not provided, so improvements in work efficiency and safety are not sufficiently achieved. This can easily lead to the accumulation of stress and fatigue among workers, resulting in decreased productivity and increased errors.

[1140] 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.

[1141] In this invention, the server includes generative AI means for automatically recording work content and work activities, evaluation means for evaluating the records of work content and work activities generated by the generative AI, feedback means for providing points for reflection, review, and improvement based on the evaluation means, emotion engine means for recognizing the emotional state of the worker, and means for providing appropriate feedback to the worker based on the emotion engine means. This enables efficient recording and evaluation of work content and work activities, and further enables improvement of work efficiency and safety by providing feedback that takes into account the emotional state of the worker.

[1142] "Generative AI means" is an artificial intelligence technology that automatically records work content and activities and generates those records as daily reports.

[1143] "Evaluation methods" are technologies for analyzing the work content and records of work activities generated by generative AI and evaluating their content.

[1144] "Feedback methods" are techniques for providing points for reflection, reflection, and improvement based on evaluation methods.

[1145] "Emotion engine means" is a technology for estimating and recognizing a worker's emotional state from their tone of voice, facial expressions, choice of words, etc.

[1146] The "means for providing appropriate feedback" is a technology that takes into consideration the emotional state of the worker based on the emotion engine means and provides feedback to improve work efficiency and safety.

[1147] A system for carrying out this invention has the following configuration: A server includes generative AI means for automatically recording work content and work activities, evaluation means for evaluating the records of work content and work activities generated by the generative AI, feedback means for providing points for reflection, review, and improvement based on the evaluation means, emotion engine means for recognizing the emotional state of a worker, and means for providing appropriate feedback to the worker based on the emotion engine means.

[1148] Hardware and software used

[1149] Hardware:

[1150] Factory Robots

[1151] Microphone (voice data collection)

[1152] Camera (video data collection)

[1153] Computer (data processing)

[1154] software:

[1155] Python

[1156] EmotionEngine (emotion recognition engine)

[1157] WorkLog (work record management)

[1158] Data processing and calculation

[1159] 1. Record your work:

[1160] The server uses the WorkLog class to record work content. It receives work data (e.g., work content, work time) as input and adds it to the log.

[1161] 2. Recognition of emotional states:

[1162] The server uses the EmotionEngine class to estimate the emotional state from audio, video, and text data, and outputs the emotional state (e.g., stress level, fatigue level).

[1163] 3. Providing Feedback:

[1164] The server provides appropriate feedback to the worker based on their emotional state, for example, sending a notification to take a break if their stress level is high.

[1165] Specific examples

[1166] Record your work:

[1167] If a worker does "assembly work" for two hours, record the details.

[1168] Emotional state recognition:

[1169] Recognizes the emotional state of a worker when they look tired during a video conference.

[1170] Providing feedback:

[1171] If a worker is tired, a notification will be sent saying, "We recommend you take a break."

[1172] Prompt Sentence Examples

[1173] Design a system in which a factory robot records its work, recognizes the worker's emotional state, and provides feedback. To record work, use operation logs and input data from work tools and systems, and to recognize the worker's emotional state, use tone of voice, facial expressions, and choice of words. Include specific examples of feedback.

[1174] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1175] Step 1:

[1176] The server receives work data (e.g., work content, work time) as input to record the work content of the worker. Specifically, if a worker performs "assembly work" for two hours, the content is added to the WorkLog class. The input data is the worker's operation log and input data, and the output is the recorded work content.

[1177] Step 2:

[1178] The server collects audio, video, and text data to recognize the worker's emotional state. Specifically, audio data collected by a microphone, video data collected by a camera, and text data from a chat tool are input into the EmotionEngine class. The input data are audio, video, and text data, and the output is an estimated emotional state (e.g., stress level, fatigue level).

[1179] Step 3:

[1180] The server uses the EmotionEngine class to estimate the worker's emotional state from the collected data. Specifically, it analyzes the tone of voice, facial expressions, and word choice to evaluate the worker's emotional state. The input data is audio, video, and text data, and the output is the evaluation result of the worker's emotional state.

[1181] Step 4:

[1182] The server uses evaluation tools to analyze the work content and work activity records generated by the generative AI. Specifically, it evaluates the efficiency and accuracy of the work content and identifies areas for improvement. The input data is the recorded work content, and the output is the evaluation results.

[1183] Step 5:

[1184] The server provides appropriate feedback to the worker based on the evaluation results and emotional state. Specifically, if the stress level is high, the server sends a notification encouraging the worker to take a break. The input data are the evaluation results and emotional state, and the output is the feedback content.

[1185] Step 6:

[1186] The server sends a notification to the worker using the feedback means. Specifically, it displays a message on the worker's terminal saying, "We recommend you take a break." The input data is the feedback content, and the output is the notification to the worker.

[1187] Example 2

[1188] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1189] In conventional business record systems, recording of work content and work activities is often done manually, resulting in inefficiency. Furthermore, because the evaluation of work achievements and problems is also done manually, it tends to rely on subjective judgment. Furthermore, because evaluations and feedback do not take into account the emotional state of the worker, it is difficult to properly grasp the worker's psychological burden and stress. To solve these problems, there is a need for a system that automates the recording of work content and work activities and provides objective evaluations and feedback.

[1190] 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.

[1191] In this invention, the server includes a generative AI means for automatically recording work content and work activities, an evaluation means for evaluating the records of work content and work activities generated by the generative AI, a feedback means for providing points for reflection, review, and improvement based on the evaluation means, an emotion engine means for estimating the emotional state of the worker, and a means for reflecting the emotional state estimated by the emotion engine means in the records of work content and work activities. This makes it possible to automate the recording of work content and work activities and provide objective evaluation and feedback. Furthermore, by providing evaluation and feedback that takes the worker's emotional state into consideration, it is possible to appropriately understand and improve the worker's psychological burden and stress.

[1192] "Generative AI means" refers to artificial intelligence technology that automatically records work content and activities and generates them in the form of daily reports, etc.

[1193] "Evaluation means" refers to a device or program that has the function of analyzing the work content and work activity records generated by the generative AI means and automatically extracting the degree of work achievement and problems.

[1194] "Feedback means" refers to a device or program that has the function of providing points for reflection, review, and improvement based on the evaluation results obtained by the evaluation means.

[1195] "Emotion engine means" refers to artificial intelligence technology for estimating the emotional state of workers, and has the function of analyzing the joy, difficulties, stress, etc. that workers are feeling.

[1196] The "means for reflecting the emotional state in the record of work content or work activity" refers to a device or program having a function of adding the emotional state estimated by the emotion engine means to the generated record of work content or work activity.

[1197] MODE FOR CARRYING OUT THE INVENTION

[1198] The present invention relates to a system for automatically recording work content and work activities and providing evaluations and feedback. Specific embodiments of this system will be described below.

[1199] Hardware and software used

[1200] Hardware: Servers, terminals

[1201] Software: Generative AI model, emotion engine

[1202] System Overview

[1203] In this system, users input data on their work content and work activities after completing their work, and a generative AI model generates a daily report based on that data. The generated daily report is analyzed by an evaluation means, and the degree of work achievement and problems are extracted. Furthermore, an emotion engine means estimates the worker's emotional state, and this emotional state is reflected in the daily report. The final daily report is then provided with feedback means to provide points for reflection, reflection, and improvement, and is displayed on a terminal for the user and their supervisor to view.

[1204] Program processing

[1205] 1. The user enters the daily report data

[1206] Users use a dedicated application on their device to input information about the day's work, results, and impressions.

[1207] Specifically, you enter the number of visits, number of successful transactions, main business activities, and emotions felt.

[1208] 2. The device sends the data to the server

[1209] The terminal transmits the input data to the server in real time.

[1210] Specifically, data is sent to the server using an HTTP request.

[1211] 3. The server generates a daily report using the generative AI model

[1212] The server inputs the received data into a generative AI model to generate an initial version of the daily report.

[1213] Specifically, a prompt sentence is input into the generative AI model to generate the text of the daily report.

[1214] 4. The server passes the daily report to the evaluation tool

[1215] The server passes the generated daily report to the evaluation means.

[1216] Specifically, the evaluation means' API is called to send daily report data.

[1217] 5. The server extracts the degree of accomplishment and problems of the business.

[1218] The server analyzes the data returned from the evaluation means and extracts the degree of accomplishment of the work and any problems.

[1219] Specifically, it compares work goals with actual results and calculates the degree of achievement. It also extracts problems and areas for improvement from the contents of daily reports.

[1220] 6. The server uses the emotion engine to estimate the emotional state.

[1221] The server uses an emotion engine to estimate the emotional state of the worker.

[1222] Specifically, the text data of the daily report is input into an emotion engine to estimate the emotional state.

[1223] 7. The server reflects the emotional state in the daily report

[1224] The server reflects the estimated emotional state in the daily report.

[1225] Specifically, emotional states are added to the text of daily reports.

[1226] 8. The server generates the final daily report and sends it to the device.

[1227] The server generates the final daily report and sends it to the terminal.

[1228] Specifically, the final daily report data is sent to the terminal in JSON format.

[1229] 9. The device displays the daily report to the user.

[1230] The terminal displays the received daily report to the user.

[1231] Specifically, daily reports are displayed on the UI of a dedicated application.

[1232] Specific examples

[1233] For example, a sales representative enters the following data:

[1234] Number of visits: 5

[1235] Number of successful transactions: 2

[1236] Main duties: Developing new customers and following up with existing customers

[1237] Emotions felt: Stress

[1238] Example prompt sentence:

[1239] Today I made five visits and closed two deals. I developed new clients and followed up with existing clients. I felt stressed.

[1240] Based on this data, the server uses a generative AI model to generate a daily report like this:

[1241] Today, there were five visits and two successful sales. We developed new clients and followed up with existing clients. Our work is only 40% accomplished, meaning we have not yet reached our target number of successful sales. There is room for improvement in our approach to developing new clients. Additionally, we need additional suggestions to improve customer satisfaction when following up with existing clients. Our staff is finding it difficult to develop new clients and is feeling stressed.

[1242] In this way, a daily report is generated that includes the work content and emotional state.

[1243] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1244] Program processing flow

[1245] Step 1:

[1246] The user enters the daily report data.

[1247] Input: The user uses a dedicated application on the device to input information about the day's work, results, and feelings.

[1248] Specific behavior: The user fills out an input form with information such as the number of visits, number of successful transactions, main tasks, and feelings.

[1249] Output: Input data is saved to the terminal.

[1250] Step 2:

[1251] The device sends the data to the server

[1252] Input: User input data stored on the device.

[1253] Specific operation: The device uses an HTTP request to send input data to the server.

[1254] Output: The user input data is sent to the server.

[1255] Step 3:

[1256] The server generates daily reports using the generative AI model

[1257] Input: User input data sent to the server.

[1258] Specific operation: The server inputs a prompt sentence into the generative AI model to generate an initial version of the daily report.

[1259] Output: The initial version of the daily report text is generated.

[1260] Step 4:

[1261] The server passes the daily report to the evaluation means

[1262] Input: The initial version of the generated daily report text.

[1263] Specific operation: The server calls the evaluation means API and sends the daily report data.

[1264] Output: Daily report data is passed to the evaluation means.

[1265] Step 5:

[1266] The server extracts the degree of accomplishment and problems of the work

[1267] Input: The evaluation data returned by the evaluation instrument.

[1268] Specific operation: The server compares the business goals and actual results, calculates the degree of achievement, and extracts problems and areas for improvement from the contents of the daily report.

[1269] Output: The degree of accomplishment, problems, and areas for improvement of the work are extracted.

[1270] Step 6:

[1271] The server uses an emotion engine to estimate the emotional state.

[1272] Input: The initial version of the daily report text.

[1273] Specific operation: The server inputs the text data of the daily report into the emotion engine and estimates the emotional state.

[1274] Output: The worker's emotional state is estimated.

[1275] Step 7:

[1276] The server reflects the emotional state in the daily report.

[1277] Input: Estimated emotional state and initial version of daily report text.

[1278] Specific behavior: The server adds the emotional state to the text of the daily report.

[1279] Output: A final version of the daily report reflecting the emotional state is generated.

[1280] Step 8:

[1281] The server generates the final daily report and sends it to the device.

[1282] Input: Final version of daily report reflecting emotional state.

[1283] Specific operation: The server sends the final daily report data in JSON format to the terminal.

[1284] Output: The final daily report data is sent to the terminal.

[1285] Step 9:

[1286] The device displays the daily report to the user.

[1287] Input: Final daily report data sent from the server.

[1288] Specific operation: The device displays the daily report on the UI of a dedicated application.

[1289] Output: The user can view the final daily report.

[1290] (Application example 2)

[1291] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1292] In conventional business record systems, recording of work content and work activities is often done manually, which is time-consuming and labor-intensive, and can lead to a lack of accuracy and consistency in the records. In addition, evaluations and feedback do not take into account the emotional state of employees, so there is a risk that employee stress or a decline in motivation may be overlooked. This leads to the issue of insufficient efforts to improve and streamline work.

[1293] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1294] In this invention, the server includes generative AI means for automatically recording work content and work activities, evaluation means for evaluating the records of work content and work activities generated by the generative AI, feedback means for providing points for reflection, reflection, and improvement based on the evaluation means, emotion estimation means for estimating and recording the emotional state of the worker using an emotion engine, and daily report generation means for reflecting the emotional state estimated by the emotion estimation means in the daily report. This not only automates the recording of work content and work activities and enables accurate and consistent recording, but also provides evaluations and feedback that take the emotional state of the worker into consideration, thereby improving and streamlining work and preventing stress and a decrease in motivation for the worker.

[1295] "Generative AI means" refers to artificial intelligence technology that automatically records work content and activities and generates documents such as daily reports.

[1296] "Evaluation methods" are technologies for evaluating the work content and records of work activities generated by generative AI and extracting the level of achievement and problems.

[1297] "Feedback methods" are techniques for providing points for reflection, reflection, and improvement based on evaluation methods.

[1298] The "emotion estimation means" is a technology for estimating and recording the emotional state of a worker using an emotion engine.

[1299] The "daily report generation means" is a technology for reflecting the emotional state estimated by the emotion estimation means in the daily report.

[1300] A system for carrying out this invention is configured as follows: A server includes generative AI means for automatically recording work content and work activities, evaluation means for evaluating the records of work content and work activities generated by the generative AI, feedback means for providing points for reflection, review, and improvement based on the evaluation means, emotion estimation means for estimating and recording the emotional state of the worker using an emotion engine, and daily report generation means for reflecting the emotional state estimated by the emotion estimation means in a daily report.

[1301] Hardware and software used

[1302] Hardware: Factory robots, sensors (temperature, humidity, vibration, etc.)

[1303] Software: Python, OpenAI API, sentiment analysis library (e.g., sentiment_analysis)

[1304] Data processing and calculation

[1305] 1. Work data acquisition: Factory robots record their daily work, for example, collecting data that indicates that work A has been completed and work B has not yet been completed.

[1306] 2. Acquisition of emotional data: The emotion engine estimates the emotional state of the worker based on sensor information. For example, it collects data on whether the worker is feeling stressed.

[1307] 3. Daily report generation: Using a generative AI model (OpenAI API), a daily report is generated based on task data and emotion data. Instructions are given to the generative AI using prompt statements.

[1308] 4. Daily report evaluation: Evaluate the generated daily reports and identify achievements and problems. Based on the evaluation results, make specific improvement proposals.

[1309] Specific examples

[1310] For example, suppose a factory robot has the following task and emotion data:

[1311] Operation data: Operation A is completed, and operation B is incomplete.

[1312] Emotional data: Workers are feeling stressed.

[1313] Based on this data, the generative AI model is given the following prompt:

[1314] Please generate a daily report based on the following work data:

[1315] Task data: Task A: Completed, Task B: Incomplete

[1316] Emotional data: workers are stressed

[1317] The generative AI model generates a daily report based on this prompt, and the evaluation means evaluates the daily report. Based on the evaluation results, the feedback means provides specific suggestions for improvement. This not only automates the recording of work content and work activities, enabling accurate and consistent recording, but also provides evaluations and feedback that take into account the worker's emotional state, thereby improving and streamlining work and preventing worker stress and a decline in motivation.

[1318] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1319] Step 1:

[1320] The server acquires work data from the factory robots. Specifically, the factory robots record their daily work and send that data to the server. The input is the work data, and the output is the work data saved on the server. For example, data such as "Task A: Completed, Task B: Incomplete" is acquired.

[1321] Step 2:

[1322] The server uses an emotion engine to estimate the worker's emotional state based on sensor information. Specifically, it analyzes sensor information such as temperature, humidity, and vibration to estimate the worker's emotional state. The input is sensor information, and the output is estimated emotional data. For example, data such as "the worker is feeling stressed" can be obtained.

[1323] Step 3:

[1324] The server generates daily reports using a generative AI model. Specifically, a prompt sentence is created based on task data and emotion data and input into the generative AI model. The input is task data and emotion data, and the output is the generated daily report. An example of a prompt sentence is "Please generate a daily report based on the following task data. Task data: Task A: Completed, Task B: Incomplete. Emotion data: The worker is feeling stressed."

[1325] Step 4:

[1326] The server evaluates the generated daily reports. Specifically, it analyzes the contents of the daily reports and extracts the degree of achievement and problems of the work. The input is the generated daily report, and the output is the evaluation result. For example, the evaluation result may be "Achievement: Low, Problem: Task B is incomplete."

[1327] Step 5:

[1328] The server provides feedback based on the evaluation results. Specifically, it analyzes the evaluation results and presents points for reflection, reflection, and improvement. The input is the evaluation results, and the output is the feedback content. For example, a specific improvement suggestion such as "Check the progress of task B and provide any necessary support" is provided.

[1329] Step 6:

[1330] The server saves the generated daily report and feedback content, and notifies the user as necessary. Specifically, it saves the daily report and feedback content in a database and makes them accessible to the user. The input is the generated daily report and feedback content, and the output is the saved data and notification. For example, a notification such as "The daily report and feedback have been saved. Please check them" is sent to the user.

[1331] Example 3

[1332] Next, a description will be given of Example 3 of Form Example 3. 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."

[1333] Conventional performance evaluation systems not only evaluate the work content and records of work activities, but also have difficulty providing feedback that takes into account the emotional state of the worker. Furthermore, there is a lack of means to generate feedback in natural language, making it difficult to provide specific and appropriate improvement suggestions to the worker. This has led to the issue of insufficient improvements in the worker's work efficiency and emotional state.

[1334] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1335] In this invention, the server includes generative AI means for automatically recording work content and work activities, evaluation means for evaluating the records of work content and work activities generated by the generative AI, feedback means for providing points for reflection, review, and improvement based on the evaluation means, means for the feedback means to provide feedback based on the emotional state estimation result by the emotion engine, and means for the feedback means to generate feedback content in natural language using a generative AI model. This makes it possible to comprehensively evaluate the work content and emotional state of the worker and provide specific and appropriate feedback.

[1336] "Generative AI means" refers to artificial intelligence technology for automatically recording work content and work activities.

[1337] "Evaluation means" refers to the means for analyzing the work content and work activity records generated by generative AI means and identifying the degree of work achievement and problems.

[1338] "Feedback measures" refer to measures for providing points for reflection, reflection, and improvement based on evaluation measures.

[1339] "Emotion engine" refers to software or algorithms for estimating the emotional state of a worker.

[1340] "Generative AI model" refers to an artificial intelligence model that generates feedback content in natural language.

[1341] "Natural language generation" refers to the technology of using artificial intelligence to generate sentences in language that humans can understand.

[1342] MODE FOR CARRYING OUT THE INVENTION

[1343] The present invention relates to a system for automatically recording, evaluating, and providing feedback on work content and work activities. Specific embodiments of this system will be described below.

[1344] Hardware and software used

[1345] Server: A central server for processing data and generating evaluation results.

[1346] Devices: PCs and smartphones used by business personnel

[1347] Emotion Engine: Software for estimating the emotional state of workers

[1348] Generative AI model: An AI model for generating feedback content in natural language

[1349] Program processing procedure

[1350] 1. Data Collection

[1351] The server collects data on the work of the workers, including the progress of the work, deliverables, and working hours.

[1352] Specific operation: The server retrieves data from business management systems and project management tools (e.g., JIRA, Trello) via API.

[1353] 2. Job Evaluation

[1354] The server evaluates the work of the workers based on the collected data, and identifies the degree of achievement and problems of the work using the evaluation means.

[1355] Specific operation: The server executes the evaluation algorithm to calculate the progress rate of the work and the completion status of the task. For example, if the progress rate is less than 50%, it is determined to be late.

[1356] 3. Emotional State Estimation

[1357] The server uses an emotion engine to estimate the emotional state of the worker, determining whether the worker is feeling stressed or happy.

[1358] Specific operation: The server analyzes the employee's input data (e.g., daily reports and feedback forms) and biometric data (e.g., heart rate and facial expression recognition) to estimate their emotional state.

[1359] 4. Feedback Generation

[1360] The server generates specific feedback based on the evaluation results and the estimated emotional state, using a generative AI model to generate the feedback content in natural language.

[1361] Specific operation: The server inputs the following prompt sentence into the generative AI model.

[1362] Employee evaluation results: The project is behind schedule due to insufficient task prioritization.

[1363] Worker emotional state: High stress levels.

[1364] Generate feedback content.

[1365] The generative AI model generates appropriate feedback based on this prompt.

[1366] 5. Send Feedback

[1367] The server transmits the generated feedback to the business operator's terminal.

[1368] Specific operation: The server sends feedback via the employee's email address or chat tool (e.g., Slack, Microsoft Teams).

[1369] 6. Receiving and Using Feedback

[1370] Workers receive feedback through the device, which helps them improve their work and manage their emotional state.

[1371] Specific Actions: The worker reviews the feedback received and implements the suggested improvements and advice, such as reevaluating task priorities and taking short breaks to reduce stress.

[1372] Specific examples

[1373] For example, suppose a worker reports on the progress of a project. The server collects this report data and analyzes it using an evaluation tool. As a result of the analysis, it is determined that the project is behind schedule. At the same time, if the emotion engine estimates that the worker's stress level is high, the server generates the following feedback:

[1374] Feedback based on the evaluation: "The project is not progressing smoothly because we haven't prioritized the tasks properly. Let's reevaluate the tasks at our next meeting."

[1375] Feedback based on emotional state: "You seem to be stressed out by your work lately. I suggest you take a short break to reduce your stress."

[1376] In this way, the worker can receive specific and appropriate feedback, which can be used to improve the work and manage the emotional state. The flow of the identification process in the third embodiment will be described with reference to FIG.

[1377] Step 1:

[1378] Data collection

[1379] The server collects data relating to the business activities of business operators.

[1380] Input: Business data from business management systems and project management tools (e.g., JIRA, Trello).

[1381] Specific operation: The server obtains data such as work progress, deliverables, and working hours through the API.

[1382] Output: Collected business data.

[1383] Step 2:

[1384] Business evaluation

[1385] The server evaluates the work of the employee based on the collected data.

[1386] Input: Business data collected in step 1.

[1387] Specific operation: The server executes the evaluation algorithm to calculate the progress rate and task completion status. For example, if the progress rate is less than 50%, it is considered to be late.

[1388] Output: Evaluation results showing the degree of accomplishment and problems of the work.

[1389] Step 3:

[1390] Emotional state estimation

[1391] The server uses an emotion engine to estimate the emotional state of the worker.

[1392] Input: Employee input data (e.g., daily reports and feedback forms) and biometric data (e.g., heart rate, facial expression recognition).

[1393] Specific operation: The server analyzes these data and determines whether the worker is feeling stressed or happy.

[1394] Output: Estimation of the worker's emotional state.

[1395] Step 4:

[1396] Feedback Generation

[1397] The server generates specific feedback based on the evaluation results and the estimated emotional state.

[1398] Input: Evaluation results from step 2 and estimation results of emotional state from step 3.

[1399] Specific operation: The server inputs the following prompt sentence into the generative AI model.

[1400] Employee evaluation results: The project is behind schedule due to insufficient task prioritization.

[1401] Worker emotional state: High stress levels.

[1402] Generate feedback content.

[1403] The generative AI model generates appropriate feedback based on this prompt.

[1404] Output: Generated feedback in natural language.

[1405] Step 5:

[1406] Send Feedback

[1407] The server transmits the generated feedback to the business operator's terminal.

[1408] Input: The feedback generated in step 4.

[1409] Specific operation: The server sends feedback via the employee's email address or chat tool (e.g., Slack, Microsoft Teams).

[1410] Output: Feedback sent to the worker's device.

[1411] Step 6:

[1412] Receiving and using feedback

[1413] Workers receive feedback through the device, which helps them improve their work and manage their emotional state.

[1414] Input: Feedback submitted in step 5.

[1415] Specific Actions: The worker reviews the feedback received and implements the suggested improvements and advice, such as reevaluating task priorities and taking short breaks to reduce stress.

[1416] Output: Improved work performance and controlled emotional state.

[1417] (Application example 3)

[1418] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1419] Conventional work evaluation systems have difficulty comprehensively evaluating workers' work efficiency and emotional state and providing appropriate feedback. Furthermore, while there is a need for real-time detection of declines in work efficiency and overload conditions, particularly for factory robots, and appropriate improvement proposals, there has been a lack of concrete methods for achieving this. As a result, improvements in robot work efficiency and reductions in overload conditions have not been fully achieved.

[1420] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1421] In this invention, the server includes generative AI means for automatically recording work content and work activities, evaluation means for evaluating the records of work content and work activities generated by the generative AI, feedback means for providing points for reflection, review, and improvement based on the evaluation means, means for collecting robot work data and sensor information and evaluating work efficiency, means for estimating the emotional state based on the sensor information of the robot, and means for providing specific improvement suggestions and feedback based on the evaluation results and the emotional state, thereby making it possible to improve the robot's work efficiency and reduce overload.

[1422] "Generative AI methods" are artificial intelligence methods that automatically record work content and work activities and generate data.

[1423] "Evaluation means" refers to a means for evaluating the work content and work activity records generated by generative AI.

[1424] "Feedback measures" are means for providing points for reflection, reflection, and improvement based on evaluation measures.

[1425] "Task data" refers to data related to the work performed by the robot, and includes information on the movements, time, efficiency, etc.

[1426] "Sensor information" refers to information obtained from sensors mounted on the robot, and includes data such as temperature, pressure, and operating status.

[1427] "Means for evaluating work efficiency" refers to a means for evaluating work efficiency based on robot work data and sensor information.

[1428] The "means for estimating emotional state" is a means for estimating the emotional state of the robot (for example, an overloaded state or a normal state) based on the sensor information of the robot.

[1429] "Means for providing specific improvement suggestions and feedback" refers to means for providing specific improvement suggestions and feedback based on the evaluation results and emotional state.

[1430] A system for carrying out this invention is configured as follows: The server includes generative AI means for automatically recording work content and work activities, evaluation means for evaluating the generated records of work content and work activities, feedback means for providing points for reflection, review, and improvement based on the evaluation means, means for collecting robot work data and sensor information and evaluating work efficiency, means for estimating the emotional state based on the robot's sensor information, and means for providing specific improvement suggestions and feedback based on the evaluation results and the emotional state.

[1431] Hardware and Software Configuration

[1432] Hardware:

[1433] Robot body

[1434] Sensors (temperature, pressure, motion sensors, etc.)

[1435] server

[1436] software:

[1437] Generative AI Model

[1438] Evaluation Module

[1439] Emotion Engine

[1440] Data Collection Module

[1441] Data processing and calculation

[1442] The server collects data in real time from sensors installed on the robot body. The collected data is processed by the data collection module and input into the generative AI model. The generative AI model generates records of work content and work activities and passes them to the evaluation module. The evaluation module evaluates work efficiency based on the generated records, and the emotion engine estimates the robot's emotional state based on sensor information.

[1443] The evaluation results and the emotional state are passed to a feedback system, which generates specific suggestions for improvement and feedback. For example, if work efficiency is low, feedback such as "Please review your work procedures" is provided, and if the emotional state is stressed, advice such as "Please take a break" is provided.

[1444] Specific examples

[1445] For example, if a robot's efficiency drops while working in a factory, the server will provide feedback such as "Please review your work procedures." If the robot is overloaded, the server will provide advice such as "Please take a break."

[1446] Prompt Sentence Examples

[1447] An example of a prompt for the generative AI model is as follows:

[1448] Create a program that evaluates the robot's work efficiency and emotional state based on its work data and sensor information, and provides specific suggestions for improvement and feedback. If the evaluation result is low, provide feedback such as "Please review your work procedures," and if the robot's emotional state is stressed, provide feedback such as "Please take a break."

[1449] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1450] Step 1:

[1451] The server collects data in real time from sensors installed on the robot body. The input is sensor information, and the output is the collected raw data. Specifically, it acquires data such as temperature, pressure, and operating status from the sensors and sends it to the data collection module.

[1452] Step 2:

[1453] The server preprocesses the raw data collected using the data collection module. The input is the collected raw data, and the output is the preprocessed data. Specifically, it performs noise removal and data normalization, and converts the data into a format suitable for generative AI models.

[1454] Step 3:

[1455] The server inputs the preprocessed data into a generative AI model to generate records of work content and activities. The input is the preprocessed data, and the output is the generated work record. Specifically, the generative AI model analyzes the data and generates details of work content and activities in text format.

[1456] Step 4:

[1457] The server passes the generated business records to the evaluation module to evaluate the work efficiency. The input is the generated business records, and the output is the evaluation result of the work efficiency. Specifically, the evaluation module analyzes the business records and quantifies the work efficiency.

[1458] Step 5:

[1459] The server inputs sensor information into the emotion engine to estimate the robot's emotional state. The input is sensor information, and the output is the estimated emotional state. Specifically, the emotion engine analyzes the sensor information and determines whether the robot is in an overloaded state or a normal state.

[1460] Step 6:

[1461] The server passes the evaluation results and the estimated emotional state results to the feedback means, which then generates specific improvement suggestions and feedback. The input is the evaluation results of work efficiency and the estimated emotional state results, and the output is specific improvement suggestions and feedback. Specifically, the feedback means generates appropriate improvement suggestions and advice based on the evaluation results and the emotional state.

[1462] Step 7:

[1463] The server sends the generated feedback to the robot, which then modifies its behavior based on it. The input is specific improvement suggestions or feedback, and the output is the robot's behavior modification. Specific actions include the robot receiving the feedback and reviewing its work procedures or taking a break.

[1464] 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.

[1465] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by 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.

[1466] Another example of generative AI is Gemini (internet search engine). <url: https: gemini.google.com ?hl="ja">) are mentioned.

[1467] 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.

[1468] [Third embodiment]

[1469] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1470] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1471] 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).

[1472] 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.

[1473] 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.

[1474] 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).

[1475] 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. 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.

[1476] 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.

[1477] 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.

[1478] 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.

[1479] 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.

[1480] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1481] "Example 1"

[1482] In one embodiment of the present invention, generative AI automatically records the work activities performed by business personnel and generates the records as daily reports. Specifically, it works in conjunction with the business tools and systems used by business personnel, understands the work content based on the operation logs and input data, and formats the results into daily reports.

[1483] "Example 2"

[1484] The evaluation means evaluates the daily reports generated by the generative AI. Specifically, it automatically extracts the degree of achievement and problems of work based on the contents of the daily reports and outputs the evaluation results. For example, it compares the work goals with the actual results and calculates the degree of achievement. It also extracts problems and areas for improvement from the work content.

[1485] "Example 3"

[1486] The feedback method provides points for reflection, reflection, and improvement based on the evaluation method. Specifically, specific improvement suggestions are made based on the evaluation results and feedback is provided to the worker. For example, if the level of achievement of a task is low, the problem that caused it and improvement suggestions are presented to the worker.

[1487] The processing flow of each embodiment will be described below.

[1488] "Example 1"

[1489] Step 1: The worker operates the business tools and systems.

[1490] Step 2: Generative AI collects operation logs and input data from business tools and systems.

[1491] Step 3: Based on the data collected by the generative AI, the work content is understood and formatted into a daily report.

[1492] "Example 2"

[1493] Step 1: Generative AI generates daily reports.

[1494] Step 2: The evaluation tool automatically extracts the degree of achievement and problems of the work based on the contents of the generated daily report.

[1495] Step 3: The evaluation means outputs the evaluation result.

[1496] "Example 3"

[1497] Step 1: The evaluation means outputs the evaluation result.

[1498] Step 2: The feedback mechanism makes specific improvement suggestions based on the evaluation results.

[1499] Step 3: The feedback mechanism provides feedback to the operator.

[1500] Example 1

[1501] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1502] Conventional business record systems require employees to manually record their work, which takes time and effort, and often results in inaccuracies and inconsistencies in the records. Furthermore, because evaluations of work and feedback on areas for improvement are also done manually, this is inefficient and can delay business improvements. There is a need for a system that can solve these problems, automate business records, and provide efficient feedback.

[1503] 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.

[1504] In this invention, the server includes generative AI means for automatically recording work content and work activities, evaluation means for evaluating the records of work content and work activities generated by the generative AI, feedback means for providing points for reflection, review, and improvement based on the evaluation means, data collection means for collecting operation logs and input data from work tools and systems, data analysis means for analyzing the collected data and understanding the work content, daily report generation means for generating daily reports based on the analysis results, and daily report distribution means for distributing the generated daily reports to users. This enables automation of work records and efficient feedback.

[1505] "Generative AI means" refers to artificial intelligence technology that automatically records work content and activities and formats them into daily reports and other formats.

[1506] "Evaluation means" refers to the function for analyzing the work content and records of work activities generated by generative AI and evaluating their content.

[1507] "Feedback means" refers to a function for providing points for reflection, review, and improvement based on the evaluation results obtained by the evaluation means.

[1508] "Data collection means" refers to the function for collecting operation logs and input data from business tools and systems.

[1509] "Data analysis means" refers to the function for analyzing collected data and understanding business operations.

[1510] The "daily report generation means" refers to a function for generating a daily report based on the analysis results obtained by the data analysis means.

[1511] The "daily report distribution means" refers to a function for distributing the generated daily report to the user.

[1512] The present invention relates to a system for automatically recording work content and work activities and generating a daily report. A specific embodiment of this system will be described below.

[1513] Server Roles

[1514] The server runs a generative AI means that automatically records business content and business activities. This generative AI works in conjunction with business tools and systems to collect their operation logs and input data. Specifically, the server obtains data from systems such as Microsoft Excel, Google Docs, Salesforce, and SAP via API. The collected data is analyzed by a data analysis means within the server, and the business content is identified. Based on the analysis results, the server generates a daily report using a daily report generation means. The generated daily report is distributed to the user via a daily report distribution means. For example, the server sends the generated daily report to the user's email address.

[1515] Device Role

[1516] A terminal generates an operation log when a user operates a business tool or system. Specifically, the terminal monitors user operations in real time and records the details of the operation in a log file. For example, when a user enters data into Microsoft Excel, the terminal records the details of the input as a log. The generated operation log and input data are sent from the terminal to a server. The terminal periodically communicates with the server and uploads the collected data.

[1517] User Roles

[1518] Users use business tools and systems on a daily basis to carry out their work activities. Specifically, they perform operations such as data entry and information updates. For example, a user updates customer information and adds a new contact in Salesforce. A daily report is automatically generated by the user simply by performing their daily work activities without any special operations. The generated daily report is distributed from the server, and the user can check the received daily report via email or chat tools.

[1519] Specific examples

[1520] Example 1: Recording sales activities

[1521] The server uses the Salesforce API to retrieve the log of customer information updated by the user. The server analyzes the operation log "Updated customer A's contact information" and identifies the updated content. The server generates a daily report stating "Today, customer A's information was updated and a new contact was added" and sends it to the user's email address.

[1522] Example 2: Recording Data Entry

[1523] When a user inputs data into Microsoft Excel, the device records the input as a log. The device sends the collected operation logs to the server every hour. The server receives the operation logs sent from the device, analyzes the operation log "Enter sales data," and identifies the sales data that was input. The server generates a daily report stating, "Today, sales data was entered and total sales amounted to XX yen," and sends it to the user's email address.

[1524] Prompt Sentence Examples

[1525] "Please generate a daily report based on the operation log when a business user updates customer information in Salesforce."

[1526] "Generate a daily report based on sales data entered in Microsoft Excel."

[1527] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1528] Step 1:

[1529] The server collects operation logs and input data from business tools and systems. Specifically, the server obtains data from systems such as Microsoft Excel, Google Docs, Salesforce, and SAP via API. As input, it receives operation logs and input data from business tools and systems, and as output, it stores the collected data in an internal database.

[1530] Step 2:

[1531] The server analyzes the collected data. Specifically, it uses natural language processing (NLP) technology to extract important information from operation logs and input data. As input, it receives operation logs and input data stored in an internal database, and as output, it generates analysis results. For example, the server analyzes the operation log "Update customer A's contact information" and identifies the updated content.

[1532] Step 3:

[1533] The server generates a daily report based on the analysis results. Specifically, the server uses a generative AI model to format the extracted information in natural language. It receives the analysis results as input and generates a daily report as output. For example, the server generates a daily report stating, "Today, customer A's information was updated and a new contact was added."

[1534] Step 4:

[1535] The server distributes the generated daily report to the user. Specifically, the server sends the daily report via email or a chat tool (for example, Slack or Microsoft Teams). The server receives the generated daily report as input and sends the daily report to the user's email address or chat tool as output. For example, the server sends the generated daily report to the user's email address.

[1536] Step 5:

[1537] A terminal generates an operation log when a user operates a business tool or system. Specifically, the terminal monitors user operations in real time and records the operation details in a log file. It receives user operations as input and generates an operation log as output. For example, when a user enters data into Microsoft Excel, the terminal records the input details as a log.

[1538] Step 6:

[1539] The terminal sends the generated operation logs and input data to the server. Specifically, the terminal periodically communicates with the server and uploads the collected data. It receives the generated operation logs and input data as input and sends data to the server as output. For example, the terminal sends the collected operation logs to the server every hour.

[1540] Step 7:

[1541] Users use business tools and systems on a daily basis to perform business activities. Specifically, users perform operations such as data entry and information updates. As input, they use business tools and systems, and as output, they generate operation logs and input data. For example, a user updates customer information and adds a new contact in Salesforce.

[1542] Step 8:

[1543] The user checks the daily report delivered from the server. Specifically, the user views the daily report received via email or chat tool. The user receives the daily report delivered from the server as input, and checks the contents of the daily report as output. For example, the user opens the daily report received by email and checks the work content.

[1544] (Application example 1)

[1545] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1546] In the past, work records in factories were often done manually, which placed a heavy burden on workers and was prone to errors and omissions. Furthermore, work evaluations and feedback on areas for improvement were not properly conducted, making it difficult to improve operations efficiently. Furthermore, the process of formatting work details into daily reports was time-consuming and labor-intensive.

[1547] 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.

[1548] In this invention, the server includes a generative AI means for automatically recording work content and work activities, an evaluation means for evaluating the records of work content and work activities generated by the generative AI, a feedback means for providing points for reflection, review, and improvement based on the evaluation means, a means for automatically recording the work content of machines operating in the factory and generating the results as a daily report, and a means for saving the daily report. This enables automated and accurate recording of work records, reduces the burden on workers, and enables efficient work improvement. Furthermore, the automatic generation of daily reports enables quick understanding and evaluation of work content.

[1549] "Generative AI methods" are artificial intelligence technologies that automatically record work content and activities and generate documents such as daily reports based on those records.

[1550] "Evaluation means" refers to technology for analyzing the work content and records of work activities generated by generative AI means and evaluating their content.

[1551] "Feedback means" refers to a technique for providing points for reflection, review, and improvement based on the evaluation results obtained by the evaluation means.

[1552] "Machines operating in factories" refer to automated devices and robots used to perform manufacturing, assembly, and other tasks in factories.

[1553] "Means for automatically recording work content" refers to technology for automatically recording the operation and work content of machines operating in a factory.

[1554] The "means for generating a daily report" is a technology for automatically generating a document in daily report format based on the recorded work content.

[1555] The "means for storing the daily report" is a technology for storing the generated daily report in a digital format.

[1556] A system for carrying out the present invention is for automatically recording the work details of machines operating in a factory and generating a daily report. A specific embodiment of this system will be described below.

[1557] System Configuration

[1558] The system includes the following main hardware and software:

[1559] Hardware: Factory robots (e.g., general-purpose robots), servers, data storage devices

[1560] Software: Python, generative AI models (e.g., GPT-3), database management system

[1561] Program processing

[1562] The server receives and records data on the work content sent by the factory robots. Specifically, it saves the robot's movements and work content as a log with a timestamp. Next, it uses a generative AI model to analyze the recorded data and format it as a daily report. The generated daily report is stored in a database and can be accessed as needed.

[1563] Specific examples

[1564] For example, when a factory robot performs tasks such as "starting the assembly line," "checking product quality," and "packing products into boxes," each task is recorded with a timestamp. A generative AI model analyzes this data and formats it into a daily report.

[1565] Prompt Sentence Examples

[1566] Please generate a daily report based on the work log below.

[1567] 1. 2023-10-01T09:00:00 - Start of assembly line

[1568] 2. 2023-10-01T10:00:00 - Check the quality of the product

[1569] 3. 2023-10-01T11:00:00 - Packing the products into boxes

[1570] The format of the report is as follows:

[1571] Date: YYYY-MM-DD

[1572] What you'll do:

[1573] Task 1: Task Details

[1574] Task 2: Task Details

[1575] Task 3: Task Details

[1576] In this way, a system is realized that automatically records the work content of factory robots and generates it as a daily report. This system enables automated and accurate recording of work records, reduces the burden on workers, and enables efficient business improvement. In addition, the automatic generation of daily reports makes it possible to quickly understand and evaluate work content.

[1577] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1578] Step 1:

[1579] The server receives data on the work content sent from the factory robot.

[1580] Input: Task data from factory robots (e.g., "Start the assembly line," "Check the quality of the product," etc.)

[1581] Output: A time-stamped log of work

[1582] Specific operation: The server receives data on the work content sent from the factory robots in real time, assigns a timestamp to each task, and saves it as a log.

[1583] Step 2:

[1584] The server stores the received work log in a database.

[1585] Input: Timestamp work log

[1586] Output: Work logs stored in a database

[1587] Specific operation: The server sends a time-stamped work log to the database management system and stores it in the database.

[1588] Step 3:

[1589] The server uses a generative AI model to analyze the saved work logs and format them into a daily report.

[1590] Input: Work logs stored in the database

[1591] Output: Formatted daily report

[1592] Specific operation: The server calls a generative AI model (e.g., GPT-3) and provides the saved work log as input. The generative AI model analyzes the work log and generates a document in the form of a daily report.

[1593] Step 4:

[1594] The server stores the generated daily report in a database.

[1595] Input: Formatted daily report

[1596] Output: Daily reports stored in a database

[1597] Specific operation: The server sends the generated daily report to the database management system and stores it in the database.

[1598] Step 5:

[1599] The user can obtain and view the daily report from the database as needed.

[1600] Input: User request

[1601] Output: Daily report provided to the user

[1602] Specific operation: The user sends a request for a daily report to the server. The server retrieves the relevant daily report from the database and provides it to the user.

[1603] Example 2

[1604] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1605] Conventional work evaluation systems required manual recording of work content and work activities, making the evaluation and feedback process cumbersome and time-consuming. Furthermore, the evaluations often lacked accuracy and consistency, making it difficult to identify specific areas for improvement. This led to the issue of insufficient work efficiency and improvement.

[1606] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: a generative AI means for automatically recording work content and work activities; an evaluation means for evaluating the records of work content and work activities generated by the generative AI; a feedback means for providing points for reflection, review, and improvement based on the evaluation means; an input means for a user to input a daily report; a transmission means for transmitting the input daily report data to the server; an analysis means for the server to receive the daily report data and input a prompt sentence to the generative AI model; a generation means for receiving the analysis results from the generative AI model and generating an evaluation report; a transmission means for transmitting the generated evaluation report to a terminal; and a confirmation means for a user to check the evaluation report. This automates the process from recording work content and work activities to evaluation and feedback, improves the accuracy and consistency of evaluation, and enables specific areas for improvement to be quickly identified.

[1607] "Generative AI means" refers to artificial intelligence technology for automatically recording work content and work activities.

[1608] "Evaluation means" refers to a function that analyzes the work content and work activity records generated by generative AI and evaluates the degree of work achievement and problems.

[1609] "Feedback means" refers to a function for providing points for reflection, reflection, and improvement based on evaluation means.

[1610] "Input means" refers to an interface for a user to input a daily report.

[1611] "Transmission means" refers to a function for transmitting input daily report data to a server.

[1612] "Analysis means" refers to the function that allows the server to receive daily report data and input prompt sentences into the generative AI model.

[1613] "Generation means" refers to the function for receiving the analysis results from the generative AI model and generating an evaluation report.

[1614] The "verification means" refers to an interface for the user to verify the evaluation report.

[1615] The present invention relates to a system for automatically recording work content and work activities and providing evaluations and feedback. Specific embodiments of this system will be described below.

[1616] System configuration

[1617] The system consists of the following major components:

[1618] 1. Generative AI means:

[1619] Generative AI uses artificial intelligence technology to automatically record work content and work activities. Specifically, it uses natural language processing technology to analyze daily reports entered by users and automatically record work content.

[1620] 2. Evaluation method:

[1621] The evaluation means analyzes the work content and work activity records generated by the generative AI and evaluates the degree of work achievement and problems. The evaluation means analyzes the contents of the daily report using a generative AI model (e.g., OpenAI's GPT-4).

[1622] 3. Feedback methods:

[1623] The feedback method provides points for reflection, reflection, and improvement based on the evaluation method. Specifically, specific improvement proposals are made based on the evaluation results.

[1624] 4. Input method:

[1625] This is an interface for users to input daily reports. This is realized using devices such as PCs and smartphones.

[1626] 5. Means of transmission:

[1627] This function allows the terminal to send the daily report data entered to the server. The data is encrypted using SSL / TLS before being sent.

[1628] 6. Analysis methods:

[1629] This function allows the server to receive daily report data and input prompt sentences into the generative AI model. The prompt sentences are generated based on the contents of the daily report.

[1630] 7. Generation means:

[1631] This function allows the server to receive the analysis results from the generated AI model and generate an evaluation report that lists the degree of task achievement, specific problems, and areas for improvement.

[1632] 8. Verification Method:

[1633] This is an interface for the user to check the evaluation report. The evaluation report is provided to the user via the terminal.

[1634] System Operation

[1635] The operation of this system is as follows.

[1636] 1. Enter your daily report:

[1637] After work, the user uses the terminal to enter a daily report. For example, the user might enter, "Today's sales target was 1 million yen, but the actual result was 900,000 yen. It took too long to respond to customers."

[1638] 2. Data transmission:

[1639] The terminal sends the entered daily report data to the server. The data is encrypted before transmission, ensuring security.

[1640] 3. Data Analysis:

[1641] The server inputs the received daily report data into the generative AI model. An example of a prompt sentence is, "Analyze the following daily report and extract the degree of achievement and problems of the work. Daily report: 'Today's sales target was 1 million yen, and the actual result was 900,000 yen. It took too long to respond to customers.'"

[1642] 4. Generate the assessment report:

[1643] The server generates an evaluation report based on the analysis results from the generative AI model, which details the level of achievement, specific problems, and areas for improvement.

[1644] 5. Review the evaluation report:

[1645] Users can check the evaluation report through their terminal and use it to consider next steps to improve their business operations.

[1646] In this way, the process from recording work content and work activities to evaluation and feedback can be automated, improving the accuracy and consistency of evaluations and enabling specific areas for improvement to be quickly identified.

[1647] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1648] Step 1:

[1649] The user inputs a daily report.

[1650] After work, the user uses the device to enter a daily report. Specifically, the user opens a dedicated application and enters, "Today's sales target was 1 million yen, but the actual result was 900,000 yen. It took too long to respond to customers." The entered data is saved on the device as daily report data.

[1651] Step 2:

[1652] The terminal transmits the daily report data to the server.

[1653] The terminal sends the daily report data entered by the user to the server by pressing the "Send" button. When sent, the data is encrypted using SSL / TLS. The input is the daily report data, and the output is the encrypted daily report data.

[1654] Step 3:

[1655] The server receives the daily report data.

[1656] The server receives the encrypted daily report data sent from the terminal and decrypts it. The decrypted daily report data is stored in a database. The input is the encrypted daily report data, and the output is the decrypted daily report data.

[1657] Step 4:

[1658] The server inputs a prompt sentence into the generative AI model.

[1659] The server generates a prompt sentence based on the received daily report data. For example, a prompt sentence such as "Analyze the following daily report and extract the degree of achievement and problems of the work. Daily report: 'Today's sales target was 1 million yen, and the actual result was 900,000 yen. It took too long to respond to customers.'" is input into the generative AI model. The input is the daily report data, and the output is the prompt sentence.

[1660] Step 5:

[1661] The server receives the analysis results from the generative AI model.

[1662] The server receives analysis results from a generative AI model (e.g., OpenAI's GPT-4). The analysis results include the task's achievement level, problems, and areas for improvement. The input is a prompt, and the output is the analysis results.

[1663] Step 6:

[1664] The server generates the analysis results as an evaluation report.

[1665] The server generates an evaluation report based on the analysis results received from the generative AI model. The evaluation report details the level of achievement, specific problems, and areas for improvement. The input is the analysis results, and the output is the evaluation report.

[1666] Step 7:

[1667] The server sends the evaluation report to the terminal.

[1668] The server sends the generated evaluation report to the terminal and notifies the user. During transmission, data integrity and security are ensured. The input is the evaluation report, and the output is the evaluation report sent to the terminal.

[1669] Step 8:

[1670] The user checks the evaluation report.

[1671] The user receives a notification, opens the application, and checks the evaluation report, which states, "Achievement: 90%; Issue: Customer response time was too long." The input is the evaluation report, and the output is the user's confirmation.

[1672] In this way, a system is realized in which the server, terminals, and users work together to evaluate daily reports.

[1673] (Application example 2)

[1674] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1675] Conventional business record systems require manual recording of work content and activities, which takes time and effort. Evaluation and feedback are also done manually, which often results in inefficiency and inaccuracy. Furthermore, there is no way to check evaluation results in real time, which can lead to missed opportunities for business improvement. To solve these problems, there is a need for a system that automates business records, evaluations, and feedback, and also allows evaluation results to be checked in real time.

[1676] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1677] In this invention, the server includes generative AI means for automatically recording work content and work activities, evaluation means for evaluating the records of work content and work activities generated by the generative AI, feedback means for providing points for reflection, review, and improvement based on the evaluation means, and display means for displaying the evaluation results on a smartphone. This enables automation of work recording, evaluation, and feedback, and also allows the evaluation results to be checked in real time.

[1678] "Generative AI means" refers to artificial intelligence technology for automatically recording work content and work activities.

[1679] "Evaluation means" refers to the function for evaluating the work content and records of work activities generated by generative AI.

[1680] "Feedback means" refers to a function for providing points for reflection, reflection, and improvement based on evaluation means.

[1681] "Display means" refers to the function for displaying the evaluation results on a smartphone.

[1682] The system for carrying out this invention includes generative AI means, evaluation means, feedback means, and display means. Specific embodiments of each means will be described below.

[1683] First, generative AI means use artificial intelligence technology to automatically record work content and work activities. Specifically, it receives data on work content and work activities as input and automatically generates it in the form of a daily report. The generated daily report is saved as text data.

[1684] Next, the evaluation means has the function of evaluating the daily reports generated by the generative AI means. This evaluation means uses OpenAI's API to automatically extract the degree of achievement, problems, and areas for improvement based on the contents of the daily reports. The evaluation means generates the contents of the daily reports as prompt sentences and sends them to OpenAI's API to obtain the evaluation results.

[1685] The feedback method provides points for reflection, reflection, and improvement based on the evaluation results obtained by the evaluation method. This feedback includes specific suggestions for improvement, and contributes to improving the efficiency and quality of work.

[1686] The display function has the function of displaying the evaluation results on a smartphone. The evaluation results can be checked in real time through the smartphone application, allowing users to immediately grasp the progress of their work and areas for improvement.

[1687] For example, you can use the following prompt to evaluate daily reports:

[1688] Example prompt sentence:

[1689] Please rate the following daily report.

[1690] Daily report contents:

[1691] Robot A had a goal of assembling 100 parts during an 8-hour shift.

[1692] In fact, it was made up of 90 parts.

[1693] There was a delay in parts supply midway through, which caused work to be temporarily halted.

[1694] Evaluation content:

[1695] 1. Task accomplishment

[1696] 2. Problems

[1697] 3. Improvements

[1698] This prompt is used to ask the generative AI model to evaluate the daily report. The evaluation results are output from three perspectives: the degree of accomplishment, problems, and areas for improvement.

[1699] The hardware used is a smartphone, and the software uses Python and OpenAI API. For data processing, the contents of the daily reports are generated as prompt sentences, and for data calculation, OpenAI API is used to generate evaluations.

[1700] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1701] Step 1:

[1702] The server receives data on work content and work activities. The input data includes information such as the progress of work, work content, and time. The server passes this data to a generative AI means, which automatically generates a daily report. The generated daily report is saved as text data.

[1703] Step 2:

[1704] The server passes the generated daily report to the evaluation means. The evaluation means generates a prompt sentence from the content of the daily report. Specifically, it converts the content of the daily report into the following format:

[1705] Please rate the following daily report.

[1706] Daily report contents:

[1707] [Daily report contents]

[1708] Evaluation content:

[1709] 1. Task accomplishment

[1710] 2. Problems

[1711] 3. Improvements

[1712] By generating this prompt sentence, the evaluation means prepares to evaluate the contents of the daily report.

[1713] Step 3:

[1714] The server sends the generated prompt to OpenAI's API. The input data is the prompt, and the output data is the evaluation result. OpenAI's API automatically extracts the task achievement level, problems, and areas for improvement based on the prompt, and returns the evaluation result.

[1715] Step 4:

[1716] The server receives the evaluation results returned from the OpenAI API and passes them to the feedback mechanism. The feedback mechanism provides points for reflection, reflection, and improvement based on the evaluation results. Specifically, it analyzes the evaluation results and generates specific improvement proposals.

[1717] Step 5:

[1718] The server passes the improvement suggestions obtained from the feedback means to the display means. The display means displays the evaluation results and improvement suggestions on the smartphone. The user can check the evaluation results and improvement suggestions in real time via the smartphone.

[1719] Step 6:

[1720] Users can check the evaluation results and improvement suggestions displayed on their smartphones and make improvements to their work as needed, thereby improving work efficiency and quality.

[1721] Example 3

[1722] Next, a third embodiment of the third embodiment will be described. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1723] Conventional work evaluation systems have difficulty not only evaluating the level of work performance of employees but also providing specific suggestions for improvement. In addition, feedback based on evaluation results is often abstract, and it is often unclear how employees should specifically improve. This has led to the issue of not being able to fully improve employees' work efficiency.

[1724] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1725] In this invention, the server includes generative artificial intelligence means for automatically recording work content and work activities, evaluation means for evaluating the records of work content and work activities generated by the generative artificial intelligence, feedback means for providing points for reflection, review, and improvement based on the evaluation means, generative artificial intelligence model means for generating specific improvement proposals based on the evaluation results by the feedback means, prompt sentence generation means for inputting the evaluation results to the generative artificial intelligence model means, and notification means for providing feedback obtained from the generative artificial intelligence model means to the worker. This makes it possible to provide specific and practical improvement proposals to the worker.

[1726] "Generative artificial intelligence means" refers to artificial intelligence technology for automatically recording work content and work activities.

[1727] "Evaluation means" refers to technology for analyzing the work content and work activity records generated by the generative artificial intelligence means and evaluating the degree of work achievement.

[1728] "Feedback measures" refer to techniques for providing points for reflection, reflection, and improvement based on evaluation measures.

[1729] "Generative artificial intelligence model means" refers to artificial intelligence technology for generating specific improvement proposals based on evaluation results.

[1730] The "prompt sentence generation means" refers to a technique for generating a prompt sentence for inputting the evaluation result to the generation artificial intelligence model means.

[1731] "Notification means" refers to a technology for providing feedback obtained from the generative artificial intelligence model means to a business operator.

[1732] This invention is a system for evaluating the degree of work performance of an employee and providing specific suggestions for improvement. The program processing of this system will be specifically described below.

[1733] The server uses a generative artificial intelligence means to automatically record the work content and work activities of the worker. This generative artificial intelligence means collects data from the terminal used by the worker and records the work content and work activities. For example, it collects task completion information entered by the worker into a task management application and data from a time tracking tool that records work hours.

[1734] The server then analyzes the collected data using an evaluation tool. Specifically, it uses Scikit-learn, a Python machine learning library, to evaluate the worker's level of work achievement. The evaluation tool quantifies the level of work achievement and identifies the cause of low achievement. For example, it quantifies the level of work achievement based on the number of tasks an employee completes in a week and the time required to complete them. If achievement is low, the server identifies issues with task prioritization and time management.

[1735] The server then generates specific improvement suggestions based on the evaluation results. This process uses OpenAI's GPT-4, a generative AI model. The server inputs the evaluation results into the generative AI model as a prompt sentence, generating feedback for the worker. For example, the following prompt sentence could be input into the generative AI model:

[1736] "Worker A's performance is 50% and their main issue is improper task prioritization. Please provide specific suggestions for improving this issue."

[1737] When this prompt sentence is fed into a generative AI model, the model generates the following feedback:

[1738] "Employee A, we have confirmed that your work completion rate is 50%. The main problem is that you are not prioritizing your tasks properly. To improve this, it is important to first classify your daily tasks based on importance and urgency, and clarify their priorities. We also recommend that you regularly check your progress and re-prioritize your tasks as necessary."

[1739] Finally, the server notifies the worker of the generated feedback to their device. For example, it sends a notification to the worker's smartphone saying, "We recommend that you review the prioritization of your tasks and classify them based on importance and urgency."

[1740] In this way, the server can generate specific improvement proposals based on the evaluation results and provide feedback to the business operator. This system allows the business operator to receive specific and practical improvement proposals, thereby improving business efficiency. The flow of the identification process in Example 3 will be described with reference to Figure 15.

[1741] Step 1:

[1742] The server collects data on work content and work activities from the workers' devices. Specifically, it collects task completion information entered by workers into a task management application and data from a time tracking tool that records work time. Input data includes task names, completion dates and times, and required time. This data is sent to the server and saved as a record of work content and work activities.

[1743] Step 2:

[1744] The server analyzes the collected data using evaluation methods. Specifically, it uses Scikit-learn, a Python machine learning library, to evaluate the worker's level of work achievement. The input data is the records of work content and work activities collected in Step 1. The server uses this data to quantify the level of work achievement and identify the causes of low achievement. For example, it identifies problems with task prioritization and time management.

[1745] Step 3:

[1746] The server generates specific improvement proposals based on the evaluation results. A generative AI model is used in this process. The input data is the evaluation results obtained in step 2. The server inputs the evaluation results into the generative AI model as a prompt sentence, and generates feedback for the worker. For example, it generates a prompt sentence such as, "Worker A's task achievement rate is 50%, and the main problem is that the prioritization of tasks is inappropriate. Please provide specific proposals to improve this problem."

[1747] Step 4:

[1748] The server notifies the worker's device of the feedback obtained from the generative AI model. The input data is the feedback generated in step 3. The server sends a notification to the worker's smartphone saying, "We recommend that you review your task prioritization and classify them based on importance and urgency." The worker can use this feedback to improve their work.

[1749] In this way, the server can generate specific improvement suggestions based on the evaluation results and provide feedback to the operator.

[1750] (Application example 3)

[1751] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1752] Traditionally, evaluation of work efficiency and accuracy in factories has relied on human monitoring and manual recording, making it difficult to provide efficient feedback and suggest improvements. Furthermore, as work becomes increasingly automated, there is a need for a method to evaluate the performance of machinery in real time and quickly provide feedback on specific areas for improvement.

[1753] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means. In this invention, the server includes generative AI means for automatically recording work content and work activities, evaluation means for evaluating the records of work content and work activities generated by the generative AI, feedback means for providing points for reflection, review, and improvements based on the evaluation means, and means for evaluating the work efficiency and accuracy of machinery performing work in a factory and providing feedback on areas for improvement. This makes it possible to evaluate the work efficiency and accuracy of machinery in real time and quickly provide feedback on specific improvement suggestions.

[1754] "Generative AI means" refers to artificial intelligence technology for automatically recording work content and work activities.

[1755] "Evaluation means" refers to the means for evaluating the work content and work activity records generated by generative AI.

[1756] "Feedback measures" refer to measures for providing points for reflection, reflection, and improvement based on evaluation measures.

[1757] "Machinery" refers to automated devices and robots used to perform work within a factory.

[1758] "Work efficiency" refers to an index that indicates how much work a machine or device can complete within a certain amount of time.

[1759] "Precision" refers to an indicator of the accuracy and smallness of error when a machine or device performs its work.

[1760] "Areas for improvement" refers to specific methods and means proposed based on the evaluation results to improve work efficiency and accuracy.

[1761] A system for implementing this invention includes a generative AI means for automatically recording work content and work activities, an evaluation means for evaluating the generated records of work content and work activities, a feedback means for providing points for reflection, review, and improvement based on the evaluation means, and a means for evaluating the work efficiency and accuracy of machinery and equipment used in work within a factory and providing feedback on points for improvement.

[1762] The server automatically records work content and work activities using generative AI means. The generative AI means monitors the progress of work and work content in real time and collects data. The collected data is analyzed by evaluation means, and work efficiency and accuracy are evaluated.

[1763] The evaluation means calculates performance indicators such as work time and error rate based on the collected data, thereby quantifying the work efficiency and accuracy of the machine and obtaining evaluation results.

[1764] The feedback mechanism generates specific improvement suggestions based on the evaluation results. For example, if a task takes a long time, it suggests optimizing the motion path or calibrating the tool. If the error rate is high, it identifies the cause of the error and suggests how to correct it.

[1765] As a concrete example, feedback can be obtained by inputting the following prompt sentences into a generative AI model:

[1766] Example prompt sentence:

[1767] A factory robot performed a part assembly task. The task took 15 seconds and resulted in two errors. Please rate its performance and provide feedback on areas for improvement.

[1768] In response to this prompt, the generative AI model provides the following feedback:

[1769] Examples of feedback generated:

[1770] Performance Score: 50

[1771] Improvement Needed:

[1772] Reduce task time. Consider optimizing the movement path.

[1773] Reduce errors. Check the calibration of the tools.

[1774] The system is implemented using Python programming. The hardware used includes factory robots and sensors, and the software includes Python and an evaluation system. This makes it possible to evaluate the work efficiency and accuracy of machinery in real time and quickly provide feedback on specific improvement suggestions.

[1775] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1776] Step 1:

[1777] The server automatically records work content and activities using generative AI methods. Specifically, it collects work data (such as work time and number of errors) from factory robots in real time and stores it in a database. The input is sensor data from the factory robots, and the output is work records stored in the database.

[1778] Step 2:

[1779] The server analyzes the collected data using the evaluation tools. Specifically, it calculates performance indicators such as work time and number of errors, and evaluates work efficiency and accuracy. The input is the work records stored in the database, and the output is the evaluation results (performance scores, etc.).

[1780] Step 3:

[1781] The server generates specific improvement suggestions using feedback means based on the evaluation results. Specifically, it analyzes the evaluation results and suggests optimizing the operation path if the task time is long, or suggests tool calibration if the error rate is high. The input is the evaluation results, and the output is feedback including improvement suggestions.

[1782] Step 4:

[1783] The server sends the generated feedback to the factory robot's management system. Specifically, it generates the feedback content in text format and notifies the management system. The input is the feedback including the improvement suggestions, and the output is the feedback notification sent to the management system.

[1784] Step 5:

[1785] The user checks the feedback through the management system and makes any necessary improvements. Specifically, the user checks the feedback and optimizes the motion path or calibrates the tool. The input is the feedback displayed on the management system, and the output is improved work efficiency and accuracy.

[1786] 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.

[1787] "Example 1"

[1788] One embodiment of the present invention provides a system including an emotion engine that recognizes the emotions of workers. In this system, a generative AI not only automatically records the work content and work activities of workers, but also simultaneously records the worker's emotional state. The emotion engine estimates the worker's emotional state from the worker's tone of voice, facial expression, choice of words, etc. Specifically, the emotion engine estimates the worker's emotional state from the worker's tone of voice when operating business tools, facial expressions during video conferences, choice of words in chat tools, etc.

[1789] "Example 2"

[1790] Furthermore, the generative AI reflects the emotional state of the worker estimated by the emotion engine in the daily report. Specifically, the emotional state of the worker on that day, such as when the worker is feeling happy, when they are facing difficulties, when they are feeling stressed, etc., is recorded in the daily report. This allows the worker and their superiors to understand not only the work content but also the emotional state of the worker. "Example 3"

[1791] Furthermore, the feedback means provides feedback based not only on the evaluation results of the work content by the evaluation means, but also on the estimation results of the emotional state by the emotion engine. Specifically, when the worker is feeling stressed, advice on how to reduce stress is provided. Also, when the worker is feeling joy, the source of that joy is analyzed and advice on how to achieve the same joy is provided. This enables more appropriate feedback that takes into account the worker's emotional state.

[1792] The processing flow of each embodiment will be described below.

[1793] "Example 1"

[1794] Step 1: The worker interacts with the tools they use. This interaction may reflect their emotional state, such as tone of voice, facial expression, and choice of words.

[1795] Step 2: The emotion engine estimates the worker's emotional state from factors such as the worker's tone of voice, facial expressions, and choice of words.

[1796] Step 3: The generative AI automatically records the worker's work content and activities, along with the worker's emotional state estimated by the emotion engine.

[1797] "Example 2"

[1798] Step 1: Generative AI automatically records the work content and work activities of employees.

[1799] Step 2: The emotion engine estimates the worker's emotional state.

[1800] Step 3: The generative AI reflects the emotional state of the employee estimated by the emotion engine in the daily report.

[1801] "Example 3"

[1802] Step 1: The evaluation instrument evaluates the job content.

[1803] Step 2: The emotion engine estimates the worker's emotional state.

[1804] Step 3: The feedback means provides feedback based on the evaluation results of the work content by the evaluation means and the estimation results of the emotional state by the emotion engine.

[1805] Example 1

[1806] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1807] Conventional business record systems could automatically record the work content and activities of employees, but were unable to simultaneously record their emotional state. This made it difficult to provide feedback or suggest improvements that took into account the employee's psychological state. Furthermore, work content records were rarely automatically generated as daily reports, placing a heavy burden on employees. To solve these issues, a system that simultaneously records work content and emotional state and automatically generates daily reports is needed.

[1808] 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.

[1809] In this invention, the server includes generative AI means for automatically recording work content and work activities, evaluation means for evaluating the records of work content and work activities generated by the generative AI, feedback means for providing points for reflection, review, and improvement based on the evaluation means, emotion engine means for estimating the emotional state of the worker, and means for recording the emotional state estimated by the emotion engine means. This makes it possible to simultaneously record work content and emotional state and automatically generate a daily report.

[1810] "Generative AI methods" are artificial intelligence methods that automatically record work content and work activities and generate them as daily reports.

[1811] "Evaluation means" refers to a means for evaluating the work content and work activity records generated by generative AI.

[1812] "Feedback measures" are means for providing points for reflection, reflection, and improvement based on evaluation measures.

[1813] The "emotion engine means" is a means for estimating the emotional state of a worker.

[1814] The "recording means" is a means for recording the emotional state estimated by the emotion engine means.

[1815] MODE FOR CARRYING OUT THE INVENTION

[1816] This invention is a system that automatically records the work content and work activities of employees and generates a daily report. Furthermore, by estimating and recording the employee's emotional state, it is possible to provide more detailed feedback. This system includes elements such as a server, a terminal, and a user.

[1817] 1. Program Generation

[1818] The server automati...

Claims

1. A means for collecting operation logs and input data generated in response to operations on a business tool or system; A means for identifying the content of a business performed using the business tool or the system by analyzing the collected operation log and input data; A means for generating a daily report based on the identified work content; A system including:

2. The operation log and the input data are transmitted from a terminal device used by a user who performed the task, The daily report is delivered to the user who performed the task. The system of claim 1 .

3. A means for acquiring business data indicative of business content or business activities; A means for generating a daily report using a generative AI model based on the business data; A means for extracting achievement levels and problems based on the generated daily reports and generating improvement proposals; A system including:

Images