system

Abstract

Provide a system. A means for a user to input data relating to management tasks; A means for transmitting input data from the terminal to a server; A means for analyzing the data received by the server and extracting features to be input into an AI model for generating automation rules for management tasks; a means for the server to perform management tasks based on the generated automation rules; A system that includes a means to collect user feedback and retrain the AI ​​model.

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] Many employees are overwhelmed with administrative tasks on a daily basis, leaving them with no time to focus on their creative work. In particular, routine tasks such as operational reporting and data entry are a major burden, leading to a decline in productivity. There is a need for a system that streamlines these tasks and allows employees to focus on more valuable work. [Means for solving the problem]

[0005] This invention provides a means for users to input data related to management tasks and send that data to a server. The server then analyzes the received data and extracts the features necessary to generate automation rules for the management tasks. The server then provides a means to execute the management tasks based on the generated automation rules. It also collects feedback from users and retrains the AI ​​model based on this feedback to continuously improve the system. This frees employees from the tedious daily management tasks and creates an environment where they can focus on more creative work.

[0006] A "user" is a person or role that operates the system and inputs data.

[0007] A "terminal" is an electronic device that allows a user to input data and communicate with a server.

[0008] A "server" is a computer system that receives data sent from a terminal and performs analysis and automated processing.

[0009] "Data" refers to information related to administrative tasks entered by users and input information for processing by the server.

[0010] "Analysis" is the process by which the server extracts useful information and identifies patterns from the data it receives.

[0011] "Features" are the specific data points and attributes that an AI model needs to generate rules for automating administrative tasks based on data.

[0012] "AI Model" means an artificial intelligence algorithm or system used to generate automation rules for administrative tasks based on data analysis.

[0013] "Automation rules" are instructions and rules generated by the server to automatically perform administrative tasks that would otherwise be performed manually.

[0014] "Administrative tasks" refers to operational tasks such as progress reporting, data entry, and monitoring and implementation of business processes.

[0015] "Feedback" refers to the opinions, improvements, and evaluation information provided by a user to an automated system.

[0016] "Retraining" is the process of updating an AI model based on feedback to improve its accuracy and performance. [Brief explanation of the drawings]

[0017] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0038] The system of the present invention begins when a user inputs data related to management tasks and sends that data to a server. The terminal is responsible for sending the data received from the user to the server. The server analyzes the received data and extracts the features necessary to automate the management tasks. The server then uses an AI model to generate automation rules for the management tasks and executes the automation process based on those rules. The system also continuously improves by collecting feedback from users and retraining the AI ​​model.

[0039] Data collection and input

[0040] A user uses a terminal to input data related to management tasks. For example, when a user reports the progress of a project, he or she inputs "Project A is 40% complete" on the terminal. This data is sent from the terminal to the server.

[0041] Data analysis

[0042] The server analyzes the data received from the terminal. For example, it analyzes the patterns of reports made at specific times or with specific frequency based on the progress report history stored in the database. This analysis identifies routine management task patterns.

[0043] Utilizing AI models

[0044] The server extracts features based on data analysis and inputs them into the AI ​​model. For example, the feature values ​​extracted include the user's reporting time, project progress, and information about the person in charge. Based on these features, the AI ​​model generates automation rules for management tasks. Rules such as "automatically check progress reports at 9:00 and 17:00 every day and send reports to the supervisor" are generated here.

[0045] Executing the automation

[0046] The user checks the generated automation rules on the terminal and approves them if there are no problems. For example, by checking an automatically generated report and clicking the "Approve" button, the server executes the automated process based on the rule. Every day at 9:00 and 17:00, a progress report is automatically generated and sent to the relevant supervisor by email.

[0047] Feedback and Improvements

[0048] The server collects the results of the automated process and stores them in a database. The user uses a device to enter feedback on the format and content of the generated report. For example, the user may provide feedback such as, "Please improve the format of the report." This feedback is sent to the server and used to retrain the AI ​​model. The server then uses the feedback to improve the AI ​​model, thereby increasing the accuracy and efficiency of future automated processes.

[0049] As a concrete example, suppose a user needs to report project progress every day at 9:00 and 17:00. The user accesses a terminal and enters, "Project A progress is 40%." The terminal sends this data to a server, which analyzes the data and identifies common patterns. Based on the identified patterns, an AI model generates a rule that states, "Check and report progress every day at 9:00 and 17:00." Once the generated rule is confirmed and approved by the user, the server automatically executes the management task at the specified time every day. As a result, the user is freed from reporting tasks and can focus on more important tasks.

[0050] The processing flow will be explained below.

[0051] Step 1: Data collection and entry

[0052] Action 1-1: A user uses a terminal to input data related to management operations.

[0053] Example: A user types into a terminal, "Project A is 40% complete."

[0054] Operation 1-2: The terminal transmits the input data to the server.

[0055] Example: The device sends input data in JSON format as a POST request to the server's API endpoint.

[0056] Step 2: Data analysis

[0057] Operation 2-1: The server receives the data sent from the terminal and stores it in a database.

[0058] Example: The server stores the received progress data in a "progress report" table in a MySQL database.

[0059] Action 2-2: The server analyzes the stored data.

[0060] Example: The server runs a query based on historical progress report data to analyze patterns in the time and frequency of reports.

[0061] Step 3: Feature extraction

[0062] Action 3-1: The server extracts features from the analysis data.

[0063] Example: The server extracts features such as reporting time, progress percentage, and project name.

[0064] Operation 3-2: The server inputs the extracted features into the AI ​​model.

[0065] Example: Convert features into tensor format and input them into an AI model.

[0066] Step 4: Leveraging AI models

[0067] Action 4-1: The server uses the AI ​​model to generate automation rules.

[0068] Example: An AI model generates a rule that says, "Check and report progress every day at 9:00 and 17:00."

[0069] Action 4-2: The server verifies the generated rules and makes corrections if necessary.

[0070] Example: The server checks the validity of the rules and manually corrects them if necessary.

[0071] Step 5: Verify and run your automation

[0072] Action 5-1: The user checks the automation rules generated on the terminal.

[0073] Example: A user checks an automatically generated report on their device and clicks the "Approve" button.

[0074] Operation 5-2: The server receives user approval and executes management tasks based on automated rules.

[0075] Example: Every day at 9:00 and 17:00, the server automatically generates a progress report and emails it to the manager.

[0076] Step 6: Gather feedback and retrain

[0077] Action 6-1: The server collects the results of the automated processing.

[0078] Example: Storing the sending history of automatically generated reports in a database.

[0079] Action 6-2: The user uses the device to provide feedback.

[0080] Example: A user enters feedback from a terminal saying, "Please improve the report format."

[0081] Action 6-3: The server retrains the AI ​​model based on the feedback.

[0082] Example: Adding feedback to a training dataset and retraining an AI model.

[0083] This frees users from the hassle of daily management tasks and allows them to focus on more creative work.

[0084] Example 1

[0085] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0086] Traditional management tasks required tedious manual data entry and report creation, requiring a great deal of effort and time. These manual tasks were prone to errors, reducing work efficiency. Furthermore, creating and executing automation rules in existing systems was time-consuming, making it difficult for users to execute business processes quickly and accurately. To solve these issues, automation and streamlining of management tasks was necessary.

[0087] 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.

[0088] In this invention, the server includes means for analyzing received information and extracting features to be input into a generative AI model for generating automation rules for business processes, means for executing business processes based on the generated automation rules, and means for acquiring progress information at certain time periods and sending automatically generated reports. This reduces the amount of manual work required by users, providing an environment where users can focus on important tasks.

[0089] "Information" refers to data that expresses the content of a user's business.

[0090] A "terminal" is a device that allows a user to input information, and includes, for example, a computer or a smartphone.

[0091] A "server" is a computer system that receives information sent from a terminal and analyzes and processes it.

[0092] "Analyzing" is the process of analyzing received information to understand its structure and content.

[0093] A "generative AI model" is an artificial intelligence algorithm that generates business automation rules based on large amounts of data.

[0094] "Features" are important data elements or attributes that are extracted for input into a generative AI model.

[0095] "Automation rules" are a set of rules and procedures established to efficiently automate business processes.

[0096] A "report" is a document summarizing the progress and results of work, and is usually sent to other parties.

[0097] "Feedback" refers to improvements and ratings provided by users to the server, which are used to improve the system.

[0098] The system of the present invention begins when a user inputs information about a task and sends it from their terminal to a server. The terminal is a device operated by the user and serves to transmit information. The server analyzes the information received from the terminal and generates automation rules using a generative AI model.

[0099] Specifically, the server uses programming languages ​​such as Python or R to analyze the received information. Furthermore, machine learning libraries such as Scikit-learn and TENSORFLOW (registered trademark) are used as the generative AI model. Based on the results of this analysis, the server extracts features and inputs them into the AI ​​model to generate automation rules. Operations are then automated based on the generated rules, and reports are sent to the user.

[0100] For example, if a user types "Project A is 40% complete," that information is sent to the server. The server analyzes past progress data and the user's reporting patterns. The AI ​​model then generates a rule that says, "Check progress reports every day at 9:00 and 17:00 and send reports to your supervisor."

[0101] Additionally, users can use their devices to provide feedback on the format and content of the generated report, such as "Please improve the format of the report." This feedback is sent to the server and used to retrain the AI ​​model, improving the accuracy and efficiency of future automated processes.

[0102] An example of a prompt is as follows:

[0103] "Users need to report on project progress daily. Can you explain how to automate this reporting?"

[0104] "Please explain in detail the steps in your system that analyzes business data and generates automated rules."

[0105] "Please tell me how the AI ​​model works to automatically generate a progress report and send it to my boss at a fixed time every day."

[0106] This automates tasks that users previously performed manually, providing an environment in which users can focus on important tasks.

[0107] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0108] Step 1:

[0109] The user uses the terminal to input information about the business.

[0110] Specifically, the user inputs into the terminal, "Project A is 40% complete."

[0111] Input: Information about the job entered by the user.

[0112] Output: Data of information entered into the terminal.

[0113] Step 2:

[0114] The terminal transmits the input information to the server.

[0115] The device sends information to the server using an HTTP POST request.

[0116] Input: Data of information entered into the device.

[0117] Output: The data of the information sent to the server.

[0118] Step 3:

[0119] The server analyzes the received information.

[0120] The server uses Python or R to analyze the incoming data and references a database to understand its meaning.

[0121] Input: The data of the information sent to the server.

[0122] Output: Parsed data.

[0123] Step 4:

[0124] The server extracts features from the analyzed data.

[0125] The server uses machine learning libraries such as Scikit-learn and TensorFlow to extract important features from the data, such as user ID, reporting time, and progress.

[0126] Input: Parsed data.

[0127] Output: Extracted features.

[0128] Step 5:

[0129] The server inputs features into the generated AI model and generates automation rules.

[0130] The server inputs the extracted features into an AI model and generates rules such as "check progress reports every day at 9:00 and 17:00 and automatically send the results to the supervisor."

[0131] Input: Extracted features.

[0132] Output: The generated automation rule.

[0133] Step 6:

[0134] The user checks the generated automation rules and approves them from the terminal.

[0135] The user checks the automation rules on the device's confirmation screen and clicks the "Approve" button.

[0136] Input: The generated automation rule.

[0137] Output: The approved automation rule.

[0138] Step 7:

[0139] The server executes tasks based on the approved automation rules.

[0140] The server retrieves the latest progress information at the specified time and sends an automatically generated report to the superior via the mail server.

[0141] Input: Approved automation rules.

[0142] Output: Report sent to supervisor.

[0143] Step 8:

[0144] The server records the results of the automated process and collects user feedback.

[0145] The server stores the processing results in a database, and the user inputs feedback on the format and content of the report through the terminal, such as "Please improve the format of the report."

[0146] Input: The report you wish to provide feedback on.

[0147] Output: Collected feedback data.

[0148] Step 9:

[0149] The server retrains the generative AI model based on the collected feedback.

[0150] The collected feedback is used to adjust the AI ​​model to improve the accuracy and efficiency of future automated processes.

[0151] Input: Collected feedback data.

[0152] Output: The retrained generative AI model.

[0153] (Application example 1)

[0154] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0155] Factory production management requires a lot of manual work, such as reporting production progress and checking production line efficiency, which creates the risk of reduced efficiency and human error.In addition, it is difficult to detect abnormalities on the production line early and take appropriate measures, which affects overall production efficiency, creating an issue.

[0156] 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.

[0157] In this invention, the server includes: a means for a user to input data related to management tasks; a means for a terminal to send the input data to the server; a means for the server to analyze the received data and extract features to be input into an AI model for generating automation rules for management tasks; a means for the server to execute management tasks based on the generated automation rules; a means for collecting feedback from users and retraining the AI ​​model; a means for the terminal to report factory production progress; a means for the server to generate automation rules based on the reports and for a robot to check production line efficiency. This automates the reporting of production progress and the checking of production line efficiency, making it possible to detect efficiency declines early and take measures.

[0158] "User" means a person or entity that utilizes the system to input data related to administrative tasks.

[0159] "Management work" refers to tasks such as reporting production progress at production sites such as factories, checking the efficiency of production lines, and inventory management.

[0160] A "terminal" is a device used by a user to input data and send it to a server, such as a smartphone or tablet.

[0161] The "server" is a computer system that analyzes the received data and operates an AI model to generate automation rules for administrative tasks.

[0162] "Features" refer to important information and patterns of management operations that are extracted through data analysis and input into the AI ​​model.

[0163] "AI Model" means a machine learning model used to generate rules for automating administrative tasks based on received data.

[0164] "Automation rules" are specific procedures and rules generated using AI models to efficiently execute management tasks.

[0165] "Feedback" refers to opinions and requests for improvement provided by users regarding the results of automated processing, and is information used to retrain AI models.

[0166] "Production progress" is data that indicates the progress and completion status of production lines in a factory.

[0167] A "robot" is a mechanical device that can receive commands from a server to check the efficiency of a production line and take necessary improvement measures.

[0168] This invention is a system for automating production management tasks in a factory, and begins when a user inputs data related to the management tasks and a terminal transmits the data to a server. Specific embodiments are described below.

[0169] Users use devices such as smartphones and tablets to input data on production progress and production line efficiency. For example, they may report that "production progress on line A is 80% of normal." The input data is then sent from the device to the server.

[0170] The server analyzes the received data and extracts the features necessary to generate automation rules for management tasks. These features include the degree of production progress, production line information, and information about the person in charge. This data is then input into a machine learning model (AI model).

[0171] The AI ​​model generates automation rules for management tasks based on the received features. For example, it generates a rule such as "Check production progress every day at 9:00 and 17:00, and take immediate action if any abnormalities are found." The generated rules are then applied to the automation of management tasks by the server.

[0172] The user can review the generated automation rules and approve them as necessary. This approval prepares the server to perform the actual management tasks. For example, the user can click the "Approve" button on their smartphone to officially apply the automation rules.

[0173] The server executes management tasks based on automation rules. Specifically, it sends commands to the robot to check the efficiency of the production line and detect abnormalities. The robot then inspects the production line according to the server's instructions and takes necessary corrective measures.

[0174] In addition, the server collects feedback from users and uses it to retrain the AI ​​model. For example, if a user provides feedback such as "Please improve the report format," that information is sent to the server and used to improve the accuracy of the AI ​​model.

[0175] As a concrete example, consider a case where a user needs to report production progress every day at 9:00 and 17:00. The user accesses a terminal and enters, "Production progress on Line A is 80% of normal." The terminal sends this data to a server, which analyzes the data and identifies common patterns. Based on the identified patterns, an AI model generates a rule that states, "Confirm and report progress every day at 9:00 and 17:00." Once the generated rule is confirmed and approved by the user, the server automatically executes the management task at the specified time every day. As a result, the user is freed from reporting tasks and can focus on more important tasks.

[0176] The hardware used includes smartphones and tablets for users to input data, a server that receives and analyzes the data, and factory robots that operate based on instructions.Software used includes Python for data analysis, the machine learning library Scikit-learn, and Flask for robot control.

[0177] An example of a prompt is as follows:

[0178] "Production progress on Line A is at 80% of normal. Please investigate the cause of the decrease in efficiency."

[0179] "Line B efficiency is normal. No special improvements are required."

[0180] In this way, the present invention makes it possible to improve the efficiency of production management operations in factories, reduce human error, and detect abnormalities in the production line early and take measures to correct them.

[0181] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0182] Step 1:

[0183] The user uses a terminal to input data related to management tasks. Specifically, they use a smartphone or tablet to input information such as production progress and production line efficiency. They input prompt statements such as "Production progress on line A is 80% of normal." The input data is temporarily saved in the terminal.

[0184] Input: Production progress data entered by the user into a smartphone or tablet

[0185] Output: Temporarily saved production progress data

[0186] Step 2:

[0187] The device sends the entered data to the server. The device converts the entered data into an appropriate format and sends it to the server's API endpoint. The sent data is received on the server side.

[0188] Input: Temporarily saved production progress data

[0189] Output: Production progress data sent to the server

[0190] Step 3:

[0191] The server analyzes the received data and extracts features. Specifically, it extracts important information (e.g., progress level, production line, person in charge) from the received production progress data. Machine learning libraries such as Python and Scikit-learn are used for the analysis.

[0192] Input: Production progress data sent to the server

[0193] Output: Extracted features (progress, production line information, etc.)

[0194] Step 4:

[0195] The server inputs the extracted features into an AI model and generates automation rules. The AI ​​model has been retrained in advance based on feedback, so it analyzes the input data and generates appropriate automation rules for management tasks. For example, the generated rules might be something like, "Check production progress every day at 9:00 and 17:00, and take immediate action if any abnormalities are found."

[0196] Input: extracted features

[0197] Output: Generated automation rules

[0198] Step 5:

[0199] The server notifies the user of the generated automated rule, and the user reviews and approves the rule. The user receives a notification on their smartphone or tablet, checks the rule, and approves it by clicking the "Approve" button.

[0200] Input: Generated automation rules

[0201] Output: User approval

[0202] Step 6:

[0203] With the user's approval, the server executes management tasks based on automation rules. For example, it can issue instructions to robots to check the efficiency of the production line or take measures to deal with abnormalities. The robots receive instructions from the server, inspect the production line, and take necessary corrective measures.

[0204] Input: User approval

[0205] Output: Instructions to the robot and execution results

[0206] Step 7:

[0207] The server collects the results of the automated processing and collects feedback from users based on those results. For example, users can input their opinions or requests, such as "Please improve the report format," into their smartphones or tablets, and the input is sent to the server.

[0208] Input: Results of automated processing

[0209] Output: User feedback

[0210] Step 8:

[0211] The server retrains the AI ​​model based on the feedback, and uses the collected feedback data to refine the AI ​​model, improving the accuracy and efficiency of the automation rules for future management tasks.

[0212] Input: User feedback

[0213] Output: Retrained AI model

[0214] In this way, the automation of factory production management operations is efficiently realized through cooperation between the server, terminals, and users.

[0215] 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.

[0216] The system of the present invention begins when a user inputs data related to management tasks and sends that data to a server. The terminal is responsible for sending the data received from the user to the server. The server analyzes the received data and extracts the features necessary to automate the management tasks. The server uses an AI model to generate automation rules for the management tasks and executes the automation process based on those rules. The system also continuously improves by collecting feedback from users and retraining the AI ​​model.

[0217] Furthermore, the present invention incorporates an emotion engine that recognizes emotions from user input data and feedback. The emotion engine analyzes the user's emotional state in real time and adjusts the automation rules generated by the AI ​​model based on the analysis results. This provides more personalized automation rules that take the user's emotional state into account.

[0218] Data collection and input

[0219] A user uses a terminal to input data related to management tasks. For example, when reporting the progress of a project, the user inputs "Project A is 40% complete" on the terminal. This data is sent from the terminal to the server. At the same time, the terminal runs an emotion engine to analyze the user's emotions from the input and feedback.

[0220] Data analysis and sentiment analysis

[0221] The server receives the data sent from the device and stores it in a database. For example, when the server analyzes progress report data, the emotion engine also analyzes the user's input data and feedback to identify the user's emotional state. Based on the results, the server extracts features to generate automation rules for management tasks.

[0222] Utilizing AI models

[0223] The server extracts features based on data analysis and sentiment analysis and inputs them into the AI ​​model. For example, the user's reporting time, progress percentage, project name, and emotional state are extracted as features. The AI ​​model generates rules for automating management tasks based on these features. In addition to the rule "check and report progress every day at 9:00 and 17:00," adjustments based on emotions are made, such as "reduce reminders if the user is feeling stressed."

[0224] Check and run your automation

[0225] The user checks the generated automation rules on their device and approves them if there are no problems. For example, by checking an automatically generated report and clicking the "Approve" button, the server executes the automated process based on the rules. Progress reports are automatically generated every day at 9:00 and 17:00 and are emailed to the relevant supervisor. Adjustments are also made according to the user's emotional state.

[0226] Gathering feedback and retraining

[0227] The server collects the results of the automated process and stores them in a database. The user uses a device to input feedback about the format and content of the generated report. For example, the user may provide feedback such as, "Please improve the format of the report." This feedback is sent to the server and used to retrain the AI ​​model along with emotion data from the emotion engine. The server uses the feedback to improve the AI ​​model, thereby increasing the accuracy and efficiency of future automated processes.

[0228] As a concrete example, suppose a user needs to report project progress every day at 9:00 AM and 5:00 PM. The user enters "Project A is 40% complete" into their device. The device sends this data to a server, which analyzes the data and identifies common patterns. At the same time, an emotion engine analyzes the user's input and feedback and identifies that the user is feeling stressed. Based on this result, an AI model generates a rule that states, "Confirm and report progress every day at 9:00 AM and 5:00 PM, but reduce reminders to reduce user stress." Once the user confirms and approves the generated rule, the server automatically executes the management task at the specified time every day. As a result, the user is freed from reporting tasks, allowing them to focus on more important tasks and reducing their emotional burden.

[0229] The processing flow will be explained below.

[0230] Step 1: Data collection and entry

[0231] Action 1-1: A user uses a terminal to input data related to management operations.

[0232] Example: A user types into a terminal, "Project A is 40% complete."

[0233] Operation 1-2: The terminal transmits the input data to the server.

[0234] Example: The device sends input data in JSON format as a POST request to the server's API endpoint.

[0235] Action 1-3: The device analyzes the user's facial expressions, input speed, etc. and sends the results to the emotion engine.

[0236] Example: Sending user facial expression data captured by a camera to an emotion engine.

[0237] Step 2: Data analysis and sentiment analysis

[0238] Operation 2-1: The server receives the data sent from the terminal and stores it in a database.

[0239] Example: The server stores the received progress data in a "progress report" table in a MySQL database.

[0240] Action 2-2: The server analyzes the stored data.

[0241] Example: The server runs a query based on historical progress report data to analyze patterns in the time and frequency of reports.

[0242] Action 2-3: The emotion engine analyzes the transmitted data and identifies the user's emotional state.

[0243] Example: An emotion engine analyzes facial expression data and determines that the user is stressed.

[0244] Step 3: Feature extraction

[0245] Action 3-1: The server extracts features from the analysis data.

[0246] Example: The server extracts features such as reporting time, progress percentage, project name, and user emotional state.

[0247] Operation 3-2: The server inputs the extracted features into the AI ​​model.

[0248] Example: Convert the extracted features into tensor format and input them into an AI model.

[0249] Step 4: Leveraging AI models

[0250] Action 4-1: The server uses the AI ​​model to generate automation rules.

[0251] Example: An AI model generates a rule that says, "Check and report progress every day at 9:00 and 17:00, but reduce reminders if the user is feeling stressed."

[0252] Action 4-2: The server verifies the generated rules and makes corrections if necessary.

[0253] Example: The server checks the validity of the rules and manually corrects them if necessary.

[0254] Step 5: Verify and run your automation

[0255] Action 5-1: The user checks the automation rules generated on the terminal.

[0256] Example: A user checks an automatically generated report on their device and clicks the "Approve" button.

[0257] Operation 5-2: The server receives user approval and executes management tasks based on automated rules.

[0258] Example: Every day at 9:00 and 17:00, the server automatically generates a progress report and emails it to the manager, adjusting the frequency of reminders based on the user's emotional state.

[0259] Step 6: Gather feedback and retrain

[0260] Action 6-1: The server collects the results of the automated processing.

[0261] Example: Storing the submission history of automatically generated reports or the user's emotional state in a database.

[0262] Action 6-2: The user uses the device to provide feedback.

[0263] Example: A user enters feedback from a terminal saying, "Please improve the report format."

[0264] Action 6-3: The server retrains the AI ​​model based on the feedback.

[0265] Example: Adding feedback and emotional states to a training dataset and retraining an AI model.

[0266] In this way, the system of the present invention automates administrative tasks while taking into account the user's emotional state, freeing the user from tedious tasks and providing an environment in which they can concentrate on more creative tasks.

[0267] Example 2

[0268] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0269] Conventional management task systems required users to manually input information and perform management tasks each time, resulting in reduced work efficiency. Furthermore, automation rules were generated without taking the user's emotional state into consideration, which could cause stress for the user and lead to poor work performance. Furthermore, there was an insufficient mechanism for effectively collecting feedback and utilizing it to improve the system.

[0270] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for recognizing emotions from user input information and feedback and including them in features, a means for extracting features to be input into a generative AI model for generating automation rules for management tasks, and a means for executing management tasks based on the automation rules. This makes it possible to generate and execute automation rules for management tasks taking into account the user's emotional state, thereby improving work efficiency and user satisfaction.

[0271] A "user" is an entity that inputs information related to management tasks and operates the system.

[0272] A "terminal" is a device for transmitting information entered by a user to a server.

[0273] A "server" is a computer system that receives and analyzes information sent by users, and generates and executes rules for automating administrative tasks.

[0274] "Information" refers to data and feedback about administrative tasks entered by users.

[0275] The "means for recognizing emotions and including them in features" refers to a device or software function that analyzes the emotional state from the user's input information and feedback and extracts the results as features.

[0276] A "generative AI model" is an artificial intelligence algorithm that generates optimal automation rules for management tasks based on input features.

[0277] "Features" are parameters or elements used in data analysis, and are the basic data used to generate automation rules for management tasks.

[0278] "Automation rules" are a series of actions and procedures that the server creates based on the generative AI model to perform management tasks.

[0279] "Feedback" refers to opinions, evaluations, and information on areas for improvement provided by users.

[0280] The system of the present invention starts when a user inputs information about a management task and sends that information to a server. A specific embodiment of this system will be described below.

[0281] A user uses a terminal to input information related to management tasks. For example, when a user reports on the progress of a project, they input text data such as "Project A is 40% complete" into the terminal. The terminal detects the input information and activates the emotion engine. The emotion engine analyzes the user's input status and feedback to recognize the user's emotional state. This makes it possible to obtain the user's stress level and emotional state as analysis results.

[0282] The device sends the input information and emotion analysis results to the server, which receives this information and stores it in a database. The server uses data processing libraries such as Python's Pandas and NumPy to analyze the stored information. This analysis identifies trends and patterns in the progress reports, and uses the emotion engine's analysis results to extract the user's emotional state as features.

[0283] The extracted features are input into an AI model on the server. The AI ​​model is built using machine learning libraries such as TensorFlow and PyTorch, and generates optimal automation rules for management tasks based on the features. For example, it might generate rules such as "check and report progress every day at 9:00 and 17:00" or "reduce reminders if the user is feeling stressed."

[0284] The server sends the generated automation rules to the user's device, where the user can review them. If the user determines that the rules are acceptable, they can click the "Approve" button, and the server will automatically execute management tasks based on the rules. For example, progress reports will be automatically generated at 9:00 and 17:00 every day and emailed to the relevant supervisor. Adjustments will also be made based on the user's emotional state.

[0285] Additionally, the user can use the device to input feedback on the format and content of the automatically generated report. For example, the user may provide feedback such as, "Please improve the format of the report." The device then sends this feedback along with emotion data to the server, which stores it in a database. The server then retrains the AI ​​model based on the feedback and emotion data from the emotion engine, improving the accuracy and efficiency of future automated processes.

[0286] As a concrete example, consider a situation where a user needs to report project progress every day at 9:00 and 17:00. The user enters "Project A progress is 40%" into the device, and the device sends this data to the server. At the same time, the emotion engine runs and identifies that the user is feeling stressed. Based on this result, the AI ​​model generates a rule that states, "Progress checks and reports will be performed every day at 9:00 and 17:00, but with fewer reminders to reduce the user's stress." Once the generated rule is confirmed and approved by the user, the server automatically executes the management tasks at the specified time every day.

[0287] An example of a prompt sentence is the text data, "Project A is 40% complete." This system frees users from reporting tasks, allowing them to focus on important tasks and reducing emotional burden.

[0288] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0289] Step 1:

[0290] The user inputs information about management tasks. For example, "Project A is 40% complete" into the terminal. This input information is captured as data on the terminal. At the same time, the terminal activates the emotion engine. The emotion engine analyzes the user's input and recent feedback to recognize the user's emotional state.

[0291] Input: Administrative information entered by the user (e.g., "Project A is 40% complete").

[0292] Output: Analysis of the user's input information and emotional state.

[0293] Specific behavior:

[0294] The device retrieves the information entered in the text field and performs emotion analysis by calling the emotion engine via an API call.

[0295] Step 2:

[0296] The device sends the user's input information and emotion analysis results to the server using HTTP or HTTPS as the communication protocol.

[0297] Input: Analysis of the user's input information and emotional state.

[0298] Output: Data sent to the server.

[0299] Specific behavior:

[0300] The device converts the acquired input information and emotion analysis results into JSON format or similar and sends them to the server as an HTTP request.

[0301] Step 3:

[0302] The server receives the information sent from the device and stores it in a database, which stores progress report information and the user's emotional state.

[0303] Input: User input information and emotional state sent from the device.

[0304] Output: Information stored in a database.

[0305] Specific behavior:

[0306] The server parses the received data and inserts it into a database in the appropriate format, for example, by using SQL to store the data.

[0307] Step 4:

[0308] The server analyzes the stored data and extracts features. It uses data processing libraries such as Python's Pandas and NumPy to identify trends and patterns in the progress reports. At the same time, it uses the analysis results of the emotion engine to extract features that represent the user's emotional state.

[0309] Input: User input information and emotional state stored in a database.

[0310] Output: Extracted features (e.g., reporting time, progress percentage, project name, emotional state).

[0311] Specific behavior:

[0312] The server reads the data from the database, analyzes it using a data processing library, and extracts features.

[0313] Step 5:

[0314] The server inputs the features into a generative AI model, which is built using machine learning libraries such as TensorFlow and PyTorch, and generates optimal automation rules for management tasks based on the input features.

[0315] Input: Extracted features.

[0316] Output: The generated automation rule.

[0317] Specific behavior:

[0318] The server inputs the features into the generative AI model, and the model performs calculations to generate rules.

[0319] Step 6:

[0320] The server sends the generated automation rules to the user's device, where the user can check the rules.

[0321] Input: The generated automation rule.

[0322] Output: The automation rule that is displayed on the user's device.

[0323] Specific behavior:

[0324] The server converts the generated rules into JSON format and sends them to the terminal. The terminal displays the received data.

[0325] Step 7:

[0326] The user reviews and approves the generated automation rule on the device, for example by clicking the "Approve" button.

[0327] Input: The generated automation rule.

[0328] Output: User authorization information.

[0329] Specific behavior:

[0330] The user checks the rules displayed on the screen and clicks the "Approve" button. The device then sends this approval information to the server.

[0331] Step 8:

[0332] The server automatically executes administrative tasks based on approved rules, such as automatically generating progress reports at 9:00 and 17:00 every day and emailing them to relevant superiors, and also adjusts according to the user's emotional state.

[0333] Inputs: User authorization information and generated automation rules.

[0334] Output: Automatically performed administrative tasks.

[0335] Specific behavior:

[0336] The server schedules tasks based on approved rules, automatically executes administrative tasks, and notifies relevant parties of the execution results.

[0337] Step 9:

[0338] The user can enter feedback on the format and content of the automatically generated report, for example, "Please improve the format of the report."

[0339] Input: User feedback information.

[0340] Output: Feedback information data.

[0341] Specific behavior:

[0342] The device captures the feedback entered in the text field and sends it to the server.

[0343] Step 10:

[0344] The server receives the feedback, performs sentiment analysis again using the emotion engine, and stores the results in a database.The generative AI model is then retrained based on the feedback to improve the accuracy and efficiency of future automated processes.

[0345] Input: User feedback information and sentiment analysis results.

[0346] Output: The retrained generative AI model.

[0347] Specific behavior:

[0348] The server analyzes the feedback and inputs it as retraining data into the generative AI model, improving the model's accuracy.

[0349] (Application example 2)

[0350] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0351] While conventional management task automation systems are capable of analyzing data and generating automation rules, they are unable to take into account the emotions and stress levels of workers, which means that the burden on workers remains low. Furthermore, there is no means for retraining to incorporate feedback, making it difficult to continuously improve the system.

[0352] 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.

[0353] In this invention, the server includes a means for analyzing the user's emotional state using an emotion analysis engine and adjusting the automation rules generated by the AI ​​model based on the analysis results, a means for monitoring the worker's progress and emotional state in real time, and a means for collecting feedback from the user and retraining the AI ​​model, thereby enabling the generation of automation rules that take the worker's emotional state into account and the continuous improvement of the system.

[0354] "Administrative tasks" refer to tasks and procedures that allow users to efficiently carry out their daily business activities.

[0355] "Data input means" refers to the interface and functions that allow users to input information about management tasks into the terminal.

[0356] "Data transmission means" refers to a communication function for transferring input data from the terminal to the server.

[0357] "Data analysis means" refers to a processing function for analyzing data received by the server and extracting necessary information and features.

[0358] An "AI model" refers to a machine learning algorithm that learns patterns from large amounts of data and generates automated rules.

[0359] "Automation rules" refer to a set of procedures or conditions generated by an AI model to streamline administrative tasks.

[0360] An "emotion analysis engine" refers to a function that analyzes the emotional state from user input and feedback and outputs the results.

[0361] "Emotional state" refers to the emotional state of the user when entering data or providing feedback, such as stress, fatigue, or joy.

[0362] "Feedback collection means" refers to a function for collecting evaluations and opinions from users and sending that data to a server.

[0363] "Retraining tools" refers to functions that allow the AI ​​model to retrain based on collected feedback data to improve its accuracy.

[0364] "Real-time monitoring means" refers to a function for monitoring the progress and emotional state of workers in real time.

[0365] This invention is a system for improving the efficiency of factory robots and management tasks in the manufacturing industry. It generates automation rules based on data entered by the user and their emotional state, reducing the burden on workers.

[0366] System Configuration

[0367] Hardware

[0368] Devices: Smartphones, tablets, surveillance cameras in factories, etc.

[0369] Server: Cloud-based or on-premise servers for high-performance data processing.

[0370] Robot: Factory robots used on production lines.

[0371] software

[0372] Programming language: Python

[0373] Machine learning libraries: (TensorFlow, PyTorch, etc.)

[0374] Sentiment analysis engine: Natural language processing engine (e.g., IBM Watson® NLP tool)

[0375] Data Entry and Submission

[0376] Users use smartphones or tablets to input the progress of the production line, entering prompt statements such as "Production progress on Line A is 70%. Today's production work is a little tired." This data is sent to the server in real time.

[0377] Data and Sentiment Analysis

[0378] The server analyzes the received data and extracts features. Using an emotion analysis engine, it analyzes the emotional state (stress or fatigue) from the prompt text entered by the user.

[0379] Automated rule generation using AI models

[0380] The server inputs the extracted features into an AI model to generate automation rules, such as "Check progress every day at 10:00 and 16:00, but reduce reminders if the worker feels fatigued."

[0381] User approval and automatic execution

[0382] The generated automation rules are presented to the user for review and approval. Approved rules are automatically executed by the server. Progress reports are generated at the specified time and sent to the relevant supervisor.

[0383] Feedback gathering and retraining

[0384] Users can input feedback on generated reports and automation rules. Feedback such as "The timing of the report was appropriate, but please change the format" is sent to the server as data. This feedback data is used to retrain the AI ​​model, continuously improving the accuracy and efficiency of the system.

[0385] Specific examples

[0386] Suppose the user enters the following prompt:

[0387] "Production line A is 70% complete. Production work today is a little tiring."

[0388] The server receives this data and uses an emotion analysis engine to identify the emotional state of "fatigue." Based on this information, the AI ​​model generates a new automation rule: "Check progress every day at 10:00 and 16:00, but reduce reminders if the worker feels fatigued." Once the user confirms and approves this rule, the server automatically executes tasks based on this rule. This reduces the burden on workers and enables more efficient management work.

[0389] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0390] Step 1:

[0391] Data Entry and Submission

[0392] The user uses a smartphone or tablet to input the progress of the production line and their emotional state. An example input is, "Production progress on Line A is 70%. Today's production work is a little tiring." This data is saved on the device in real time and then sent to the server.

[0393] input:

[0394] Production line progress

[0395] The user's emotional state

[0396] output:

[0397] Sending data from the device to the server

[0398] Step 2:

[0399] Data reception and analysis

[0400] The server receives the progress data and emotional state data sent by the user. The server uses a data analysis engine to analyze the received data and extract important features (e.g., progress %, working time zone, emotional state).

[0401] input:

[0402] Progress data sent from the device

[0403] Emotional state data

[0404] output:

[0405] Extracted features

[0406] Step 3:

[0407] Emotion analysis

[0408] The server uses an emotion analysis engine to analyze the user's emotional state from the input data, and this analysis identifies an emotional state such as "the user is tired."

[0409] input:

[0410] User input data

[0411] output:

[0412] The user's emotional state

[0413] Step 4:

[0414] Input to AI model and rule generation

[0415] The server inputs the extracted features into a generative AI model to generate rules for automating administrative tasks. For example, specific rules such as "Check progress every day at 10:00 and 16:00, but reduce reminders if the worker feels fatigued" are generated.

[0416] input:

[0417] Extracted features

[0418] output:

[0419] Generated automation rules

[0420] Step 5:

[0421] Presenting and confirming rules

[0422] The generated automation rules are presented to the user, who can review them and click the "Approve" button if there are no problems.

[0423] input:

[0424] Generated automation rules

[0425] output:

[0426] User approval or correction requests

[0427] Step 6:

[0428] Executing automated rules

[0429] After the user approves, the server automatically executes management tasks based on the automation rules, such as automatically generating a progress report at a specified time and sending it to the relevant superior.

[0430] input:

[0431] Approved automation rules

[0432] output:

[0433] Automated administrative tasks

[0434] Step 7:

[0435] Feedback gathering and retraining

[0436] Users can input feedback about generated reports and automation rules. This feedback is sent to the server and used to retrain the AI ​​model. For example, specific feedback such as "The timing of the report was appropriate, but please change the format" can be collected.

[0437] input:

[0438] User Feedback

[0439] output:

[0440] Improved AI models improve accuracy of next automation rules

[0441] 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.

[0442] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0443] 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.

[0444] [Second embodiment]

[0445] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0446] 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.

[0447] 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).

[0448] 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.

[0449] 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.

[0450] 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).

[0451] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0452] 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.

[0453] 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.

[0454] 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.

[0455] 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.

[0456] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0457] The system of the present invention begins when a user inputs data related to management tasks and sends that data to a server. The terminal is responsible for sending the data received from the user to the server. The server analyzes the received data and extracts the features necessary to automate the management tasks. The server then uses an AI model to generate automation rules for the management tasks and executes the automation process based on those rules. The system also continuously improves by collecting feedback from users and retraining the AI ​​model.

[0458] Data collection and input

[0459] A user uses a terminal to input data related to management tasks. For example, when a user reports the progress of a project, he or she inputs "Project A is 40% complete" on the terminal. This data is sent from the terminal to the server.

[0460] Data analysis

[0461] The server analyzes the data received from the terminal. For example, it analyzes the patterns of reports made at specific times or with specific frequency based on the progress report history stored in the database. This analysis identifies routine management task patterns.

[0462] Utilizing AI models

[0463] The server extracts features based on data analysis and inputs them into the AI ​​model. For example, the feature values ​​extracted include the user's reporting time, project progress, and information about the person in charge. Based on these features, the AI ​​model generates automation rules for management tasks. Rules such as "automatically check progress reports at 9:00 and 17:00 every day and send reports to the supervisor" are generated here.

[0464] Executing the automation

[0465] The user checks the generated automation rules on the terminal and approves them if there are no problems. For example, by checking an automatically generated report and clicking the "Approve" button, the server executes the automated process based on the rule. Every day at 9:00 and 17:00, a progress report is automatically generated and sent to the relevant supervisor by email.

[0466] Feedback and Improvements

[0467] The server collects the results of the automated process and stores them in a database. The user uses a device to enter feedback on the format and content of the generated report. For example, the user may provide feedback such as, "Please improve the format of the report." This feedback is sent to the server and used to retrain the AI ​​model. The server then uses the feedback to improve the AI ​​model, thereby increasing the accuracy and efficiency of future automated processes.

[0468] As a concrete example, suppose a user needs to report project progress every day at 9:00 and 17:00. The user accesses a terminal and enters, "Project A progress is 40%." The terminal sends this data to a server, which analyzes the data and identifies common patterns. Based on the identified patterns, an AI model generates a rule that states, "Check and report progress every day at 9:00 and 17:00." Once the generated rule is confirmed and approved by the user, the server automatically executes the management task at the specified time every day. As a result, the user is freed from reporting tasks and can focus on more important tasks.

[0469] The processing flow will be explained below.

[0470] Step 1: Data collection and entry

[0471] Action 1-1: A user uses a terminal to input data related to management operations.

[0472] Example: A user types into a terminal, "Project A is 40% complete."

[0473] Operation 1-2: The terminal transmits the input data to the server.

[0474] Example: The device sends input data in JSON format as a POST request to the server's API endpoint.

[0475] Step 2: Data analysis

[0476] Operation 2-1: The server receives the data sent from the terminal and stores it in a database.

[0477] Example: The server stores the received progress data in a "progress report" table in a MySQL database.

[0478] Action 2-2: The server analyzes the stored data.

[0479] Example: The server runs a query based on historical progress report data to analyze patterns in the time and frequency of reports.

[0480] Step 3: Feature extraction

[0481] Action 3-1: The server extracts features from the analysis data.

[0482] Example: The server extracts features such as reporting time, progress percentage, and project name.

[0483] Operation 3-2: The server inputs the extracted features into the AI ​​model.

[0484] Example: Convert features into tensor format and input them into an AI model.

[0485] Step 4: Leveraging AI models

[0486] Action 4-1: The server uses the AI ​​model to generate automation rules.

[0487] Example: An AI model generates a rule that says, "Check and report progress every day at 9:00 and 17:00."

[0488] Action 4-2: The server verifies the generated rules and makes corrections if necessary.

[0489] Example: The server checks the validity of the rules and manually corrects them if necessary.

[0490] Step 5: Verify and run your automation

[0491] Action 5-1: The user checks the automation rules generated on the terminal.

[0492] Example: A user checks an automatically generated report on their device and clicks the "Approve" button.

[0493] Operation 5-2: The server receives user approval and executes management tasks based on automated rules.

[0494] Example: Every day at 9:00 and 17:00, the server automatically generates a progress report and emails it to the manager.

[0495] Step 6: Gather feedback and retrain

[0496] Action 6-1: The server collects the results of the automated processing.

[0497] Example: Storing the sending history of automatically generated reports in a database.

[0498] Action 6-2: The user uses the device to provide feedback.

[0499] Example: A user enters feedback from a terminal saying, "Please improve the report format."

[0500] Action 6-3: The server retrains the AI ​​model based on the feedback.

[0501] Example: Adding feedback to a training dataset and retraining an AI model.

[0502] This frees users from the hassle of daily management tasks and allows them to focus on more creative work.

[0503] Example 1

[0504] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0505] Traditional management tasks required tedious manual data entry and report creation, requiring a great deal of effort and time. These manual tasks were prone to errors, reducing work efficiency. Furthermore, creating and executing automation rules in existing systems was time-consuming, making it difficult for users to execute business processes quickly and accurately. To solve these issues, automation and streamlining of management tasks was necessary.

[0506] 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.

[0507] In this invention, the server includes means for analyzing received information and extracting features to be input into a generative AI model for generating automation rules for business processes, means for executing business processes based on the generated automation rules, and means for acquiring progress information at certain time periods and sending automatically generated reports. This reduces the amount of manual work required by users, providing an environment where users can focus on important tasks.

[0508] "Information" refers to data that expresses the content of a user's business.

[0509] A "terminal" is a device that allows a user to input information, and includes, for example, a computer or a smartphone.

[0510] A "server" is a computer system that receives information sent from a terminal and analyzes and processes it.

[0511] "Analyzing" is the process of analyzing received information to understand its structure and content.

[0512] A "generative AI model" is an artificial intelligence algorithm that generates business automation rules based on large amounts of data.

[0513] "Features" are important data elements or attributes that are extracted for input into a generative AI model.

[0514] "Automation rules" are a set of rules and procedures established to efficiently automate business processes.

[0515] A "report" is a document summarizing the progress and results of work, and is usually sent to other parties.

[0516] "Feedback" refers to improvements and ratings provided by users to the server, which are used to improve the system.

[0517] The system of the present invention begins when a user inputs information about a task and sends it from their terminal to a server. The terminal is a device operated by the user and serves to transmit information. The server analyzes the information received from the terminal and generates automation rules using a generative AI model.

[0518] Specifically, the server uses programming languages ​​such as Python and R to analyze the received information. Machine learning libraries such as Scikit-learn and TensorFlow are used as generative AI models. Based on the results of this analysis, the server extracts features and inputs them into the AI ​​model to generate automation rules. Tasks are then automated based on the generated rules, and reports are sent to the user.

[0519] For example, if a user types "Project A is 40% complete," that information is sent to the server. The server analyzes past progress data and the user's reporting patterns. The AI ​​model then generates a rule that says, "Check progress reports every day at 9:00 and 17:00 and send reports to your supervisor."

[0520] Additionally, users can use their devices to provide feedback on the format and content of the generated report, such as "Please improve the format of the report." This feedback is sent to the server and used to retrain the AI ​​model, improving the accuracy and efficiency of future automated processes.

[0521] An example of a prompt is as follows:

[0522] "Users need to report on project progress daily. Can you explain how to automate this reporting?"

[0523] "Please explain in detail the steps in your system that analyzes business data and generates automated rules."

[0524] "Please tell me how the AI ​​model works to automatically generate a progress report and send it to my boss at a fixed time every day."

[0525] This automates tasks that users previously performed manually, providing an environment in which users can focus on important tasks.

[0526] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0527] Step 1:

[0528] The user uses the terminal to input information about the business.

[0529] Specifically, the user inputs into the terminal, "Project A is 40% complete."

[0530] Input: Information about the job entered by the user.

[0531] Output: Data of information entered into the terminal.

[0532] Step 2:

[0533] The terminal transmits the input information to the server.

[0534] The device sends information to the server using an HTTP POST request.

[0535] Input: Data of information entered into the device.

[0536] Output: The data of the information sent to the server.

[0537] Step 3:

[0538] The server analyzes the received information.

[0539] The server uses Python or R to analyze the incoming data and references a database to understand its meaning.

[0540] Input: The data of the information sent to the server.

[0541] Output: Parsed data.

[0542] Step 4:

[0543] The server extracts features from the analyzed data.

[0544] The server uses machine learning libraries such as Scikit-learn and TensorFlow to extract important features from the data, such as user ID, reporting time, and progress.

[0545] Input: Parsed data.

[0546] Output: Extracted features.

[0547] Step 5:

[0548] The server inputs features into the generated AI model and generates automation rules.

[0549] The server inputs the extracted features into an AI model and generates rules such as "check progress reports every day at 9:00 and 17:00 and automatically send the results to the supervisor."

[0550] Input: Extracted features.

[0551] Output: The generated automation rule.

[0552] Step 6:

[0553] The user checks the generated automation rules and approves them from the terminal.

[0554] The user checks the automation rules on the device's confirmation screen and clicks the "Approve" button.

[0555] Input: The generated automation rule.

[0556] Output: The approved automation rule.

[0557] Step 7:

[0558] The server executes tasks based on the approved automation rules.

[0559] The server retrieves the latest progress information at the specified time and sends an automatically generated report to the superior via the mail server.

[0560] Input: Approved automation rules.

[0561] Output: Report sent to supervisor.

[0562] Step 8:

[0563] The server records the results of the automated process and collects user feedback.

[0564] The server stores the processing results in a database, and the user inputs feedback on the format and content of the report through the terminal, such as "Please improve the format of the report."

[0565] Input: The report you wish to provide feedback on.

[0566] Output: Collected feedback data.

[0567] Step 9:

[0568] The server retrains the generative AI model based on the collected feedback.

[0569] The collected feedback is used to adjust the AI ​​model to improve the accuracy and efficiency of future automated processes.

[0570] Input: Collected feedback data.

[0571] Output: The retrained generative AI model.

[0572] (Application example 1)

[0573] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0574] Factory production management requires a lot of manual work, such as reporting production progress and checking production line efficiency, which creates the risk of reduced efficiency and human error.In addition, it is difficult to detect abnormalities on the production line early and take appropriate measures, which affects overall production efficiency, creating an issue.

[0575] 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.

[0576] In this invention, the server includes: a means for a user to input data related to management tasks; a means for a terminal to send the input data to the server; a means for the server to analyze the received data and extract features to be input into an AI model for generating automation rules for management tasks; a means for the server to execute management tasks based on the generated automation rules; a means for collecting feedback from users and retraining the AI ​​model; a means for the terminal to report factory production progress; a means for the server to generate automation rules based on the reports and for a robot to check production line efficiency. This automates the reporting of production progress and the checking of production line efficiency, making it possible to detect efficiency declines early and take measures.

[0577] "User" means a person or entity that utilizes the system to input data related to administrative tasks.

[0578] "Management work" refers to tasks such as reporting production progress at production sites such as factories, checking the efficiency of production lines, and inventory management.

[0579] A "terminal" is a device used by a user to input data and send it to a server, such as a smartphone or tablet.

[0580] The "server" is a computer system that analyzes the received data and operates an AI model to generate automation rules for administrative tasks.

[0581] "Features" refer to important information and patterns of management operations that are extracted through data analysis and input into the AI ​​model.

[0582] "AI Model" means a machine learning model used to generate rules for automating administrative tasks based on received data.

[0583] "Automation rules" are specific procedures and rules generated using AI models to efficiently execute management tasks.

[0584] "Feedback" refers to opinions and requests for improvement provided by users regarding the results of automated processing, and is information used to retrain AI models.

[0585] "Production progress" is data that indicates the progress and completion status of production lines in a factory.

[0586] A "robot" is a mechanical device that can receive commands from a server to check the efficiency of a production line and take necessary improvement measures.

[0587] This invention is a system for automating production management tasks in a factory, and begins when a user inputs data related to the management tasks and a terminal transmits the data to a server. Specific embodiments are described below.

[0588] Users use devices such as smartphones and tablets to input data on production progress and production line efficiency. For example, they may report that "production progress on line A is 80% of normal." The input data is then sent from the device to the server.

[0589] The server analyzes the received data and extracts the features necessary to generate automation rules for management tasks. These features include the degree of production progress, production line information, and information about the person in charge. This data is then input into a machine learning model (AI model).

[0590] The AI ​​model generates automation rules for management tasks based on the received features. For example, it generates a rule such as "Check production progress every day at 9:00 and 17:00, and take immediate action if any abnormalities are found." The generated rules are then applied to the automation of management tasks by the server.

[0591] The user can review the generated automation rules and approve them as necessary. This approval prepares the server to perform the actual management tasks. For example, the user can click the "Approve" button on their smartphone to officially apply the automation rules.

[0592] The server executes management tasks based on automation rules. Specifically, it sends commands to the robot to check the efficiency of the production line and detect abnormalities. The robot then inspects the production line according to the server's instructions and takes necessary corrective measures.

[0593] In addition, the server collects feedback from users and uses it to retrain the AI ​​model. For example, if a user provides feedback such as "Please improve the report format," that information is sent to the server and used to improve the accuracy of the AI ​​model.

[0594] As a concrete example, consider a case where a user needs to report production progress every day at 9:00 and 17:00. The user accesses a terminal and enters, "Production progress on Line A is 80% of normal." The terminal sends this data to a server, which analyzes the data and identifies common patterns. Based on the identified patterns, an AI model generates a rule that states, "Confirm and report progress every day at 9:00 and 17:00." Once the generated rule is confirmed and approved by the user, the server automatically executes the management task at the specified time every day. As a result, the user is freed from reporting tasks and can focus on more important tasks.

[0595] The hardware used includes smartphones and tablets for users to input data, a server that receives and analyzes the data, and factory robots that operate based on instructions.Software used includes Python for data analysis, the machine learning library Scikit-learn, and Flask for robot control.

[0596] An example of a prompt is as follows:

[0597] "Production progress on Line A is at 80% of normal. Please investigate the cause of the decrease in efficiency."

[0598] "Line B efficiency is normal. No special improvements are required."

[0599] In this way, the present invention makes it possible to improve the efficiency of production management operations in factories, reduce human error, and detect abnormalities in the production line early and take measures to correct them.

[0600] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0601] Step 1:

[0602] The user uses a terminal to input data related to management tasks. Specifically, they use a smartphone or tablet to input information such as production progress and production line efficiency. They input prompt statements such as "Production progress on line A is 80% of normal." The input data is temporarily saved in the terminal.

[0603] Input: Production progress data entered by the user into a smartphone or tablet

[0604] Output: Temporarily saved production progress data

[0605] Step 2:

[0606] The device sends the entered data to the server. The device converts the entered data into an appropriate format and sends it to the server's API endpoint. The sent data is received on the server side.

[0607] Input: Temporarily saved production progress data

[0608] Output: Production progress data sent to the server

[0609] Step 3:

[0610] The server analyzes the received data and extracts features. Specifically, it extracts important information (e.g., progress level, production line, person in charge) from the received production progress data. Machine learning libraries such as Python and Scikit-learn are used for the analysis.

[0611] Input: Production progress data sent to the server

[0612] Output: Extracted features (progress, production line information, etc.)

[0613] Step 4:

[0614] The server inputs the extracted features into an AI model and generates automation rules. The AI ​​model has been retrained in advance based on feedback, so it analyzes the input data and generates appropriate automation rules for management tasks. For example, the generated rules might be something like, "Check production progress every day at 9:00 and 17:00, and take immediate action if any abnormalities are found."

[0615] Input: extracted features

[0616] Output: Generated automation rules

[0617] Step 5:

[0618] The server notifies the user of the generated automated rule, and the user reviews and approves the rule. The user receives a notification on their smartphone or tablet, checks the rule, and approves it by clicking the "Approve" button.

[0619] Input: Generated automation rules

[0620] Output: User approval

[0621] Step 6:

[0622] With the user's approval, the server executes management tasks based on automation rules. For example, it can issue instructions to robots to check the efficiency of the production line or take measures to deal with abnormalities. The robots receive instructions from the server, inspect the production line, and take necessary corrective measures.

[0623] Input: User approval

[0624] Output: Instructions to the robot and execution results

[0625] Step 7:

[0626] The server collects the results of the automated processing and collects feedback from users based on those results. For example, users can input their opinions or requests, such as "Please improve the report format," into their smartphones or tablets, and the input is sent to the server.

[0627] Input: Results of automated processing

[0628] Output: User feedback

[0629] Step 8:

[0630] The server retrains the AI ​​model based on the feedback, and uses the collected feedback data to refine the AI ​​model, improving the accuracy and efficiency of the automation rules for future management tasks.

[0631] Input: User feedback

[0632] Output: Retrained AI model

[0633] In this way, the automation of factory production management operations is efficiently realized through cooperation between the server, terminals, and users.

[0634] 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.

[0635] The system of the present invention begins when a user inputs data related to management tasks and sends that data to a server. The terminal is responsible for sending the data received from the user to the server. The server analyzes the received data and extracts the features necessary to automate the management tasks. The server uses an AI model to generate automation rules for the management tasks and executes the automation process based on those rules. The system also continuously improves by collecting feedback from users and retraining the AI ​​model.

[0636] Furthermore, the present invention incorporates an emotion engine that recognizes emotions from user input data and feedback. The emotion engine analyzes the user's emotional state in real time and adjusts the automation rules generated by the AI ​​model based on the analysis results. This provides more personalized automation rules that take the user's emotional state into account.

[0637] Data collection and input

[0638] A user uses a terminal to input data related to management tasks. For example, when reporting the progress of a project, the user inputs "Project A is 40% complete" on the terminal. This data is sent from the terminal to the server. At the same time, the terminal runs an emotion engine to analyze the user's emotions from the input and feedback.

[0639] Data analysis and sentiment analysis

[0640] The server receives the data sent from the device and stores it in a database. For example, when the server analyzes progress report data, the emotion engine also analyzes the user's input data and feedback to identify the user's emotional state. Based on the results, the server extracts features to generate automation rules for management tasks.

[0641] Utilizing AI models

[0642] The server extracts features based on data analysis and sentiment analysis and inputs them into the AI ​​model. For example, the user's reporting time, progress percentage, project name, and emotional state are extracted as features. The AI ​​model generates rules for automating management tasks based on these features. In addition to the rule "check and report progress every day at 9:00 and 17:00," adjustments based on emotions are made, such as "reduce reminders if the user is feeling stressed."

[0643] Check and run your automation

[0644] The user checks the generated automation rules on their device and approves them if there are no problems. For example, by checking an automatically generated report and clicking the "Approve" button, the server executes the automated process based on the rules. Progress reports are automatically generated every day at 9:00 and 17:00 and are emailed to the relevant supervisor. Adjustments are also made according to the user's emotional state.

[0645] Gathering feedback and retraining

[0646] The server collects the results of the automated process and stores them in a database. The user uses a device to input feedback about the format and content of the generated report. For example, the user may provide feedback such as, "Please improve the format of the report." This feedback is sent to the server and used to retrain the AI ​​model along with emotion data from the emotion engine. The server uses the feedback to improve the AI ​​model, thereby increasing the accuracy and efficiency of future automated processes.

[0647] As a concrete example, suppose a user needs to report project progress every day at 9:00 AM and 5:00 PM. The user enters "Project A is 40% complete" into their device. The device sends this data to a server, which analyzes the data and identifies common patterns. At the same time, an emotion engine analyzes the user's input and feedback and identifies that the user is feeling stressed. Based on this result, an AI model generates a rule that states, "Confirm and report progress every day at 9:00 AM and 5:00 PM, but reduce reminders to reduce user stress." Once the user confirms and approves the generated rule, the server automatically executes the management task at the specified time every day. As a result, the user is freed from reporting tasks, allowing them to focus on more important tasks and reducing their emotional burden.

[0648] The processing flow will be explained below.

[0649] Step 1: Data collection and entry

[0650] Action 1-1: A user uses a terminal to input data related to management operations.

[0651] Example: A user types into a terminal, "Project A is 40% complete."

[0652] Operation 1-2: The terminal transmits the input data to the server.

[0653] Example: The device sends input data in JSON format as a POST request to the server's API endpoint.

[0654] Action 1-3: The device analyzes the user's facial expressions, input speed, etc. and sends the results to the emotion engine.

[0655] Example: Sending user facial expression data captured by a camera to an emotion engine.

[0656] Step 2: Data analysis and sentiment analysis

[0657] Operation 2-1: The server receives the data sent from the terminal and stores it in a database.

[0658] Example: The server stores the received progress data in a "progress report" table in a MySQL database.

[0659] Action 2-2: The server analyzes the stored data.

[0660] Example: The server runs a query based on historical progress report data to analyze patterns in the time and frequency of reports.

[0661] Action 2-3: The emotion engine analyzes the transmitted data and identifies the user's emotional state.

[0662] Example: An emotion engine analyzes facial expression data and determines that the user is stressed.

[0663] Step 3: Feature extraction

[0664] Action 3-1: The server extracts features from the analysis data.

[0665] Example: The server extracts features such as reporting time, progress percentage, project name, and user emotional state.

[0666] Operation 3-2: The server inputs the extracted features into the AI ​​model.

[0667] Example: Convert the extracted features into tensor format and input them into an AI model.

[0668] Step 4: Leveraging AI models

[0669] Action 4-1: The server uses the AI ​​model to generate automation rules.

[0670] Example: An AI model generates a rule that says, "Check and report progress every day at 9:00 and 17:00, but reduce reminders if the user is feeling stressed."

[0671] Action 4-2: The server verifies the generated rules and makes corrections if necessary.

[0672] Example: The server checks the validity of the rules and manually corrects them if necessary.

[0673] Step 5: Verify and run your automation

[0674] Action 5-1: The user checks the automation rules generated on the terminal.

[0675] Example: A user checks an automatically generated report on their device and clicks the "Approve" button.

[0676] Operation 5-2: The server receives user approval and executes management tasks based on automated rules.

[0677] Example: Every day at 9:00 and 17:00, the server automatically generates a progress report and emails it to the manager, adjusting the frequency of reminders based on the user's emotional state.

[0678] Step 6: Gather feedback and retrain

[0679] Action 6-1: The server collects the results of the automated processing.

[0680] Example: Storing the submission history of automatically generated reports or the user's emotional state in a database.

[0681] Action 6-2: The user uses the device to provide feedback.

[0682] Example: A user enters feedback from a terminal saying, "Please improve the report format."

[0683] Action 6-3: The server retrains the AI ​​model based on the feedback.

[0684] Example: Adding feedback and emotional states to a training dataset and retraining an AI model.

[0685] In this way, the system of the present invention automates administrative tasks while taking into account the user's emotional state, freeing the user from tedious tasks and providing an environment in which they can concentrate on more creative tasks.

[0686] Example 2

[0687] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0688] Conventional management task systems required users to manually input information and perform management tasks each time, resulting in reduced work efficiency. Furthermore, automation rules were generated without taking the user's emotional state into consideration, which could cause stress for the user and lead to poor work performance. Furthermore, there was an insufficient mechanism for effectively collecting feedback and utilizing it to improve the system.

[0689] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for recognizing emotions from user input information and feedback and including them in features, a means for extracting features to be input into a generative AI model for generating automation rules for management tasks, and a means for executing management tasks based on the automation rules. This makes it possible to generate and execute automation rules for management tasks taking into account the user's emotional state, thereby improving work efficiency and user satisfaction.

[0690] A "user" is an entity that inputs information related to management tasks and operates the system.

[0691] A "terminal" is a device for transmitting information entered by a user to a server.

[0692] A "server" is a computer system that receives and analyzes information sent by users, and generates and executes rules for automating administrative tasks.

[0693] "Information" refers to data and feedback about administrative tasks entered by users.

[0694] The "means for recognizing emotions and including them in features" refers to a device or software function that analyzes the emotional state from the user's input information and feedback and extracts the results as features.

[0695] A "generative AI model" is an artificial intelligence algorithm that generates optimal automation rules for management tasks based on input features.

[0696] "Features" are parameters or elements used in data analysis, and are the basic data used to generate automation rules for management tasks.

[0697] "Automation rules" are a series of actions and procedures that the server creates based on the generative AI model to perform management tasks.

[0698] "Feedback" refers to opinions, evaluations, and information on areas for improvement provided by users.

[0699] The system of the present invention starts when a user inputs information about a management task and sends that information to a server. A specific embodiment of this system will be described below.

[0700] A user uses a terminal to input information related to management tasks. For example, when a user reports on the progress of a project, they input text data such as "Project A is 40% complete" into the terminal. The terminal detects the input information and activates the emotion engine. The emotion engine analyzes the user's input status and feedback to recognize the user's emotional state. This makes it possible to obtain the user's stress level and emotional state as analysis results.

[0701] The device sends the input information and emotion analysis results to the server, which receives this information and stores it in a database. The server uses data processing libraries such as Python's Pandas and NumPy to analyze the stored information. This analysis identifies trends and patterns in the progress reports, and uses the emotion engine's analysis results to extract the user's emotional state as features.

[0702] The extracted features are input into an AI model on the server. The AI ​​model is built using machine learning libraries such as TensorFlow and PyTorch, and generates optimal automation rules for management tasks based on the features. For example, it might generate rules such as "check and report progress every day at 9:00 and 17:00" or "reduce reminders if the user is feeling stressed."

[0703] The server sends the generated automation rules to the user's device, where the user can review them. If the user determines that the rules are acceptable, they can click the "Approve" button, and the server will automatically execute management tasks based on the rules. For example, progress reports will be automatically generated at 9:00 and 17:00 every day and emailed to the relevant supervisor. Adjustments will also be made based on the user's emotional state.

[0704] Additionally, the user can use the device to input feedback on the format and content of the automatically generated report. For example, the user may provide feedback such as, "Please improve the format of the report." The device then sends this feedback along with emotion data to the server, which stores it in a database. The server then retrains the AI ​​model based on the feedback and emotion data from the emotion engine, improving the accuracy and efficiency of future automated processes.

[0705] As a concrete example, consider a situation where a user needs to report project progress every day at 9:00 and 17:00. The user enters "Project A progress is 40%" into the device, and the device sends this data to the server. At the same time, the emotion engine runs and identifies that the user is feeling stressed. Based on this result, the AI ​​model generates a rule that states, "Progress checks and reports will be performed every day at 9:00 and 17:00, but with fewer reminders to reduce the user's stress." Once the generated rule is confirmed and approved by the user, the server automatically executes the management tasks at the specified time every day.

[0706] An example of a prompt sentence is the text data, "Project A is 40% complete." This system frees users from reporting tasks, allowing them to focus on important tasks and reducing emotional burden.

[0707] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0708] Step 1:

[0709] The user inputs information about management tasks. For example, "Project A is 40% complete" into the terminal. This input information is captured as data on the terminal. At the same time, the terminal activates the emotion engine. The emotion engine analyzes the user's input and recent feedback to recognize the user's emotional state.

[0710] Input: Administrative information entered by the user (e.g., "Project A is 40% complete").

[0711] Output: Analysis of the user's input information and emotional state.

[0712] Specific behavior:

[0713] The device retrieves the information entered in the text field and performs emotion analysis by calling the emotion engine via an API call.

[0714] Step 2:

[0715] The device sends the user's input information and emotion analysis results to the server using HTTP or HTTPS as the communication protocol.

[0716] Input: Analysis of the user's input information and emotional state.

[0717] Output: Data sent to the server.

[0718] Specific behavior:

[0719] The device converts the acquired input information and emotion analysis results into JSON format or similar and sends them to the server as an HTTP request.

[0720] Step 3:

[0721] The server receives the information sent from the device and stores it in a database, which stores progress report information and the user's emotional state.

[0722] Input: User input information and emotional state sent from the device.

[0723] Output: Information stored in a database.

[0724] Specific behavior:

[0725] The server parses the received data and inserts it into a database in the appropriate format, for example, by using SQL to store the data.

[0726] Step 4:

[0727] The server analyzes the stored data and extracts features. It uses data processing libraries such as Python's Pandas and NumPy to identify trends and patterns in the progress reports. At the same time, it uses the analysis results of the emotion engine to extract features that represent the user's emotional state.

[0728] Input: User input information and emotional state stored in a database.

[0729] Output: Extracted features (e.g., reporting time, progress percentage, project name, emotional state).

[0730] Specific behavior:

[0731] The server reads the data from the database, analyzes it using a data processing library, and extracts features.

[0732] Step 5:

[0733] The server inputs the features into a generative AI model, which is built using machine learning libraries such as TensorFlow and PyTorch, and generates optimal automation rules for management tasks based on the input features.

[0734] Input: Extracted features.

[0735] Output: The generated automation rule.

[0736] Specific behavior:

[0737] The server inputs the features into the generative AI model, and the model performs calculations to generate rules.

[0738] Step 6:

[0739] The server sends the generated automation rules to the user's device, where the user can check the rules.

[0740] Input: The generated automation rule.

[0741] Output: The automation rule that is displayed on the user's device.

[0742] Specific behavior:

[0743] The server converts the generated rules into JSON format and sends them to the terminal. The terminal displays the received data.

[0744] Step 7:

[0745] The user reviews and approves the generated automation rule on the device, for example by clicking the "Approve" button.

[0746] Input: The generated automation rule.

[0747] Output: User authorization information.

[0748] Specific behavior:

[0749] The user checks the rules displayed on the screen and clicks the "Approve" button. The device then sends this approval information to the server.

[0750] Step 8:

[0751] The server automatically executes administrative tasks based on approved rules, such as automatically generating progress reports at 9:00 and 17:00 every day and emailing them to relevant superiors, and also adjusts according to the user's emotional state.

[0752] Inputs: User authorization information and generated automation rules.

[0753] Output: Automatically performed administrative tasks.

[0754] Specific behavior:

[0755] The server schedules tasks based on approved rules, automatically executes administrative tasks, and notifies relevant parties of the execution results.

[0756] Step 9:

[0757] The user can enter feedback on the format and content of the automatically generated report, for example, "Please improve the format of the report."

[0758] Input: User feedback information.

[0759] Output: Feedback information data.

[0760] Specific behavior:

[0761] The device captures the feedback entered in the text field and sends it to the server.

[0762] Step 10:

[0763] The server receives the feedback, performs sentiment analysis again using the emotion engine, and stores the results in a database.The generative AI model is then retrained based on the feedback to improve the accuracy and efficiency of future automated processes.

[0764] Input: User feedback information and sentiment analysis results.

[0765] Output: The retrained generative AI model.

[0766] Specific behavior:

[0767] The server analyzes the feedback and inputs it as retraining data into the generative AI model, improving the model's accuracy.

[0768] (Application example 2)

[0769] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0770] While conventional management task automation systems are capable of analyzing data and generating automation rules, they are unable to take into account the emotions and stress levels of workers, which means that the burden on workers remains low. Furthermore, there is no means for retraining to incorporate feedback, making it difficult to continuously improve the system.

[0771] 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.

[0772] In this invention, the server includes a means for analyzing the user's emotional state using an emotion analysis engine and adjusting the automation rules generated by the AI ​​model based on the analysis results, a means for monitoring the worker's progress and emotional state in real time, and a means for collecting feedback from the user and retraining the AI ​​model, thereby enabling the generation of automation rules that take the worker's emotional state into account and the continuous improvement of the system.

[0773] "Administrative tasks" refer to tasks and procedures that allow users to efficiently carry out their daily business activities.

[0774] "Data input means" refers to the interface and functions that allow users to input information about management tasks into the terminal.

[0775] "Data transmission means" refers to a communication function for transferring input data from the terminal to the server.

[0776] "Data analysis means" refers to a processing function for analyzing data received by the server and extracting necessary information and features.

[0777] An "AI model" refers to a machine learning algorithm that learns patterns from large amounts of data and generates automated rules.

[0778] "Automation rules" refer to a set of procedures or conditions generated by an AI model to streamline administrative tasks.

[0779] An "emotion analysis engine" refers to a function that analyzes the emotional state from user input and feedback and outputs the results.

[0780] "Emotional state" refers to the emotional state of the user when entering data or providing feedback, such as stress, fatigue, or joy.

[0781] "Feedback collection means" refers to a function for collecting evaluations and opinions from users and sending that data to a server.

[0782] "Retraining tools" refers to functions that allow the AI ​​model to retrain based on collected feedback data to improve its accuracy.

[0783] "Real-time monitoring means" refers to a function for monitoring the progress and emotional state of workers in real time.

[0784] This invention is a system for improving the efficiency of factory robots and management tasks in the manufacturing industry. It generates automation rules based on data entered by the user and their emotional state, reducing the burden on workers.

[0785] System Configuration

[0786] Hardware

[0787] Devices: Smartphones, tablets, surveillance cameras in factories, etc.

[0788] Server: Cloud-based or on-premise servers for high-performance data processing.

[0789] Robot: Factory robots used on production lines.

[0790] software

[0791] Programming language: Python

[0792] Machine learning libraries: (TensorFlow, PyTorch, etc.)

[0793] Sentiment analysis engine: Natural language processing engine (e.g. IBM Watson's NLP tool)

[0794] Data Entry and Submission

[0795] Users use smartphones or tablets to input the progress of the production line, entering prompt statements such as "Production progress on Line A is 70%. Today's production work is a little tired." This data is sent to the server in real time.

[0796] Data and Sentiment Analysis

[0797] The server analyzes the received data and extracts features. Using an emotion analysis engine, it analyzes the emotional state (stress or fatigue) from the prompt text entered by the user.

[0798] Automated rule generation using AI models

[0799] The server inputs the extracted features into an AI model to generate automation rules, such as "Check progress every day at 10:00 and 16:00, but reduce reminders if the worker feels fatigued."

[0800] User approval and automatic execution

[0801] The generated automation rules are presented to the user for review and approval. Approved rules are automatically executed by the server. Progress reports are generated at the specified time and sent to the relevant supervisor.

[0802] Feedback gathering and retraining

[0803] Users can input feedback on generated reports and automation rules. Feedback such as "The timing of the report was appropriate, but please change the format" is sent to the server as data. This feedback data is used to retrain the AI ​​model, continuously improving the accuracy and efficiency of the system.

[0804] Specific examples

[0805] Suppose the user enters the following prompt:

[0806] "Production line A is 70% complete. Production work today is a little tiring."

[0807] The server receives this data and uses an emotion analysis engine to identify the emotional state of "fatigue." Based on this information, the AI ​​model generates a new automation rule: "Check progress every day at 10:00 and 16:00, but reduce reminders if the worker feels fatigued." Once the user confirms and approves this rule, the server automatically executes tasks based on this rule. This reduces the burden on workers and enables more efficient management work.

[0808] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0809] Step 1:

[0810] Data Entry and Submission

[0811] The user uses a smartphone or tablet to input the progress of the production line and their emotional state. An example input is, "Production progress on Line A is 70%. Today's production work is a little tiring." This data is saved on the device in real time and then sent to the server.

[0812] input:

[0813] Production line progress

[0814] The user's emotional state

[0815] output:

[0816] Sending data from the device to the server

[0817] Step 2:

[0818] Data reception and analysis

[0819] The server receives the progress data and emotional state data sent by the user. The server uses a data analysis engine to analyze the received data and extract important features (e.g., progress %, working time zone, emotional state).

[0820] input:

[0821] Progress data sent from the device

[0822] Emotional state data

[0823] output:

[0824] Extracted features

[0825] Step 3:

[0826] Emotion analysis

[0827] The server uses an emotion analysis engine to analyze the user's emotional state from the input data, and this analysis identifies an emotional state such as "the user is tired."

[0828] input:

[0829] User input data

[0830] output:

[0831] The user's emotional state

[0832] Step 4:

[0833] Input to AI model and rule generation

[0834] The server inputs the extracted features into a generative AI model to generate rules for automating administrative tasks. For example, specific rules such as "Check progress every day at 10:00 and 16:00, but reduce reminders if the worker feels fatigued" are generated.

[0835] input:

[0836] Extracted features

[0837] output:

[0838] Generated automation rules

[0839] Step 5:

[0840] Presenting and confirming rules

[0841] The generated automation rules are presented to the user, who can review them and click the "Approve" button if there are no problems.

[0842] input:

[0843] Generated automation rules

[0844] output:

[0845] User approval or correction requests

[0846] Step 6:

[0847] Executing automated rules

[0848] After the user approves, the server automatically executes management tasks based on the automation rules, such as automatically generating a progress report at a specified time and sending it to the relevant superior.

[0849] input:

[0850] Approved automation rules

[0851] output:

[0852] Automated administrative tasks

[0853] Step 7:

[0854] Feedback gathering and retraining

[0855] Users can input feedback about generated reports and automation rules. This feedback is sent to the server and used to retrain the AI ​​model. For example, specific feedback such as "The timing of the report was appropriate, but please change the format" can be collected.

[0856] input:

[0857] User Feedback

[0858] output:

[0859] Improved AI models improve accuracy of next automation rules

[0860] 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.

[0861] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0862] 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.

[0863] [Third embodiment]

[0864] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0865] 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.

[0866] 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).

[0867] 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.

[0868] 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.

[0869] 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).

[0870] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0871] 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.

[0872] 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.

[0873] 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.

[0874] 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.

[0875] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0876] The system of the present invention begins when a user inputs data related to management tasks and sends that data to a server. The terminal is responsible for sending the data received from the user to the server. The server analyzes the received data and extracts the features necessary to automate the management tasks. The server then uses an AI model to generate automation rules for the management tasks and executes the automation process based on those rules. The system also continuously improves by collecting feedback from users and retraining the AI ​​model.

[0877] Data collection and input

[0878] A user uses a terminal to input data related to management tasks. For example, when a user reports the progress of a project, he or she inputs "Project A is 40% complete" on the terminal. This data is sent from the terminal to the server.

[0879] Data analysis

[0880] The server analyzes the data received from the terminal. For example, it analyzes the patterns of reports made at specific times or with specific frequency based on the progress report history stored in the database. This analysis identifies routine management task patterns.

[0881] Utilizing AI models

[0882] The server extracts features based on data analysis and inputs them into the AI ​​model. For example, the feature values ​​extracted include the user's reporting time, project progress, and information about the person in charge. Based on these features, the AI ​​model generates automation rules for management tasks. Rules such as "automatically check progress reports at 9:00 and 17:00 every day and send reports to the supervisor" are generated here.

[0883] Executing the automation

[0884] The user checks the generated automation rules on the terminal and approves them if there are no problems. For example, by checking an automatically generated report and clicking the "Approve" button, the server executes the automated process based on the rule. Every day at 9:00 and 17:00, a progress report is automatically generated and sent to the relevant supervisor by email.

[0885] Feedback and Improvements

[0886] The server collects the results of the automated process and stores them in a database. The user uses a device to enter feedback on the format and content of the generated report. For example, the user may provide feedback such as, "Please improve the format of the report." This feedback is sent to the server and used to retrain the AI ​​model. The server then uses the feedback to improve the AI ​​model, thereby increasing the accuracy and efficiency of future automated processes.

[0887] As a concrete example, suppose a user needs to report project progress every day at 9:00 and 17:00. The user accesses a terminal and enters, "Project A progress is 40%." The terminal sends this data to a server, which analyzes the data and identifies common patterns. Based on the identified patterns, an AI model generates a rule that states, "Check and report progress every day at 9:00 and 17:00." Once the generated rule is confirmed and approved by the user, the server automatically executes the management task at the specified time every day. As a result, the user is freed from reporting tasks and can focus on more important tasks.

[0888] The processing flow will be explained below.

[0889] Step 1: Data collection and entry

[0890] Action 1-1: A user uses a terminal to input data related to management operations.

[0891] Example: A user types into a terminal, "Project A is 40% complete."

[0892] Operation 1-2: The terminal transmits the input data to the server.

[0893] Example: The device sends input data in JSON format as a POST request to the server's API endpoint.

[0894] Step 2: Data analysis

[0895] Operation 2-1: The server receives the data sent from the terminal and stores it in a database.

[0896] Example: The server stores the received progress data in a "progress report" table in a MySQL database.

[0897] Action 2-2: The server analyzes the stored data.

[0898] Example: The server runs a query based on historical progress report data to analyze patterns in the time and frequency of reports.

[0899] Step 3: Feature extraction

[0900] Action 3-1: The server extracts features from the analysis data.

[0901] Example: The server extracts features such as reporting time, progress percentage, and project name.

[0902] Operation 3-2: The server inputs the extracted features into the AI ​​model.

[0903] Example: Convert features into tensor format and input them into an AI model.

[0904] Step 4: Leveraging AI models

[0905] Action 4-1: The server uses the AI ​​model to generate automation rules.

[0906] Example: An AI model generates a rule that says, "Check and report progress every day at 9:00 and 17:00."

[0907] Action 4-2: The server verifies the generated rules and makes corrections if necessary.

[0908] Example: The server checks the validity of the rules and manually corrects them if necessary.

[0909] Step 5: Verify and run your automation

[0910] Action 5-1: The user checks the automation rules generated on the terminal.

[0911] Example: A user checks an automatically generated report on their device and clicks the "Approve" button.

[0912] Operation 5-2: The server receives user approval and executes management tasks based on automated rules.

[0913] Example: Every day at 9:00 and 17:00, the server automatically generates a progress report and emails it to the manager.

[0914] Step 6: Gather feedback and retrain

[0915] Action 6-1: The server collects the results of the automated processing.

[0916] Example: Storing the sending history of automatically generated reports in a database.

[0917] Action 6-2: The user uses the device to provide feedback.

[0918] Example: A user enters feedback from a terminal saying, "Please improve the report format."

[0919] Action 6-3: The server retrains the AI ​​model based on the feedback.

[0920] Example: Adding feedback to a training dataset and retraining an AI model.

[0921] This frees users from the hassle of daily management tasks and allows them to focus on more creative work.

[0922] Example 1

[0923] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0924] Traditional management tasks required tedious manual data entry and report creation, requiring a great deal of effort and time. These manual tasks were prone to errors, reducing work efficiency. Furthermore, creating and executing automation rules in existing systems was time-consuming, making it difficult for users to execute business processes quickly and accurately. To solve these issues, automation and streamlining of management tasks was necessary.

[0925] 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.

[0926] In this invention, the server includes means for analyzing received information and extracting features to be input into a generative AI model for generating automation rules for business processes, means for executing business processes based on the generated automation rules, and means for acquiring progress information at certain time periods and sending automatically generated reports. This reduces the amount of manual work required by users, providing an environment where users can focus on important tasks.

[0927] "Information" refers to data that expresses the content of a user's business.

[0928] A "terminal" is a device that allows a user to input information, and includes, for example, a computer or a smartphone.

[0929] A "server" is a computer system that receives information sent from a terminal and analyzes and processes it.

[0930] "Analyzing" is the process of analyzing received information to understand its structure and content.

[0931] A "generative AI model" is an artificial intelligence algorithm that generates business automation rules based on large amounts of data.

[0932] "Features" are important data elements or attributes that are extracted for input into a generative AI model.

[0933] "Automation rules" are a set of rules and procedures established to efficiently automate business processes.

[0934] A "report" is a document summarizing the progress and results of work, and is usually sent to other parties.

[0935] "Feedback" refers to improvements and ratings provided by users to the server, which are used to improve the system.

[0936] The system of the present invention begins when a user inputs information about a task and sends it from their terminal to a server. The terminal is a device operated by the user and serves to transmit information. The server analyzes the information received from the terminal and generates automation rules using a generative AI model.

[0937] Specifically, the server uses programming languages ​​such as Python and R to analyze the received information. Machine learning libraries such as Scikit-learn and TensorFlow are used as generative AI models. Based on the results of this analysis, the server extracts features and inputs them into the AI ​​model to generate automation rules. Tasks are then automated based on the generated rules, and reports are sent to the user.

[0938] For example, if a user types "Project A is 40% complete," that information is sent to the server. The server analyzes past progress data and the user's reporting patterns. The AI ​​model then generates a rule that says, "Check progress reports every day at 9:00 and 17:00 and send reports to your supervisor."

[0939] Additionally, users can use their devices to provide feedback on the format and content of the generated report, such as "Please improve the format of the report." This feedback is sent to the server and used to retrain the AI ​​model, improving the accuracy and efficiency of future automated processes.

[0940] An example of a prompt is as follows:

[0941] "Users need to report on project progress daily. Can you explain how to automate this reporting?"

[0942] "Please explain in detail the steps in your system that analyzes business data and generates automated rules."

[0943] "Please tell me how the AI ​​model works to automatically generate a progress report and send it to my boss at a fixed time every day."

[0944] This automates tasks that users previously performed manually, providing an environment in which users can focus on important tasks.

[0945] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0946] Step 1:

[0947] The user uses the terminal to input information about the business.

[0948] Specifically, the user inputs into the terminal, "Project A is 40% complete."

[0949] Input: Information about the job entered by the user.

[0950] Output: Data of information entered into the terminal.

[0951] Step 2:

[0952] The terminal transmits the input information to the server.

[0953] The device sends information to the server using an HTTP POST request.

[0954] Input: Data of information entered into the device.

[0955] Output: The data of the information sent to the server.

[0956] Step 3:

[0957] The server analyzes the received information.

[0958] The server uses Python or R to analyze the incoming data and references a database to understand its meaning.

[0959] Input: The data of the information sent to the server.

[0960] Output: Parsed data.

[0961] Step 4:

[0962] The server extracts features from the analyzed data.

[0963] The server uses machine learning libraries such as Scikit-learn and TensorFlow to extract important features from the data, such as user ID, reporting time, and progress.

[0964] Input: Parsed data.

[0965] Output: Extracted features.

[0966] Step 5:

[0967] The server inputs features into the generated AI model and generates automation rules.

[0968] The server inputs the extracted features into an AI model and generates rules such as "check progress reports every day at 9:00 and 17:00 and automatically send the results to the supervisor."

[0969] Input: Extracted features.

[0970] Output: The generated automation rule.

[0971] Step 6:

[0972] The user checks the generated automation rules and approves them from the terminal.

[0973] The user checks the automation rules on the device's confirmation screen and clicks the "Approve" button.

[0974] Input: The generated automation rule.

[0975] Output: The approved automation rule.

[0976] Step 7:

[0977] The server executes tasks based on the approved automation rules.

[0978] The server retrieves the latest progress information at the specified time and sends an automatically generated report to the superior via the mail server.

[0979] Input: Approved automation rules.

[0980] Output: Report sent to supervisor.

[0981] Step 8:

[0982] The server records the results of the automated process and collects user feedback.

[0983] The server stores the processing results in a database, and the user inputs feedback on the format and content of the report through the terminal, such as "Please improve the format of the report."

[0984] Input: The report you wish to provide feedback on.

[0985] Output: Collected feedback data.

[0986] Step 9:

[0987] The server retrains the generative AI model based on the collected feedback.

[0988] The collected feedback is used to adjust the AI ​​model to improve the accuracy and efficiency of future automated processes.

[0989] Input: Collected feedback data.

[0990] Output: The retrained generative AI model.

[0991] (Application example 1)

[0992] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0993] Factory production management requires a lot of manual work, such as reporting production progress and checking production line efficiency, which creates the risk of reduced efficiency and human error.In addition, it is difficult to detect abnormalities on the production line early and take appropriate measures, which affects overall production efficiency, creating an issue.

[0994] 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.

[0995] In this invention, the server includes: a means for a user to input data related to management tasks; a means for a terminal to send the input data to the server; a means for the server to analyze the received data and extract features to be input into an AI model for generating automation rules for management tasks; a means for the server to execute management tasks based on the generated automation rules; a means for collecting feedback from users and retraining the AI ​​model; a means for the terminal to report factory production progress; a means for the server to generate automation rules based on the reports and for a robot to check production line efficiency. This automates the reporting of production progress and the checking of production line efficiency, making it possible to detect efficiency declines early and take measures.

[0996] "User" means a person or entity that utilizes the system to input data related to administrative tasks.

[0997] "Management work" refers to tasks such as reporting production progress at production sites such as factories, checking the efficiency of production lines, and inventory management.

[0998] A "terminal" is a device used by a user to input data and send it to a server, such as a smartphone or tablet.

[0999] The "server" is a computer system that analyzes the received data and operates an AI model to generate automation rules for administrative tasks.

[1000] "Features" refer to important information and patterns of management operations that are extracted through data analysis and input into the AI ​​model.

[1001] "AI Model" means a machine learning model used to generate rules for automating administrative tasks based on received data.

[1002] "Automation rules" are specific procedures and rules generated using AI models to efficiently execute management tasks.

[1003] "Feedback" refers to opinions and requests for improvement provided by users regarding the results of automated processing, and is information used to retrain AI models.

[1004] "Production progress" is data that indicates the progress and completion status of production lines in a factory.

[1005] A "robot" is a mechanical device that can receive commands from a server to check the efficiency of a production line and take necessary improvement measures.

[1006] This invention is a system for automating production management tasks in a factory, and begins when a user inputs data related to the management tasks and a terminal transmits the data to a server. Specific embodiments are described below.

[1007] Users use devices such as smartphones and tablets to input data on production progress and production line efficiency. For example, they may report that "production progress on line A is 80% of normal." The input data is then sent from the device to the server.

[1008] The server analyzes the received data and extracts the features necessary to generate automation rules for management tasks. These features include the degree of production progress, production line information, and information about the person in charge. This data is then input into a machine learning model (AI model).

[1009] The AI ​​model generates automation rules for management tasks based on the received features. For example, it generates a rule such as "Check production progress every day at 9:00 and 17:00, and take immediate action if any abnormalities are found." The generated rules are then applied to the automation of management tasks by the server.

[1010] The user can review the generated automation rules and approve them as necessary. This approval prepares the server to perform the actual management tasks. For example, the user can click the "Approve" button on their smartphone to officially apply the automation rules.

[1011] The server executes management tasks based on automation rules. Specifically, it sends commands to the robot to check the efficiency of the production line and detect abnormalities. The robot then inspects the production line according to the server's instructions and takes necessary corrective measures.

[1012] In addition, the server collects feedback from users and uses it to retrain the AI ​​model. For example, if a user provides feedback such as "Please improve the report format," that information is sent to the server and used to improve the accuracy of the AI ​​model.

[1013] As a concrete example, consider a case where a user needs to report production progress every day at 9:00 and 17:00. The user accesses a terminal and enters, "Production progress on Line A is 80% of normal." The terminal sends this data to a server, which analyzes the data and identifies common patterns. Based on the identified patterns, an AI model generates a rule that states, "Confirm and report progress every day at 9:00 and 17:00." Once the generated rule is confirmed and approved by the user, the server automatically executes the management task at the specified time every day. As a result, the user is freed from reporting tasks and can focus on more important tasks.

[1014] The hardware used includes smartphones and tablets for users to input data, a server that receives and analyzes the data, and factory robots that operate based on instructions.Software used includes Python for data analysis, the machine learning library Scikit-learn, and Flask for robot control.

[1015] An example of a prompt is as follows:

[1016] "Production progress on Line A is at 80% of normal. Please investigate the cause of the decrease in efficiency."

[1017] "Line B efficiency is normal. No special improvements are required."

[1018] In this way, the present invention makes it possible to improve the efficiency of production management operations in factories, reduce human error, and detect abnormalities in the production line early and take measures to correct them.

[1019] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1020] Step 1:

[1021] The user uses a terminal to input data related to management tasks. Specifically, they use a smartphone or tablet to input information such as production progress and production line efficiency. They input prompt statements such as "Production progress on line A is 80% of normal." The input data is temporarily saved in the terminal.

[1022] Input: Production progress data entered by the user into a smartphone or tablet

[1023] Output: Temporarily saved production progress data

[1024] Step 2:

[1025] The device sends the entered data to the server. The device converts the entered data into an appropriate format and sends it to the server's API endpoint. The sent data is received on the server side.

[1026] Input: Temporarily saved production progress data

[1027] Output: Production progress data sent to the server

[1028] Step 3:

[1029] The server analyzes the received data and extracts features. Specifically, it extracts important information (e.g., progress level, production line, person in charge) from the received production progress data. Machine learning libraries such as Python and Scikit-learn are used for the analysis.

[1030] Input: Production progress data sent to the server

[1031] Output: Extracted features (progress, production line information, etc.)

[1032] Step 4:

[1033] The server inputs the extracted features into an AI model and generates automation rules. The AI ​​model has been retrained in advance based on feedback, so it analyzes the input data and generates appropriate automation rules for management tasks. For example, the generated rules might be something like, "Check production progress every day at 9:00 and 17:00, and take immediate action if any abnormalities are found."

[1034] Input: extracted features

[1035] Output: Generated automation rules

[1036] Step 5:

[1037] The server notifies the user of the generated automated rule, and the user reviews and approves the rule. The user receives a notification on their smartphone or tablet, checks the rule, and approves it by clicking the "Approve" button.

[1038] Input: Generated automation rules

[1039] Output: User approval

[1040] Step 6:

[1041] With the user's approval, the server executes management tasks based on automation rules. For example, it can issue instructions to robots to check the efficiency of the production line or take measures to deal with abnormalities. The robots receive instructions from the server, inspect the production line, and take necessary corrective measures.

[1042] Input: User approval

[1043] Output: Instructions to the robot and execution results

[1044] Step 7:

[1045] The server collects the results of the automated processing and collects feedback from users based on those results. For example, users can input their opinions or requests, such as "Please improve the report format," into their smartphones or tablets, and the input is sent to the server.

[1046] Input: Results of automated processing

[1047] Output: User feedback

[1048] Step 8:

[1049] The server retrains the AI ​​model based on the feedback, and uses the collected feedback data to refine the AI ​​model, improving the accuracy and efficiency of the automation rules for future management tasks.

[1050] Input: User feedback

[1051] Output: Retrained AI model

[1052] In this way, the automation of factory production management operations is efficiently realized through cooperation between the server, terminals, and users.

[1053] 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.

[1054] The system of the present invention begins when a user inputs data related to management tasks and sends that data to a server. The terminal is responsible for sending the data received from the user to the server. The server analyzes the received data and extracts the features necessary to automate the management tasks. The server uses an AI model to generate automation rules for the management tasks and executes the automation process based on those rules. The system also continuously improves by collecting feedback from users and retraining the AI ​​model.

[1055] Furthermore, the present invention incorporates an emotion engine that recognizes emotions from user input data and feedback. The emotion engine analyzes the user's emotional state in real time and adjusts the automation rules generated by the AI ​​model based on the analysis results. This provides more personalized automation rules that take the user's emotional state into account.

[1056] Data collection and input

[1057] A user uses a terminal to input data related to management tasks. For example, when reporting the progress of a project, the user inputs "Project A is 40% complete" on the terminal. This data is sent from the terminal to the server. At the same time, the terminal runs an emotion engine to analyze the user's emotions from the input and feedback.

[1058] Data analysis and sentiment analysis

[1059] The server receives the data sent from the device and stores it in a database. For example, when the server analyzes progress report data, the emotion engine also analyzes the user's input data and feedback to identify the user's emotional state. Based on the results, the server extracts features to generate automation rules for management tasks.

[1060] Utilizing AI models

[1061] The server extracts features based on data analysis and sentiment analysis and inputs them into the AI ​​model. For example, the user's reporting time, progress percentage, project name, and emotional state are extracted as features. The AI ​​model generates rules for automating management tasks based on these features. In addition to the rule "check and report progress every day at 9:00 and 17:00," adjustments based on emotions are made, such as "reduce reminders if the user is feeling stressed."

[1062] Check and run your automation

[1063] The user checks the generated automation rules on their device and approves them if there are no problems. For example, by checking an automatically generated report and clicking the "Approve" button, the server executes the automated process based on the rules. Progress reports are automatically generated every day at 9:00 and 17:00 and are emailed to the relevant supervisor. Adjustments are also made according to the user's emotional state.

[1064] Gathering feedback and retraining

[1065] The server collects the results of the automated process and stores them in a database. The user uses a device to input feedback about the format and content of the generated report. For example, the user may provide feedback such as, "Please improve the format of the report." This feedback is sent to the server and used to retrain the AI ​​model along with emotion data from the emotion engine. The server uses the feedback to improve the AI ​​model, thereby increasing the accuracy and efficiency of future automated processes.

[1066] As a concrete example, suppose a user needs to report project progress every day at 9:00 AM and 5:00 PM. The user enters "Project A is 40% complete" into their device. The device sends this data to a server, which analyzes the data and identifies common patterns. At the same time, an emotion engine analyzes the user's input and feedback and identifies that the user is feeling stressed. Based on this result, an AI model generates a rule that states, "Confirm and report progress every day at 9:00 AM and 5:00 PM, but reduce reminders to reduce user stress." Once the user confirms and approves the generated rule, the server automatically executes the management task at the specified time every day. As a result, the user is freed from reporting tasks, allowing them to focus on more important tasks and reducing their emotional burden.

[1067] The processing flow will be explained below.

[1068] Step 1: Data collection and entry

[1069] Action 1-1: A user uses a terminal to input data related to management operations.

[1070] Example: A user types into a terminal, "Project A is 40% complete."

[1071] Operation 1-2: The terminal transmits the input data to the server.

[1072] Example: The device sends input data in JSON format as a POST request to the server's API endpoint.

[1073] Action 1-3: The device analyzes the user's facial expressions, input speed, etc. and sends the results to the emotion engine.

[1074] Example: Sending user facial expression data captured by a camera to an emotion engine.

[1075] Step 2: Data analysis and sentiment analysis

[1076] Operation 2-1: The server receives the data sent from the terminal and stores it in a database.

[1077] Example: The server stores the received progress data in a "progress report" table in a MySQL database.

[1078] Action 2-2: The server analyzes the stored data.

[1079] Example: The server runs a query based on historical progress report data to analyze patterns in the time and frequency of reports.

[1080] Action 2-3: The emotion engine analyzes the transmitted data and identifies the user's emotional state.

[1081] Example: An emotion engine analyzes facial expression data and determines that the user is stressed.

[1082] Step 3: Feature extraction

[1083] Action 3-1: The server extracts features from the analysis data.

[1084] Example: The server extracts features such as reporting time, progress percentage, project name, and user emotional state.

[1085] Operation 3-2: The server inputs the extracted features into the AI ​​model.

[1086] Example: Convert the extracted features into tensor format and input them into an AI model.

[1087] Step 4: Leveraging AI models

[1088] Action 4-1: The server uses the AI ​​model to generate automation rules.

[1089] Example: An AI model generates a rule that says, "Check and report progress every day at 9:00 and 17:00, but reduce reminders if the user is feeling stressed."

[1090] Action 4-2: The server verifies the generated rules and makes corrections if necessary.

[1091] Example: The server checks the validity of the rules and manually corrects them if necessary.

[1092] Step 5: Verify and run your automation

[1093] Action 5-1: The user checks the automation rules generated on the terminal.

[1094] Example: A user checks an automatically generated report on their device and clicks the "Approve" button.

[1095] Operation 5-2: The server receives user approval and executes management tasks based on automated rules.

[1096] Example: Every day at 9:00 and 17:00, the server automatically generates a progress report and emails it to the manager, adjusting the frequency of reminders based on the user's emotional state.

[1097] Step 6: Gather feedback and retrain

[1098] Action 6-1: The server collects the results of the automated processing.

[1099] Example: Storing the submission history of automatically generated reports or the user's emotional state in a database.

[1100] Action 6-2: The user uses the device to provide feedback.

[1101] Example: A user enters feedback from a terminal saying, "Please improve the report format."

[1102] Action 6-3: The server retrains the AI ​​model based on the feedback.

[1103] Example: Adding feedback and emotional states to a training dataset and retraining an AI model.

[1104] In this way, the system of the present invention automates administrative tasks while taking into account the user's emotional state, freeing the user from tedious tasks and providing an environment in which they can concentrate on more creative tasks.

[1105] Example 2

[1106] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1107] Conventional management task systems required users to manually input information and perform management tasks each time, resulting in reduced work efficiency. Furthermore, automation rules were generated without taking the user's emotional state into consideration, which could cause stress for the user and lead to poor work performance. Furthermore, there was an insufficient mechanism for effectively collecting feedback and utilizing it to improve the system.

[1108] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for recognizing emotions from user input information and feedback and including them in features, a means for extracting features to be input into a generative AI model for generating automation rules for management tasks, and a means for executing management tasks based on the automation rules. This makes it possible to generate and execute automation rules for management tasks taking into account the user's emotional state, thereby improving work efficiency and user satisfaction.

[1109] A "user" is an entity that inputs information related to management tasks and operates the system.

[1110] A "terminal" is a device for transmitting information entered by a user to a server.

[1111] A "server" is a computer system that receives and analyzes information sent by users, and generates and executes rules for automating administrative tasks.

[1112] "Information" refers to data and feedback about administrative tasks entered by users.

[1113] The "means for recognizing emotions and including them in features" refers to a device or software function that analyzes the emotional state from the user's input information and feedback and extracts the results as features.

[1114] A "generative AI model" is an artificial intelligence algorithm that generates optimal automation rules for management tasks based on input features.

[1115] "Features" are parameters or elements used in data analysis, and are the basic data used to generate automation rules for management tasks.

[1116] "Automation rules" are a series of actions and procedures that the server creates based on the generative AI model to perform management tasks.

[1117] "Feedback" refers to opinions, evaluations, and information on areas for improvement provided by users.

[1118] The system of the present invention starts when a user inputs information about a management task and sends that information to a server. A specific embodiment of this system will be described below.

[1119] A user uses a terminal to input information related to management tasks. For example, when a user reports on the progress of a project, they input text data such as "Project A is 40% complete" into the terminal. The terminal detects the input information and activates the emotion engine. The emotion engine analyzes the user's input status and feedback to recognize the user's emotional state. This makes it possible to obtain the user's stress level and emotional state as analysis results.

[1120] The device sends the input information and emotion analysis results to the server, which receives this information and stores it in a database. The server uses data processing libraries such as Python's Pandas and NumPy to analyze the stored information. This analysis identifies trends and patterns in the progress reports, and uses the emotion engine's analysis results to extract the user's emotional state as features.

[1121] The extracted features are input into an AI model on the server. The AI ​​model is built using machine learning libraries such as TensorFlow and PyTorch, and generates optimal automation rules for management tasks based on the features. For example, it might generate rules such as "check and report progress every day at 9:00 and 17:00" or "reduce reminders if the user is feeling stressed."

[1122] The server sends the generated automation rules to the user's device, where the user can review them. If the user determines that the rules are acceptable, they can click the "Approve" button, and the server will automatically execute management tasks based on the rules. For example, progress reports will be automatically generated at 9:00 and 17:00 every day and emailed to the relevant supervisor. Adjustments will also be made based on the user's emotional state.

[1123] Additionally, the user can use the device to input feedback on the format and content of the automatically generated report. For example, the user may provide feedback such as, "Please improve the format of the report." The device then sends this feedback along with emotion data to the server, which stores it in a database. The server then retrains the AI ​​model based on the feedback and emotion data from the emotion engine, improving the accuracy and efficiency of future automated processes.

[1124] As a concrete example, consider a situation where a user needs to report project progress every day at 9:00 and 17:00. The user enters "Project A progress is 40%" into the device, and the device sends this data to the server. At the same time, the emotion engine runs and identifies that the user is feeling stressed. Based on this result, the AI ​​model generates a rule that states, "Progress checks and reports will be performed every day at 9:00 and 17:00, but with fewer reminders to reduce the user's stress." Once the generated rule is confirmed and approved by the user, the server automatically executes the management tasks at the specified time every day.

[1125] An example of a prompt sentence is the text data, "Project A is 40% complete." This system frees users from reporting tasks, allowing them to focus on important tasks and reducing emotional burden.

[1126] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1127] Step 1:

[1128] The user inputs information about management tasks. For example, "Project A is 40% complete" into the terminal. This input information is captured as data on the terminal. At the same time, the terminal activates the emotion engine. The emotion engine analyzes the user's input and recent feedback to recognize the user's emotional state.

[1129] Input: Administrative information entered by the user (e.g., "Project A is 40% complete").

[1130] Output: Analysis of the user's input information and emotional state.

[1131] Specific behavior:

[1132] The device retrieves the information entered in the text field and performs emotion analysis by calling the emotion engine via an API call.

[1133] Step 2:

[1134] The device sends the user's input information and emotion analysis results to the server using HTTP or HTTPS as the communication protocol.

[1135] Input: Analysis of the user's input information and emotional state.

[1136] Output: Data sent to the server.

[1137] Specific behavior:

[1138] The device converts the acquired input information and emotion analysis results into JSON format or similar and sends them to the server as an HTTP request.

[1139] Step 3:

[1140] The server receives the information sent from the device and stores it in a database, which stores progress report information and the user's emotional state.

[1141] Input: User input information and emotional state sent from the device.

[1142] Output: Information stored in a database.

[1143] Specific behavior:

[1144] The server parses the received data and inserts it into a database in the appropriate format, for example, by using SQL to store the data.

[1145] Step 4:

[1146] The server analyzes the stored data and extracts features. It uses data processing libraries such as Python's Pandas and NumPy to identify trends and patterns in the progress reports. At the same time, it uses the analysis results of the emotion engine to extract features that represent the user's emotional state.

[1147] Input: User input information and emotional state stored in a database.

[1148] Output: Extracted features (e.g., reporting time, progress percentage, project name, emotional state).

[1149] Specific behavior:

[1150] The server reads the data from the database, analyzes it using a data processing library, and extracts features.

[1151] Step 5:

[1152] The server inputs the features into a generative AI model, which is built using machine learning libraries such as TensorFlow and PyTorch, and generates optimal automation rules for management tasks based on the input features.

[1153] Input: Extracted features.

[1154] Output: The generated automation rule.

[1155] Specific behavior:

[1156] The server inputs the features into the generative AI model, and the model performs calculations to generate rules.

[1157] Step 6:

[1158] The server sends the generated automation rules to the user's device, where the user can check the rules.

[1159] Input: The generated automation rule.

[1160] Output: The automation rule that is displayed on the user's device.

[1161] Specific behavior:

[1162] The server converts the generated rules into JSON format and sends them to the terminal. The terminal displays the received data.

[1163] Step 7:

[1164] The user reviews and approves the generated automation rule on the device, for example by clicking the "Approve" button.

[1165] Input: The generated automation rule.

[1166] Output: User authorization information.

[1167] Specific behavior:

[1168] The user checks the rules displayed on the screen and clicks the "Approve" button. The device then sends this approval information to the server.

[1169] Step 8:

[1170] The server automatically executes administrative tasks based on approved rules, such as automatically generating progress reports at 9:00 and 17:00 every day and emailing them to relevant superiors, and also adjusts according to the user's emotional state.

[1171] Inputs: User authorization information and generated automation rules.

[1172] Output: Automatically performed administrative tasks.

[1173] Specific behavior:

[1174] The server schedules tasks based on approved rules, automatically executes administrative tasks, and notifies relevant parties of the execution results.

[1175] Step 9:

[1176] The user can enter feedback on the format and content of the automatically generated report, for example, "Please improve the format of the report."

[1177] Input: User feedback information.

[1178] Output: Feedback information data.

[1179] Specific behavior:

[1180] The device captures the feedback entered in the text field and sends it to the server.

[1181] Step 10:

[1182] The server receives the feedback, performs sentiment analysis again using the emotion engine, and stores the results in a database.The generative AI model is then retrained based on the feedback to improve the accuracy and efficiency of future automated processes.

[1183] Input: User feedback information and sentiment analysis results.

[1184] Output: The retrained generative AI model.

[1185] Specific behavior:

[1186] The server analyzes the feedback and inputs it as retraining data into the generative AI model, improving the model's accuracy.

[1187] (Application example 2)

[1188] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1189] While conventional management task automation systems are capable of analyzing data and generating automation rules, they are unable to take into account the emotions and stress levels of workers, which means that the burden on workers remains low. Furthermore, there is no means for retraining to incorporate feedback, making it difficult to continuously improve the system.

[1190] 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.

[1191] In this invention, the server includes a means for analyzing the user's emotional state using an emotion analysis engine and adjusting the automation rules generated by the AI ​​model based on the analysis results, a means for monitoring the worker's progress and emotional state in real time, and a means for collecting feedback from the user and retraining the AI ​​model, thereby enabling the generation of automation rules that take the worker's emotional state into account and the continuous improvement of the system.

[1192] "Administrative tasks" refer to tasks and procedures that allow users to efficiently carry out their daily business activities.

[1193] "Data input means" refers to the interface and functions that allow users to input information about management tasks into the terminal.

[1194] "Data transmission means" refers to a communication function for transferring input data from the terminal to the server.

[1195] "Data analysis means" refers to a processing function for analyzing data received by the server and extracting necessary information and features.

[1196] An "AI model" refers to a machine learning algorithm that learns patterns from large amounts of data and generates automated rules.

[1197] "Automation rules" refer to a set of procedures or conditions generated by an AI model to streamline administrative tasks.

[1198] An "emotion analysis engine" refers to a function that analyzes the emotional state from user input and feedback and outputs the results.

[1199] "Emotional state" refers to the emotional state of the user when entering data or providing feedback, such as stress, fatigue, or joy.

[1200] "Feedback collection means" refers to a function for collecting evaluations and opinions from users and sending that data to a server.

[1201] "Retraining tools" refers to functions that allow the AI ​​model to retrain based on collected feedback data to improve its accuracy.

[1202] "Real-time monitoring means" refers to a function for monitoring the progress and emotional state of workers in real time.

[1203] This invention is a system for improving the efficiency of factory robots and management tasks in the manufacturing industry. It generates automation rules based on data entered by the user and their emotional state, reducing the burden on workers.

[1204] System Configuration

[1205] Hardware

[1206] Devices: Smartphones, tablets, surveillance cameras in factories, etc.

[1207] Server: Cloud-based or on-premise servers for high-performance data processing.

[1208] Robot: Factory robots used on production lines.

[1209] software

[1210] Programming language: Python

[1211] Machine learning libraries: (TensorFlow, PyTorch, etc.)

[1212] Sentiment analysis engine: Natural language processing engine (e.g. IBM Watson's NLP tool)

[1213] Data Entry and Submission

[1214] Users use smartphones or tablets to input the progress of the production line, entering prompt statements such as "Production progress on Line A is 70%. Today's production work is a little tired." This data is sent to the server in real time.

[1215] Data and Sentiment Analysis

[1216] The server analyzes the received data and extracts features. Using an emotion analysis engine, it analyzes the emotional state (stress or fatigue) from the prompt text entered by the user.

[1217] Automated rule generation using AI models

[1218] The server inputs the extracted features into an AI model to generate automation rules, such as "Check progress every day at 10:00 and 16:00, but reduce reminders if the worker feels fatigued."

[1219] User approval and automatic execution

[1220] The generated automation rules are presented to the user for review and approval. Approved rules are automatically executed by the server. Progress reports are generated at the specified time and sent to the relevant supervisor.

[1221] Feedback gathering and retraining

[1222] Users can input feedback on generated reports and automation rules. Feedback such as "The timing of the report was appropriate, but please change the format" is sent to the server as data. This feedback data is used to retrain the AI ​​model, continuously improving the accuracy and efficiency of the system.

[1223] Specific examples

[1224] Suppose the user enters the following prompt:

[1225] "Production line A is 70% complete. Production work today is a little tiring."

[1226] The server receives this data and uses an emotion analysis engine to identify the emotional state of "fatigue." Based on this information, the AI ​​model generates a new automation rule: "Check progress every day at 10:00 and 16:00, but reduce reminders if the worker feels fatigued." Once the user confirms and approves this rule, the server automatically executes tasks based on this rule. This reduces the burden on workers and enables more efficient management work.

[1227] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1228] Step 1:

[1229] Data Entry and Submission

[1230] The user uses a smartphone or tablet to input the progress of the production line and their emotional state. An example input is, "Production progress on Line A is 70%. Today's production work is a little tiring." This data is saved on the device in real time and then sent to the server.

[1231] input:

[1232] Production line progress

[1233] The user's emotional state

[1234] output:

[1235] Sending data from the device to the server

[1236] Step 2:

[1237] Data reception and analysis

[1238] The server receives the progress data and emotional state data sent by the user. The server uses a data analysis engine to analyze the received data and extract important features (e.g., progress %, working time zone, emotional state).

[1239] input:

[1240] Progress data sent from the device

[1241] Emotional state data

[1242] output:

[1243] Extracted features

[1244] Step 3:

[1245] Emotion analysis

[1246] The server uses an emotion analysis engine to analyze the user's emotional state from the input data, and this analysis identifies an emotional state such as "the user is tired."

[1247] input:

[1248] User input data

[1249] output:

[1250] The user's emotional state

[1251] Step 4:

[1252] Input to AI model and rule generation

[1253] The server inputs the extracted features into a generative AI model to generate rules for automating administrative tasks. For example, specific rules such as "Check progress every day at 10:00 and 16:00, but reduce reminders if the worker feels fatigued" are generated.

[1254] input:

[1255] Extracted features

[1256] output:

[1257] Generated automation rules

[1258] Step 5:

[1259] Presenting and confirming rules

[1260] The generated automation rules are presented to the user, who can review them and click the "Approve" button if there are no problems.

[1261] input:

[1262] Generated automation rules

[1263] output:

[1264] User approval or correction requests

[1265] Step 6:

[1266] Executing automated rules

[1267] After the user approves, the server automatically executes management tasks based on the automation rules, such as automatically generating a progress report at a specified time and sending it to the relevant superior.

[1268] input:

[1269] Approved automation rules

[1270] output:

[1271] Automated administrative tasks

[1272] Step 7:

[1273] Feedback gathering and retraining

[1274] Users can input feedback about generated reports and automation rules. This feedback is sent to the server and used to retrain the AI ​​model. For example, specific feedback such as "The timing of the report was appropriate, but please change the format" can be collected.

[1275] input:

[1276] User Feedback

[1277] output:

[1278] Improved AI models improve accuracy of next automation rules

[1279] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1280] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1281] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1282] [Fourth embodiment]

[1283] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1284] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1285] 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).

[1286] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1287] 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.

[1288] 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).

[1289] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1290] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1291] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1292] 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.

[1293] 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.

[1294] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1295] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1296] The system of the present invention begins when a user inputs data related to management tasks and sends that data to a server. The terminal is responsible for sending the data received from the user to the server. The server analyzes the received data and extracts the features necessary to automate the management tasks. The server then uses an AI model to generate automation rules for the management tasks and executes the automation process based on those rules. The system also continuously improves by collecting feedback from users and retraining the AI ​​model.

[1297] Data collection and input

[1298] A user uses a terminal to input data related to management tasks. For example, when a user reports the progress of a project, he or she inputs "Project A is 40% complete" on the terminal. This data is sent from the terminal to the server.

[1299] Data analysis

[1300] The server analyzes the data received from the terminal. For example, it analyzes the patterns of reports made at specific times or with specific frequency based on the progress report history stored in the database. This analysis identifies routine management task patterns.

[1301] Utilizing AI models

[1302] The server extracts features based on data analysis and inputs them into the AI ​​model. For example, the feature values ​​extracted include the user's reporting time, project progress, and information about the person in charge. Based on these features, the AI ​​model generates automation rules for management tasks. Rules such as "automatically check progress reports at 9:00 and 17:00 every day and send reports to the supervisor" are generated here.

[1303] Executing the automation

[1304] The user checks the generated automation rules on the terminal and approves them if there are no problems. For example, by checking an automatically generated report and clicking the "Approve" button, the server executes the automated process based on the rule. Every day at 9:00 and 17:00, a progress report is automatically generated and sent to the relevant supervisor by email.

[1305] Feedback and Improvements

[1306] The server collects the results of the automated process and stores them in a database. The user uses a device to enter feedback on the format and content of the generated report. For example, the user may provide feedback such as, "Please improve the format of the report." This feedback is sent to the server and used to retrain the AI ​​model. The server then uses the feedback to improve the AI ​​model, thereby increasing the accuracy and efficiency of future automated processes.

[1307] As a concrete example, suppose a user needs to report project progress every day at 9:00 and 17:00. The user accesses a terminal and enters, "Project A progress is 40%." The terminal sends this data to a server, which analyzes the data and identifies common patterns. Based on the identified patterns, an AI model generates a rule that states, "Check and report progress every day at 9:00 and 17:00." Once the generated rule is confirmed and approved by the user, the server automatically executes the management task at the specified time every day. As a result, the user is freed from reporting tasks and can focus on more important tasks.

[1308] The processing flow will be explained below.

[1309] Step 1: Data collection and entry

[1310] Action 1-1: A user uses a terminal to input data related to management operations.

[1311] Example: A user types into a terminal, "Project A is 40% complete."

[1312] Operation 1-2: The terminal transmits the input data to the server.

[1313] Example: The device sends input data in JSON format as a POST request to the server's API endpoint.

[1314] Step 2: Data analysis

[1315] Operation 2-1: The server receives the data sent from the terminal and stores it in a database.

[1316] Example: The server stores the received progress data in a "progress report" table in a MySQL database.

[1317] Action 2-2: The server analyzes the stored data.

[1318] Example: The server runs a query based on historical progress report data to analyze patterns in the time and frequency of reports.

[1319] Step 3: Feature extraction

[1320] Action 3-1: The server extracts features from the analysis data.

[1321] Example: The server extracts features such as reporting time, progress percentage, and project name.

[1322] Operation 3-2: The server inputs the extracted features into the AI ​​model.

[1323] Example: Convert features into tensor format and input them into an AI model.

[1324] Step 4: Leveraging AI models

[1325] Action 4-1: The server uses the AI ​​model to generate automation rules.

[1326] Example: An AI model generates a rule that says, "Check and report progress every day at 9:00 and 17:00."

[1327] Action 4-2: The server verifies the generated rules and makes corrections if necessary.

[1328] Example: The server checks the validity of the rules and manually corrects them if necessary.

[1329] Step 5: Verify and run your automation

[1330] Action 5-1: The user checks the automation rules generated on the terminal.

[1331] Example: A user checks an automatically generated report on their device and clicks the "Approve" button.

[1332] Operation 5-2: The server receives user approval and executes management tasks based on automated rules.

[1333] Example: Every day at 9:00 and 17:00, the server automatically generates a progress report and emails it to the manager.

[1334] Step 6: Gather feedback and retrain

[1335] Action 6-1: The server collects the results of the automated processing.

[1336] Example: Storing the sending history of automatically generated reports in a database.

[1337] Action 6-2: The user uses the device to provide feedback.

[1338] Example: A user enters feedback from a terminal saying, "Please improve the report format."

[1339] Action 6-3: The server retrains the AI ​​model based on the feedback.

[1340] Example: Adding feedback to a training dataset and retraining an AI model.

[1341] This frees users from the hassle of daily management tasks and allows them to focus on more creative work.

[1342] Example 1

[1343] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1344] Traditional management tasks required tedious manual data entry and report creation, requiring a great deal of effort and time. These manual tasks were prone to errors, reducing work efficiency. Furthermore, creating and executing automation rules in existing systems was time-consuming, making it difficult for users to execute business processes quickly and accurately. To solve these issues, automation and streamlining of management tasks was necessary.

[1345] 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.

[1346] In this invention, the server includes means for analyzing received information and extracting features to be input into a generative AI model for generating automation rules for business processes, means for executing business processes based on the generated automation rules, and means for acquiring progress information at certain time periods and sending automatically generated reports. This reduces the amount of manual work required by users, providing an environment where users can focus on important tasks.

[1347] "Information" refers to data that expresses the content of a user's business.

[1348] A "terminal" is a device that allows a user to input information, and includes, for example, a computer or a smartphone.

[1349] A "server" is a computer system that receives information sent from a terminal and analyzes and processes it.

[1350] "Analyzing" is the process of analyzing received information to understand its structure and content.

[1351] A "generative AI model" is an artificial intelligence algorithm that generates business automation rules based on large amounts of data.

[1352] "Features" are important data elements or attributes that are extracted for input into a generative AI model.

[1353] "Automation rules" are a set of rules and procedures established to efficiently automate business processes.

[1354] A "report" is a document summarizing the progress and results of work, and is usually sent to other parties.

[1355] "Feedback" refers to improvements and ratings provided by users to the server, which are used to improve the system.

[1356] The system of the present invention begins when a user inputs information about a task and sends it from their terminal to a server. The terminal is a device operated by the user and serves to transmit information. The server analyzes the information received from the terminal and generates automation rules using a generative AI model.

[1357] Specifically, the server uses programming languages ​​such as Python and R to analyze the received information. Machine learning libraries such as Scikit-learn and TensorFlow are used as generative AI models. Based on the results of this analysis, the server extracts features and inputs them into the AI ​​model to generate automation rules. Tasks are then automated based on the generated rules, and reports are sent to the user.

[1358] For example, if a user types "Project A is 40% complete," that information is sent to the server. The server analyzes past progress data and the user's reporting patterns. The AI ​​model then generates a rule that says, "Check progress reports every day at 9:00 and 17:00 and send reports to your supervisor."

[1359] Additionally, users can use their devices to provide feedback on the format and content of the generated report, such as "Please improve the format of the report." This feedback is sent to the server and used to retrain the AI ​​model, improving the accuracy and efficiency of future automated processes.

[1360] An example of a prompt is as follows:

[1361] "Users need to report on project progress daily. Can you explain how to automate this reporting?"

[1362] "Please explain in detail the steps in your system that analyzes business data and generates automated rules."

[1363] "Please tell me how the AI ​​model works to automatically generate a progress report and send it to my boss at a fixed time every day."

[1364] This automates tasks that users previously performed manually, providing an environment in which users can focus on important tasks.

[1365] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1366] Step 1:

[1367] The user uses the terminal to input information about the business.

[1368] Specifically, the user inputs into the terminal, "Project A is 40% complete."

[1369] Input: Information about the job entered by the user.

[1370] Output: Data of information entered into the terminal.

[1371] Step 2:

[1372] The terminal transmits the input information to the server.

[1373] The device sends information to the server using an HTTP POST request.

[1374] Input: Data of information entered into the device.

[1375] Output: The data of the information sent to the server.

[1376] Step 3:

[1377] The server analyzes the received information.

[1378] The server uses Python or R to analyze the incoming data and references a database to understand its meaning.

[1379] Input: The data of the information sent to the server.

[1380] Output: Parsed data.

[1381] Step 4:

[1382] The server extracts features from the analyzed data.

[1383] The server uses machine learning libraries such as Scikit-learn and TensorFlow to extract important features from the data, such as user ID, reporting time, and progress.

[1384] Input: Parsed data.

[1385] Output: Extracted features.

[1386] Step 5:

[1387] The server inputs features into the generated AI model and generates automation rules.

[1388] The server inputs the extracted features into an AI model and generates rules such as "check progress reports every day at 9:00 and 17:00 and automatically send the results to the supervisor."

[1389] Input: Extracted features.

[1390] Output: The generated automation rule.

[1391] Step 6:

[1392] The user checks the generated automation rules and approves them from the terminal.

[1393] The user checks the automation rules on the device's confirmation screen and clicks the "Approve" button.

[1394] Input: The generated automation rule.

[1395] Output: The approved automation rule.

[1396] Step 7:

[1397] The server executes tasks based on the approved automation rules.

[1398] The server retrieves the latest progress information at the specified time and sends an automatically generated report to the superior via the mail server.

[1399] Input: Approved automation rules.

[1400] Output: Report sent to supervisor.

[1401] Step 8:

[1402] The server records the results of the automated process and collects user feedback.

[1403] The server stores the processing results in a database, and the user inputs feedback on the format and content of the report through the terminal, such as "Please improve the format of the report."

[1404] Input: The report you wish to provide feedback on.

[1405] Output: Collected feedback data.

[1406] Step 9:

[1407] The server retrains the generative AI model based on the collected feedback.

[1408] The collected feedback is used to adjust the AI ​​model to improve the accuracy and efficiency of future automated processes.

[1409] Input: Collected feedback data.

[1410] Output: The retrained generative AI model.

[1411] (Application example 1)

[1412] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1413] Factory production management requires a lot of manual work, such as reporting production progress and checking production line efficiency, which creates the risk of reduced efficiency and human error.In addition, it is difficult to detect abnormalities on the production line early and take appropriate measures, which affects overall production efficiency, creating an issue.

[1414] 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.

[1415] In this invention, the server includes: a means for a user to input data related to management tasks; a means for a terminal to send the input data to the server; a means for the server to analyze the received data and extract features to be input into an AI model for generating automation rules for management tasks; a means for the server to execute management tasks based on the generated automation rules; a means for collecting feedback from users and retraining the AI ​​model; a means for the terminal to report factory production progress; a means for the server to generate automation rules based on the reports and for a robot to check production line efficiency. This automates the reporting of production progress and the checking of production line efficiency, making it possible to detect efficiency declines early and take measures.

[1416] "User" means a person or entity that utilizes the system to input data related to administrative tasks.

[1417] "Management work" refers to tasks such as reporting production progress at production sites such as factories, checking the efficiency of production lines, and inventory management.

[1418] A "terminal" is a device used by a user to input data and send it to a server, such as a smartphone or tablet.

[1419] The "server" is a computer system that analyzes the received data and operates an AI model to generate automation rules for administrative tasks.

[1420] "Features" refer to important information and patterns of management operations that are extracted through data analysis and input into the AI ​​model.

[1421] "AI Model" means a machine learning model used to generate rules for automating administrative tasks based on received data.

[1422] "Automation rules" are specific procedures and rules generated using AI models to efficiently execute management tasks.

[1423] "Feedback" refers to opinions and requests for improvement provided by users regarding the results of automated processing, and is information used to retrain AI models.

[1424] "Production progress" is data that indicates the progress and completion status of production lines in a factory.

[1425] A "robot" is a mechanical device that can receive commands from a server to check the efficiency of a production line and take necessary improvement measures.

[1426] This invention is a system for automating production management tasks in a factory, and begins when a user inputs data related to the management tasks and a terminal transmits the data to a server. Specific embodiments are described below.

[1427] Users use devices such as smartphones and tablets to input data on production progress and production line efficiency. For example, they may report that "production progress on line A is 80% of normal." The input data is then sent from the device to the server.

[1428] The server analyzes the received data and extracts the features necessary to generate automation rules for management tasks. These features include the degree of production progress, production line information, and information about the person in charge. This data is then input into a machine learning model (AI model).

[1429] The AI ​​model generates automation rules for management tasks based on the received features. For example, it generates a rule such as "Check production progress every day at 9:00 and 17:00, and take immediate action if any abnormalities are found." The generated rules are then applied to the automation of management tasks by the server.

[1430] The user can review the generated automation rules and approve them as necessary. This approval prepares the server to perform the actual management tasks. For example, the user can click the "Approve" button on their smartphone to officially apply the automation rules.

[1431] The server executes management tasks based on automation rules. Specifically, it sends commands to the robot to check the efficiency of the production line and detect abnormalities. The robot then inspects the production line according to the server's instructions and takes necessary corrective measures.

[1432] In addition, the server collects feedback from users and uses it to retrain the AI ​​model. For example, if a user provides feedback such as "Please improve the report format," that information is sent to the server and used to improve the accuracy of the AI ​​model.

[1433] As a concrete example, consider a case where a user needs to report production progress every day at 9:00 and 17:00. The user accesses a terminal and enters, "Production progress on Line A is 80% of normal." The terminal sends this data to a server, which analyzes the data and identifies common patterns. Based on the identified patterns, an AI model generates a rule that states, "Confirm and report progress every day at 9:00 and 17:00." Once the generated rule is confirmed and approved by the user, the server automatically executes the management task at the specified time every day. As a result, the user is freed from reporting tasks and can focus on more important tasks.

[1434] The hardware used includes smartphones and tablets for users to input data, a server that receives and analyzes the data, and factory robots that operate based on instructions.Software used includes Python for data analysis, the machine learning library Scikit-learn, and Flask for robot control.

[1435] An example of a prompt is as follows:

[1436] "Production progress on Line A is at 80% of normal. Please investigate the cause of the decrease in efficiency."

[1437] "Line B efficiency is normal. No special improvements are required."

[1438] In this way, the present invention makes it possible to improve the efficiency of production management operations in factories, reduce human error, and detect abnormalities in the production line early and take measures to correct them.

[1439] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1440] Step 1:

[1441] The user uses a terminal to input data related to management tasks. Specifically, they use a smartphone or tablet to input information such as production progress and production line efficiency. They input prompt statements such as "Production progress on line A is 80% of normal." The input data is temporarily saved in the terminal.

[1442] Input: Production progress data entered by the user into a smartphone or tablet

[1443] Output: Temporarily saved production progress data

[1444] Step 2:

[1445] The device sends the entered data to the server. The device converts the entered data into an appropriate format and sends it to the server's API endpoint. The sent data is received on the server side.

[1446] Input: Temporarily saved production progress data

[1447] Output: Production progress data sent to the server

[1448] Step 3:

[1449] The server analyzes the received data and extracts features. Specifically, it extracts important information (e.g., progress level, production line, person in charge) from the received production progress data. Machine learning libraries such as Python and Scikit-learn are used for the analysis.

[1450] Input: Production progress data sent to the server

[1451] Output: Extracted features (progress, production line information, etc.)

[1452] Step 4:

[1453] The server inputs the extracted features into an AI model and generates automation rules. The AI ​​model has been retrained in advance based on feedback, so it analyzes the input data and generates appropriate automation rules for management tasks. For example, the generated rules might be something like, "Check production progress every day at 9:00 and 17:00, and take immediate action if any abnormalities are found."

[1454] Input: extracted features

[1455] Output: Generated automation rules

[1456] Step 5:

[1457] The server notifies the user of the generated automated rule, and the user reviews and approves the rule. The user receives a notification on their smartphone or tablet, checks the rule, and approves it by clicking the "Approve" button.

[1458] Input: Generated automation rules

[1459] Output: User approval

[1460] Step 6:

[1461] With the user's approval, the server executes management tasks based on automation rules. For example, it can issue instructions to robots to check the efficiency of the production line or take measures to deal with abnormalities. The robots receive instructions from the server, inspect the production line, and take necessary corrective measures.

[1462] Input: User approval

[1463] Output: Instructions to the robot and execution results

[1464] Step 7:

[1465] The server collects the results of the automated processing and collects feedback from users based on those results. For example, users can input their opinions or requests, such as "Please improve the report format," into their smartphones or tablets, and the input is sent to the server.

[1466] Input: Results of automated processing

[1467] Output: User feedback

[1468] Step 8:

[1469] The server retrains the AI ​​model based on the feedback, and uses the collected feedback data to refine the AI ​​model, improving the accuracy and efficiency of the automation rules for future management tasks.

[1470] Input: User feedback

[1471] Output: Retrained AI model

[1472] In this way, the automation of factory production management operations is efficiently realized through cooperation between the server, terminals, and users.

[1473] 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.

[1474] The system of the present invention begins when a user inputs data related to management tasks and sends that data to a server. The terminal is responsible for sending the data received from the user to the server. The server analyzes the received data and extracts the features necessary to automate the management tasks. The server uses an AI model to generate automation rules for the management tasks and executes the automation process based on those rules. The system also continuously improves by collecting feedback from users and retraining the AI ​​model.

[1475] Furthermore, the present invention incorporates an emotion engine that recognizes emotions from user input data and feedback. The emotion engine analyzes the user's emotional state in real time and adjusts the automation rules generated by the AI ​​model based on the analysis results. This provides more personalized automation rules that take the user's emotional state into account.

[1476] Data collection and input

[1477] A user uses a terminal to input data related to management tasks. For example, when reporting the progress of a project, the user inputs "Project A is 40% complete" on the terminal. This data is sent from the terminal to the server. At the same time, the terminal runs an emotion engine to analyze the user's emotions from the input and feedback.

[1478] Data analysis and sentiment analysis

[1479] The server receives the data sent from the device and stores it in a database. For example, when the server analyzes progress report data, the emotion engine also analyzes the user's input data and feedback to identify the user's emotional state. Based on the results, the server extracts features to generate automation rules for management tasks.

[1480] Utilizing AI models

[1481] The server extracts features based on data analysis and sentiment analysis and inputs them into the AI ​​model. For example, the user's reporting time, progress percentage, project name, and emotional state are extracted as features. The AI ​​model generates rules for automating management tasks based on these features. In addition to the rule "check and report progress every day at 9:00 and 17:00," adjustments based on emotions are made, such as "reduce reminders if the user is feeling stressed."

[1482] Check and run your automation

[1483] The user checks the generated automation rules on their device and approves them if there are no problems. For example, by checking an automatically generated report and clicking the "Approve" button, the server executes the automated process based on the rules. Progress reports are automatically generated every day at 9:00 and 17:00 and are emailed to the relevant supervisor. Adjustments are also made according to the user's emotional state.

[1484] Gathering feedback and retraining

[1485] The server collects the results of the automated process and stores them in a database. The user uses a device to input feedback about the format and content of the generated report. For example, the user may provide feedback such as, "Please improve the format of the report." This feedback is sent to the server and used to retrain the AI ​​model along with emotion data from the emotion engine. The server uses the feedback to improve the AI ​​model, thereby increasing the accuracy and efficiency of future automated processes.

[1486] As a concrete example, suppose a user needs to report project progress every day at 9:00 AM and 5:00 PM. The user enters "Project A is 40% complete" into their device. The device sends this data to a server, which analyzes the data and identifies common patterns. At the same time, an emotion engine analyzes the user's input and feedback and identifies that the user is feeling stressed. Based on this result, an AI model generates a rule that states, "Confirm and report progress every day at 9:00 AM and 5:00 PM, but reduce reminders to reduce user stress." Once the user confirms and approves the generated rule, the server automatically executes the management task at the specified time every day. As a result, the user is freed from reporting tasks, allowing them to focus on more important tasks and reducing their emotional burden.

[1487] The processing flow will be explained below.

[1488] Step 1: Data collection and entry

[1489] Action 1-1: A user uses a terminal to input data related to management operations.

[1490] Example: A user types into a terminal, "Project A is 40% complete."

[1491] Operation 1-2: The terminal transmits the input data to the server.

[1492] Example: The device sends input data in JSON format as a POST request to the server's API endpoint.

[1493] Action 1-3: The device analyzes the user's facial expressions, input speed, etc. and sends the results to the emotion engine.

[1494] Example: Sending user facial expression data captured by a camera to an emotion engine.

[1495] Step 2: Data analysis and sentiment analysis

[1496] Operation 2-1: The server receives the data sent from the terminal and stores it in a database.

[1497] Example: The server stores the received progress data in a "progress report" table in a MySQL database.

[1498] Action 2-2: The server analyzes the stored data.

[1499] Example: The server runs a query based on historical progress report data to analyze patterns in the time and frequency of reports.

[1500] Action 2-3: The emotion engine analyzes the transmitted data and identifies the user's emotional state.

[1501] Example: An emotion engine analyzes facial expression data and determines that the user is stressed.

[1502] Step 3: Feature extraction

[1503] Action 3-1: The server extracts features from the analysis data.

[1504] Example: The server extracts features such as reporting time, progress percentage, project name, and user emotional state.

[1505] Operation 3-2: The server inputs the extracted features into the AI ​​model.

[1506] Example: Convert the extracted features into tensor format and input them into an AI model.

[1507] Step 4: Leveraging AI models

[1508] Action 4-1: The server uses the AI ​​model to generate automation rules.

[1509] Example: An AI model generates a rule that says, "Check and report progress every day at 9:00 and 17:00, but reduce reminders if the user is feeling stressed."

[1510] Action 4-2: The server verifies the generated rules and makes corrections if necessary.

[1511] Example: The server checks the validity of the rules and manually corrects them if necessary.

[1512] Step 5: Verify and run your automation

[1513] Action 5-1: The user checks the automation rules generated on the terminal.

[1514] Example: A user checks an automatically generated report on their device and clicks the "Approve" button.

[1515] Operation 5-2: The server receives user approval and executes management tasks based on automated rules.

[1516] Example: Every day at 9:00 and 17:00, the server automatically generates a progress report and emails it to the manager, adjusting the frequency of reminders based on the user's emotional state.

[1517] Step 6: Gather feedback and retrain

[1518] Action 6-1: The server collects the results of the automated processing.

[1519] Example: Storing the submission history of automatically generated reports or the user's emotional state in a database.

[1520] Action 6-2: The user uses the device to provide feedback.

[1521] Example: A user enters feedback from a terminal saying, "Please improve the report format."

[1522] Action 6-3: The server retrains the AI ​​model based on the feedback.

[1523] Example: Adding feedback and emotional states to a training dataset and retraining an AI model.

[1524] In this way, the system of the present invention automates administrative tasks while taking into account the user's emotional state, freeing the user from tedious tasks and providing an environment in which they can concentrate on more creative tasks.

[1525] Example 2

[1526] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1527] Conventional management task systems required users to manually input information and perform management tasks each time, resulting in reduced work efficiency. Furthermore, automation rules were generated without taking the user's emotional state into consideration, which could cause stress for the user and lead to poor work performance. Furthermore, there was an insufficient mechanism for effectively collecting feedback and utilizing it to improve the system.

[1528] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for recognizing emotions from user input information and feedback and including them in features, a means for extracting features to be input into a generative AI model for generating automation rules for management tasks, and a means for executing management tasks based on the automation rules. This makes it possible to generate and execute automation rules for management tasks taking into account the user's emotional state, thereby improving work efficiency and user satisfaction.

[1529] A "user" is an entity that inputs information related to management tasks and operates the system.

[1530] A "terminal" is a device for transmitting information entered by a user to a server.

[1531] A "server" is a computer system that receives and analyzes information sent by users, and generates and executes rules for automating administrative tasks.

[1532] "Information" refers to data and feedback about administrative tasks entered by users.

[1533] The "means for recognizing emotions and including them in features" refers to a device or software function that analyzes the emotional state from the user's input information and feedback and extracts the results as features.

[1534] A "generative AI model" is an artificial intelligence algorithm that generates optimal automation rules for management tasks based on input features.

[1535] "Features" are parameters or elements used in data analysis, and are the basic data used to generate automation rules for management tasks.

[1536] "Automation rules" are a series of actions and procedures that the server creates based on the generative AI model to perform management tasks.

[1537] "Feedback" refers to opinions, evaluations, and information on areas for improvement provided by users.

[1538] The system of the present invention starts when a user inputs information about a management task and sends that information to a server. A specific embodiment of this system will be described below.

[1539] A user uses a terminal to input information related to management tasks. For example, when a user reports on the progress of a project, they input text data such as "Project A is 40% complete" into the terminal. The terminal detects the input information and activates the emotion engine. The emotion engine analyzes the user's input status and feedback to recognize the user's emotional state. This makes it possible to obtain the user's stress level and emotional state as analysis results.

[1540] The device sends the input information and emotion analysis results to the server, which receives this information and stores it in a database. The server uses data processing libraries such as Python's Pandas and NumPy to analyze the stored information. This analysis identifies trends and patterns in the progress reports, and uses the emotion engine's analysis results to extract the user's emotional state as features.

[1541] The extracted features are input into an AI model on the server. The AI ​​model is built using machine learning libraries such as TensorFlow and PyTorch, and generates optimal automation rules for management tasks based on the features. For example, it might generate rules such as "check and report progress every day at 9:00 and 17:00" or "reduce reminders if the user is feeling stressed."

[1542] The server sends the generated automation rules to the user's device, where the user can review them. If the user determines that the rules are acceptable, they can click the "Approve" button, and the server will automatically execute management tasks based on the rules. For example, progress reports will be automatically generated at 9:00 and 17:00 every day and emailed to the relevant supervisor. Adjustments will also be made based on the user's emotional state.

[1543] Additionally, the user can use the device to input feedback on the format and content of the automatically generated report. For example, the user may provide feedback such as, "Please improve the format of the report." The device then sends this feedback along with emotion data to the server, which stores it in a database. The server then retrains the AI ​​model based on the feedback and emotion data from the emotion engine, improving the accuracy and efficiency of future automated processes.

[1544] As a concrete example, consider a situation where a user needs to report project progress every day at 9:00 and 17:00. The user enters "Project A progress is 40%" into the device, and the device sends this data to the server. At the same time, the emotion engine runs and identifies that the user is feeling stressed. Based on this result, the AI ​​model generates a rule that states, "Progress checks and reports will be performed every day at 9:00 and 17:00, but with fewer reminders to reduce the user's stress." Once the generated rule is confirmed and approved by the user, the server automatically executes the management tasks at the specified time every day.

[1545] An example of a prompt sentence is the text data, "Project A is 40% complete." This system frees users from reporting tasks, allowing them to focus on important tasks and reducing emotional burden.

[1546] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1547] Step 1:

[1548] The user inputs information about management tasks. For example, "Project A is 40% complete" into the terminal. This input information is captured as data on the terminal. At the same time, the terminal activates the emotion engine. The emotion engine analyzes the user's input and recent feedback to recognize the user's emotional state.

[1549] Input: Administrative information entered by the user (e.g., "Project A is 40% complete").

[1550] Output: Analysis of the user's input information and emotional state.

[1551] Specific behavior:

[1552] The device retrieves the information entered in the text field and performs emotion analysis by calling the emotion engine via an API call.

[1553] Step 2:

[1554] The device sends the user's input information and emotion analysis results to the server using HTTP or HTTPS as the communication protocol.

[1555] Input: Analysis of the user's input information and emotional state.

[1556] Output: Data sent to the server.

[1557] Specific behavior:

[1558] The device converts the acquired input information and emotion analysis results into JSON format or similar and sends them to the server as an HTTP request.

[1559] Step 3:

[1560] The server receives the information sent from the device and stores it in a database, which stores progress report information and the user's emotional state.

[1561] Input: User input information and emotional state sent from the device.

[1562] Output: Information stored in a database.

[1563] Specific behavior:

[1564] The server parses the received data and inserts it into a database in the appropriate format, for example, by using SQL to store the data.

[1565] Step 4:

[1566] The server analyzes the stored data and extracts features. It uses data processing libraries such as Python's Pandas and NumPy to identify trends and patterns in the progress reports. At the same time, it uses the analysis results of the emotion engine to extract features that represent the user's emotional state.

[1567] Input: User input information and emotional state stored in a database.

[1568] Output: Extracted features (e.g., reporting time, progress percentage, project name, emotional state).

[1569] Specific behavior:

[1570] The server reads the data from the database, analyzes it using a data processing library, and extracts features.

[1571] Step 5:

[1572] The server inputs the features into a generative AI model, which is built using machine learning libraries such as TensorFlow and PyTorch, and generates optimal automation rules for management tasks based on the input features.

[1573] Input: Extracted features.

[1574] Output: The generated automation rule.

[1575] Specific behavior:

[1576] The server inputs the features into the generative AI model, and the model performs calculations to generate rules.

[1577] Step 6:

[1578] The server sends the generated automation rules to the user's device, where the user can check the rules.

[1579] Input: The generated automation rule.

[1580] Output: The automation rule that is displayed on the user's device.

[1581] Specific behavior:

[1582] The server converts the generated rules into JSON format and sends them to the terminal. The terminal displays the received data.

[1583] Step 7:

[1584] The user reviews and approves the generated automation rule on the device, for example by clicking the "Approve" button.

[1585] Input: The generated automation rule.

[1586] Output: User authorization information.

[1587] Specific behavior:

[1588] The user checks the rules displayed on the screen and clicks the "Approve" button. The device then sends this approval information to the server.

[1589] Step 8:

[1590] The server automatically executes administrative tasks based on approved rules, such as automatically generating progress reports at 9:00 and 17:00 every day and emailing them to relevant superiors, and also adjusts according to the user's emotional state.

[1591] Inputs: User authorization information and generated automation rules.

[1592] Output: Automatically performed administrative tasks.

[1593] Specific behavior:

[1594] The server schedules tasks based on approved rules, automatically executes administrative tasks, and notifies relevant parties of the execution results.

[1595] Step 9:

[1596] The user can enter feedback on the format and content of the automatically generated report, for example, "Please improve the format of the report."

[1597] Input: User feedback information.

[1598] Output: Feedback information data.

[1599] Specific behavior:

[1600] The device captures the feedback entered in the text field and sends it to the server.

[1601] Step 10:

[1602] The server receives the feedback, performs sentiment analysis again using the emotion engine, and stores the results in a database.The generative AI model is then retrained based on the feedback to improve the accuracy and efficiency of future automated processes.

[1603] Input: User feedback information and sentiment analysis results.

[1604] Output: The retrained generative AI model.

[1605] Specific behavior:

[1606] The server analyzes the feedback and inputs it as retraining data into the generative AI model, improving the model's accuracy.

[1607] (Application example 2)

[1608] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1609] While conventional management task automation systems are capable of analyzing data and generating automation rules, they are unable to take into account the emotions and stress levels of workers, which means that the burden on workers remains low. Furthermore, there is no means for retraining to incorporate feedback, making it difficult to continuously improve the system.

[1610] 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.

[1611] In this invention, the server includes a means for analyzing the user's emotional state using an emotion analysis engine and adjusting the automation rules generated by the AI ​​model based on the analysis results, a means for monitoring the worker's progress and emotional state in real time, and a means for collecting feedback from the user and retraining the AI ​​model, thereby enabling the generation of automation rules that take the worker's emotional state into account and the continuous improvement of the system.

[1612] "Administrative tasks" refer to tasks and procedures that allow users to efficiently carry out their daily business activities.

[1613] "Data input means" refers to the interface and functions that allow users to input information about management tasks into the terminal.

[1614] "Data transmission means" refers to a communication function for transferring input data from the terminal to the server.

[1615] "Data analysis means" refers to a processing function for analyzing data received by the server and extracting necessary information and features.

[1616] An "AI model" refers to a machine learning algorithm that learns patterns from large amounts of data and generates automated rules.

[1617] "Automation rules" refer to a set of procedures or conditions generated by an AI model to streamline administrative tasks.

[1618] An "emotion analysis engine" refers to a function that analyzes the emotional state from user input and feedback and outputs the results.

[1619] "Emotional state" refers to the emotional state of the user when entering data or providing feedback, such as stress, fatigue, or joy.

[1620] "Feedback collection means" refers to a function for collecting evaluations and opinions from users and sending that data to a server.

[1621] "Retraining tools" refers to functions that allow the AI ​​model to retrain based on collected feedback data to improve its accuracy.

[1622] "Real-time monitoring means" refers to a function for monitoring the progress and emotional state of workers in real time.

[1623] This invention is a system for improving the efficiency of factory robots and management tasks in the manufacturing industry. It generates automation rules based on data entered by the user and their emotional state, reducing the burden on workers.

[1624] System Configuration

[1625] Hardware

[1626] Devices: Smartphones, tablets, surveillance cameras in factories, etc.

[1627] Server: Cloud-based or on-premise servers for high-performance data processing.

[1628] Robot: Factory robots used on production lines.

[1629] software

[1630] Programming language: Python

[1631] Machine learning libraries: (TensorFlow, PyTorch, etc.)

[1632] Sentiment analysis engine: Natural language processing engine (e.g. IBM Watson's NLP tool)

[1633] Data Entry and Submission

[1634] Users use smartphones or tablets to input the progress of the production line, entering prompt statements such as "Production progress on Line A is 70%. Today's production work is a little tired." This data is sent to the server in real time.

[1635] Data and Sentiment Analysis

[1636] The server analyzes the received data and extracts features. Using an emotion analysis engine, it analyzes the emotional state (stress or fatigue) from the prompt text entered by the user.

[1637] Automated rule generation using AI models

[1638] The server inputs the extracted features into an AI model to generate automation rules, such as "Check progress every day at 10:00 and 16:00, but reduce reminders if the worker feels fatigued."

[1639] User approval and automatic execution

[1640] The generated automation rules are presented to the user for review and approval. Approved rules are automatically executed by the server. Progress reports are generated at the specified time and sent to the relevant supervisor.

[1641] Feedback gathering and retraining

[1642] Users can input feedback on generated reports and automation rules. Feedback such as "The timing of the report was appropriate, but please change the format" is sent to the server as data. This feedback data is used to retrain the AI ​​model, continuously improving the accuracy and efficiency of the system.

[1643] Specific examples

[1644] Suppose the user enters the following prompt:

[1645] "Production line A is 70% complete. Production work today is a little tiring."

[1646] The server receives this data and uses an emotion analysis engine to identify the emotional state of "fatigue." Based on this information, the AI ​​model generates a new automation rule: "Check progress every day at 10:00 and 16:00, but reduce reminders if the worker feels fatigued." Once the user confirms and approves this rule, the server automatically executes tasks based on this rule. This reduces the burden on workers and enables more efficient management work.

[1647] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1648] Step 1:

[1649] Data Entry and Submission

[1650] The user uses a smartphone or tablet to input the progress of the production line and their emotional state. An example input is, "Production progress on Line A is 70%. Today's production work is a little tiring." This data is saved on the device in real time and then sent to the server.

[1651] input:

[1652] Production line progress

[1653] The user's emotional state

[1654] output:

[1655] Sending data from the device to the server

[1656] Step 2:

[1657] Data reception and analysis

[1658] The server receives the progress data and emotional state data sent by the user. The server uses a data analysis engine to analyze the received data and extract important features (e.g., progress %, working time zone, emotional state).

[1659] input:

[1660] Progress data sent from the device

[1661] Emotional state data

[1662] output:

[1663] Extracted features

[1664] Step 3:

[1665] Emotion analysis

[1666] The server uses an emotion analysis engine to analyze the user's emotional state from the input data, and this analysis identifies an emotional state such as "the user is tired."

[1667] input:

[1668] User input data

[1669] output:

[1670] The user's emotional state

[1671] Step 4:

[1672] Input to AI model and rule generation

[1673] The server inputs the extracted features into a generative AI model to generate rules for automating administrative tasks. For example, specific rules such as "Check progress every day at 10:00 and 16:00, but reduce reminders if the worker feels fatigued" are generated.

[1674] input:

[1675] Extracted features

[1676] output:

[1677] Generated automation rules

[1678] Step 5:

[1679] Presenting and confirming rules

[1680] The generated automation rules are presented to the user, who can review them and click the "Approve" button if there are no problems.

[1681] input:

[1682] Generated automation rules

[1683] output:

[1684] User approval or correction requests

[1685] Step 6:

[1686] Executing automated rules

[1687] After the user approves, the server automatically executes management tasks based on the automation rules, such as automatically generating a progress report at a specified time and sending it to the relevant superior.

[1688] input:

[1689] Approved automation rules

[1690] output:

[1691] Automated administrative tasks

[1692] Step 7:

[1693] Feedback gathering and retraining

[1694] Users can input feedback about generated reports and automation rules. This feedback is sent to the server and used to retrain the AI ​​model. For example, specific feedback such as "The timing of the report was appropriate, but please change the format" can be collected.

[1695] input:

[1696] User Feedback

[1697] output:

[1698] Improved AI models improve accuracy of next automation rules

[1699] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1700] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1701] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1702] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1703] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1704] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1705] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1706] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1707] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1708] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1709] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1710] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1711] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1712] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1713] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1714] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1715] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1716] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1717] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1718] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1719] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1720] The following is further disclosed regarding the above embodiment.

[1721] (Claim 1)

[1722] means for a user to input data relating to administrative tasks;

[1723] A means for transmitting input data from the terminal to a server;

[1724] A means for analyzing the data received by the server and extracting features to be input into an AI model for generating automation rules for management tasks;

[1725] a means for the server to perform management tasks based on the generated automation rules;

[1726] A system that includes a means to collect user feedback and retrain the AI ​​model.

[1727] (Claim 2)

[1728] 10. The system of claim 1, wherein the server includes means for performing administrative tasks based on automated rules with user approval.

[1729] (Claim 3)

[1730] 10. The system of claim 1, wherein the server includes means for identifying common management practice patterns from the analyzed data.

[1731] "Example 1"

[1732] (Claim 1)

[1733] a means for a user to input business information;

[1734] A means for transmitting input information from the terminal to a server;

[1735] A means for analyzing the information received by the server and extracting features to be input into a generative AI model for generating business automation rules;

[1736] A means for the server to execute a task based on the generated automation rules;

[1737] A means of collecting user feedback and retraining the generative AI model; and

[1738] A system including a means for a server to obtain progress information at a fixed time period and send automatically generated reports.

[1739] (Claim 2)

[1740] 2. The system of claim 1, wherein the server includes means for executing tasks based on automated rules with user approval.

[1741] (Claim 3)

[1742] 10. The system of claim 1, wherein the server includes means for identifying common business patterns from the analyzed information.

[1743] "Application Example 1"

[1744] (Claim 1)

[1745] means for a user to input data relating to administrative tasks;

[1746] A means for transmitting input data from the terminal to a server;

[1747] A means for analyzing the data received by the server and extracting features to be input into an AI model for generating automation rules for management tasks;

[1748] a means for the server to perform management tasks based on the generated automation rules;

[1749] A means to collect user feedback and retrain the AI ​​model;

[1750] a means for the terminal to report on the production progress of the factory;

[1751] The server generates automation rules based on the reports, providing the robot with a means to check the efficiency of the production line.

[1752] Including system.

[1753] (Claim 2)

[1754] 10. The system of claim 1, wherein the server includes means for performing administrative tasks based on automated rules with user approval.

[1755] (Claim 3)

[1756] 10. The system of claim 1, wherein the server includes means for identifying common management practice patterns from the analyzed data.

[1757] "Example 2: Combining Emotion Engines"

[1758] (Claim 1)

[1759] a means for a user to input information regarding administrative tasks;

[1760] A means for transmitting input information from the terminal to a server;

[1761] A means for analyzing the information received by the server and extracting features to be input into a generative AI model for generating automation rules for management tasks;

[1762] a means for the server to perform management tasks based on the generated automation rules;

[1763] A means of collecting user feedback and retraining the generative AI model; and

[1764] A means for recognizing emotions from user input information and feedback and including the emotions in the features;

[1765] A system including:

[1766] (Claim 2)

[1767] 10. The system of claim 1, wherein the server includes means for performing administrative tasks based on automated rules with user approval.

[1768] (Claim 3)

[1769] 10. The system of claim 1, wherein the server includes means for identifying common management patterns from the analyzed information.

[1770] "Application example 2 when combining emotion engines"

[1771] (Claim 1)

[1772] means for a user to input data relating to administrative tasks;

[1773] A means for transmitting input data from the terminal to a server;

[1774] A means for analyzing the data received by the server and extracting features to be input into an AI model for generating automation rules for management tasks;

[1775] a means for the server to perform management tasks based on the generated automation rules;

[1776] A means to collect user feedback and retrain the AI ​​model;

[1777] A means for analyzing the user's emotional state using an emotion analysis engine and adjusting the automation rules generated by the AI ​​model based on the analysis results;

[1778] A system including a means for monitoring the progress and emotional state of workers in real time.

[1779] (Claim 2)

[1780] 10. The system of claim 1, wherein the server includes means for performing administrative tasks based on automated rules with user approval.

[1781] (Claim 3)

[1782] The system of claim 1, wherein the server includes means for identifying common management task patterns from the analyzed data, and means for adjusting automation rules based on data entered by workers and emotion analysis results. [Explanation of symbols]

[1783] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for a user to input data relating to administrative tasks; A means for transmitting input data from the terminal to a server; A means for analyzing the data received by the server and extracting features to be input into an AI model for generating automation rules for management tasks; a means for the server to perform management tasks based on the generated automation rules; A system that includes a means to collect user feedback and retrain the AI ​​model.

2. 2. The system of claim 1, wherein the server includes means for performing administrative tasks based on automated rules with user approval.

3. 2. The system of claim 1, wherein the server includes means for identifying common administrative patterns from the analyzed data.

Images