System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting and storing business data in a database; means for analyzing the stored data and identifying a problem; means for generating an improvement proposal optimized for the identified problem; and means for displaying the generated improvement proposal to a user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In today's business environment, efficient organizational management is a source of competitive advantage. However, identifying specific issues within an organization and implementing sustainable improvement measures can sometimes be difficult. Furthermore, the cost of using expensive consultants is a significant hurdle, making it unsuitable for small and medium-sized enterprises. Furthermore, organizational issues include insufficient data utilization, inefficient communication, and resistance to change. Individual employees also face challenges such as unclear goals, lack of leadership, uneven division of labor, overlapping tasks, opaque processes, and a lack of opportunities for skill development. This invention aims to centrally resolve these issues and improve the performance of the entire organization. [Means for solving the problem]

[0005] This invention relates to a system that includes a means for collecting business data and storing it in a database, a means for analyzing the stored data and identifying issues, a means for generating improvement proposals optimized for the identified issues, and a means for displaying the generated improvement proposals to a user. This system enables integrated management and visualization of data across an entire organization. Furthermore, by including a means for collecting feedback from users and reflecting it in the analysis results, continuous improvement is achieved. Converting the collected data into an analyzable format enables efficient data analysis and provides optimal solutions for the identified issues. In this way, various issues within an organization can be effectively resolved, leading to sustainable performance improvement.

[0006] "Business data" refers to information such as the progress of tasks, project status, and feedback occurring within an organization.

[0007] A "database" is a system that stores collected business data and makes it easy to search and analyze it.

[0008] "Analysis" is the process of processing collected data and converting it into meaningful information to identify issues.

[0009] "Issues" refer to problems or bottlenecks that hinder the efficiency of organizational operations or the progress of business.

[0010] An "improvement proposal" is a proposal for the optimal solution or measure for an identified issue.

[0011] "User" refers to an individual or department that uses the system to input business data and receive analysis results and improvement suggestions.

[0012] "Feedback" is information and opinions provided by users that are reflected in the system's self-learning and improvement.

[0013] "Collection" is the process of gathering business data from users.

[0014] "Storage" means storing collected data in a database and keeping it safe.

[0015] "Display" means providing the analysis results and improvement suggestions visually to the user.

[0016] "Self-learning" is the process by which the system improves the accuracy of its next analysis and suggestions based on analysis results and user feedback.

[0017] "Format conversion" is the process of increasing the usefulness of collected data by converting it into an analyzable format. [Brief explanation of the drawings]

[0018] [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

[0019] 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.

[0020] First, the terms used in the following description will be explained.

[0021] 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).

[0022] 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.

[0023] 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.

[0024] 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.

[0025] 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."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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."

[0039] The present invention, "Organization Management Assist on AI," is a system that collects and analyzes an organization's business data, identifies issues, and generates and displays optimized improvement proposals. The program processing of this system is explained in detail below.

[0040] Program processing

[0041] Data Collection Phase

[0042] User (Device):

[0043] Users enter their daily work data (e.g., task progress, project status, feedback, etc.) into dedicated applications and web portals.

[0044] server:

[0045] Business data sent from the terminal is received in real time and stored safely and efficiently in a database.

[0046] Data analysis phase

[0047] server:

[0048] The data is pre-processed and cleansed into an analyzable format, then machine learning algorithms are used to analyze performance data across the organization and identify key issues. The analysis also includes natural language processing to perform a detailed analysis of the feedback provided by users.

[0049] server:

[0050] By comparing it with past data and learning from new data, the AI ​​model parameters are updated using a self-learning function, improving the accuracy of the next analysis.

[0051] Issue visualization phase

[0052] server:

[0053] Once the analysis results are available, the overall performance of the organization and the identified challenges are visualized in the form of a dashboard, which includes an assessment of different departments and highlights the major bottlenecks.

[0054] User (Device):

[0055] Access the dashboard to see the current status of your organization and any identified challenges in real time.

[0056] Improvement proposal phase

[0057] server:

[0058] Generates optimized improvement proposals for identified issues. For example, if the issue of "lack of communication" is identified, suggestions will be made such as setting up regular meetings or introducing a dedicated chat tool.

[0059] server:

[0060] The generated improvement suggestions are displayed in a detailed report format on a dashboard, allowing users to intuitively understand them.

[0061] User (Device):

[0062] The system reviews the proposals and evaluates whether they can be implemented. After implementing the proposals, the system provides feedback on their effectiveness, providing data that will be useful for analyzing the system's future.

[0063] Specific examples

[0064] Data collection:

[0065] User (terminal): Sales department employees input daily sales performance data into the system.

[0066] Server: Receives the data in real time and stores it in a database.

[0067] Data Analysis:

[0068] Server: Analyzes stored sales performance data using machine learning algorithms and natural language processing to compare the performance of different sales teams.

[0069] Issue visualization:

[0070] Server: Based on the analysis results, a dashboard displays the performance of different sales teams and key issues.

[0071] Users (devices): Check the status of their team on the dashboard and recognize areas that need improvement.

[0072] Improvement suggestions:

[0073] Server: Based on the analysis results, specific improvement suggestions such as "certain sales teams should increase weekly meetings" are displayed.

[0074] User (terminal): Implements improvement suggestions and inputs feedback on the results into the system.

[0075] This system will enable efficient optimization of business operations across the organization, leading to sustained performance improvements.

[0076] The processing flow will be explained below.

[0077] Step 1:

[0078] User (device): Enters daily work data, such as task progress, project status, and feedback, into dedicated applications and web portals.

[0079] Step 2:

[0080] Terminal: Collects business data entered by the user in real time and sends it to the server.

[0081] Step 3:

[0082] Server: Receives data sent from the device and stores it in a database. When storing the data, it checks the consistency of the data and performs data cleansing (deleting duplicate data and correcting inconsistent data) as necessary.

[0083] Step 4:

[0084] Server: Transforms the stored data into an analyzable format, which includes normalizing the data and standardizing the format.

[0085] Step 5:

[0086] Server: Based on the cleansed data, it uses machine learning algorithms to analyze it. Specifically, it analyzes performance data for the entire organization and for each individual to identify key issues. For example, if progress on a task is slow, it analyzes all relevant data points to identify the cause.

[0087] Step 6:

[0088] Server: Based on the analysis results, the identified issues are generated in the form of a report, which includes an assessment of different departments and highlights the main bottlenecks.

[0089] Step 7:

[0090] Server: The generated reports are reflected in the dashboard, allowing users to intuitively understand the information.

[0091] Step 8:

[0092] Users (devices): Access the dashboard to check the current status of the organization and any identified issues.

[0093] Step 9:

[0094] Server: Generates optimized improvement proposals for identified issues. For example, if a lack of communication is identified, the server will make specific proposals such as scheduling regular meetings or introducing a dedicated chat tool.

[0095] Step 10:

[0096] Server: Generated improvement suggestions are displayed in the form of detailed reports on the dashboard.

[0097] Step 11:

[0098] User (device): Checks the proposal and evaluates whether it can be implemented. Also, inputs feedback to help with the next analysis.

[0099] Step 12:

[0100] Server: Receives feedback from users and executes a self-learning process to reflect it in analysis results and improvement suggestions. This improves the accuracy of the next analysis and makes it possible to provide more effective improvement suggestions.

[0101] Example 1

[0102] 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."

[0103] Conventional organizational management systems only collect and analyze business data, making it difficult to extract useful information from large amounts of data and make specific improvement proposals. Furthermore, there is no mechanism for effectively incorporating user feedback, making it difficult for the system to self-improve.

[0104] 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.

[0105] In this invention, the server includes means for collecting business data and storing it in a database, means for preprocessing and cleansing the stored data, means for analyzing the data using a machine learning algorithm and identifying issues, means for visualizing the issues in a dashboard format based on the analysis results, means for generating improvement proposals optimized for the identified issues, and means for displaying the generated improvement proposals to a user, thereby enabling performance improvement and optimization of the entire organization.

[0106] "Business Data" refers to information related to daily business activities, such as task progress, project status, and feedback.

[0107] "Database" refers to an information system that securely stores collected business data and makes it easy to access and manage.

[0108] "Preprocessing" refers to tasks such as filling in missing values, normalizing data, and cleansing data in order to convert raw data into an analyzable format.

[0109] "Cleansing" refers to the process of removing unnecessary data and correcting incorrect data in order to improve data quality.

[0110] A "machine learning algorithm" refers to a calculation method that learns data patterns based on past data and makes predictions and classifications for future data.

[0111] A "dashboard" is a tool that visually displays the results of data analysis, allowing users to intuitively understand an organization's performance and identified issues.

[0112] "Improvement proposals" refer to optimized solutions or measures for issues identified based on the results of data analysis.

[0113] "Feedback from users" refers to information such as opinions, impressions, and areas for improvement after users use the system provided.

[0114] "Self-learning function" refers to the function that learns from new data and improves the accuracy of the model.

[0115] An "AI model" refers to a computational model built to solve a specific problem based on patterns and rules learned from data using machine learning algorithms.

[0116] The present invention, "Organization Management Assist on AI," is a system that collects and analyzes business data of an organization, identifies issues, and generates and displays optimized improvement proposals. This system is configured as follows.

[0117] Data Collection Phase

[0118] Users enter their daily work data (e.g., task progress, project status, feedback) into dedicated applications or web portals that are designed to provide a user-friendly interface and make data entry easy.

[0119] The terminal sends the business data entered by the user to the server in real time. The communication is encrypted to ensure the security of the data.

[0120] The server receives the business data sent from the terminal and stores it safely and efficiently in a database. A database management system such as MySQL can be used.

[0121] Data analysis phase

[0122] The server preprocesses and cleanses the received data into an analyzable format using Pandas, a Python data analysis library.

[0123] The server then uses machine learning algorithms to analyze the data and identify issues, such as the Python scikit-learn library, and the natural language processing library NLTK to further analyze the feedback provided by users.

[0124] Furthermore, the server uses a self-learning function to update the parameters of the AI ​​model to improve the accuracy of the next analysis. For example, TensorFlow can be used to train the AI ​​model.

[0125] Issue visualization phase

[0126] The server then uses the analysis results to visualize the overall performance of the organization and any identified issues in the form of a dashboard, which can be created using, for example, Tableau or Power BI, and includes an assessment of different departments and highlights key bottlenecks.

[0127] Users can access the dashboard to check the current status of the organization and identified issues in real time. The user interface is intuitive and designed to allow users to easily grasp the information.

[0128] Improvement proposal phase

[0129] The server generates improvement proposals optimized for the identified issues. For example, if a "lack of communication" issue is identified, it will recommend setting up regular meetings or introducing a dedicated chat tool (e.g., Slack).

[0130] The server displays the generated improvement proposals in the form of a detailed report on the dashboard, including the background of the proposals and specific implementation methods, and uses graphs and charts to make the proposals intuitively understandable to the user.

[0131] The user reviews the proposals and evaluates whether they are feasible to implement. After implementing the proposals, the user enters feedback into the system about their effectiveness. For example, the user may report on the usability and effectiveness of a newly introduced tool as part of an improvement proposal.

[0132] Prompt Sentence Examples

[0133] "Analyze sales department data, identify team performance issues and make suggestions for improvement."

[0134] This allows the system to optimize and continuously improve the performance of the entire organization.

[0135] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0136] Step 1: Data entry

[0137] Users use a dedicated application or web portal to enter their daily work data, including task progress, project status, feedback, etc. Once the data is complete, it is sent to the system.

[0138] Input: Business data such as task progress, project status, and feedback

[0139] Output: Business data sent to the server in real time

[0140] Step 2: Send data

[0141] The terminal encrypts the business data entered by the user and transmits it to the server in real time using a secure protocol.

[0142] Input: Business data entered by the user

[0143] Output: Encrypted and securely transmitted business data

[0144] Step 3: Save Data

[0145] The server receives business data sent from the terminal and stores it safely and efficiently in a database, while checking to see if the data is missing.

[0146] Input: Encrypted business data

[0147] Output: Complete business data stored in a database

[0148] Step 4: Data Preprocessing

[0149] The server performs pre-processing to convert the stored business data into an analyzable format, including imputing missing values, normalizing the data, and cleansing it.

[0150] Input: Business data stored in a database

[0151] Output: Cleansed and normalized parsable data

[0152] Step 5: Data analysis

[0153] The server then uses machine learning algorithms (e.g., scikit-learn) to analyze the preprocessed data, which includes assessing the organization's overall performance and identifying key issues.

[0154] Input: Preprocessed business data

[0155] Output: Key issues identified and performance analysis results

[0156] Step 6: Natural Language Processing

[0157] The server uses natural language processing (e.g., NLTK) to perform detailed analysis of the feedback provided by the user, and integrates insights gained from the feedback into the analysis results.

[0158] Input: User feedback

[0159] Output: Feedback insights integrated into analysis results

[0160] Step 7: Self-study

[0161] The server compares the data with past data and learns from new data, updating the parameters of the AI ​​model using TensorFlow.

[0162] Input: All analysis results

[0163] Output: Updated AI model parameters

[0164] Step 8: Visualize the issue

[0165] Based on the analysis results, the server visualizes the organization's overall performance and identified issues in dashboard format (e.g., Tableau).

[0166] Input: All analysis results

[0167] Output: Analysis results and specific tasks displayed on a dashboard

[0168] Step 9: View the Dashboard

[0169] Users access the dashboard to see the current state of their organization and identified issues in real time.

[0170] Input: Analysis results and specific issues displayed on the dashboard

[0171] Output: User recognition of issues and understanding of the current state of the organization

[0172] Step 10: Generate improvement suggestions

[0173] The server generates optimized improvement proposals for the identified issues. For example, if a "lack of communication" issue is identified, it will recommend setting up regular meetings and introducing a dedicated chat tool.

[0174] Input: Identified Issues

[0175] Output: Improvement suggestions

[0176] Step 11: Displaying improvement suggestions

[0177] The server displays the generated improvement suggestions in the form of a detailed report on a dashboard.

[0178] Input: Improvement suggestion

[0179] Output: Detailed improvement suggestions displayed in a dashboard

[0180] Step 12: Evaluate and provide feedback on the proposal

[0181] The user checks the proposals, evaluates whether they are feasible to implement, and after implementing the proposals, inputs feedback about their effectiveness into the system.

[0182] Input: Improvement suggestions, feedback after implementation

[0183] Output: Feedback data entered into the system

[0184] This allows the system to use user feedback to improve the accuracy of its next analysis and improvement suggestions.

[0185] (Application example 1)

[0186] 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."

[0187] Conventional organizational management systems were able to identify issues and generate improvement proposals by collecting and analyzing business data, but it was difficult to monitor the operating status and work efficiency of robots at production sites in real time and optimize identified issues.In addition, there was no system that could make specific optimization proposals for production efficiency based on robot operating data, making it impossible to instantly improve productivity.

[0188] 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.

[0189] In this invention, the server includes means for collecting business data and storing it in a database, means for analyzing the stored data and identifying issues, means for generating improvement proposals optimized for the identified issues, means for displaying the generated improvement proposals to a user, and means for collecting operation data from a robot and optimizing production efficiency based on the analysis results, thereby enabling specific optimization of production efficiency based on the robot operation data.

[0190] "Business data" refers to information about various business operations conducted by an organization, including task progress, project status, feedback, and the like.

[0191] "Database" means a structured data storage system for efficiently and securely storing and managing collected business data.

[0192] "Analysis" refers to the process of preprocessing the collected data, converting it into an analyzable format using machine learning algorithms and natural language processing, and extracting information that will be useful in the actual operation of the organization.

[0193] "Issues" are bottlenecks in organizational management and problems requiring improvement that are identified from the analyzed data.

[0194] An "improvement proposal" is a specific action plan that proposes an optimized solution or new approach to an identified issue.

[0195] "User" refers to a member or administrator of an organization who uses the system to input business data and check the analysis results and improvement suggestions.

[0196] "Feedback" refers to information including opinions and evaluations provided by users, and is data used to improve the accuracy of the system's analysis results and improvement suggestions.

[0197] A "robot" is a machine that operates in a factory and automatically performs tasks such as assembling and processing products.

[0198] "Operational data" refers to information about the robot's performance, such as its operating status, work efficiency, and error rate.

[0199] "Production efficiency" refers to the efficiency and production volume of work at production sites such as factories, and is an indicator evaluated based on factors such as the operating status of robots and work accuracy.

[0200] A "server" is a computer system that receives business data and robot operation data sent by users, and analyzes, stores, and displays them.

[0201] This invention, "Organizational Management Assist on AI," collects operational data and work efficiency data from robots used in factories in real time, detects specific issues, and generates and displays improvement proposals. The configuration of this system is described below.

[0202] Hardware and software used

[0203] 1. Robot (terminal): An automatic machine that operates in a factory and performs tasks such as assembling and processing products.

[0204] 2. Administrator's terminal: A device for viewing the dashboard and reviewing improvement suggestions on a PC or tablet.

[0205] 3. Server: A computer system that manages all processes of receiving, storing, analyzing, and displaying data. Specifically, it uses the following software:

[0206] Database: MySQL

[0207] Machine learning algorithm: TensorFlow

[0208] Dashboard display tool: Tableau

[0209] Natural language processing libraries required for specific evaluations and analyses

[0210] Program processing explanation

[0211] 1. Data Collection Phase

[0212] The robot (terminal) collects operational data (e.g., operating time, number of errors) and sends it to the server via a dedicated application.

[0213] The server receives the data sent from the robot in real time and stores it securely in a database.

[0214] 2. Data analysis phase

[0215] The server cleanses and pre-processes the received data into a parsable format.

[0216] The data is analyzed using a machine learning algorithm (TensorFlow) to evaluate the robot's performance.

[0217] Using natural language processing, feedback from users is also included in the analysis.

[0218] 3. Issue Visualization Phase

[0219] Based on the analysis results, the server displays the robot's operating status and issues on a dashboard (Tableau).

[0220] The administrator (terminal) accesses the dashboard to check the current status of the robot and any identified issues in real time.

[0221] 4. Improvement proposal phase

[0222] The server generates an optimized improvement proposal for the identified issue. For example, if a "parts supply shortage" is identified, it will propose reviewing the inventory management system and introducing an automatic replenishment system.

[0223] The administrator (terminal) checks the generated improvement proposals, evaluates their implementation, and then inputs feedback about their effectiveness into the system.

[0224] Specific examples

[0225] If Robot A sends data showing that its average operating time has decreased by 5% over the course of a week, the server will use this data to identify a shortage of parts supply and suggest that the inventory management system be revised.

[0226] Prompt Sentence Examples

[0227] Examples of prompts for generative AI models include:

[0228] "Analyze the performance of Robot A this week, identify key issues, and generate improvement suggestions."

[0229] This system makes it possible to specifically optimize production efficiency based on operational data from robots within the factory, thereby improving productivity.

[0230] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0231] Step 1: Data collection

[0232] Description: The robot (terminal) collects operational data from within the factory and sends it to a server via a dedicated application. Specifically, this data includes operating hours, number of errors, production volume, etc.

[0233] Input: Operational data obtained from the robot's sensors and internal systems.

[0234] Output: The raw data sent to the server.

[0235] Step 2: Receiving and storing data

[0236] Description: The server receives the data sent from the robot in real time and stores it securely in a database, specifically in a database system such as MySQL.

[0237] Input: Raw data sent by the robot.

[0238] Output: Operational data stored in a database.

[0239] Step 3: Data preprocessing and cleansing

[0240] Description: The server converts the received data into a parsable format and performs data cleansing, which includes imputing missing values ​​and removing outliers.

[0241] Input: Raw data stored in a database.

[0242] Output: Preprocessed and cleansed data.

[0243] Step 4: Data analysis

[0244] Description: The server analyzes the data using machine learning algorithms (TensorFlow) to evaluate the robot's performance, including calculating the availability rate and evaluating the error rate.

[0245] Input: Preprocessed and cleansed data.

[0246] Output: Robot performance evaluation results.

[0247] Step 5: Identify the issue

[0248] Description: The server extracts identified issues from performance data based on the analysis results. For example, if errors occur frequently within a certain period of time, this is identified as an issue.

[0249] Input: Robot performance evaluation results.

[0250] Output: Identified issues.

[0251] Step 6: Collect and analyze feedback

[0252] Description: The server collects feedback from users (administrators) and reflects it in the analysis results. This is done to improve the accuracy of future analysis of the system.

[0253] Input: Feedback data from users.

[0254] Output: Feedback reflected in the system.

[0255] Step 7: Generate improvement suggestions

[0256] Description: The server generates an optimized improvement proposal based on the identified issues. For example, if the issue of "shortage of parts supply" is identified, it proposes reviewing the inventory management system.

[0257] Input: Identified issue.

[0258] Output: Generated improvement suggestions.

[0259] Step 8: View the proposal

[0260] Description: The server displays the generated improvement suggestions on a dashboard (Tableau) so that the user can understand them intuitively.

[0261] Input: Generated improvement suggestions.

[0262] Output: Improvement suggestions displayed in a dashboard.

[0263] Step 9: Evaluate proposals and provide feedback

[0264] Description: The user (administrator) checks the improvement proposals displayed on the dashboard, evaluates their implementation, and then enters feedback about their effectiveness into the system.

[0265] Input: Improvement suggestions displayed on the dashboard.

[0266] Output: Feedback data.

[0267] Through the above processing steps, the server can achieve specific optimization of production efficiency based on the robot's operation data and provide useful improvement suggestions to the user.

[0268] 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.

[0269] The present invention, "Organizational Management Assist on AI," combines a system that collects and analyzes an organization's business data, identifies issues, and generates and displays optimized improvement proposals with an emotion engine that recognizes the user's emotions. The program processing of this system is explained in detail below.

[0270] Program processing

[0271] Data Collection Phase

[0272] User (Device):

[0273] Users input their daily work data (e.g., task progress, project status, feedback, etc.) into dedicated applications or web portals, and may also input their emotions (e.g., stress, satisfaction, etc.) at the same time.

[0274] Device:

[0275] Business data and emotional data entered by the user are collected in real time and sent to the server.

[0276] Data analysis phase

[0277] server:

[0278] The data sent from the device is received and stored in a database. When storing, the consistency between the business data and the emotion data is checked, and the data is cleansed as necessary.

[0279] server:

[0280] The stored data is converted into an analyzable format, and the emotion engine is used to analyze the user's emotion data.

[0281] server:

[0282] It analyzes operational and emotional data comprehensively and uses machine learning algorithms to evaluate the performance data of the entire organization and each individual, and identifies key issues. For example, if progress on a task is delayed, it analyzes whether the delay is due to emotional factors.

[0283] server:

[0284] Based on the analysis results, the identified issues are generated in the form of a report, including an assessment of different departments and highlighting key bottlenecks.

[0285] Issue visualization phase

[0286] server:

[0287] The generated reports are reflected on a dashboard, allowing users to intuitively understand the information. The results of the analysis of the sentiment data are also displayed on the dashboard.

[0288] User (Device):

[0289] Access the dashboard to see the current state of the organization and any identified challenges. Users can also view their own emotional state.

[0290] Improvement proposal phase

[0291] server:

[0292] It generates optimized improvement proposals for identified issues, such as "providing refreshment time for highly stressed employees" or "assigning highly motivated employees to new projects" based on emotional data.

[0293] server:

[0294] Generated improvement suggestions are displayed in a dashboard in the form of detailed reports.

[0295] User (Device):

[0296] The system checks the proposals and evaluates whether they can be implemented. After implementing the proposals, the system provides feedback on their effectiveness, providing data that will be useful for analyzing the system's future.

[0297] Feedback and self-learning phase

[0298] server:

[0299] It receives feedback and undergoes a self-learning process to incorporate it into its analysis results and improvement suggestions, taking into account sentiment data to improve the accuracy of its next analysis.

[0300] Specific examples

[0301] Data collection:

[0302] User (terminal): Sales department employees enter their daily sales performance data and their own stress levels into the system.

[0303] Server: Receives the data in real time and stores it in a database.

[0304] Data Analysis:

[0305] Server: Analyzes stored sales performance data and stress level data to compare the performance and emotional state of different sales teams.

[0306] Issue visualization:

[0307] Server: Based on the analysis results, the sales performance and stress level of each team are displayed on a dashboard.

[0308] User (device): Check the status of their team on the dashboard and recognize areas that need improvement and the need for stress management.

[0309] Improvement suggestions:

[0310] Server: Based on the analysis, it displays suggestions such as "certain sales teams should adjust their workload" or emotion-based suggestions such as "set rest time for members with high stress levels."

[0311] User (terminal): Implements improvement suggestions and inputs feedback on the results into the system.

[0312] This system not only efficiently optimizes business operations across the organization, but also achieves sustainable performance improvement, including employee emotional management.

[0313] The processing flow will be explained below.

[0314] Step 1:

[0315] User (terminal): The user inputs daily work data (e.g., task progress and project status) and emotional data (e.g., stress level and motivation) into a dedicated application or web portal.

[0316] Step 2:

[0317] Terminal: Collects business data and emotional data entered by the user in real time and sends it to the server.

[0318] Step 3:

[0319] Server: Receives data sent from the device and stores it in a database. When storing the data, it checks its consistency and performs data cleansing (deleting duplicate data and correcting inconsistent data) as necessary.

[0320] Step 4:

[0321] Server: The stored business data and emotion data are converted into an analyzable format. At this stage, the data is normalized and the format is standardized.

[0322] Step 5:

[0323] Server: The converted data is analyzed using machine learning algorithms. Performance data for the entire organization and for each individual is evaluated to identify key issues. For example, if sales performance is declining, the server analyzes whether this is due to emotional factors (e.g., high stress levels).

[0324] Step 6:

[0325] Server: Utilizing the emotion engine, further analyzes the user's emotion data, thereby identifying not only business issues but also emotional issues.

[0326] Step 7:

[0327] Server: Based on the analysis results, the identified issues are generated in the form of a report, which includes evaluations by different departments, key bottlenecks, and analysis results based on sentiment data.

[0328] Step 8:

[0329] Server: The generated reports are reflected in the dashboard, allowing users to intuitively understand the information.

[0330] Step 9:

[0331] User (device): Access the dashboard to check the current state of the organization, identified issues, and the results of the sentiment data analysis.

[0332] Step 10:

[0333] Server: Generates optimized improvement proposals for identified issues, including proposals based on emotional data. For example, it makes specific proposals such as "providing refreshment time for highly stressed users" or "assigning highly motivated users to new projects."

[0334] Step 11:

[0335] Server: Generated improvement suggestions are displayed in the form of detailed reports on the dashboard.

[0336] Step 12:

[0337] User (device): Checks the proposal, evaluates whether it can be implemented, and provides feedback and data on its effectiveness.

[0338] Step 13:

[0339] Server: Receives user feedback and executes a self-learning process to reflect it in analysis results and improvement suggestions. Feedback includes emotional data, which improves the accuracy of the next analysis.

[0340] Example 2

[0341] 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."

[0342] Conventional business data analysis systems only target business data and do not consider employee emotional data, making it difficult to make optimal business improvement proposals. Furthermore, there is no self-learning process that incorporates feedback on analysis results into the system, limiting improvements to analysis accuracy. Therefore, there is a need for the development of an integrated system that simultaneously improves business efficiency and manages employee emotions.

[0343] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0344] In this invention, the server includes: means for collecting business data and emotion data and storing them in a database; means for verifying the consistency of the stored business data and emotion data and performing data cleansing as necessary; means for converting the collected business data and emotion data into an analyzable format; means for analyzing the emotion data using an emotion analysis engine; means for comprehensively analyzing the business data and emotion data, evaluating performance data using a machine learning algorithm, and identifying major issues; means for generating a report based on the identified issues and highlighting evaluations for different departments and major bottlenecks; means for reflecting the generated report on a dashboard and displaying information intuitively to a user; means for generating improvement proposals optimized for the identified issues and making specific proposals based on the emotion data; and means for displaying the generated improvement proposals in a detailed report format on the dashboard. This simultaneously achieves business efficiency and employee emotion management, thereby enabling improved performance across the organization and sustainable business improvement.

[0345] "Business data" refers to various information related to business, such as task progress, project status, and feedback.

[0346] "Emotion data" refers to information that indicates the user's psychological state, such as stress or satisfaction.

[0347] A "database" refers to a system that stores business data and emotional data in a structured format and allows it to be searched and manipulated as needed.

[0348] "Verifying consistency" refers to the process of validating data formats and checking relationships between data to ensure data consistency and accuracy.

[0349] "Data cleansing" refers to the process of correcting data inconsistencies and outliers to improve data quality.

[0350] "Converting to an analyzable format" refers to the process of formatting data into a form suitable for analysis and processing.

[0351] An "emotion analysis engine" refers to software or algorithms that analyze user emotional data and output the results.

[0352] A "machine learning algorithm" refers to a computational method that learns from data and automatically performs specific tasks.

[0353] "Performance data" refers to data used to evaluate the work performance and results of an organization or individual.

[0354] A "report" refers to a document that systematically organizes and visually displays analysis results and evaluation contents.

[0355] A "dashboard" is an interface that aggregates multiple data visualizations and allows users to grasp key indicators and information at a glance.

[0356] "Improvement proposals" refer to specific proposals for achieving more effective work performance and emotional management in response to identified issues.

[0357] The "self-learning process" refers to the process by which the system incorporates new data and feedback to automatically improve the accuracy of its analysis.

[0358] The present invention relates to a system called "Organizational Management Assist on AI," which collects and analyzes business data and emotional data, identifies issues, and makes optimal improvement proposals. Specific embodiments for implementing this system are described below.

[0359] Data Collection Phase

[0360] User (Device):

[0361] Users use a dedicated application or web portal to input daily work data (e.g., task progress, project status, feedback, etc.) as well as emotional data (e.g., stress, satisfaction, etc.), allowing data on work status and employee emotional states to be collected simultaneously.

[0362] Examples of software used: dedicated applications, web portals

[0363] Example: Sales staff use a dedicated application to enter their sales performance and daily stress levels.

[0364] Data collection and transmission

[0365] Device:

[0366] The business data and emotion data entered by the user are sent to the server in real time using API calls to ensure data is collected without delay.

[0367] Examples of hardware and software used: API, network communication

[0368] Example: A sales department employee's device sends data to the server as soon as the data entry is completed.

[0369] Data analysis phase

[0370] server:

[0371] The server checks the integrity of the received data and performs data cleansing if necessary before storing it in a database (e.g., MySQL, PostgreSQL, etc.). The stored data is then converted into an analyzable format. Sentiment data is then analyzed using a sentiment analysis engine (e.g., IBM Watson, Affectiva, etc.).

[0372] Examples of software used: MySQL, PostgreSQL, IBM Watson, Affectiva

[0373] Example: The server receives sales performance data and emotion data, unifies the format, and stores it in a database. The emotion analysis engine analyzes the stress level data.

[0374] Analyzing performance data

[0375] server:

[0376] By integrating and analyzing operational and sentiment data and using machine learning algorithms (e.g., TensorFlow, scikit-learn, etc.) to evaluate performance data, we can accurately assess the performance of the entire organization and individual employees and identify key issues.

[0377] Examples of software used: TensorFlow, scikit-learn

[0378] Example: The server analyzes sales performance data and stress data to determine whether stress is the cause of poor performance.

[0379] Report generation and visualization

[0380] server:

[0381] Based on the analysis results, reports are generated to highlight the performance of different departments and major bottlenecks. The generated reports are reflected in a dashboard, displaying information in an intuitive and easy-to-understand format for users.

[0382] Examples of software used: Tableau, Microsoft Power BI

[0383] Example: Based on the analysis results, the performance of the sales and development departments and their respective issues are compiled into a report and displayed on a dashboard.

[0384] Generate and implement improvement suggestions

[0385] server:

[0386] For identified issues, the system generates optimized improvement proposals that take emotional data into account. The proposals are displayed in a detailed report format on a dashboard, allowing users to review the proposals and evaluate whether or not they should be implemented. After implementing the proposals, users can enter feedback about their effectiveness into the system, which accumulates feedback data.

[0387] Example: Based on the analysis results, suggestions such as "A specific sales team should adjust their workload" or "Set rest time for employees with high stress levels" are displayed. The user implements these suggestions and provides feedback on the results.

[0388] Self-Learning Process

[0389] server:

[0390] A self-learning process is performed to incorporate received feedback into analysis results and improvement suggestions, thereby improving the accuracy of the next analysis and continuously improving system performance.

[0391] Examples of software used: machine learning models, feedback analysis algorithms

[0392] Example: Feedback data is used as new learning data to retrain a performance evaluation model.

[0393] Example prompts for generative AI models

[0394] Please display the analysis results of this month's sales department performance and each employee's stress level.

[0395] Compare the progress of Project X with the satisfaction of your team members.

[0396] Display the best improvement suggestions for highly stressed employees.

[0397] In this way, the present invention provides an innovative system that effectively integrates and analyzes business data and emotional data, simultaneously optimizing business operations and managing employee emotions.

[0398] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0399] Step 1:

[0400] Entering data

[0401] Users use a dedicated application or web portal to input daily work data (e.g., task progress, project status, feedback, etc.) and emotional data (e.g., stress, satisfaction, etc.).

[0402] Input: Business data and emotion data

[0403] Specific operation: Through the application UI, the user selects the progress of the task from a drop-down menu and sets the stress level using a slider. After entering the data, the data is registered by pressing the submit button.

[0404] Step 2:

[0405] Sending data

[0406] The terminal transmits the business data and emotion data input by the user to the server in real time.

[0407] Input: Data entered by the user

[0408] Output: Data sent to the server

[0409] Specific operation: The device uses an API call to send input data to the server, and during this process checks the HTTP response to ensure the data was sent correctly.

[0410] Step 3:

[0411] Receiving and storing data

[0412] The server receives the data sent from the terminal, first checks its integrity, and then stores the data in the database.

[0413] Input: Data sent from the terminal

[0414] Output: Data stored in the database

[0415] Specific operation: The server validates the format and content of the received data, for example, rejecting incomplete records and mismatched data. After the validation, the data is inserted into a database such as MySQL or PostgreSQL.

[0416] Step 4:

[0417] Data cleansing and transformation

[0418] The server cleanses the stored data and converts it into an analyzable format.

[0419] Input: Saved data

[0420] Output: Data in a parsable format

[0421] Specific operations: The server performs operations to improve data quality, such as imputing missing values, correcting outliers, and standardizing data formats. For example, it converts all date and time data to a unified format (YYYY-MM-DD).

[0422] Step 5:

[0423] Emotional Data Analysis

[0424] The server uses an emotion analysis engine (e.g., IBM Watson, Affectiva, etc.) to analyze the user's emotion data.

[0425] Input: Cleansed emotion data

[0426] Output: Parsed emotion data

[0427] Specific operation: The server sends the emotion data to the analysis engine's API and stores the returned analysis results in a database. For example, it receives analysis results such as "high stress level" or "low satisfaction level."

[0428] Step 6:

[0429] Comprehensive Data Analysis

[0430] The server comprehensively analyzes business data and sentiment data, evaluates performance data using machine learning algorithms (e.g., TensorFlow, scikit-learn, etc.), and identifies key issues.

[0431] Input: Data in a parsable format, parsed emotion data

[0432] Output: Performance evaluation results, identified issues

[0433] Specific operation: The server inputs data into a machine learning model to evaluate, for example, whether delays in task progress are due to emotional factors. The model's output is stored in a database.

[0434] Step 7:

[0435] Generate reports

[0436] The server generates reports based on the analysis results, highlighting the performance of different departments and highlighting key bottlenecks.

[0437] Input: Performance evaluation results, identified issues

[0438] Output: Generated report

[0439] Specific operation: The report generation system dynamically inserts analysis results based on templates to create visually easy-to-understand reports, which are then saved in PDF or web format.

[0440] Step 8:

[0441] Reflected on the dashboard

[0442] The server reflects the generated report on the dashboard and displays the information so that the user can intuitively understand it.

[0443] Input: Generated report

[0444] Output: The data displayed on the dashboard

[0445] Specific operation: The server uses a data visualization tool (e.g., Tableau, Microsoft Power BI, etc.) to visualize the report contents as graphs and charts and display them on a dashboard.

[0446] Step 9:

[0447] Accessing the Dashboard

[0448] Users can access a dashboard to view the current state of their organization, identify identified challenges, and even view their own emotional state.

[0449] Input: User login information

[0450] Output: The displayed dashboard

[0451] How it works: Users can log in to the dashboard using a dedicated application or a web browser to view various data. For example, they can use the filter function to view data for a specific time range.

[0452] Step 10:

[0453] Generate improvement suggestions

[0454] The server generates improvement proposals optimized for the identified issues and makes specific proposals based on emotion data.

[0455] Input: Identified issues, emotion data

[0456] Output: Improvement suggestions

[0457] Specific operation: Based on the analysis results, the server generates suggestions such as "providing refreshment time for employees with high stress levels" and "assigning highly motivated employees to new projects," and compiles them in report format.

[0458] Step 11:

[0459] Viewing improvement suggestions

[0460] The server displays the generated improvement suggestions in the form of a detailed report on a dashboard.

[0461] Input: Improvement suggestion

[0462] Output: Improvement suggestions displayed in a dashboard

[0463] Specific behavior: Improvement suggestions will be displayed on the dashboard in a visually easy-to-understand format with explanatory text and graphs. Also, a notification function will be implemented to allow users to check the suggestions.

[0464] Step 12:

[0465] Evaluation and feedback of proposals

[0466] The user checks the proposals, evaluates whether they are feasible to implement, and after implementing the proposals, inputs feedback on their effectiveness.

[0467] Input: Suggestion rating, feedback

[0468] Output: Feedback data

[0469] Specific operation: After checking the proposal on the dashboard, the user clicks the button to rate it, enters the effects in the feedback form, and submits it.

[0470] Step 13:

[0471] Receiving Feedback

[0472] The server receives the feedback from the user and stores it in a database.

[0473] Input: Feedback data

[0474] Output: Saved feedback data

[0475] What it does: Validates the feedback data and stores it in the database, appropriately labeling it as a new data point.

[0476] Step 14:

[0477] Implementing a self-learning process

[0478] The server uses the feedback data to perform a self-learning process to improve the analysis results and suggestions for improvement, thereby improving the accuracy of the next analysis.

[0479] Input: Saved feedback data

[0480] Output: Updated analytical model

[0481] Specific operation: The server retrains the machine learning model based on the feedback data and adds new data to the training dataset, thereby improving the accuracy of the analytical model.

[0482] Through the above processing steps, the present invention effectively integrates and analyzes business data and emotion data, thereby simultaneously optimizing business operations and managing employee emotions.

[0483] (Application example 2)

[0484] 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."

[0485] Simultaneously managing employees' work efficiency and emotional state is a major challenge for many companies. Conventional systems typically handle work data and emotional data separately, making it difficult to effectively generate optimal improvement proposals. Furthermore, an inability to properly grasp employees' emotional states can lead to ineffective work style improvements, resulting in lower productivity and employee satisfaction.

[0486] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting business data and saving it in a database, means for analyzing the saved data and identifying issues, means for analyzing user emotion data, means for comprehensively analyzing the business data and emotion data and generating optimized improvement proposals, and means for displaying the generated improvement proposals to the user. As a result, by comprehensively analyzing the business data and emotion data and making optimal improvement proposals, it is possible to simultaneously improve employee productivity and manage emotions.

[0487] "Business Data" means information related to an employee's or organization's business, including task progress and project status.

[0488] A "database" is a system for efficiently storing and managing collected data.

[0489] "Challenges" refer to problems or bottlenecks that hinder the work performance of an organization or individual.

[0490] "Emotion data" is information about the user's emotional state, and includes psychological factors such as stress and satisfaction.

[0491] "Analysis" is the process of analyzing collected data and extracting meaningful information and trends.

[0492] An "improvement proposal" is a specific proposal or action plan aimed at resolving an identified issue.

[0493] "User" refers to an individual or member of an organization who uses this system.

[0494] "Storage" means recording the collected data in a database for later use.

[0495] "Comprehensive" means treating different types of data as a whole and conducting a comprehensive analysis.

[0496] A "system" is a collection of components that have multiple functions and work together to operate.

[0497] A specific system for implementing this invention consists of several main components and steps. First, the user's device collects daily work data and emotional data. This is done using various sensors in the factory and employee feedback devices (tablets, PCs, etc.). The collected data is then sent to a server and stored in a database.

[0498] A program is installed on the server to convert the data into an analyzable format. At this stage, data cleansing is performed to remove inconsistencies and missing data. Next, an algorithm is run to comprehensively analyze the business data and emotion data. Specifically, Python's Pandas and machine learning models (e.g., RandomForestRegressor) are used for the analysis. A virtual emotion engine library (EmotionEngine) is also used to analyze the emotion data.

[0499] Once the analysis is complete, the server generates optimized improvement proposals based on the identified issues. These proposals may include, for example, "providing additional break time for specific employees" or "adjusting the workload of employees with high stress levels." The generated improvement proposals are displayed to the user in a dashboard format, allowing the user to review them and implement them as necessary.

[0500] Feedback on the execution results is also collected through the same system to inform future analysis, allowing the self-learning algorithm to improve the system's analysis accuracy.

[0501] To give a specific example, employees in the sales department enter their daily task progress and stress levels into the system. The collected data is sent to a server and stored in a database. The server analyzes the data and compares sales performance with stress levels. The analysis results are displayed on a dashboard, and suggestions for improvement, such as "applying additional break time," are made to specific employees.

[0502] An example prompt is:

[0503] "Collect factory sensor and employee feedback data, analyze productivity and emotional state, and generate optimal improvement proposals for identified issues."

[0504] This system simultaneously improves employee productivity and manages emotions by integrating and analyzing business data and emotional data.

[0505] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0506] Step 1:

[0507] Users (terminals) collect daily work data and emotional data. Specifically, various sensors in the factory input task progress status, and employees input emotional data (such as stress level and satisfaction) using their feedback terminals (tablets, PCs, etc.). The input data is sent to the server in real time. An example of input data is "2023-10-01, Task A, in progress, stress level: high."

[0508] Step 2:

[0509] The server stores the business data and emotion data sent from the device in a database. Specifically, data processing involves converting the received data into a predefined format and performing data cleansing. Inconsistencies and missing data are removed. If the input is "Stress level: high," it is validated within a safe range and stored in the database.

[0510] Step 3:

[0511] The server converts the stored data into an analyzable format. Specifically, it uses Python's Pandas library to change the data into a table format. For example, it converts the data into a format where each row represents data for one employee. During this process, it removes unnecessary data and extracts only the necessary fields. An unformatted data frame is given as input, and a formatted data frame is generated as output.

[0512] Step 4:

[0513] The server runs machine learning algorithms to analyze the formatted data. Specifically, it uses models such as RandomForestRegressor to comprehensively analyze business data and emotional data. It also uses an emotional analysis engine such as EmotionEngine. This analysis predicts employee productivity and emotional state. The identified data frame is used as input, and a new data frame containing the predicted results is generated as output.

[0514] Step 5:

[0515] The server generates identified issues and optimized improvement proposals based on the analysis results. Specific actions include "recommending additional break time for employees with high stress levels." The analysis result data frame is used as input, and the output is a list of improvement proposals.

[0516] Step 6:

[0517] The server displays the generated improvement suggestions on the user's dashboard. Specifically, the suggestions are displayed as graphs and text reports that are updated in real time on the web application dashboard. The input is the list of improvement suggestions, and the output is the visualized dashboard.

[0518] Step 7:

[0519] The user (device) checks the displayed improvement suggestions and inputs feedback as necessary. A specific example is feedback such as "As a result of applying additional break time, the stress level decreased." Feedback text is used as input, and the output is sent to the server as feedback data.

[0520] Step 8:

[0521] The server analyzes the collected feedback and performs a self-learning process to improve the accuracy of the next analysis and recommendation. Specifically, it uses the feedback data to retrain the machine learning model. The feedback data is used as input, and the output is an updated machine learning model.

[0522] In this way, a system is constructed that comprehensively analyzes business data and emotional data, and generates and displays optimal improvement proposals.

[0523] 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.

[0524] 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.

[0525] 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.

[0526] [Second embodiment]

[0527] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0528] 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.

[0529] 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).

[0530] 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.

[0531] 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.

[0532] 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).

[0533] 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.

[0534] 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.

[0535] 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.

[0536] 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.

[0537] 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.

[0538] 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."

[0539] The present invention, "Organization Management Assist on AI," is a system that collects and analyzes an organization's business data, identifies issues, and generates and displays optimized improvement proposals. The program processing of this system is explained in detail below.

[0540] Program processing

[0541] Data Collection Phase

[0542] User (Device):

[0543] Users enter their daily work data (e.g., task progress, project status, feedback, etc.) into dedicated applications and web portals.

[0544] server:

[0545] Business data sent from the terminal is received in real time and stored safely and efficiently in a database.

[0546] Data analysis phase

[0547] server:

[0548] The data is pre-processed and cleansed into an analyzable format, then machine learning algorithms are used to analyze performance data across the organization and identify key issues. The analysis also includes natural language processing to perform a detailed analysis of the feedback provided by users.

[0549] server:

[0550] By comparing it with past data and learning from new data, the AI ​​model parameters are updated using a self-learning function, improving the accuracy of the next analysis.

[0551] Issue visualization phase

[0552] server:

[0553] Once the analysis results are available, the overall performance of the organization and the identified challenges are visualized in the form of a dashboard, which includes an assessment of different departments and highlights the major bottlenecks.

[0554] User (Device):

[0555] Access the dashboard to see the current status of your organization and any identified challenges in real time.

[0556] Improvement proposal phase

[0557] server:

[0558] Generates optimized improvement proposals for identified issues. For example, if the issue of "lack of communication" is identified, suggestions will be made such as setting up regular meetings or introducing a dedicated chat tool.

[0559] server:

[0560] The generated improvement suggestions are displayed in a detailed report format on a dashboard, allowing users to intuitively understand them.

[0561] User (Device):

[0562] The system reviews the proposals and evaluates whether they can be implemented. After implementing the proposals, the system provides feedback on their effectiveness, providing data that will be useful for analyzing the system's future.

[0563] Specific examples

[0564] Data collection:

[0565] User (terminal): Sales department employees input daily sales performance data into the system.

[0566] Server: Receives the data in real time and stores it in a database.

[0567] Data Analysis:

[0568] Server: Analyzes stored sales performance data using machine learning algorithms and natural language processing to compare the performance of different sales teams.

[0569] Issue visualization:

[0570] Server: Based on the analysis results, a dashboard displays the performance of different sales teams and key issues.

[0571] Users (devices): Check the status of their team on the dashboard and recognize areas that need improvement.

[0572] Improvement suggestions:

[0573] Server: Based on the analysis results, specific improvement suggestions such as "certain sales teams should increase weekly meetings" are displayed.

[0574] User (terminal): Implements improvement suggestions and inputs feedback on the results into the system.

[0575] This system will enable efficient optimization of business operations across the organization, leading to sustained performance improvements.

[0576] The processing flow will be explained below.

[0577] Step 1:

[0578] User (device): Enters daily work data, such as task progress, project status, and feedback, into dedicated applications and web portals.

[0579] Step 2:

[0580] Terminal: Collects business data entered by the user in real time and sends it to the server.

[0581] Step 3:

[0582] Server: Receives data sent from the device and stores it in a database. When storing the data, it checks the consistency of the data and performs data cleansing (deleting duplicate data and correcting inconsistent data) as necessary.

[0583] Step 4:

[0584] Server: Transforms the stored data into an analyzable format, which includes normalizing the data and standardizing the format.

[0585] Step 5:

[0586] Server: Based on the cleansed data, it uses machine learning algorithms to analyze it. Specifically, it analyzes performance data for the entire organization and for each individual to identify key issues. For example, if progress on a task is slow, it analyzes all relevant data points to identify the cause.

[0587] Step 6:

[0588] Server: Based on the analysis results, the identified issues are generated in the form of a report, which includes an assessment of different departments and highlights the main bottlenecks.

[0589] Step 7:

[0590] Server: The generated reports are reflected in the dashboard, allowing users to intuitively understand the information.

[0591] Step 8:

[0592] Users (devices): Access the dashboard to check the current status of the organization and any identified issues.

[0593] Step 9:

[0594] Server: Generates optimized improvement proposals for identified issues. For example, if a lack of communication is identified, the server will make specific proposals such as scheduling regular meetings or introducing a dedicated chat tool.

[0595] Step 10:

[0596] Server: Generated improvement suggestions are displayed in the form of detailed reports on the dashboard.

[0597] Step 11:

[0598] User (device): Checks the proposal and evaluates whether it can be implemented. Also, inputs feedback to help with the next analysis.

[0599] Step 12:

[0600] Server: Receives feedback from users and executes a self-learning process to reflect it in analysis results and improvement suggestions. This improves the accuracy of the next analysis and makes it possible to provide more effective improvement suggestions.

[0601] Example 1

[0602] 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."

[0603] Conventional organizational management systems only collect and analyze business data, making it difficult to extract useful information from large amounts of data and make specific improvement proposals. Furthermore, there is no mechanism for effectively incorporating user feedback, making it difficult for the system to self-improve.

[0604] 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.

[0605] In this invention, the server includes means for collecting business data and storing it in a database, means for preprocessing and cleansing the stored data, means for analyzing the data using a machine learning algorithm and identifying issues, means for visualizing the issues in a dashboard format based on the analysis results, means for generating improvement proposals optimized for the identified issues, and means for displaying the generated improvement proposals to a user, thereby enabling performance improvement and optimization of the entire organization.

[0606] "Business Data" refers to information related to daily business activities, such as task progress, project status, and feedback.

[0607] "Database" refers to an information system that securely stores collected business data and makes it easy to access and manage.

[0608] "Preprocessing" refers to tasks such as filling in missing values, normalizing data, and cleansing data in order to convert raw data into an analyzable format.

[0609] "Cleansing" refers to the process of removing unnecessary data and correcting incorrect data in order to improve data quality.

[0610] A "machine learning algorithm" refers to a calculation method that learns data patterns based on past data and makes predictions and classifications for future data.

[0611] A "dashboard" is a tool that visually displays the results of data analysis, allowing users to intuitively understand an organization's performance and identified issues.

[0612] "Improvement proposals" refer to optimized solutions or measures for issues identified based on the results of data analysis.

[0613] "Feedback from users" refers to information such as opinions, impressions, and areas for improvement after users use the system provided.

[0614] "Self-learning function" refers to the function that learns from new data and improves the accuracy of the model.

[0615] An "AI model" refers to a computational model built to solve a specific problem based on patterns and rules learned from data using machine learning algorithms.

[0616] The present invention, "Organization Management Assist on AI," is a system that collects and analyzes business data of an organization, identifies issues, and generates and displays optimized improvement proposals. This system is configured as follows.

[0617] Data Collection Phase

[0618] Users enter their daily work data (e.g., task progress, project status, feedback) into dedicated applications or web portals that are designed to provide a user-friendly interface and make data entry easy.

[0619] The terminal sends the business data entered by the user to the server in real time. The communication is encrypted to ensure the security of the data.

[0620] The server receives the business data sent from the terminal and stores it safely and efficiently in a database. A database management system such as MySQL can be used.

[0621] Data analysis phase

[0622] The server preprocesses and cleanses the received data into an analyzable format using Pandas, a Python data analysis library.

[0623] The server then uses machine learning algorithms to analyze the data and identify issues, such as the Python scikit-learn library, and the natural language processing library NLTK to further analyze the feedback provided by users.

[0624] Furthermore, the server uses a self-learning function to update the parameters of the AI ​​model to improve the accuracy of the next analysis. For example, TensorFlow can be used to train the AI ​​model.

[0625] Issue visualization phase

[0626] The server then uses the analysis results to visualize the overall performance of the organization and any identified issues in the form of a dashboard, which can be created using, for example, Tableau or Power BI, and includes an assessment of different departments and highlights key bottlenecks.

[0627] Users can access the dashboard to check the current status of the organization and identified issues in real time. The user interface is intuitive and designed to allow users to easily grasp the information.

[0628] Improvement proposal phase

[0629] The server generates improvement proposals optimized for the identified issues. For example, if a "lack of communication" issue is identified, it will recommend setting up regular meetings or introducing a dedicated chat tool (e.g., Slack).

[0630] The server displays the generated improvement proposals in the form of a detailed report on the dashboard, including the background of the proposals and specific implementation methods, and uses graphs and charts to make the proposals intuitively understandable to the user.

[0631] The user reviews the proposals and evaluates whether they are feasible to implement. After implementing the proposals, the user enters feedback into the system about their effectiveness. For example, the user may report on the usability and effectiveness of a newly introduced tool as part of an improvement proposal.

[0632] Prompt Sentence Examples

[0633] "Analyze sales department data, identify team performance issues and make suggestions for improvement."

[0634] This allows the system to optimize and continuously improve the performance of the entire organization.

[0635] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0636] Step 1: Data entry

[0637] Users use a dedicated application or web portal to enter their daily work data, including task progress, project status, feedback, etc. Once the data is complete, it is sent to the system.

[0638] Input: Business data such as task progress, project status, and feedback

[0639] Output: Business data sent to the server in real time

[0640] Step 2: Send data

[0641] The terminal encrypts the business data entered by the user and transmits it to the server in real time using a secure protocol.

[0642] Input: Business data entered by the user

[0643] Output: Encrypted and securely transmitted business data

[0644] Step 3: Save Data

[0645] The server receives business data sent from the terminal and stores it safely and efficiently in a database, while checking to see if the data is missing.

[0646] Input: Encrypted business data

[0647] Output: Complete business data stored in a database

[0648] Step 4: Data Preprocessing

[0649] The server performs pre-processing to convert the stored business data into an analyzable format, including imputing missing values, normalizing the data, and cleansing it.

[0650] Input: Business data stored in a database

[0651] Output: Cleansed and normalized parsable data

[0652] Step 5: Data analysis

[0653] The server then uses machine learning algorithms (e.g., scikit-learn) to analyze the preprocessed data, which includes assessing the organization's overall performance and identifying key issues.

[0654] Input: Preprocessed business data

[0655] Output: Key issues identified and performance analysis results

[0656] Step 6: Natural Language Processing

[0657] The server uses natural language processing (e.g., NLTK) to perform detailed analysis of the feedback provided by the user, and integrates insights gained from the feedback into the analysis results.

[0658] Input: User feedback

[0659] Output: Feedback insights integrated into analysis results

[0660] Step 7: Self-study

[0661] The server compares the data with past data and learns from new data, updating the parameters of the AI ​​model using TensorFlow.

[0662] Input: All analysis results

[0663] Output: Updated AI model parameters

[0664] Step 8: Visualize the issue

[0665] Based on the analysis results, the server visualizes the organization's overall performance and identified issues in dashboard format (e.g., Tableau).

[0666] Input: All analysis results

[0667] Output: Analysis results and specific tasks displayed on a dashboard

[0668] Step 9: View the Dashboard

[0669] Users access the dashboard to see the current state of their organization and identified issues in real time.

[0670] Input: Analysis results and specific issues displayed on the dashboard

[0671] Output: User recognition of issues and understanding of the current state of the organization

[0672] Step 10: Generate improvement suggestions

[0673] The server generates optimized improvement proposals for the identified issues. For example, if a "lack of communication" issue is identified, it will recommend setting up regular meetings and introducing a dedicated chat tool.

[0674] Input: Identified Issues

[0675] Output: Improvement suggestions

[0676] Step 11: Displaying improvement suggestions

[0677] The server displays the generated improvement suggestions in the form of a detailed report on a dashboard.

[0678] Input: Improvement suggestion

[0679] Output: Detailed improvement suggestions displayed in a dashboard

[0680] Step 12: Evaluate and provide feedback on the proposal

[0681] The user checks the proposals, evaluates whether they are feasible to implement, and after implementing the proposals, inputs feedback about their effectiveness into the system.

[0682] Input: Improvement suggestions, feedback after implementation

[0683] Output: Feedback data entered into the system

[0684] This allows the system to use user feedback to improve the accuracy of its next analysis and improvement suggestions.

[0685] (Application example 1)

[0686] 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."

[0687] Conventional organizational management systems were able to identify issues and generate improvement proposals by collecting and analyzing business data, but it was difficult to monitor the operating status and work efficiency of robots at production sites in real time and optimize identified issues.In addition, there was no system that could make specific optimization proposals for production efficiency based on robot operating data, making it impossible to instantly improve productivity.

[0688] 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.

[0689] In this invention, the server includes means for collecting business data and storing it in a database, means for analyzing the stored data and identifying issues, means for generating improvement proposals optimized for the identified issues, means for displaying the generated improvement proposals to a user, and means for collecting operation data from a robot and optimizing production efficiency based on the analysis results, thereby enabling specific optimization of production efficiency based on the robot operation data.

[0690] "Business data" refers to information about various business operations conducted by an organization, including task progress, project status, feedback, and the like.

[0691] "Database" means a structured data storage system for efficiently and securely storing and managing collected business data.

[0692] "Analysis" refers to the process of preprocessing the collected data, converting it into an analyzable format using machine learning algorithms and natural language processing, and extracting information that will be useful in the actual operation of the organization.

[0693] "Issues" are bottlenecks in organizational management and problems requiring improvement that are identified from the analyzed data.

[0694] An "improvement proposal" is a specific action plan that proposes an optimized solution or new approach to an identified issue.

[0695] "User" refers to a member or administrator of an organization who uses the system to input business data and check the analysis results and improvement suggestions.

[0696] "Feedback" refers to information including opinions and evaluations provided by users, and is data used to improve the accuracy of the system's analysis results and improvement suggestions.

[0697] A "robot" is a machine that operates in a factory and automatically performs tasks such as assembling and processing products.

[0698] "Operational data" refers to information about the robot's performance, such as its operating status, work efficiency, and error rate.

[0699] "Production efficiency" refers to the efficiency and production volume of work at production sites such as factories, and is an indicator evaluated based on factors such as the operating status of robots and work accuracy.

[0700] A "server" is a computer system that receives business data and robot operation data sent by users, and analyzes, stores, and displays them.

[0701] This invention, "Organizational Management Assist on AI," collects operational data and work efficiency data from robots used in factories in real time, detects specific issues, and generates and displays improvement proposals. The configuration of this system is described below.

[0702] Hardware and software used

[0703] 1. Robot (terminal): An automatic machine that operates in a factory and performs tasks such as assembling and processing products.

[0704] 2. Administrator's terminal: A device for viewing the dashboard and reviewing improvement suggestions on a PC or tablet.

[0705] 3. Server: A computer system that manages all processes of receiving, storing, analyzing, and displaying data. Specifically, it uses the following software:

[0706] Database: MySQL

[0707] Machine learning algorithm: TensorFlow

[0708] Dashboard display tool: Tableau

[0709] Natural language processing libraries required for specific evaluations and analyses

[0710] Program processing explanation

[0711] 1. Data Collection Phase

[0712] The robot (terminal) collects operational data (e.g., operating time, number of errors) and sends it to the server via a dedicated application.

[0713] The server receives the data sent from the robot in real time and stores it securely in a database.

[0714] 2. Data analysis phase

[0715] The server cleanses and pre-processes the received data into a parsable format.

[0716] The data is analyzed using a machine learning algorithm (TensorFlow) to evaluate the robot's performance.

[0717] Using natural language processing, feedback from users is also included in the analysis.

[0718] 3. Issue Visualization Phase

[0719] Based on the analysis results, the server displays the robot's operating status and issues on a dashboard (Tableau).

[0720] The administrator (terminal) accesses the dashboard to check the current status of the robot and any identified issues in real time.

[0721] 4. Improvement proposal phase

[0722] The server generates an optimized improvement proposal for the identified issue. For example, if a "parts supply shortage" is identified, it will propose reviewing the inventory management system and introducing an automatic replenishment system.

[0723] The administrator (terminal) checks the generated improvement proposals, evaluates their implementation, and then inputs feedback about their effectiveness into the system.

[0724] Specific examples

[0725] If Robot A sends data showing that its average operating time has decreased by 5% over the course of a week, the server will use this data to identify a shortage of parts supply and suggest that the inventory management system be revised.

[0726] Prompt Sentence Examples

[0727] Examples of prompts for generative AI models include:

[0728] "Analyze the performance of Robot A this week, identify key issues, and generate improvement suggestions."

[0729] This system makes it possible to specifically optimize production efficiency based on operational data from robots within the factory, thereby improving productivity.

[0730] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0731] Step 1: Data collection

[0732] Description: The robot (terminal) collects operational data from within the factory and sends it to a server via a dedicated application. Specifically, this data includes operating hours, number of errors, production volume, etc.

[0733] Input: Operational data obtained from the robot's sensors and internal systems.

[0734] Output: The raw data sent to the server.

[0735] Step 2: Receiving and storing data

[0736] Description: The server receives the data sent from the robot in real time and stores it securely in a database, specifically in a database system such as MySQL.

[0737] Input: Raw data sent by the robot.

[0738] Output: Operational data stored in a database.

[0739] Step 3: Data preprocessing and cleansing

[0740] Description: The server converts the received data into a parsable format and performs data cleansing, which includes imputing missing values ​​and removing outliers.

[0741] Input: Raw data stored in a database.

[0742] Output: Preprocessed and cleansed data.

[0743] Step 4: Data analysis

[0744] Description: The server analyzes the data using machine learning algorithms (TensorFlow) to evaluate the robot's performance, including calculating the availability rate and evaluating the error rate.

[0745] Input: Preprocessed and cleansed data.

[0746] Output: Robot performance evaluation results.

[0747] Step 5: Identify the issue

[0748] Description: The server extracts identified issues from performance data based on the analysis results. For example, if errors occur frequently within a certain period of time, this is identified as an issue.

[0749] Input: Robot performance evaluation results.

[0750] Output: Identified issues.

[0751] Step 6: Collect and analyze feedback

[0752] Description: The server collects feedback from users (administrators) and reflects it in the analysis results. This is done to improve the accuracy of future analysis of the system.

[0753] Input: Feedback data from users.

[0754] Output: Feedback reflected in the system.

[0755] Step 7: Generate improvement suggestions

[0756] Description: The server generates an optimized improvement proposal based on the identified issues. For example, if the issue of "shortage of parts supply" is identified, it proposes reviewing the inventory management system.

[0757] Input: Identified issue.

[0758] Output: Generated improvement suggestions.

[0759] Step 8: View the proposal

[0760] Description: The server displays the generated improvement suggestions on a dashboard (Tableau) so that the user can understand them intuitively.

[0761] Input: Generated improvement suggestions.

[0762] Output: Improvement suggestions displayed in a dashboard.

[0763] Step 9: Evaluate proposals and provide feedback

[0764] Description: The user (administrator) checks the improvement proposals displayed on the dashboard, evaluates their implementation, and then enters feedback about their effectiveness into the system.

[0765] Input: Improvement suggestions displayed on the dashboard.

[0766] Output: Feedback data.

[0767] Through the above processing steps, the server can achieve specific optimization of production efficiency based on the robot's operation data and provide useful improvement suggestions to the user.

[0768] 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.

[0769] The present invention, "Organizational Management Assist on AI," combines a system that collects and analyzes an organization's business data, identifies issues, and generates and displays optimized improvement proposals with an emotion engine that recognizes the user's emotions. The program processing of this system is explained in detail below.

[0770] Program processing

[0771] Data Collection Phase

[0772] User (Device):

[0773] Users input their daily work data (e.g., task progress, project status, feedback, etc.) into dedicated applications or web portals, and may also input their emotions (e.g., stress, satisfaction, etc.) at the same time.

[0774] Device:

[0775] Business data and emotional data entered by the user are collected in real time and sent to the server.

[0776] Data analysis phase

[0777] server:

[0778] The data sent from the device is received and stored in a database. When storing, the consistency between the business data and the emotion data is checked, and the data is cleansed as necessary.

[0779] server:

[0780] The stored data is converted into an analyzable format, and the emotion engine is used to analyze the user's emotion data.

[0781] server:

[0782] It analyzes operational and emotional data comprehensively and uses machine learning algorithms to evaluate the performance data of the entire organization and each individual, and identifies key issues. For example, if progress on a task is delayed, it analyzes whether the delay is due to emotional factors.

[0783] server:

[0784] Based on the analysis results, the identified issues are generated in the form of a report, including an assessment of different departments and highlighting key bottlenecks.

[0785] Issue visualization phase

[0786] server:

[0787] The generated reports are reflected on a dashboard, allowing users to intuitively understand the information. The results of the analysis of the sentiment data are also displayed on the dashboard.

[0788] User (Device):

[0789] Access the dashboard to see the current state of the organization and any identified challenges. Users can also view their own emotional state.

[0790] Improvement proposal phase

[0791] server:

[0792] It generates optimized improvement proposals for identified issues, such as "providing refreshment time for highly stressed employees" or "assigning highly motivated employees to new projects" based on emotional data.

[0793] server:

[0794] Generated improvement suggestions are displayed in a dashboard in the form of detailed reports.

[0795] User (Device):

[0796] The system checks the proposals and evaluates whether they can be implemented. After implementing the proposals, the system provides feedback on their effectiveness, providing data that will be useful for analyzing the system's future.

[0797] Feedback and self-learning phase

[0798] server:

[0799] It receives feedback and undergoes a self-learning process to incorporate it into its analysis results and improvement suggestions, taking into account sentiment data to improve the accuracy of its next analysis.

[0800] Specific examples

[0801] Data collection:

[0802] User (terminal): Sales department employees enter their daily sales performance data and their own stress levels into the system.

[0803] Server: Receives the data in real time and stores it in a database.

[0804] Data Analysis:

[0805] Server: Analyzes stored sales performance data and stress level data to compare the performance and emotional state of different sales teams.

[0806] Issue visualization:

[0807] Server: Based on the analysis results, the sales performance and stress level of each team are displayed on a dashboard.

[0808] User (device): Check the status of their team on the dashboard and recognize areas that need improvement and the need for stress management.

[0809] Improvement suggestions:

[0810] Server: Based on the analysis, it displays suggestions such as "certain sales teams should adjust their workload" or emotion-based suggestions such as "set rest time for members with high stress levels."

[0811] User (terminal): Implements improvement suggestions and inputs feedback on the results into the system.

[0812] This system not only efficiently optimizes business operations across the organization, but also achieves sustainable performance improvement, including employee emotional management.

[0813] The processing flow will be explained below.

[0814] Step 1:

[0815] User (terminal): The user inputs daily work data (e.g., task progress and project status) and emotional data (e.g., stress level and motivation) into a dedicated application or web portal.

[0816] Step 2:

[0817] Terminal: Collects business data and emotional data entered by the user in real time and sends it to the server.

[0818] Step 3:

[0819] Server: Receives data sent from the device and stores it in a database. When storing the data, it checks its consistency and performs data cleansing (deleting duplicate data and correcting inconsistent data) as necessary.

[0820] Step 4:

[0821] Server: The stored business data and emotion data are converted into an analyzable format. At this stage, the data is normalized and the format is standardized.

[0822] Step 5:

[0823] Server: The converted data is analyzed using machine learning algorithms. Performance data for the entire organization and for each individual is evaluated to identify key issues. For example, if sales performance is declining, the server analyzes whether this is due to emotional factors (e.g., high stress levels).

[0824] Step 6:

[0825] Server: Utilizing the emotion engine, further analyzes the user's emotion data, thereby identifying not only business issues but also emotional issues.

[0826] Step 7:

[0827] Server: Based on the analysis results, the identified issues are generated in the form of a report, which includes evaluations by different departments, key bottlenecks, and analysis results based on sentiment data.

[0828] Step 8:

[0829] Server: The generated reports are reflected in the dashboard, allowing users to intuitively understand the information.

[0830] Step 9:

[0831] User (device): Access the dashboard to check the current state of the organization, identified issues, and the results of the sentiment data analysis.

[0832] Step 10:

[0833] Server: Generates optimized improvement proposals for identified issues, including proposals based on emotional data. For example, it makes specific proposals such as "providing refreshment time for highly stressed users" or "assigning highly motivated users to new projects."

[0834] Step 11:

[0835] Server: Generated improvement suggestions are displayed in the form of detailed reports on the dashboard.

[0836] Step 12:

[0837] User (device): Checks the proposal, evaluates whether it can be implemented, and provides feedback and data on its effectiveness.

[0838] Step 13:

[0839] Server: Receives user feedback and executes a self-learning process to reflect it in analysis results and improvement suggestions. Feedback includes emotional data, which improves the accuracy of the next analysis.

[0840] Example 2

[0841] 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."

[0842] Conventional business data analysis systems only target business data and do not consider employee emotional data, making it difficult to make optimal business improvement proposals. Furthermore, there is no self-learning process that incorporates feedback on analysis results into the system, limiting improvements to analysis accuracy. Therefore, there is a need for the development of an integrated system that simultaneously improves business efficiency and manages employee emotions.

[0843] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0844] In this invention, the server includes: means for collecting business data and emotion data and storing them in a database; means for verifying the consistency of the stored business data and emotion data and performing data cleansing as necessary; means for converting the collected business data and emotion data into an analyzable format; means for analyzing the emotion data using an emotion analysis engine; means for comprehensively analyzing the business data and emotion data, evaluating performance data using a machine learning algorithm, and identifying major issues; means for generating a report based on the identified issues and highlighting evaluations for different departments and major bottlenecks; means for reflecting the generated report on a dashboard and displaying information intuitively to a user; means for generating improvement proposals optimized for the identified issues and making specific proposals based on the emotion data; and means for displaying the generated improvement proposals in a detailed report format on the dashboard. This simultaneously achieves business efficiency and employee emotion management, thereby enabling improved performance across the organization and sustainable business improvement.

[0845] "Business data" refers to various information related to business, such as task progress, project status, and feedback.

[0846] "Emotion data" refers to information that indicates the user's psychological state, such as stress or satisfaction.

[0847] A "database" refers to a system that stores business data and emotional data in a structured format and allows it to be searched and manipulated as needed.

[0848] "Verifying consistency" refers to the process of validating data formats and checking relationships between data to ensure data consistency and accuracy.

[0849] "Data cleansing" refers to the process of correcting data inconsistencies and outliers to improve data quality.

[0850] "Converting to an analyzable format" refers to the process of formatting data into a form suitable for analysis and processing.

[0851] An "emotion analysis engine" refers to software or algorithms that analyze user emotional data and output the results.

[0852] A "machine learning algorithm" refers to a computational method that learns from data and automatically performs specific tasks.

[0853] "Performance data" refers to data used to evaluate the work performance and results of an organization or individual.

[0854] A "report" refers to a document that systematically organizes and visually displays analysis results and evaluation contents.

[0855] A "dashboard" is an interface that aggregates multiple data visualizations and allows users to grasp key indicators and information at a glance.

[0856] "Improvement proposals" refer to specific proposals for achieving more effective work performance and emotional management in response to identified issues.

[0857] The "self-learning process" refers to the process by which the system incorporates new data and feedback to automatically improve the accuracy of its analysis.

[0858] The present invention relates to a system called "Organizational Management Assist on AI," which collects and analyzes business data and emotional data, identifies issues, and makes optimal improvement proposals. Specific embodiments for implementing this system are described below.

[0859] Data Collection Phase

[0860] User (Device):

[0861] Users use a dedicated application or web portal to input daily work data (e.g., task progress, project status, feedback, etc.) as well as emotional data (e.g., stress, satisfaction, etc.), allowing data on work status and employee emotional states to be collected simultaneously.

[0862] Examples of software used: dedicated applications, web portals

[0863] Example: Sales staff use a dedicated application to enter their sales performance and daily stress levels.

[0864] Data collection and transmission

[0865] Device:

[0866] The business data and emotion data entered by the user are sent to the server in real time using API calls to ensure data is collected without delay.

[0867] Examples of hardware and software used: API, network communication

[0868] Example: A sales department employee's device sends data to the server as soon as the data entry is completed.

[0869] Data analysis phase

[0870] server:

[0871] The server checks the integrity of the received data and performs data cleansing if necessary before storing it in a database (e.g., MySQL, PostgreSQL, etc.). The stored data is then converted into an analyzable format. Sentiment data is then analyzed using a sentiment analysis engine (e.g., IBM Watson, Affectiva, etc.).

[0872] Examples of software used: MySQL, PostgreSQL, IBM Watson, Affectiva

[0873] Example: The server receives sales performance data and emotion data, unifies the format, and stores it in a database. The emotion analysis engine analyzes the stress level data.

[0874] Analyzing performance data

[0875] server:

[0876] By integrating and analyzing operational and sentiment data and using machine learning algorithms (e.g., TensorFlow, scikit-learn, etc.) to evaluate performance data, we can accurately assess the performance of the entire organization and individual employees and identify key issues.

[0877] Examples of software used: TensorFlow, scikit-learn

[0878] Example: The server analyzes sales performance data and stress data to determine whether stress is the cause of poor performance.

[0879] Report generation and visualization

[0880] server:

[0881] Based on the analysis results, reports are generated to highlight the performance of different departments and major bottlenecks. The generated reports are reflected in a dashboard, displaying information in an intuitive and easy-to-understand format for users.

[0882] Examples of software used: Tableau, Microsoft Power BI

[0883] Example: Based on the analysis results, the performance of the sales and development departments and their respective issues are compiled into a report and displayed on a dashboard.

[0884] Generate and implement improvement suggestions

[0885] server:

[0886] For identified issues, the system generates optimized improvement proposals that take emotional data into account. The proposals are displayed in a detailed report format on a dashboard, allowing users to review the proposals and evaluate whether or not they should be implemented. After implementing the proposals, users can enter feedback about their effectiveness into the system, which accumulates feedback data.

[0887] Example: Based on the analysis results, suggestions such as "A specific sales team should adjust their workload" or "Set rest time for employees with high stress levels" are displayed. The user implements these suggestions and provides feedback on the results.

[0888] Self-Learning Process

[0889] server:

[0890] A self-learning process is performed to incorporate received feedback into analysis results and improvement suggestions, thereby improving the accuracy of the next analysis and continuously improving system performance.

[0891] Examples of software used: machine learning models, feedback analysis algorithms

[0892] Example: Feedback data is used as new learning data to retrain a performance evaluation model.

[0893] Example prompts for generative AI models

[0894] Please display the analysis results of this month's sales department performance and each employee's stress level.

[0895] Compare the progress of Project X with the satisfaction of your team members.

[0896] Display the best improvement suggestions for highly stressed employees.

[0897] In this way, the present invention provides an innovative system that effectively integrates and analyzes business data and emotional data, simultaneously optimizing business operations and managing employee emotions.

[0898] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0899] Step 1:

[0900] Entering data

[0901] Users use a dedicated application or web portal to input daily work data (e.g., task progress, project status, feedback, etc.) and emotional data (e.g., stress, satisfaction, etc.).

[0902] Input: Business data and emotion data

[0903] Specific operation: Through the application UI, the user selects the progress of the task from a drop-down menu and sets the stress level using a slider. After entering the data, the data is registered by pressing the submit button.

[0904] Step 2:

[0905] Sending data

[0906] The terminal transmits the business data and emotion data input by the user to the server in real time.

[0907] Input: Data entered by the user

[0908] Output: Data sent to the server

[0909] Specific operation: The device uses an API call to send input data to the server, and during this process checks the HTTP response to ensure the data was sent correctly.

[0910] Step 3:

[0911] Receiving and storing data

[0912] The server receives the data sent from the terminal, first checks its integrity, and then stores the data in the database.

[0913] Input: Data sent from the terminal

[0914] Output: Data stored in the database

[0915] Specific operation: The server validates the format and content of the received data, for example, rejecting incomplete records and mismatched data. After the validation, the data is inserted into a database such as MySQL or PostgreSQL.

[0916] Step 4:

[0917] Data cleansing and transformation

[0918] The server cleanses the stored data and converts it into an analyzable format.

[0919] Input: Saved data

[0920] Output: Data in a parsable format

[0921] Specific operations: The server performs operations to improve data quality, such as imputing missing values, correcting outliers, and standardizing data formats. For example, it converts all date and time data to a unified format (YYYY-MM-DD).

[0922] Step 5:

[0923] Emotional Data Analysis

[0924] The server uses an emotion analysis engine (e.g., IBM Watson, Affectiva, etc.) to analyze the user's emotion data.

[0925] Input: Cleansed emotion data

[0926] Output: Parsed emotion data

[0927] Specific operation: The server sends the emotion data to the analysis engine's API and stores the returned analysis results in a database. For example, it receives analysis results such as "high stress level" or "low satisfaction level."

[0928] Step 6:

[0929] Comprehensive Data Analysis

[0930] The server comprehensively analyzes business data and sentiment data, evaluates performance data using machine learning algorithms (e.g., TensorFlow, scikit-learn, etc.), and identifies key issues.

[0931] Input: Data in a parsable format, parsed emotion data

[0932] Output: Performance evaluation results, identified issues

[0933] Specific operation: The server inputs data into a machine learning model to evaluate, for example, whether delays in task progress are due to emotional factors. The model's output is stored in a database.

[0934] Step 7:

[0935] Generate reports

[0936] The server generates reports based on the analysis results, highlighting the performance of different departments and highlighting key bottlenecks.

[0937] Input: Performance evaluation results, identified issues

[0938] Output: Generated report

[0939] Specific operation: The report generation system dynamically inserts analysis results based on templates to create visually easy-to-understand reports, which are then saved in PDF or web format.

[0940] Step 8:

[0941] Reflected on the dashboard

[0942] The server reflects the generated report on the dashboard and displays the information so that the user can intuitively understand it.

[0943] Input: Generated report

[0944] Output: The data displayed on the dashboard

[0945] Specific operation: The server uses a data visualization tool (e.g., Tableau, Microsoft Power BI, etc.) to visualize the report contents as graphs and charts and display them on a dashboard.

[0946] Step 9:

[0947] Accessing the Dashboard

[0948] Users can access a dashboard to view the current state of their organization, identify identified challenges, and even view their own emotional state.

[0949] Input: User login information

[0950] Output: The displayed dashboard

[0951] How it works: Users can log in to the dashboard using a dedicated application or a web browser to view various data. For example, they can use the filter function to view data for a specific time range.

[0952] Step 10:

[0953] Generate improvement suggestions

[0954] The server generates improvement proposals optimized for the identified issues and makes specific proposals based on emotion data.

[0955] Input: Identified issues, emotion data

[0956] Output: Improvement suggestions

[0957] Specific operation: Based on the analysis results, the server generates suggestions such as "providing refreshment time for employees with high stress levels" and "assigning highly motivated employees to new projects," and compiles them in report format.

[0958] Step 11:

[0959] Viewing improvement suggestions

[0960] The server displays the generated improvement suggestions in the form of a detailed report on a dashboard.

[0961] Input: Improvement suggestion

[0962] Output: Improvement suggestions displayed in a dashboard

[0963] Specific behavior: Improvement suggestions will be displayed on the dashboard in a visually easy-to-understand format with explanatory text and graphs. Also, a notification function will be implemented to allow users to check the suggestions.

[0964] Step 12:

[0965] Evaluation and feedback of proposals

[0966] The user checks the proposals, evaluates whether they are feasible to implement, and after implementing the proposals, inputs feedback on their effectiveness.

[0967] Input: Suggestion rating, feedback

[0968] Output: Feedback data

[0969] Specific operation: After checking the proposal on the dashboard, the user clicks the button to rate it, enters the effects in the feedback form, and submits it.

[0970] Step 13:

[0971] Receiving Feedback

[0972] The server receives the feedback from the user and stores it in a database.

[0973] Input: Feedback data

[0974] Output: Saved feedback data

[0975] What it does: Validates the feedback data and stores it in the database, appropriately labeling it as a new data point.

[0976] Step 14:

[0977] Implementing a self-learning process

[0978] The server uses the feedback data to perform a self-learning process to improve the analysis results and suggestions for improvement, thereby improving the accuracy of the next analysis.

[0979] Input: Saved feedback data

[0980] Output: Updated analytical model

[0981] Specific operation: The server retrains the machine learning model based on the feedback data and adds new data to the training dataset, thereby improving the accuracy of the analytical model.

[0982] Through the above processing steps, the present invention effectively integrates and analyzes business data and emotion data, thereby simultaneously optimizing business operations and managing employee emotions.

[0983] (Application example 2)

[0984] 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."

[0985] Simultaneously managing employees' work efficiency and emotional state is a major challenge for many companies. Conventional systems typically handle work data and emotional data separately, making it difficult to effectively generate optimal improvement proposals. Furthermore, an inability to properly grasp employees' emotional states can lead to ineffective work style improvements, resulting in lower productivity and employee satisfaction.

[0986] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting business data and saving it in a database, means for analyzing the saved data and identifying issues, means for analyzing user emotion data, means for comprehensively analyzing the business data and emotion data and generating optimized improvement proposals, and means for displaying the generated improvement proposals to the user. As a result, by comprehensively analyzing the business data and emotion data and making optimal improvement proposals, it is possible to simultaneously improve employee productivity and manage emotions.

[0987] "Business Data" means information related to an employee's or organization's business, including task progress and project status.

[0988] A "database" is a system for efficiently storing and managing collected data.

[0989] "Challenges" refer to problems or bottlenecks that hinder the work performance of an organization or individual.

[0990] "Emotion data" is information about the user's emotional state, and includes psychological factors such as stress and satisfaction.

[0991] "Analysis" is the process of analyzing collected data and extracting meaningful information and trends.

[0992] An "improvement proposal" is a specific proposal or action plan aimed at resolving an identified issue.

[0993] "User" refers to an individual or member of an organization who uses this system.

[0994] "Storage" means recording the collected data in a database for later use.

[0995] "Comprehensive" means treating different types of data as a whole and conducting a comprehensive analysis.

[0996] A "system" is a collection of components that have multiple functions and work together to operate.

[0997] A specific system for implementing this invention consists of several main components and steps. First, the user's device collects daily work data and emotional data. This is done using various sensors in the factory and employee feedback devices (tablets, PCs, etc.). The collected data is then sent to a server and stored in a database.

[0998] A program is installed on the server to convert the data into an analyzable format. At this stage, data cleansing is performed to remove inconsistencies and missing data. Next, an algorithm is run to comprehensively analyze the business data and emotion data. Specifically, Python's Pandas and machine learning models (e.g., RandomForestRegressor) are used for the analysis. A virtual emotion engine library (EmotionEngine) is also used to analyze the emotion data.

[0999] Once the analysis is complete, the server generates optimized improvement proposals based on the identified issues. These proposals may include, for example, "providing additional break time for specific employees" or "adjusting the workload of employees with high stress levels." The generated improvement proposals are displayed to the user in a dashboard format, allowing the user to review them and implement them as necessary.

[1000] Feedback on the execution results is also collected through the same system to inform future analysis, allowing the self-learning algorithm to improve the system's analysis accuracy.

[1001] To give a specific example, employees in the sales department enter their daily task progress and stress levels into the system. The collected data is sent to a server and stored in a database. The server analyzes the data and compares sales performance with stress levels. The analysis results are displayed on a dashboard, and suggestions for improvement, such as "applying additional break time," are made to specific employees.

[1002] An example prompt is:

[1003] "Collect factory sensor and employee feedback data, analyze productivity and emotional state, and generate optimal improvement proposals for identified issues."

[1004] This system simultaneously improves employee productivity and manages emotions by integrating and analyzing business data and emotional data.

[1005] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1006] Step 1:

[1007] Users (terminals) collect daily work data and emotional data. Specifically, various sensors in the factory input task progress status, and employees input emotional data (such as stress level and satisfaction) using their feedback terminals (tablets, PCs, etc.). The input data is sent to the server in real time. An example of input data is "2023-10-01, Task A, in progress, stress level: high."

[1008] Step 2:

[1009] The server stores the business data and emotion data sent from the device in a database. Specifically, data processing involves converting the received data into a predefined format and performing data cleansing. Inconsistencies and missing data are removed. If the input is "Stress level: high," it is validated within a safe range and stored in the database.

[1010] Step 3:

[1011] The server converts the stored data into an analyzable format. Specifically, it uses Python's Pandas library to change the data into a table format. For example, it converts the data into a format where each row represents data for one employee. During this process, it removes unnecessary data and extracts only the necessary fields. An unformatted data frame is given as input, and a formatted data frame is generated as output.

[1012] Step 4:

[1013] The server runs machine learning algorithms to analyze the formatted data. Specifically, it uses models such as RandomForestRegressor to comprehensively analyze business data and emotional data. It also uses an emotional analysis engine such as EmotionEngine. This analysis predicts employee productivity and emotional state. The identified data frame is used as input, and a new data frame containing the predicted results is generated as output.

[1014] Step 5:

[1015] The server generates identified issues and optimized improvement proposals based on the analysis results. Specific actions include "recommending additional break time for employees with high stress levels." The analysis result data frame is used as input, and the output is a list of improvement proposals.

[1016] Step 6:

[1017] The server displays the generated improvement suggestions on the user's dashboard. Specifically, the suggestions are displayed as graphs and text reports that are updated in real time on the web application dashboard. The input is the list of improvement suggestions, and the output is the visualized dashboard.

[1018] Step 7:

[1019] The user (device) checks the displayed improvement suggestions and inputs feedback as necessary. A specific example is feedback such as "As a result of applying additional break time, the stress level decreased." Feedback text is used as input, and the output is sent to the server as feedback data.

[1020] Step 8:

[1021] The server analyzes the collected feedback and performs a self-learning process to improve the accuracy of the next analysis and recommendation. Specifically, it uses the feedback data to retrain the machine learning model. The feedback data is used as input, and the output is an updated machine learning model.

[1022] In this way, a system is constructed that comprehensively analyzes business data and emotional data, and generates and displays optimal improvement proposals.

[1023] 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.

[1024] 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.

[1025] 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.

[1026] [Third embodiment]

[1027] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1028] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1029] 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).

[1030] 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.

[1031] 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.

[1032] 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).

[1033] 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.

[1034] 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.

[1035] 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.

[1036] 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.

[1037] 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.

[1038] 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."

[1039] The present invention, "Organization Management Assist on AI," is a system that collects and analyzes an organization's business data, identifies issues, and generates and displays optimized improvement proposals. The program processing of this system is explained in detail below.

[1040] Program processing

[1041] Data Collection Phase

[1042] User (Device):

[1043] Users enter their daily work data (e.g., task progress, project status, feedback, etc.) into dedicated applications and web portals.

[1044] server:

[1045] Business data sent from the terminal is received in real time and stored safely and efficiently in a database.

[1046] Data analysis phase

[1047] server:

[1048] The data is pre-processed and cleansed into an analyzable format, then machine learning algorithms are used to analyze performance data across the organization and identify key issues. The analysis also includes natural language processing to perform a detailed analysis of the feedback provided by users.

[1049] server:

[1050] By comparing it with past data and learning from new data, the AI ​​model parameters are updated using a self-learning function, improving the accuracy of the next analysis.

[1051] Issue visualization phase

[1052] server:

[1053] Once the analysis results are available, the overall performance of the organization and the identified challenges are visualized in the form of a dashboard, which includes an assessment of different departments and highlights the major bottlenecks.

[1054] User (Device):

[1055] Access the dashboard to see the current status of your organization and any identified challenges in real time.

[1056] Improvement proposal phase

[1057] server:

[1058] Generates optimized improvement proposals for identified issues. For example, if the issue of "lack of communication" is identified, suggestions will be made such as setting up regular meetings or introducing a dedicated chat tool.

[1059] server:

[1060] The generated improvement suggestions are displayed in a detailed report format on a dashboard, allowing users to intuitively understand them.

[1061] User (Device):

[1062] The system reviews the proposals and evaluates whether they can be implemented. After implementing the proposals, the system provides feedback on their effectiveness, providing data that will be useful for analyzing the system's future.

[1063] Specific examples

[1064] Data collection:

[1065] User (terminal): Sales department employees input daily sales performance data into the system.

[1066] Server: Receives the data in real time and stores it in a database.

[1067] Data Analysis:

[1068] Server: Analyzes stored sales performance data using machine learning algorithms and natural language processing to compare the performance of different sales teams.

[1069] Issue visualization:

[1070] Server: Based on the analysis results, a dashboard displays the performance of different sales teams and key issues.

[1071] Users (devices): Check the status of their team on the dashboard and recognize areas that need improvement.

[1072] Improvement suggestions:

[1073] Server: Based on the analysis results, specific improvement suggestions such as "certain sales teams should increase weekly meetings" are displayed.

[1074] User (terminal): Implements improvement suggestions and inputs feedback on the results into the system.

[1075] This system will enable efficient optimization of business operations across the organization, leading to sustained performance improvements.

[1076] The processing flow will be explained below.

[1077] Step 1:

[1078] User (device): Enters daily work data, such as task progress, project status, and feedback, into dedicated applications and web portals.

[1079] Step 2:

[1080] Terminal: Collects business data entered by the user in real time and sends it to the server.

[1081] Step 3:

[1082] Server: Receives data sent from the device and stores it in a database. When storing the data, it checks the consistency of the data and performs data cleansing (deleting duplicate data and correcting inconsistent data) as necessary.

[1083] Step 4:

[1084] Server: Transforms the stored data into an analyzable format, which includes normalizing the data and standardizing the format.

[1085] Step 5:

[1086] Server: Based on the cleansed data, it uses machine learning algorithms to analyze it. Specifically, it analyzes performance data for the entire organization and for each individual to identify key issues. For example, if progress on a task is slow, it analyzes all relevant data points to identify the cause.

[1087] Step 6:

[1088] Server: Based on the analysis results, the identified issues are generated in the form of a report, which includes an assessment of different departments and highlights the main bottlenecks.

[1089] Step 7:

[1090] Server: The generated reports are reflected in the dashboard, allowing users to intuitively understand the information.

[1091] Step 8:

[1092] Users (devices): Access the dashboard to check the current status of the organization and any identified issues.

[1093] Step 9:

[1094] Server: Generates optimized improvement proposals for identified issues. For example, if a lack of communication is identified, the server will make specific proposals such as scheduling regular meetings or introducing a dedicated chat tool.

[1095] Step 10:

[1096] Server: Generated improvement suggestions are displayed in the form of detailed reports on the dashboard.

[1097] Step 11:

[1098] User (device): Checks the proposal and evaluates whether it can be implemented. Also, inputs feedback to help with the next analysis.

[1099] Step 12:

[1100] Server: Receives feedback from users and executes a self-learning process to reflect it in analysis results and improvement suggestions. This improves the accuracy of the next analysis and makes it possible to provide more effective improvement suggestions.

[1101] Example 1

[1102] 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."

[1103] Conventional organizational management systems only collect and analyze business data, making it difficult to extract useful information from large amounts of data and make specific improvement proposals. Furthermore, there is no mechanism for effectively incorporating user feedback, making it difficult for the system to self-improve.

[1104] 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.

[1105] In this invention, the server includes means for collecting business data and storing it in a database, means for preprocessing and cleansing the stored data, means for analyzing the data using a machine learning algorithm and identifying issues, means for visualizing the issues in a dashboard format based on the analysis results, means for generating improvement proposals optimized for the identified issues, and means for displaying the generated improvement proposals to a user, thereby enabling performance improvement and optimization of the entire organization.

[1106] "Business Data" refers to information related to daily business activities, such as task progress, project status, and feedback.

[1107] "Database" refers to an information system that securely stores collected business data and makes it easy to access and manage.

[1108] "Preprocessing" refers to tasks such as filling in missing values, normalizing data, and cleansing data in order to convert raw data into an analyzable format.

[1109] "Cleansing" refers to the process of removing unnecessary data and correcting incorrect data in order to improve data quality.

[1110] A "machine learning algorithm" refers to a calculation method that learns data patterns based on past data and makes predictions and classifications for future data.

[1111] A "dashboard" is a tool that visually displays the results of data analysis, allowing users to intuitively understand an organization's performance and identified issues.

[1112] "Improvement proposals" refer to optimized solutions or measures for issues identified based on the results of data analysis.

[1113] "Feedback from users" refers to information such as opinions, impressions, and areas for improvement after users use the system provided.

[1114] "Self-learning function" refers to the function that learns from new data and improves the accuracy of the model.

[1115] An "AI model" refers to a computational model built to solve a specific problem based on patterns and rules learned from data using machine learning algorithms.

[1116] The present invention, "Organization Management Assist on AI," is a system that collects and analyzes business data of an organization, identifies issues, and generates and displays optimized improvement proposals. This system is configured as follows.

[1117] Data Collection Phase

[1118] Users enter their daily work data (e.g., task progress, project status, feedback) into dedicated applications or web portals that are designed to provide a user-friendly interface and make data entry easy.

[1119] The terminal sends the business data entered by the user to the server in real time. The communication is encrypted to ensure the security of the data.

[1120] The server receives the business data sent from the terminal and stores it safely and efficiently in a database. A database management system such as MySQL can be used.

[1121] Data analysis phase

[1122] The server preprocesses and cleanses the received data into an analyzable format using Pandas, a Python data analysis library.

[1123] The server then uses machine learning algorithms to analyze the data and identify issues, such as the Python scikit-learn library, and the natural language processing library NLTK to further analyze the feedback provided by users.

[1124] Furthermore, the server uses a self-learning function to update the parameters of the AI ​​model to improve the accuracy of the next analysis. For example, TensorFlow can be used to train the AI ​​model.

[1125] Issue visualization phase

[1126] The server then uses the analysis results to visualize the overall performance of the organization and any identified issues in the form of a dashboard, which can be created using, for example, Tableau or Power BI, and includes an assessment of different departments and highlights key bottlenecks.

[1127] Users can access the dashboard to check the current status of the organization and identified issues in real time. The user interface is intuitive and designed to allow users to easily grasp the information.

[1128] Improvement proposal phase

[1129] The server generates improvement proposals optimized for the identified issues. For example, if a "lack of communication" issue is identified, it will recommend setting up regular meetings or introducing a dedicated chat tool (e.g., Slack).

[1130] The server displays the generated improvement proposals in the form of a detailed report on the dashboard, including the background of the proposals and specific implementation methods, and uses graphs and charts to make the proposals intuitively understandable to the user.

[1131] The user reviews the proposals and evaluates whether they are feasible to implement. After implementing the proposals, the user enters feedback into the system about their effectiveness. For example, the user may report on the usability and effectiveness of a newly introduced tool as part of an improvement proposal.

[1132] Prompt Sentence Examples

[1133] "Analyze sales department data, identify team performance issues and make suggestions for improvement."

[1134] This allows the system to optimize and continuously improve the performance of the entire organization.

[1135] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1136] Step 1: Data entry

[1137] Users use a dedicated application or web portal to enter their daily work data, including task progress, project status, feedback, etc. Once the data is complete, it is sent to the system.

[1138] Input: Business data such as task progress, project status, and feedback

[1139] Output: Business data sent to the server in real time

[1140] Step 2: Send data

[1141] The terminal encrypts the business data entered by the user and transmits it to the server in real time using a secure protocol.

[1142] Input: Business data entered by the user

[1143] Output: Encrypted and securely transmitted business data

[1144] Step 3: Save Data

[1145] The server receives business data sent from the terminal and stores it safely and efficiently in a database, while checking to see if the data is missing.

[1146] Input: Encrypted business data

[1147] Output: Complete business data stored in a database

[1148] Step 4: Data Preprocessing

[1149] The server performs pre-processing to convert the stored business data into an analyzable format, including imputing missing values, normalizing the data, and cleansing it.

[1150] Input: Business data stored in a database

[1151] Output: Cleansed and normalized parsable data

[1152] Step 5: Data analysis

[1153] The server then uses machine learning algorithms (e.g., scikit-learn) to analyze the preprocessed data, which includes assessing the organization's overall performance and identifying key issues.

[1154] Input: Preprocessed business data

[1155] Output: Key issues identified and performance analysis results

[1156] Step 6: Natural Language Processing

[1157] The server uses natural language processing (e.g., NLTK) to perform detailed analysis of the feedback provided by the user, and integrates insights gained from the feedback into the analysis results.

[1158] Input: User feedback

[1159] Output: Feedback insights integrated into analysis results

[1160] Step 7: Self-study

[1161] The server compares the data with past data and learns from new data, updating the parameters of the AI ​​model using TensorFlow.

[1162] Input: All analysis results

[1163] Output: Updated AI model parameters

[1164] Step 8: Visualize the issue

[1165] Based on the analysis results, the server visualizes the organization's overall performance and identified issues in dashboard format (e.g., Tableau).

[1166] Input: All analysis results

[1167] Output: Analysis results and specific tasks displayed on a dashboard

[1168] Step 9: View the Dashboard

[1169] Users access the dashboard to see the current state of their organization and identified issues in real time.

[1170] Input: Analysis results and specific issues displayed on the dashboard

[1171] Output: User recognition of issues and understanding of the current state of the organization

[1172] Step 10: Generate improvement suggestions

[1173] The server generates optimized improvement proposals for the identified issues. For example, if a "lack of communication" issue is identified, it will recommend setting up regular meetings and introducing a dedicated chat tool.

[1174] Input: Identified Issues

[1175] Output: Improvement suggestions

[1176] Step 11: Displaying improvement suggestions

[1177] The server displays the generated improvement suggestions in the form of a detailed report on a dashboard.

[1178] Input: Improvement suggestion

[1179] Output: Detailed improvement suggestions displayed in a dashboard

[1180] Step 12: Evaluate and provide feedback on the proposal

[1181] The user checks the proposals, evaluates whether they are feasible to implement, and after implementing the proposals, inputs feedback about their effectiveness into the system.

[1182] Input: Improvement suggestions, feedback after implementation

[1183] Output: Feedback data entered into the system

[1184] This allows the system to use user feedback to improve the accuracy of its next analysis and improvement suggestions.

[1185] (Application example 1)

[1186] 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."

[1187] Conventional organizational management systems were able to identify issues and generate improvement proposals by collecting and analyzing business data, but it was difficult to monitor the operating status and work efficiency of robots at production sites in real time and optimize identified issues.In addition, there was no system that could make specific optimization proposals for production efficiency based on robot operating data, making it impossible to instantly improve productivity.

[1188] 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.

[1189] In this invention, the server includes means for collecting business data and storing it in a database, means for analyzing the stored data and identifying issues, means for generating improvement proposals optimized for the identified issues, means for displaying the generated improvement proposals to a user, and means for collecting operation data from a robot and optimizing production efficiency based on the analysis results, thereby enabling specific optimization of production efficiency based on the robot operation data.

[1190] "Business data" refers to information about various business operations conducted by an organization, including task progress, project status, feedback, and the like.

[1191] "Database" means a structured data storage system for efficiently and securely storing and managing collected business data.

[1192] "Analysis" refers to the process of preprocessing the collected data, converting it into an analyzable format using machine learning algorithms and natural language processing, and extracting information that will be useful in the actual operation of the organization.

[1193] "Issues" are bottlenecks in organizational management and problems requiring improvement that are identified from the analyzed data.

[1194] An "improvement proposal" is a specific action plan that proposes an optimized solution or new approach to an identified issue.

[1195] "User" refers to a member or administrator of an organization who uses the system to input business data and check the analysis results and improvement suggestions.

[1196] "Feedback" refers to information including opinions and evaluations provided by users, and is data used to improve the accuracy of the system's analysis results and improvement suggestions.

[1197] A "robot" is a machine that operates in a factory and automatically performs tasks such as assembling and processing products.

[1198] "Operational data" refers to information about the robot's performance, such as its operating status, work efficiency, and error rate.

[1199] "Production efficiency" refers to the efficiency and production volume of work at production sites such as factories, and is an indicator evaluated based on factors such as the operating status of robots and work accuracy.

[1200] A "server" is a computer system that receives business data and robot operation data sent by users, and analyzes, stores, and displays them.

[1201] This invention, "Organizational Management Assist on AI," collects operational data and work efficiency data from robots used in factories in real time, detects specific issues, and generates and displays improvement proposals. The configuration of this system is described below.

[1202] Hardware and software used

[1203] 1. Robot (terminal): An automatic machine that operates in a factory and performs tasks such as assembling and processing products.

[1204] 2. Administrator's terminal: A device for viewing the dashboard and reviewing improvement suggestions on a PC or tablet.

[1205] 3. Server: A computer system that manages all processes of receiving, storing, analyzing, and displaying data. Specifically, it uses the following software:

[1206] Database: MySQL

[1207] Machine learning algorithm: TensorFlow

[1208] Dashboard display tool: Tableau

[1209] Natural language processing libraries required for specific evaluations and analyses

[1210] Program processing explanation

[1211] 1. Data Collection Phase

[1212] The robot (terminal) collects operational data (e.g., operating time, number of errors) and sends it to the server via a dedicated application.

[1213] The server receives the data sent from the robot in real time and stores it securely in a database.

[1214] 2. Data analysis phase

[1215] The server cleanses and pre-processes the received data into a parsable format.

[1216] The data is analyzed using a machine learning algorithm (TensorFlow) to evaluate the robot's performance.

[1217] Using natural language processing, feedback from users is also included in the analysis.

[1218] 3. Issue Visualization Phase

[1219] Based on the analysis results, the server displays the robot's operating status and issues on a dashboard (Tableau).

[1220] The administrator (terminal) accesses the dashboard to check the current status of the robot and any identified issues in real time.

[1221] 4. Improvement proposal phase

[1222] The server generates an optimized improvement proposal for the identified issue. For example, if a "parts supply shortage" is identified, it will propose reviewing the inventory management system and introducing an automatic replenishment system.

[1223] The administrator (terminal) checks the generated improvement proposals, evaluates their implementation, and then inputs feedback about their effectiveness into the system.

[1224] Specific examples

[1225] If Robot A sends data showing that its average operating time has decreased by 5% over the course of a week, the server will use this data to identify a shortage of parts supply and suggest that the inventory management system be revised.

[1226] Prompt Sentence Examples

[1227] Examples of prompts for generative AI models include:

[1228] "Analyze the performance of Robot A this week, identify key issues, and generate improvement suggestions."

[1229] This system makes it possible to specifically optimize production efficiency based on operational data from robots within the factory, thereby improving productivity.

[1230] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1231] Step 1: Data collection

[1232] Description: The robot (terminal) collects operational data from within the factory and sends it to a server via a dedicated application. Specifically, this data includes operating hours, number of errors, production volume, etc.

[1233] Input: Operational data obtained from the robot's sensors and internal systems.

[1234] Output: The raw data sent to the server.

[1235] Step 2: Receiving and storing data

[1236] Description: The server receives the data sent from the robot in real time and stores it securely in a database, specifically in a database system such as MySQL.

[1237] Input: Raw data sent by the robot.

[1238] Output: Operational data stored in a database.

[1239] Step 3: Data preprocessing and cleansing

[1240] Description: The server converts the received data into a parsable format and performs data cleansing, which includes imputing missing values ​​and removing outliers.

[1241] Input: Raw data stored in a database.

[1242] Output: Preprocessed and cleansed data.

[1243] Step 4: Data analysis

[1244] Description: The server analyzes the data using machine learning algorithms (TensorFlow) to evaluate the robot's performance, including calculating the availability rate and evaluating the error rate.

[1245] Input: Preprocessed and cleansed data.

[1246] Output: Robot performance evaluation results.

[1247] Step 5: Identify the issue

[1248] Description: The server extracts identified issues from performance data based on the analysis results. For example, if errors occur frequently within a certain period of time, this is identified as an issue.

[1249] Input: Robot performance evaluation results.

[1250] Output: Identified issues.

[1251] Step 6: Collect and analyze feedback

[1252] Description: The server collects feedback from users (administrators) and reflects it in the analysis results. This is done to improve the accuracy of future analysis of the system.

[1253] Input: Feedback data from users.

[1254] Output: Feedback reflected in the system.

[1255] Step 7: Generate improvement suggestions

[1256] Description: The server generates an optimized improvement proposal based on the identified issues. For example, if the issue of "shortage of parts supply" is identified, it proposes reviewing the inventory management system.

[1257] Input: Identified issue.

[1258] Output: Generated improvement suggestions.

[1259] Step 8: View the proposal

[1260] Description: The server displays the generated improvement suggestions on a dashboard (Tableau) so that the user can understand them intuitively.

[1261] Input: Generated improvement suggestions.

[1262] Output: Improvement suggestions displayed in a dashboard.

[1263] Step 9: Evaluate proposals and provide feedback

[1264] Description: The user (administrator) checks the improvement proposals displayed on the dashboard, evaluates their implementation, and then enters feedback about their effectiveness into the system.

[1265] Input: Improvement suggestions displayed on the dashboard.

[1266] Output: Feedback data.

[1267] Through the above processing steps, the server can achieve specific optimization of production efficiency based on the robot's operation data and provide useful improvement suggestions to the user.

[1268] 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.

[1269] The present invention, "Organizational Management Assist on AI," combines a system that collects and analyzes an organization's business data, identifies issues, and generates and displays optimized improvement proposals with an emotion engine that recognizes the user's emotions. The program processing of this system is explained in detail below.

[1270] Program processing

[1271] Data Collection Phase

[1272] User (Device):

[1273] Users input their daily work data (e.g., task progress, project status, feedback, etc.) into dedicated applications or web portals, and may also input their emotions (e.g., stress, satisfaction, etc.) at the same time.

[1274] Device:

[1275] Business data and emotional data entered by the user are collected in real time and sent to the server.

[1276] Data analysis phase

[1277] server:

[1278] The data sent from the device is received and stored in a database. When storing, the consistency between the business data and the emotion data is checked, and the data is cleansed as necessary.

[1279] server:

[1280] The stored data is converted into an analyzable format, and the emotion engine is used to analyze the user's emotion data.

[1281] server:

[1282] It analyzes operational and emotional data comprehensively and uses machine learning algorithms to evaluate the performance data of the entire organization and each individual, and identifies key issues. For example, if progress on a task is delayed, it analyzes whether the delay is due to emotional factors.

[1283] server:

[1284] Based on the analysis results, the identified issues are generated in the form of a report, including an assessment of different departments and highlighting key bottlenecks.

[1285] Issue visualization phase

[1286] server:

[1287] The generated reports are reflected on a dashboard, allowing users to intuitively understand the information. The results of the analysis of the sentiment data are also displayed on the dashboard.

[1288] User (Device):

[1289] Access the dashboard to see the current state of the organization and any identified challenges. Users can also view their own emotional state.

[1290] Improvement proposal phase

[1291] server:

[1292] It generates optimized improvement proposals for identified issues, such as "providing refreshment time for highly stressed employees" or "assigning highly motivated employees to new projects" based on emotional data.

[1293] server:

[1294] Generated improvement suggestions are displayed in a dashboard in the form of detailed reports.

[1295] User (Device):

[1296] The system checks the proposals and evaluates whether they can be implemented. After implementing the proposals, the system provides feedback on their effectiveness, providing data that will be useful for analyzing the system's future.

[1297] Feedback and self-learning phase

[1298] server:

[1299] It receives feedback and undergoes a self-learning process to incorporate it into its analysis results and improvement suggestions, taking into account sentiment data to improve the accuracy of its next analysis.

[1300] Specific examples

[1301] Data collection:

[1302] User (terminal): Sales department employees enter their daily sales performance data and their own stress levels into the system.

[1303] Server: Receives the data in real time and stores it in a database.

[1304] Data Analysis:

[1305] Server: Analyzes stored sales performance data and stress level data to compare the performance and emotional state of different sales teams.

[1306] Issue visualization:

[1307] Server: Based on the analysis results, the sales performance and stress level of each team are displayed on a dashboard.

[1308] User (device): Check the status of their team on the dashboard and recognize areas that need improvement and the need for stress management.

[1309] Improvement suggestions:

[1310] Server: Based on the analysis, it displays suggestions such as "certain sales teams should adjust their workload" or emotion-based suggestions such as "set rest time for members with high stress levels."

[1311] User (terminal): Implements improvement suggestions and inputs feedback on the results into the system.

[1312] This system not only efficiently optimizes business operations across the organization, but also achieves sustainable performance improvement, including employee emotional management.

[1313] The processing flow will be explained below.

[1314] Step 1:

[1315] User (terminal): The user inputs daily work data (e.g., task progress and project status) and emotional data (e.g., stress level and motivation) into a dedicated application or web portal.

[1316] Step 2:

[1317] Terminal: Collects business data and emotional data entered by the user in real time and sends it to the server.

[1318] Step 3:

[1319] Server: Receives data sent from the device and stores it in a database. When storing the data, it checks its consistency and performs data cleansing (deleting duplicate data and correcting inconsistent data) as necessary.

[1320] Step 4:

[1321] Server: The stored business data and emotion data are converted into an analyzable format. At this stage, the data is normalized and the format is standardized.

[1322] Step 5:

[1323] Server: The converted data is analyzed using machine learning algorithms. Performance data for the entire organization and for each individual is evaluated to identify key issues. For example, if sales performance is declining, the server analyzes whether this is due to emotional factors (e.g., high stress levels).

[1324] Step 6:

[1325] Server: Utilizing the emotion engine, further analyzes the user's emotion data, thereby identifying not only business issues but also emotional issues.

[1326] Step 7:

[1327] Server: Based on the analysis results, the identified issues are generated in the form of a report, which includes evaluations by different departments, key bottlenecks, and analysis results based on sentiment data.

[1328] Step 8:

[1329] Server: The generated reports are reflected in the dashboard, allowing users to intuitively understand the information.

[1330] Step 9:

[1331] User (device): Access the dashboard to check the current state of the organization, identified issues, and the results of the sentiment data analysis.

[1332] Step 10:

[1333] Server: Generates optimized improvement proposals for identified issues, including proposals based on emotional data. For example, it makes specific proposals such as "providing refreshment time for highly stressed users" or "assigning highly motivated users to new projects."

[1334] Step 11:

[1335] Server: Generated improvement suggestions are displayed in the form of detailed reports on the dashboard.

[1336] Step 12:

[1337] User (device): Checks the proposal, evaluates whether it can be implemented, and provides feedback and data on its effectiveness.

[1338] Step 13:

[1339] Server: Receives user feedback and executes a self-learning process to reflect it in analysis results and improvement suggestions. Feedback includes emotional data, which improves the accuracy of the next analysis.

[1340] Example 2

[1341] 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."

[1342] Conventional business data analysis systems only target business data and do not consider employee emotional data, making it difficult to make optimal business improvement proposals. Furthermore, there is no self-learning process that incorporates feedback on analysis results into the system, limiting improvements to analysis accuracy. Therefore, there is a need for the development of an integrated system that simultaneously improves business efficiency and manages employee emotions.

[1343] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1344] In this invention, the server includes: means for collecting business data and emotion data and storing them in a database; means for verifying the consistency of the stored business data and emotion data and performing data cleansing as necessary; means for converting the collected business data and emotion data into an analyzable format; means for analyzing the emotion data using an emotion analysis engine; means for comprehensively analyzing the business data and emotion data, evaluating performance data using a machine learning algorithm, and identifying major issues; means for generating a report based on the identified issues and highlighting evaluations for different departments and major bottlenecks; means for reflecting the generated report on a dashboard and displaying information intuitively to a user; means for generating improvement proposals optimized for the identified issues and making specific proposals based on the emotion data; and means for displaying the generated improvement proposals in a detailed report format on the dashboard. This simultaneously achieves business efficiency and employee emotion management, thereby enabling improved performance across the organization and sustainable business improvement.

[1345] "Business data" refers to various information related to business, such as task progress, project status, and feedback.

[1346] "Emotion data" refers to information that indicates the user's psychological state, such as stress or satisfaction.

[1347] A "database" refers to a system that stores business data and emotional data in a structured format and allows it to be searched and manipulated as needed.

[1348] "Verifying consistency" refers to the process of validating data formats and checking relationships between data to ensure data consistency and accuracy.

[1349] "Data cleansing" refers to the process of correcting data inconsistencies and outliers to improve data quality.

[1350] "Converting to an analyzable format" refers to the process of formatting data into a form suitable for analysis and processing.

[1351] An "emotion analysis engine" refers to software or algorithms that analyze user emotional data and output the results.

[1352] A "machine learning algorithm" refers to a computational method that learns from data and automatically performs specific tasks.

[1353] "Performance data" refers to data used to evaluate the work performance and results of an organization or individual.

[1354] A "report" refers to a document that systematically organizes and visually displays analysis results and evaluation contents.

[1355] A "dashboard" is an interface that aggregates multiple data visualizations and allows users to grasp key indicators and information at a glance.

[1356] "Improvement proposals" refer to specific proposals for achieving more effective work performance and emotional management in response to identified issues.

[1357] The "self-learning process" refers to the process by which the system incorporates new data and feedback to automatically improve the accuracy of its analysis.

[1358] The present invention relates to a system called "Organizational Management Assist on AI," which collects and analyzes business data and emotional data, identifies issues, and makes optimal improvement proposals. Specific embodiments for implementing this system are described below.

[1359] Data Collection Phase

[1360] User (Device):

[1361] Users use a dedicated application or web portal to input daily work data (e.g., task progress, project status, feedback, etc.) as well as emotional data (e.g., stress, satisfaction, etc.), allowing data on work status and employee emotional states to be collected simultaneously.

[1362] Examples of software used: dedicated applications, web portals

[1363] Example: Sales staff use a dedicated application to enter their sales performance and daily stress levels.

[1364] Data collection and transmission

[1365] Device:

[1366] The business data and emotion data entered by the user are sent to the server in real time using API calls to ensure data is collected without delay.

[1367] Examples of hardware and software used: API, network communication

[1368] Example: A sales department employee's device sends data to the server as soon as the data entry is completed.

[1369] Data analysis phase

[1370] server:

[1371] The server checks the integrity of the received data and performs data cleansing if necessary before storing it in a database (e.g., MySQL, PostgreSQL, etc.). The stored data is then converted into an analyzable format. Sentiment data is then analyzed using a sentiment analysis engine (e.g., IBM Watson, Affectiva, etc.).

[1372] Examples of software used: MySQL, PostgreSQL, IBM Watson, Affectiva

[1373] Example: The server receives sales performance data and emotion data, unifies the format, and stores it in a database. The emotion analysis engine analyzes the stress level data.

[1374] Analyzing performance data

[1375] server:

[1376] By integrating and analyzing operational and sentiment data and using machine learning algorithms (e.g., TensorFlow, scikit-learn, etc.) to evaluate performance data, we can accurately assess the performance of the entire organization and individual employees and identify key issues.

[1377] Examples of software used: TensorFlow, scikit-learn

[1378] Example: The server analyzes sales performance data and stress data to determine whether stress is the cause of poor performance.

[1379] Report generation and visualization

[1380] server:

[1381] Based on the analysis results, reports are generated to highlight the performance of different departments and major bottlenecks. The generated reports are reflected in a dashboard, displaying information in an intuitive and easy-to-understand format for users.

[1382] Examples of software used: Tableau, Microsoft Power BI

[1383] Example: Based on the analysis results, the performance of the sales and development departments and their respective issues are compiled into a report and displayed on a dashboard.

[1384] Generate and implement improvement suggestions

[1385] server:

[1386] For identified issues, the system generates optimized improvement proposals that take emotional data into account. The proposals are displayed in a detailed report format on a dashboard, allowing users to review the proposals and evaluate whether or not they should be implemented. After implementing the proposals, users can enter feedback about their effectiveness into the system, which accumulates feedback data.

[1387] Example: Based on the analysis results, suggestions such as "A specific sales team should adjust their workload" or "Set rest time for employees with high stress levels" are displayed. The user implements these suggestions and provides feedback on the results.

[1388] Self-Learning Process

[1389] server:

[1390] A self-learning process is performed to incorporate received feedback into analysis results and improvement suggestions, thereby improving the accuracy of the next analysis and continuously improving system performance.

[1391] Examples of software used: machine learning models, feedback analysis algorithms

[1392] Example: Feedback data is used as new learning data to retrain a performance evaluation model.

[1393] Example prompts for generative AI models

[1394] Please display the analysis results of this month's sales department performance and each employee's stress level.

[1395] Compare the progress of Project X with the satisfaction of your team members.

[1396] Display the best improvement suggestions for highly stressed employees.

[1397] In this way, the present invention provides an innovative system that effectively integrates and analyzes business data and emotional data, simultaneously optimizing business operations and managing employee emotions.

[1398] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1399] Step 1:

[1400] Entering data

[1401] Users use a dedicated application or web portal to input daily work data (e.g., task progress, project status, feedback, etc.) and emotional data (e.g., stress, satisfaction, etc.).

[1402] Input: Business data and emotion data

[1403] Specific operation: Through the application UI, the user selects the progress of the task from a drop-down menu and sets the stress level using a slider. After entering the data, the data is registered by pressing the submit button.

[1404] Step 2:

[1405] Sending data

[1406] The terminal transmits the business data and emotion data input by the user to the server in real time.

[1407] Input: Data entered by the user

[1408] Output: Data sent to the server

[1409] Specific operation: The device uses an API call to send input data to the server, and during this process checks the HTTP response to ensure the data was sent correctly.

[1410] Step 3:

[1411] Receiving and storing data

[1412] The server receives the data sent from the terminal, first checks its integrity, and then stores the data in the database.

[1413] Input: Data sent from the terminal

[1414] Output: Data stored in the database

[1415] Specific operation: The server validates the format and content of the received data, for example, rejecting incomplete records and mismatched data. After the validation, the data is inserted into a database such as MySQL or PostgreSQL.

[1416] Step 4:

[1417] Data cleansing and transformation

[1418] The server cleanses the stored data and converts it into an analyzable format.

[1419] Input: Saved data

[1420] Output: Data in a parsable format

[1421] Specific operations: The server performs operations to improve data quality, such as imputing missing values, correcting outliers, and standardizing data formats. For example, it converts all date and time data to a unified format (YYYY-MM-DD).

[1422] Step 5:

[1423] Emotional Data Analysis

[1424] The server uses an emotion analysis engine (e.g., IBM Watson, Affectiva, etc.) to analyze the user's emotion data.

[1425] Input: Cleansed emotion data

[1426] Output: Parsed emotion data

[1427] Specific operation: The server sends the emotion data to the analysis engine's API and stores the returned analysis results in a database. For example, it receives analysis results such as "high stress level" or "low satisfaction level."

[1428] Step 6:

[1429] Comprehensive Data Analysis

[1430] The server comprehensively analyzes business data and sentiment data, evaluates performance data using machine learning algorithms (e.g., TensorFlow, scikit-learn, etc.), and identifies key issues.

[1431] Input: Data in a parsable format, parsed emotion data

[1432] Output: Performance evaluation results, identified issues

[1433] Specific operation: The server inputs data into a machine learning model to evaluate, for example, whether delays in task progress are due to emotional factors. The model's output is stored in a database.

[1434] Step 7:

[1435] Generate reports

[1436] The server generates reports based on the analysis results, highlighting the performance of different departments and highlighting key bottlenecks.

[1437] Input: Performance evaluation results, identified issues

[1438] Output: Generated report

[1439] Specific operation: The report generation system dynamically inserts analysis results based on templates to create visually easy-to-understand reports, which are then saved in PDF or web format.

[1440] Step 8:

[1441] Reflected on the dashboard

[1442] The server reflects the generated report on the dashboard and displays the information so that the user can intuitively understand it.

[1443] Input: Generated report

[1444] Output: The data displayed on the dashboard

[1445] Specific operation: The server uses a data visualization tool (e.g., Tableau, Microsoft Power BI, etc.) to visualize the report contents as graphs and charts and display them on a dashboard.

[1446] Step 9:

[1447] Accessing the Dashboard

[1448] Users can access a dashboard to view the current state of their organization, identify identified challenges, and even view their own emotional state.

[1449] Input: User login information

[1450] Output: The displayed dashboard

[1451] How it works: Users can log in to the dashboard using a dedicated application or a web browser to view various data. For example, they can use the filter function to view data for a specific time range.

[1452] Step 10:

[1453] Generate improvement suggestions

[1454] The server generates improvement proposals optimized for the identified issues and makes specific proposals based on emotion data.

[1455] Input: Identified issues, emotion data

[1456] Output: Improvement suggestions

[1457] Specific operation: Based on the analysis results, the server generates suggestions such as "providing refreshment time for employees with high stress levels" and "assigning highly motivated employees to new projects," and compiles them in report format.

[1458] Step 11:

[1459] Viewing improvement suggestions

[1460] The server displays the generated improvement suggestions in the form of a detailed report on a dashboard.

[1461] Input: Improvement suggestion

[1462] Output: Improvement suggestions displayed in a dashboard

[1463] Specific behavior: Improvement suggestions will be displayed on the dashboard in a visually easy-to-understand format with explanatory text and graphs. Also, a notification function will be implemented to allow users to check the suggestions.

[1464] Step 12:

[1465] Evaluation and feedback of proposals

[1466] The user checks the proposals, evaluates whether they are feasible to implement, and after implementing the proposals, inputs feedback on their effectiveness.

[1467] Input: Suggestion rating, feedback

[1468] Output: Feedback data

[1469] Specific operation: After checking the proposal on the dashboard, the user clicks the button to rate it, enters the effects in the feedback form, and submits it.

[1470] Step 13:

[1471] Receiving Feedback

[1472] The server receives the feedback from the user and stores it in a database.

[1473] Input: Feedback data

[1474] Output: Saved feedback data

[1475] What it does: Validates the feedback data and stores it in the database, appropriately labeling it as a new data point.

[1476] Step 14:

[1477] Implementing a self-learning process

[1478] The server uses the feedback data to perform a self-learning process to improve the analysis results and suggestions for improvement, thereby improving the accuracy of the next analysis.

[1479] Input: Saved feedback data

[1480] Output: Updated analytical model

[1481] Specific operation: The server retrains the machine learning model based on the feedback data and adds new data to the training dataset, thereby improving the accuracy of the analytical model.

[1482] Through the above processing steps, the present invention effectively integrates and analyzes business data and emotion data, thereby simultaneously optimizing business operations and managing employee emotions.

[1483] (Application example 2)

[1484] 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."

[1485] Simultaneously managing employees' work efficiency and emotional state is a major challenge for many companies. Conventional systems typically handle work data and emotional data separately, making it difficult to effectively generate optimal improvement proposals. Furthermore, an inability to properly grasp employees' emotional states can lead to ineffective work style improvements, resulting in lower productivity and employee satisfaction.

[1486] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting business data and saving it in a database, means for analyzing the saved data and identifying issues, means for analyzing user emotion data, means for comprehensively analyzing the business data and emotion data and generating optimized improvement proposals, and means for displaying the generated improvement proposals to the user. As a result, by comprehensively analyzing the business data and emotion data and making optimal improvement proposals, it is possible to simultaneously improve employee productivity and manage emotions.

[1487] "Business Data" means information related to an employee's or organization's business, including task progress and project status.

[1488] A "database" is a system for efficiently storing and managing collected data.

[1489] "Challenges" refer to problems or bottlenecks that hinder the work performance of an organization or individual.

[1490] "Emotion data" is information about the user's emotional state, and includes psychological factors such as stress and satisfaction.

[1491] "Analysis" is the process of analyzing collected data and extracting meaningful information and trends.

[1492] An "improvement proposal" is a specific proposal or action plan aimed at resolving an identified issue.

[1493] "User" refers to an individual or member of an organization who uses this system.

[1494] "Storage" means recording the collected data in a database for later use.

[1495] "Comprehensive" means treating different types of data as a whole and conducting a comprehensive analysis.

[1496] A "system" is a collection of components that have multiple functions and work together to operate.

[1497] A specific system for implementing this invention consists of several main components and steps. First, the user's device collects daily work data and emotional data. This is done using various sensors in the factory and employee feedback devices (tablets, PCs, etc.). The collected data is then sent to a server and stored in a database.

[1498] A program is installed on the server to convert the data into an analyzable format. At this stage, data cleansing is performed to remove inconsistencies and missing data. Next, an algorithm is run to comprehensively analyze the business data and emotion data. Specifically, Python's Pandas and machine learning models (e.g., RandomForestRegressor) are used for the analysis. A virtual emotion engine library (EmotionEngine) is also used to analyze the emotion data.

[1499] Once the analysis is complete, the server generates optimized improvement proposals based on the identified issues. These proposals may include, for example, "providing additional break time for specific employees" or "adjusting the workload of employees with high stress levels." The generated improvement proposals are displayed to the user in a dashboard format, allowing the user to review them and implement them as necessary.

[1500] Feedback on the execution results is also collected through the same system to inform future analysis, allowing the self-learning algorithm to improve the system's analysis accuracy.

[1501] To give a specific example, employees in the sales department enter their daily task progress and stress levels into the system. The collected data is sent to a server and stored in a database. The server analyzes the data and compares sales performance with stress levels. The analysis results are displayed on a dashboard, and suggestions for improvement, such as "applying additional break time," are made to specific employees.

[1502] An example prompt is:

[1503] "Collect factory sensor and employee feedback data, analyze productivity and emotional state, and generate optimal improvement proposals for identified issues."

[1504] This system simultaneously improves employee productivity and manages emotions by integrating and analyzing business data and emotional data.

[1505] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1506] Step 1:

[1507] Users (terminals) collect daily work data and emotional data. Specifically, various sensors in the factory input task progress status, and employees input emotional data (such as stress level and satisfaction) using their feedback terminals (tablets, PCs, etc.). The input data is sent to the server in real time. An example of input data is "2023-10-01, Task A, in progress, stress level: high."

[1508] Step 2:

[1509] The server stores the business data and emotion data sent from the device in a database. Specifically, data processing involves converting the received data into a predefined format and performing data cleansing. Inconsistencies and missing data are removed. If the input is "Stress level: high," it is validated within a safe range and stored in the database.

[1510] Step 3:

[1511] The server converts the stored data into an analyzable format. Specifically, it uses Python's Pandas library to change the data into a table format. For example, it converts the data into a format where each row represents data for one employee. During this process, it removes unnecessary data and extracts only the necessary fields. An unformatted data frame is given as input, and a formatted data frame is generated as output.

[1512] Step 4:

[1513] The server runs machine learning algorithms to analyze the formatted data. Specifically, it uses models such as RandomForestRegressor to comprehensively analyze business data and emotional data. It also uses an emotional analysis engine such as EmotionEngine. This analysis predicts employee productivity and emotional state. The identified data frame is used as input, and a new data frame containing the predicted results is generated as output.

[1514] Step 5:

[1515] The server generates identified issues and optimized improvement proposals based on the analysis results. Specific actions include "recommending additional break time for employees with high stress levels." The analysis result data frame is used as input, and the output is a list of improvement proposals.

[1516] Step 6:

[1517] The server displays the generated improvement suggestions on the user's dashboard. Specifically, the suggestions are displayed as graphs and text reports that are updated in real time on the web application dashboard. The input is the list of improvement suggestions, and the output is the visualized dashboard.

[1518] Step 7:

[1519] The user (device) checks the displayed improvement suggestions and inputs feedback as necessary. A specific example is feedback such as "As a result of applying additional break time, the stress level decreased." Feedback text is used as input, and the output is sent to the server as feedback data.

[1520] Step 8:

[1521] The server analyzes the collected feedback and performs a self-learning process to improve the accuracy of the next analysis and recommendation. Specifically, it uses the feedback data to retrain the machine learning model. The feedback data is used as input, and the output is an updated machine learning model.

[1522] In this way, a system is constructed that comprehensively analyzes business data and emotional data, and generates and displays optimal improvement proposals.

[1523] 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.

[1524] 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.

[1525] 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.

[1526] [Fourth embodiment]

[1527] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1528] 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.

[1529] 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).

[1530] 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.

[1531] 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.

[1532] 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).

[1533] 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.

[1534] 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.

[1535] 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.

[1536] 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.

[1537] 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.

[1538] 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.

[1539] 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."

[1540] The present invention, "Organization Management Assist on AI," is a system that collects and analyzes an organization's business data, identifies issues, and generates and displays optimized improvement proposals. The program processing of this system is explained in detail below.

[1541] Program processing

[1542] Data Collection Phase

[1543] User (Device):

[1544] Users enter their daily work data (e.g., task progress, project status, feedback, etc.) into dedicated applications and web portals.

[1545] server:

[1546] Business data sent from the terminal is received in real time and stored safely and efficiently in a database.

[1547] Data analysis phase

[1548] server:

[1549] The data is pre-processed and cleansed into an analyzable format, then machine learning algorithms are used to analyze performance data across the organization and identify key issues. The analysis also includes natural language processing to perform a detailed analysis of the feedback provided by users.

[1550] server:

[1551] By comparing it with past data and learning from new data, the AI ​​model parameters are updated using a self-learning function, improving the accuracy of the next analysis.

[1552] Issue visualization phase

[1553] server:

[1554] Once the analysis results are available, the overall performance of the organization and the identified challenges are visualized in the form of a dashboard, which includes an assessment of different departments and highlights the major bottlenecks.

[1555] User (Device):

[1556] Access the dashboard to see the current status of your organization and any identified challenges in real time.

[1557] Improvement proposal phase

[1558] server:

[1559] Generates optimized improvement proposals for identified issues. For example, if the issue of "lack of communication" is identified, suggestions will be made such as setting up regular meetings or introducing a dedicated chat tool.

[1560] server:

[1561] The generated improvement suggestions are displayed in a detailed report format on a dashboard, allowing users to intuitively understand them.

[1562] User (Device):

[1563] The system reviews the proposals and evaluates whether they can be implemented. After implementing the proposals, the system provides feedback on their effectiveness, providing data that will be useful for analyzing the system's future.

[1564] Specific examples

[1565] Data collection:

[1566] User (terminal): Sales department employees input daily sales performance data into the system.

[1567] Server: Receives the data in real time and stores it in a database.

[1568] Data Analysis:

[1569] Server: Analyzes stored sales performance data using machine learning algorithms and natural language processing to compare the performance of different sales teams.

[1570] Issue visualization:

[1571] Server: Based on the analysis results, a dashboard displays the performance of different sales teams and key issues.

[1572] Users (devices): Check the status of their team on the dashboard and recognize areas that need improvement.

[1573] Improvement suggestions:

[1574] Server: Based on the analysis results, specific improvement suggestions such as "certain sales teams should increase weekly meetings" are displayed.

[1575] User (terminal): Implements improvement suggestions and inputs feedback on the results into the system.

[1576] This system will enable efficient optimization of business operations across the organization, leading to sustained performance improvements.

[1577] The processing flow will be explained below.

[1578] Step 1:

[1579] User (device): Enters daily work data, such as task progress, project status, and feedback, into dedicated applications and web portals.

[1580] Step 2:

[1581] Terminal: Collects business data entered by the user in real time and sends it to the server.

[1582] Step 3:

[1583] Server: Receives data sent from the device and stores it in a database. When storing the data, it checks the consistency of the data and performs data cleansing (deleting duplicate data and correcting inconsistent data) as necessary.

[1584] Step 4:

[1585] Server: Transforms the stored data into an analyzable format, which includes normalizing the data and standardizing the format.

[1586] Step 5:

[1587] Server: Based on the cleansed data, it uses machine learning algorithms to analyze it. Specifically, it analyzes performance data for the entire organization and for each individual to identify key issues. For example, if progress on a task is slow, it analyzes all relevant data points to identify the cause.

[1588] Step 6:

[1589] Server: Based on the analysis results, the identified issues are generated in the form of a report, which includes an assessment of different departments and highlights the main bottlenecks.

[1590] Step 7:

[1591] Server: The generated reports are reflected in the dashboard, allowing users to intuitively understand the information.

[1592] Step 8:

[1593] Users (devices): Access the dashboard to check the current status of the organization and any identified issues.

[1594] Step 9:

[1595] Server: Generates optimized improvement proposals for identified issues. For example, if a lack of communication is identified, the server will make specific proposals such as scheduling regular meetings or introducing a dedicated chat tool.

[1596] Step 10:

[1597] Server: Generated improvement suggestions are displayed in the form of detailed reports on the dashboard.

[1598] Step 11:

[1599] User (device): Checks the proposal and evaluates whether it can be implemented. Also, inputs feedback to help with the next analysis.

[1600] Step 12:

[1601] Server: Receives feedback from users and executes a self-learning process to reflect it in analysis results and improvement suggestions. This improves the accuracy of the next analysis and makes it possible to provide more effective improvement suggestions.

[1602] Example 1

[1603] 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."

[1604] Conventional organizational management systems only collect and analyze business data, making it difficult to extract useful information from large amounts of data and make specific improvement proposals. Furthermore, there is no mechanism for effectively incorporating user feedback, making it difficult for the system to self-improve.

[1605] 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.

[1606] In this invention, the server includes means for collecting business data and storing it in a database, means for preprocessing and cleansing the stored data, means for analyzing the data using a machine learning algorithm and identifying issues, means for visualizing the issues in a dashboard format based on the analysis results, means for generating improvement proposals optimized for the identified issues, and means for displaying the generated improvement proposals to a user, thereby enabling performance improvement and optimization of the entire organization.

[1607] "Business Data" refers to information related to daily business activities, such as task progress, project status, and feedback.

[1608] "Database" refers to an information system that securely stores collected business data and makes it easy to access and manage.

[1609] "Preprocessing" refers to tasks such as filling in missing values, normalizing data, and cleansing data in order to convert raw data into an analyzable format.

[1610] "Cleansing" refers to the process of removing unnecessary data and correcting incorrect data in order to improve data quality.

[1611] A "machine learning algorithm" refers to a calculation method that learns data patterns based on past data and makes predictions and classifications for future data.

[1612] A "dashboard" is a tool that visually displays the results of data analysis, allowing users to intuitively understand an organization's performance and identified issues.

[1613] "Improvement proposals" refer to optimized solutions or measures for issues identified based on the results of data analysis.

[1614] "Feedback from users" refers to information such as opinions, impressions, and areas for improvement after users use the system provided.

[1615] "Self-learning function" refers to the function that learns from new data and improves the accuracy of the model.

[1616] An "AI model" refers to a computational model built to solve a specific problem based on patterns and rules learned from data using machine learning algorithms.

[1617] The present invention, "Organization Management Assist on AI," is a system that collects and analyzes business data of an organization, identifies issues, and generates and displays optimized improvement proposals. This system is configured as follows.

[1618] Data Collection Phase

[1619] Users enter their daily work data (e.g., task progress, project status, feedback) into dedicated applications or web portals that are designed to provide a user-friendly interface and make data entry easy.

[1620] The terminal sends the business data entered by the user to the server in real time. The communication is encrypted to ensure the security of the data.

[1621] The server receives the business data sent from the terminal and stores it safely and efficiently in a database. A database management system such as MySQL can be used.

[1622] Data analysis phase

[1623] The server preprocesses and cleanses the received data into an analyzable format using Pandas, a Python data analysis library.

[1624] The server then uses machine learning algorithms to analyze the data and identify issues, such as the Python scikit-learn library, and the natural language processing library NLTK to further analyze the feedback provided by users.

[1625] Furthermore, the server uses a self-learning function to update the parameters of the AI ​​model to improve the accuracy of the next analysis. For example, TensorFlow can be used to train the AI ​​model.

[1626] Issue visualization phase

[1627] The server then uses the analysis results to visualize the overall performance of the organization and any identified issues in the form of a dashboard, which can be created using, for example, Tableau or Power BI, and includes an assessment of different departments and highlights key bottlenecks.

[1628] Users can access the dashboard to check the current status of the organization and identified issues in real time. The user interface is intuitive and designed to allow users to easily grasp the information.

[1629] Improvement proposal phase

[1630] The server generates improvement proposals optimized for the identified issues. For example, if a "lack of communication" issue is identified, it will recommend setting up regular meetings or introducing a dedicated chat tool (e.g., Slack).

[1631] The server displays the generated improvement proposals in the form of a detailed report on the dashboard, including the background of the proposals and specific implementation methods, and uses graphs and charts to make the proposals intuitively understandable to the user.

[1632] The user reviews the proposals and evaluates whether they are feasible to implement. After implementing the proposals, the user enters feedback into the system about their effectiveness. For example, the user may report on the usability and effectiveness of a newly introduced tool as part of an improvement proposal.

[1633] Prompt Sentence Examples

[1634] "Analyze sales department data, identify team performance issues and make suggestions for improvement."

[1635] This allows the system to optimize and continuously improve the performance of the entire organization.

[1636] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1637] Step 1: Data entry

[1638] Users use a dedicated application or web portal to enter their daily work data, including task progress, project status, feedback, etc. Once the data is complete, it is sent to the system.

[1639] Input: Business data such as task progress, project status, and feedback

[1640] Output: Business data sent to the server in real time

[1641] Step 2: Send data

[1642] The terminal encrypts the business data entered by the user and transmits it to the server in real time using a secure protocol.

[1643] Input: Business data entered by the user

[1644] Output: Encrypted and securely transmitted business data

[1645] Step 3: Save Data

[1646] The server receives business data sent from the terminal and stores it safely and efficiently in a database, while checking to see if the data is missing.

[1647] Input: Encrypted business data

[1648] Output: Complete business data stored in a database

[1649] Step 4: Data Preprocessing

[1650] The server performs pre-processing to convert the stored business data into an analyzable format, including imputing missing values, normalizing the data, and cleansing it.

[1651] Input: Business data stored in a database

[1652] Output: Cleansed and normalized parsable data

[1653] Step 5: Data analysis

[1654] The server then uses machine learning algorithms (e.g., scikit-learn) to analyze the preprocessed data, which includes assessing the organization's overall performance and identifying key issues.

[1655] Input: Preprocessed business data

[1656] Output: Key issues identified and performance analysis results

[1657] Step 6: Natural Language Processing

[1658] The server uses natural language processing (e.g., NLTK) to perform detailed analysis of the feedback provided by the user, and integrates insights gained from the feedback into the analysis results.

[1659] Input: User feedback

[1660] Output: Feedback insights integrated into analysis results

[1661] Step 7: Self-study

[1662] The server compares the data with past data and learns from new data, updating the parameters of the AI ​​model using TensorFlow.

[1663] Input: All analysis results

[1664] Output: Updated AI model parameters

[1665] Step 8: Visualize the issue

[1666] Based on the analysis results, the server visualizes the organization's overall performance and identified issues in dashboard format (e.g., Tableau).

[1667] Input: All analysis results

[1668] Output: Analysis results and specific tasks displayed on a dashboard

[1669] Step 9: View the Dashboard

[1670] Users access the dashboard to see the current state of their organization and identified issues in real time.

[1671] Input: Analysis results and specific issues displayed on the dashboard

[1672] Output: User recognition of issues and understanding of the current state of the organization

[1673] Step 10: Generate improvement suggestions

[1674] The server generates optimized improvement proposals for the identified issues. For example, if a "lack of communication" issue is identified, it will recommend setting up regular meetings and introducing a dedicated chat tool.

[1675] Input: Identified Issues

[1676] Output: Improvement suggestions

[1677] Step 11: Displaying improvement suggestions

[1678] The server displays the generated improvement suggestions in the form of a detailed report on a dashboard.

[1679] Input: Improvement suggestion

[1680] Output: Detailed improvement suggestions displayed in a dashboard

[1681] Step 12: Evaluate and provide feedback on the proposal

[1682] The user checks the proposals, evaluates whether they are feasible to implement, and after implementing the proposals, inputs feedback about their effectiveness into the system.

[1683] Input: Improvement suggestions, feedback after implementation

[1684] Output: Feedback data entered into the system

[1685] This allows the system to use user feedback to improve the accuracy of its next analysis and improvement suggestions.

[1686] (Application example 1)

[1687] 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."

[1688] Conventional organizational management systems were able to identify issues and generate improvement proposals by collecting and analyzing business data, but it was difficult to monitor the operating status and work efficiency of robots at production sites in real time and optimize identified issues.In addition, there was no system that could make specific optimization proposals for production efficiency based on robot operating data, making it impossible to instantly improve productivity.

[1689] 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.

[1690] In this invention, the server includes means for collecting business data and storing it in a database, means for analyzing the stored data and identifying issues, means for generating improvement proposals optimized for the identified issues, means for displaying the generated improvement proposals to a user, and means for collecting operation data from a robot and optimizing production efficiency based on the analysis results, thereby enabling specific optimization of production efficiency based on the robot operation data.

[1691] "Business data" refers to information about various business operations conducted by an organization, including task progress, project status, feedback, and the like.

[1692] "Database" means a structured data storage system for efficiently and securely storing and managing collected business data.

[1693] "Analysis" refers to the process of preprocessing the collected data, converting it into an analyzable format using machine learning algorithms and natural language processing, and extracting information that will be useful in the actual operation of the organization.

[1694] "Issues" are bottlenecks in organizational management and problems requiring improvement that are identified from the analyzed data.

[1695] An "improvement proposal" is a specific action plan that proposes an optimized solution or new approach to an identified issue.

[1696] "User" refers to a member or administrator of an organization who uses the system to input business data and check the analysis results and improvement suggestions.

[1697] "Feedback" refers to information including opinions and evaluations provided by users, and is data used to improve the accuracy of the system's analysis results and improvement suggestions.

[1698] A "robot" is a machine that operates in a factory and automatically performs tasks such as assembling and processing products.

[1699] "Operational data" refers to information about the robot's performance, such as its operating status, work efficiency, and error rate.

[1700] "Production efficiency" refers to the efficiency and production volume of work at production sites such as factories, and is an indicator evaluated based on factors such as the operating status of robots and work accuracy.

[1701] A "server" is a computer system that receives business data and robot operation data sent by users, and analyzes, stores, and displays them.

[1702] This invention, "Organizational Management Assist on AI," collects operational data and work efficiency data from robots used in factories in real time, detects specific issues, and generates and displays improvement proposals. The configuration of this system is described below.

[1703] Hardware and software used

[1704] 1. Robot (terminal): An automatic machine that operates in a factory and performs tasks such as assembling and processing products.

[1705] 2. Administrator's terminal: A device for viewing the dashboard and reviewing improvement suggestions on a PC or tablet.

[1706] 3. Server: A computer system that manages all processes of receiving, storing, analyzing, and displaying data. Specifically, it uses the following software:

[1707] Database: MySQL

[1708] Machine learning algorithm: TensorFlow

[1709] Dashboard display tool: Tableau

[1710] Natural language processing libraries required for specific evaluations and analyses

[1711] Program processing explanation

[1712] 1. Data Collection Phase

[1713] The robot (terminal) collects operational data (e.g., operating time, number of errors) and sends it to the server via a dedicated application.

[1714] The server receives the data sent from the robot in real time and stores it securely in a database.

[1715] 2. Data analysis phase

[1716] The server cleanses and pre-processes the received data into a parsable format.

[1717] The data is analyzed using a machine learning algorithm (TensorFlow) to evaluate the robot's performance.

[1718] Using natural language processing, feedback from users is also included in the analysis.

[1719] 3. Issue Visualization Phase

[1720] Based on the analysis results, the server displays the robot's operating status and issues on a dashboard (Tableau).

[1721] The administrator (terminal) accesses the dashboard to check the current status of the robot and any identified issues in real time.

[1722] 4. Improvement proposal phase

[1723] The server generates an optimized improvement proposal for the identified issue. For example, if a "parts supply shortage" is identified, it will propose reviewing the inventory management system and introducing an automatic replenishment system.

[1724] The administrator (terminal) checks the generated improvement proposals, evaluates their implementation, and then inputs feedback about their effectiveness into the system.

[1725] Specific examples

[1726] If Robot A sends data showing that its average operating time has decreased by 5% over the course of a week, the server will use this data to identify a shortage of parts supply and suggest that the inventory management system be revised.

[1727] Prompt Sentence Examples

[1728] Examples of prompts for generative AI models include:

[1729] "Analyze the performance of Robot A this week, identify key issues, and generate improvement suggestions."

[1730] This system makes it possible to specifically optimize production efficiency based on operational data from robots within the factory, thereby improving productivity.

[1731] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1732] Step 1: Data collection

[1733] Description: The robot (terminal) collects operational data from within the factory and sends it to a server via a dedicated application. Specifically, this data includes operating hours, number of errors, production volume, etc.

[1734] Input: Operational data obtained from the robot's sensors and internal systems.

[1735] Output: The raw data sent to the server.

[1736] Step 2: Receiving and storing data

[1737] Description: The server receives the data sent from the robot in real time and stores it securely in a database, specifically in a database system such as MySQL.

[1738] Input: Raw data sent by the robot.

[1739] Output: Operational data stored in a database.

[1740] Step 3: Data preprocessing and cleansing

[1741] Description: The server converts the received data into a parsable format and performs data cleansing, which includes imputing missing values ​​and removing outliers.

[1742] Input: Raw data stored in a database.

[1743] Output: Preprocessed and cleansed data.

[1744] Step 4: Data analysis

[1745] Description: The server analyzes the data using machine learning algorithms (TensorFlow) to evaluate the robot's performance, including calculating the availability rate and evaluating the error rate.

[1746] Input: Preprocessed and cleansed data.

[1747] Output: Robot performance evaluation results.

[1748] Step 5: Identify the issue

[1749] Description: The server extracts identified issues from performance data based on the analysis results. For example, if errors occur frequently within a certain period of time, this is identified as an issue.

[1750] Input: Robot performance evaluation results.

[1751] Output: Identified issues.

[1752] Step 6: Collect and analyze feedback

[1753] Description: The server collects feedback from users (administrators) and reflects it in the analysis results. This is done to improve the accuracy of future analysis of the system.

[1754] Input: Feedback data from users.

[1755] Output: Feedback reflected in the system.

[1756] Step 7: Generate improvement suggestions

[1757] Description: The server generates an optimized improvement proposal based on the identified issues. For example, if the issue of "shortage of parts supply" is identified, it proposes reviewing the inventory management system.

[1758] Input: Identified issue.

[1759] Output: Generated improvement suggestions.

[1760] Step 8: View the proposal

[1761] Description: The server displays the generated improvement suggestions on a dashboard (Tableau) so that the user can understand them intuitively.

[1762] Input: Generated improvement suggestions.

[1763] Output: Improvement suggestions displayed in a dashboard.

[1764] Step 9: Evaluate proposals and provide feedback

[1765] Description: The user (administrator) checks the improvement proposals displayed on the dashboard, evaluates their implementation, and then enters feedback about their effectiveness into the system.

[1766] Input: Improvement suggestions displayed on the dashboard.

[1767] Output: Feedback data.

[1768] Through the above processing steps, the server can achieve specific optimization of production efficiency based on the robot's operation data and provide useful improvement suggestions to the user.

[1769] 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.

[1770] The present invention, "Organizational Management Assist on AI," combines a system that collects and analyzes an organization's business data, identifies issues, and generates and displays optimized improvement proposals with an emotion engine that recognizes the user's emotions. The program processing of this system is explained in detail below.

[1771] Program processing

[1772] Data Collection Phase

[1773] User (Device):

[1774] Users input their daily work data (e.g., task progress, project status, feedback, etc.) into dedicated applications or web portals, and may also input their emotions (e.g., stress, satisfaction, etc.) at the same time.

[1775] Device:

[1776] Business data and emotional data entered by the user are collected in real time and sent to the server.

[1777] Data analysis phase

[1778] server:

[1779] The data sent from the device is received and stored in a database. When storing, the consistency between the business data and the emotion data is checked, and the data is cleansed as necessary.

[1780] server:

[1781] The stored data is converted into an analyzable format, and the emotion engine is used to analyze the user's emotion data.

[1782] server:

[1783] It analyzes operational and emotional data comprehensively and uses machine learning algorithms to evaluate the performance data of the entire organization and each individual, and identifies key issues. For example, if progress on a task is delayed, it analyzes whether the delay is due to emotional factors.

[1784] server:

[1785] Based on the analysis results, the identified issues are generated in the form of a report, including an assessment of different departments and highlighting key bottlenecks.

[1786] Issue visualization phase

[1787] server:

[1788] The generated reports are reflected on a dashboard, allowing users to intuitively understand the information. The results of the analysis of the sentiment data are also displayed on the dashboard.

[1789] User (Device):

[1790] Access the dashboard to see the current state of the organization and any identified challenges. Users can also view their own emotional state.

[1791] Improvement proposal phase

[1792] server:

[1793] It generates optimized improvement proposals for identified issues, such as "providing refreshment time for highly stressed employees" or "assigning highly motivated employees to new projects" based on emotional data.

[1794] server:

[1795] Generated improvement suggestions are displayed in a dashboard in the form of detailed reports.

[1796] User (Device):

[1797] The system checks the proposals and evaluates whether they can be implemented. After implementing the proposals, the system provides feedback on their effectiveness, providing data that will be useful for analyzing the system's future.

[1798] Feedback and self-learning phase

[1799] server:

[1800] It receives feedback and undergoes a self-learning process to incorporate it into its analysis results and improvement suggestions, taking into account sentiment data to improve the accuracy of its next analysis.

[1801] Specific examples

[1802] Data collection:

[1803] User (terminal): Sales department employees enter their daily sales performance data and their own stress levels into the system.

[1804] Server: Receives the data in real time and stores it in a database.

[1805] Data Analysis:

[1806] Server: Analyzes stored sales performance data and stress level data to compare the performance and emotional state of different sales teams.

[1807] Issue visualization:

[1808] Server: Based on the analysis results, the sales performance and stress level of each team are displayed on a dashboard.

[1809] User (device): Check the status of their team on the dashboard and recognize areas that need improvement and the need for stress management.

[1810] Improvement suggestions:

[1811] Server: Based on the analysis, it displays suggestions such as "certain sales teams should adjust their workload" or emotion-based suggestions such as "set rest time for members with high stress levels."

[1812] User (terminal): Implements improvement suggestions and inputs feedback on the results into the system.

[1813] This system not only efficiently optimizes business operations across the organization, but also achieves sustainable performance improvement, including employee emotional management.

[1814] The processing flow will be explained below.

[1815] Step 1:

[1816] User (terminal): The user inputs daily work data (e.g., task progress and project status) and emotional data (e.g., stress level and motivation) into a dedicated application or web portal.

[1817] Step 2:

[1818] Terminal: Collects business data and emotional data entered by the user in real time and sends it to the server.

[1819] Step 3:

[1820] Server: Receives data sent from the device and stores it in a database. When storing the data, it checks its consistency and performs data cleansing (deleting duplicate data and correcting inconsistent data) as necessary.

[1821] Step 4:

[1822] Server: The stored business data and emotion data are converted into an analyzable format. At this stage, the data is normalized and the format is standardized.

[1823] Step 5:

[1824] Server: The converted data is analyzed using machine learning algorithms. Performance data for the entire organization and for each individual is evaluated to identify key issues. For example, if sales performance is declining, the server analyzes whether this is due to emotional factors (e.g., high stress levels).

[1825] Step 6:

[1826] Server: Utilizing the emotion engine, further analyzes the user's emotion data, thereby identifying not only business issues but also emotional issues.

[1827] Step 7:

[1828] Server: Based on the analysis results, the identified issues are generated in the form of a report, which includes evaluations by different departments, key bottlenecks, and analysis results based on sentiment data.

[1829] Step 8:

[1830] Server: The generated reports are reflected in the dashboard, allowing users to intuitively understand the information.

[1831] Step 9:

[1832] User (device): Access the dashboard to check the current state of the organization, identified issues, and the results of the sentiment data analysis.

[1833] Step 10:

[1834] Server: Generates optimized improvement proposals for identified issues, including proposals based on emotional data. For example, it makes specific proposals such as "providing refreshment time for highly stressed users" or "assigning highly motivated users to new projects."

[1835] Step 11:

[1836] Server: Generated improvement suggestions are displayed in the form of detailed reports on the dashboard.

[1837] Step 12:

[1838] User (device): Checks the proposal, evaluates whether it can be implemented, and provides feedback and data on its effectiveness.

[1839] Step 13:

[1840] Server: Receives user feedback and executes a self-learning process to reflect it in analysis results and improvement suggestions. Feedback includes emotional data, which improves the accuracy of the next analysis.

[1841] Example 2

[1842] 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."

[1843] Conventional business data analysis systems only target business data and do not consider employee emotional data, making it difficult to make optimal business improvement proposals. Furthermore, there is no self-learning process that incorporates feedback on analysis results into the system, limiting improvements to analysis accuracy. Therefore, there is a need for the development of an integrated system that simultaneously improves business efficiency and manages employee emotions.

[1844] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1845] In this invention, the server includes: means for collecting business data and emotion data and storing them in a database; means for verifying the consistency of the stored business data and emotion data and performing data cleansing as necessary; means for converting the collected business data and emotion data into an analyzable format; means for analyzing the emotion data using an emotion analysis engine; means for comprehensively analyzing the business data and emotion data, evaluating performance data using a machine learning algorithm, and identifying major issues; means for generating a report based on the identified issues and highlighting evaluations for different departments and major bottlenecks; means for reflecting the generated report on a dashboard and displaying information intuitively to a user; means for generating improvement proposals optimized for the identified issues and making specific proposals based on the emotion data; and means for displaying the generated improvement proposals in a detailed report format on the dashboard. This simultaneously achieves business efficiency and employee emotion management, thereby enabling improved performance across the organization and sustainable business improvement.

[1846] "Business data" refers to various information related to business, such as task progress, project status, and feedback.

[1847] "Emotion data" refers to information that indicates the user's psychological state, such as stress or satisfaction.

[1848] A "database" refers to a system that stores business data and emotional data in a structured format and allows it to be searched and manipulated as needed.

[1849] "Verifying consistency" refers to the process of validating data formats and checking relationships between data to ensure data consistency and accuracy.

[1850] "Data cleansing" refers to the process of correcting data inconsistencies and outliers to improve data quality.

[1851] "Converting to an analyzable format" refers to the process of formatting data into a form suitable for analysis and processing.

[1852] An "emotion analysis engine" refers to software or algorithms that analyze user emotional data and output the results.

[1853] A "machine learning algorithm" refers to a computational method that learns from data and automatically performs specific tasks.

[1854] "Performance data" refers to data used to evaluate the work performance and results of an organization or individual.

[1855] A "report" refers to a document that systematically organizes and visually displays analysis results and evaluation contents.

[1856] A "dashboard" is an interface that aggregates multiple data visualizations and allows users to grasp key indicators and information at a glance.

[1857] "Improvement proposals" refer to specific proposals for achieving more effective work performance and emotional management in response to identified issues.

[1858] The "self-learning process" refers to the process by which the system incorporates new data and feedback to automatically improve the accuracy of its analysis.

[1859] The present invention relates to a system called "Organizational Management Assist on AI," which collects and analyzes business data and emotional data, identifies issues, and makes optimal improvement proposals. Specific embodiments for implementing this system are described below.

[1860] Data Collection Phase

[1861] User (Device):

[1862] Users use a dedicated application or web portal to input daily work data (e.g., task progress, project status, feedback, etc.) as well as emotional data (e.g., stress, satisfaction, etc.), allowing data on work status and employee emotional states to be collected simultaneously.

[1863] Examples of software used: dedicated applications, web portals

[1864] Example: Sales staff use a dedicated application to enter their sales performance and daily stress levels.

[1865] Data collection and transmission

[1866] Device:

[1867] The business data and emotion data entered by the user are sent to the server in real time using API calls to ensure data is collected without delay.

[1868] Examples of hardware and software used: API, network communication

[1869] Example: A sales department employee's device sends data to the server as soon as the data entry is completed.

[1870] Data analysis phase

[1871] server:

[1872] The server checks the integrity of the received data and performs data cleansing if necessary before storing it in a database (e.g., MySQL, PostgreSQL, etc.). The stored data is then converted into an analyzable format. Sentiment data is then analyzed using a sentiment analysis engine (e.g., IBM Watson, Affectiva, etc.).

[1873] Examples of software used: MySQL, PostgreSQL, IBM Watson, Affectiva

[1874] Example: The server receives sales performance data and emotion data, unifies the format, and stores it in a database. The emotion analysis engine analyzes the stress level data.

[1875] Analyzing performance data

[1876] server:

[1877] By integrating and analyzing operational and sentiment data and using machine learning algorithms (e.g., TensorFlow, scikit-learn, etc.) to evaluate performance data, we can accurately assess the performance of the entire organization and individual employees and identify key issues.

[1878] Examples of software used: TensorFlow, scikit-learn

[1879] Example: The server analyzes sales performance data and stress data to determine whether stress is the cause of poor performance.

[1880] Report generation and visualization

[1881] server:

[1882] Based on the analysis results, reports are generated to highlight the performance of different departments and major bottlenecks. The generated reports are reflected in a dashboard, displaying information in an intuitive and easy-to-understand format for users.

[1883] Examples of software used: Tableau, Microsoft Power BI

[1884] Example: Based on the analysis results, the performance of the sales and development departments and their respective issues are compiled into a report and displayed on a dashboard.

[1885] Generate and implement improvement suggestions

[1886] server:

[1887] For identified issues, the system generates optimized improvement proposals that take emotional data into account. The proposals are displayed in a detailed report format on a dashboard, allowing users to review the proposals and evaluate whether or not they should be implemented. After implementing the proposals, users can enter feedback about their effectiveness into the system, which accumulates feedback data.

[1888] Example: Based on the analysis results, suggestions such as "A specific sales team should adjust their workload" or "Set rest time for employees with high stress levels" are displayed. The user implements these suggestions and provides feedback on the results.

[1889] Self-Learning Process

[1890] server:

[1891] A self-learning process is performed to incorporate received feedback into analysis results and improvement suggestions, thereby improving the accuracy of the next analysis and continuously improving system performance.

[1892] Examples of software used: machine learning models, feedback analysis algorithms

[1893] Example: Feedback data is used as new learning data to retrain a performance evaluation model.

[1894] Example prompts for generative AI models

[1895] Please display the analysis results of this month's sales department performance and each employee's stress level.

[1896] Compare the progress of Project X with the satisfaction of your team members.

[1897] Display the best improvement suggestions for highly stressed employees.

[1898] In this way, the present invention provides an innovative system that effectively integrates and analyzes business data and emotional data, simultaneously optimizing business operations and managing employee emotions.

[1899] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1900] Step 1:

[1901] Entering data

[1902] Users use a dedicated application or web portal to input daily work data (e.g., task progress, project status, feedback, etc.) and emotional data (e.g., stress, satisfaction, etc.).

[1903] Input: Business data and emotion data

[1904] Specific operation: Through the application UI, the user selects the progress of the task from a drop-down menu and sets the stress level using a slider. After entering the data, the data is registered by pressing the submit button.

[1905] Step 2:

[1906] Sending data

[1907] The terminal transmits the business data and emotion data input by the user to the server in real time.

[1908] Input: Data entered by the user

[1909] Output: Data sent to the server

[1910] Specific operation: The device uses an API call to send input data to the server, and during this process checks the HTTP response to ensure the data was sent correctly.

[1911] Step 3:

[1912] Receiving and storing data

[1913] The server receives the data sent from the terminal, first checks its integrity, and then stores the data in the database.

[1914] Input: Data sent from the terminal

[1915] Output: Data stored in the database

[1916] Specific operation: The server validates the format and content of the received data, for example, rejecting incomplete records and mismatched data. After the validation, the data is inserted into a database such as MySQL or PostgreSQL.

[1917] Step 4:

[1918] Data cleansing and transformation

[1919] The server cleanses the stored data and converts it into an analyzable format.

[1920] Input: Saved data

[1921] Output: Data in a parsable format

[1922] Specific operations: The server performs operations to improve data quality, such as imputing missing values, correcting outliers, and standardizing data formats. For example, it converts all date and time data to a unified format (YYYY-MM-DD).

[1923] Step 5:

[1924] Emotional Data Analysis

[1925] The server uses an emotion analysis engine (e.g., IBM Watson, Affectiva, etc.) to analyze the user's emotion data.

[1926] Input: Cleansed emotion data

[1927] Output: Parsed emotion data

[1928] Specific operation: The server sends the emotion data to the analysis engine's API and stores the returned analysis results in a database. For example, it receives analysis results such as "high stress level" or "low satisfaction level."

[1929] Step 6:

[1930] Comprehensive Data Analysis

[1931] The server comprehensively analyzes business data and sentiment data, evaluates performance data using machine learning algorithms (e.g., TensorFlow, scikit-learn, etc.), and identifies key issues.

[1932] Input: Data in a parsable format, parsed emotion data

[1933] Output: Performance evaluation results, identified issues

[1934] Specific operation: The server inputs data into a machine learning model to evaluate, for example, whether delays in task progress are due to emotional factors. The model's output is stored in a database.

[1935] Step 7:

[1936] Generate reports

[1937] The server generates reports based on the analysis results, highlighting the performance of different departments and highlighting key bottlenecks.

[1938] Input: Performance evaluation results, identified issues

[1939] Output: Generated report

[1940] Specific operation: The report generation system dynamically inserts analysis results based on templates to create visually easy-to-understand reports, which are then saved in PDF or web format.

[1941] Step 8:

[1942] Reflected on the dashboard

[1943] The server reflects the generated report on the dashboard and displays the information so that the user can intuitively understand it.

[1944] Input: Generated report

[1945] Output: The data displayed on the dashboard

[1946] Specific operation: The server uses a data visualization tool (e.g., Tableau, Microsoft Power BI, etc.) to visualize the report contents as graphs and charts and display them on a dashboard.

[1947] Step 9:

[1948] Accessing the Dashboard

[1949] Users can access a dashboard to view the current state of their organization, identify identified challenges, and even view their own emotional state.

[1950] Input: User login information

[1951] Output: The displayed dashboard

[1952] How it works: Users can log in to the dashboard using a dedicated application or a web browser to view various data. For example, they can use the filter function to view data for a specific time range.

[1953] Step 10:

[1954] Generate improvement suggestions

[1955] The server generates improvement proposals optimized for the identified issues and makes specific proposals based on emotion data.

[1956] Input: Identified issues, emotion data

[1957] Output: Improvement suggestions

[1958] Specific operation: Based on the analysis results, the server generates suggestions such as "providing refreshment time for employees with high stress levels" and "assigning highly motivated employees to new projects," and compiles them in report format.

[1959] Step 11:

[1960] Viewing improvement suggestions

[1961] The server displays the generated improvement suggestions in the form of a detailed report on a dashboard.

[1962] Input: Improvement suggestion

[1963] Output: Improvement suggestions displayed in a dashboard

[1964] Specific behavior: Improvement suggestions will be displayed on the dashboard in a visually easy-to-understand format with explanatory text and graphs. Also, a notification function will be implemented to allow users to check the suggestions.

[1965] Step 12:

[1966] Evaluation and feedback of proposals

[1967] The user checks the proposals, evaluates whether they are feasible to implement, and after implementing the proposals, inputs feedback on their effectiveness.

[1968] Input: Suggestion rating, feedback

[1969] Output: Feedback data

[1970] Specific operation: After checking the proposal on the dashboard, the user clicks the button to rate it, enters the effects in the feedback form, and submits it.

[1971] Step 13:

[1972] Receiving Feedback

[1973] The server receives the feedback from the user and stores it in a database.

[1974] Input: Feedback data

[1975] Output: Saved feedback data

[1976] What it does: Validates the feedback data and stores it in the database, appropriately labeling it as a new data point.

[1977] Step 14:

[1978] Implementing a self-learning process

[1979] The server uses the feedback data to perform a self-learning process to improve the analysis results and suggestions for improvement, thereby improving the accuracy of the next analysis.

[1980] Input: Saved feedback data

[1981] Output: Updated analytical model

[1982] Specific operation: The server retrains the machine learning model based on the feedback data and adds new data to the training dataset, thereby improving the accuracy of the analytical model.

[1983] Through the above processing steps, the present invention effectively integrates and analyzes business data and emotion data, thereby simultaneously optimizing business operations and managing employee emotions.

[1984] (Application example 2)

[1985] 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."

[1986] Simultaneously managing employees' work efficiency and emotional state is a major challenge for many companies. Conventional systems typically handle work data and emotional data separately, making it difficult to effectively generate optimal improvement proposals. Furthermore, an inability to properly grasp employees' emotional states can lead to ineffective work style improvements, resulting in lower productivity and employee satisfaction.

[1987] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting business data and saving it in a database, means for analyzing the saved data and identifying issues, means for analyzing user emotion data, means for comprehensively analyzing the business data and emotion data and generating optimized improvement proposals, and means for displaying the generated improvement proposals to the user. As a result, by comprehensively analyzing the business data and emotion data and making optimal improvement proposals, it is possible to simultaneously improve employee productivity and manage emotions.

[1988] "Business Data" means information related to an employee's or organization's business, including task progress and project status.

[1989] A "database" is a system for efficiently storing and managing collected data.

[1990] "Challenges" refer to problems or bottlenecks that hinder the work performance of an organization or individual.

[1991] "Emotion data" is information about the user's emotional state, and includes psychological factors such as stress and satisfaction.

[1992] "Analysis" is the process of analyzing collected data and extracting meaningful information and trends.

[1993] An "improvement proposal" is a specific proposal or action plan aimed at resolving an identified issue.

[1994] "User" refers to an individual or member of an organization who uses this system.

[1995] "Storage" means recording the collected data in a database for later use.

[1996] "Comprehensive" means treating different types of data as a whole and conducting a comprehensive analysis.

[1997] A "system" is a collection of components that have multiple functions and work together to operate.

[1998] A specific system for implementing this invention consists of several main components and steps. First, the user's device collects daily work data and emotional data. This is done using various sensors in the factory and employee feedback devices (tablets, PCs, etc.). The collected data is then sent to a server and stored in a database.

[1999] A program is installed on the server to convert the data into an analyzable format. At this stage, data cleansing is performed to remove inconsistencies and missing data. Next, an algorithm is run to comprehensively analyze the business data and emotion data. Specifically, Python's Pandas and machine learning models (e.g., RandomForestRegressor) are used for the analysis. A virtual emotion engine library (EmotionEngine) is also used to analyze the emotion data.

[2000] Once the analysis is complete, the server generates optimized improvement proposals based on the identified issues. These proposals may include, for example, "providing additional break time for specific employees" or "adjusting the workload of employees with high stress levels." The generated improvement proposals are displayed to the user in a dashboard format, allowing the user to review them and implement them as necessary.

[2001] Feedback on the execution results is also collected through the same system to inform future analysis, allowing the self-learning algorithm to improve the system's analysis accuracy.

[2002] To give a specific example, employees in the sales department enter their daily task progress and stress levels into the system. The collected data is sent to a server and stored in a database. The server analyzes the data and compares sales performance with stress levels. The analysis results are displayed on a dashboard, and suggestions for improvement, such as "applying additional break time," are made to specific employees.

[2003] An example prompt is:

[2004] "Collect factory sensor and employee feedback data, analyze productivity and emotional state, and generate optimal improvement proposals for identified issues."

[2005] This system simultaneously improves employee productivity and manages emotions by integrating and analyzing business data and emotional data.

[2006] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2007] Step 1:

[2008] Users (terminals) collect daily work data and emotional data. Specifically, various sensors in the factory input task progress status, and employees input emotional data (such as stress level and satisfaction) using their feedback terminals (tablets, PCs, etc.). The input data is sent to the server in real time. An example of input data is "2023-10-01, Task A, in progress, stress level: high."

[2009] Step 2:

[2010] The server stores the business data and emotion data sent from the device in a database. Specifically, data processing involves converting the received data into a predefined format and performing data cleansing. Inconsistencies and missing data are removed. If the input is "Stress level: high," it is validated within a safe range and stored in the database.

[2011] Step 3:

[2012] The server converts the stored data into an analyzable format. Specifically, it uses Python's Pandas library to change the data into a table format. For example, it converts the data into a format where each row represents data for one employee. During this process, it removes unnecessary data and extracts only the necessary fields. An unformatted data frame is given as input, and a formatted data frame is generated as output.

[2013] Step 4:

[2014] The server runs machine learning algorithms to analyze the formatted data. Specifically, it uses models such as RandomForestRegressor to comprehensively analyze business data and emotional data. It also uses an emotional analysis engine such as EmotionEngine. This analysis predicts employee productivity and emotional state. The identified data frame is used as input, and a new data frame containing the predicted results is generated as output.

[2015] Step 5:

[2016] The server generates identified issues and optimized improvement proposals based on the analysis results. Specific actions include "recommending additional break time for employees with high stress levels." The analysis result data frame is used as input, and the output is a list of improvement proposals.

[2017] Step 6:

[2018] The server displays the generated improvement suggestions on the user's dashboard. Specifically, the suggestions are displayed as graphs and text reports that are updated in real time on the web application dashboard. The input is the list of improvement suggestions, and the output is the visualized dashboard.

[2019] Step 7:

[2020] The user (device) checks the displayed improvement suggestions and inputs feedback as necessary. A specific example is feedback such as "As a result of applying additional break time, the stress level decreased." Feedback text is used as input, and the output is sent to the server as feedback data.

[2021] Step 8:

[2022] The server analyzes the collected feedback and performs a self-learning process to improve the accuracy of the next analysis and recommendation. Specifically, it uses the feedback data to retrain the machine learning model. The feedback data is used as input, and the output is an updated machine learning model.

[2023] In this way, a system is constructed that comprehensively analyzes business data and emotional data, and generates and displays optimal improvement proposals.

[2024] 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.

[2025] 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.

[2026] 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.

[2027] 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.

[2028] 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.

[2029] 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.

[2030] 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).

[2031] 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.

[2032] 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."

[2033] 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.

[2034] 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).

[2035] 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.

[2036] 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.

[2037] 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.

[2038] 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.

[2039] 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.

[2040] 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.

[2041] 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.

[2042] 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.

[2043] 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.

[2044] 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.

[2045] The following is further disclosed regarding the above embodiment.

[2046] (Claim 1)

[2047] A means for collecting business data and storing it in a database;

[2048] A means of analyzing the stored data and identifying issues;

[2049] A means for generating an improvement proposal optimized for the identified problem;

[2050] means for displaying the generated improvement suggestions to a user;

[2051] A system including:

[2052] (Claim 2)

[2053] 10. The system according to claim 1, further comprising means for collecting feedback from users and reflecting the feedback in the analysis results.

[2054] (Claim 3)

[2055] 10. The system of claim 1, further comprising means for converting the collected data into an analyzable format.

[2056] "Example 1"

[2057] (Claim 1)

[2058] A means for collecting business data and storing it in a database;

[2059] a means for pre-processing and cleansing the stored data;

[2060] A means of analyzing data and identifying issues using machine learning algorithms;

[2061] Based on the analysis results, a means to visualize issues in a dashboard format,

[2062] A means for generating an improvement proposal optimized for the identified problem;

[2063] means for displaying the generated improvement suggestions to a user;

[2064] A system including:

[2065] (Claim 2)

[2066] 10. The system according to claim 1, further comprising means for collecting feedback from users and reflecting the feedback in the analysis results.

[2067] (Claim 3)

[2068] 10. The system of claim 1, further comprising means for updating parameters of the AI ​​model using a self-learning function.

[2069] "Application Example 1"

[2070] (Claim 1)

[2071] A means for collecting business data and storing it in a database;

[2072] A means of analyzing the stored data and identifying issues;

[2073] A means for generating an improvement proposal optimized for the identified problem;

[2074] means for displaying the generated improvement suggestions to a user;

[2075] A means of collecting operational data from robots and optimizing production efficiency based on the analysis results.

[2076] A system including:

[2077] (Claim 2)

[2078] 10. The system according to claim 1, further comprising means for collecting feedback from users and reflecting the feedback in the analysis results.

[2079] (Claim 3)

[2080] 10. The system of claim 1, further comprising means for converting the collected data into an analyzable format.

[2081] "Example 2: Combining Emotion Engines"

[2082] (Claim 1)

[2083] A means for collecting business data and emotion data and storing them in a database;

[2084] A means to check the consistency of stored business data and emotion data, and to cleanse the data as necessary;

[2085] A means for converting the collected business data and emotion data into an analyzable format; and

[2086] a means for analyzing the emotion data using an emotion analysis engine;

[2087] A means to comprehensively analyze business data and sentiment data, evaluate performance data using machine learning algorithms, and identify key issues;

[2088] Generate reports based on identified issues, assess different departments and highlight key bottlenecks;

[2089] A means to reflect the generated report on a dashboard and display information intuitively to the user;

[2090] A means for generating an improvement proposal optimized for the identified problem and making a specific proposal based on the emotion data;

[2091] A means to display the generated improvement suggestions in a detailed report format on a dashboard;

[2092] A system including:

[2093] (Claim 2)

[2094] 10. The system of claim 1, further comprising means for performing a self-learning process to collect user feedback and incorporate it into the analysis results and improvement suggestions.

[2095] (Claim 3)

[2096] 10. The system of claim 1, further comprising means for converting the stored data into an analyzable format.

[2097] "Application example 2 when combining emotion engines"

[2098] (Claim 1)

[2099] A means for collecting business data and storing it in a database;

[2100] A means of analyzing the stored data and identifying issues;

[2101] means for analyzing user emotion data;

[2102] A means of comprehensively analyzing business data and emotional data to generate optimized improvement proposals;

[2103] means for displaying the generated improvement suggestions to a user;

[2104] A system including:

[2105] (Claim 2)

[2106] 10. The system according to claim 1, further comprising means for collecting feedback from users and reflecting the feedback in the analysis results.

[2107] (Claim 3)

[2108] 10. The system of claim 1, further comprising means for converting the collected data into an analyzable format. [Explanation of symbols]

[2109] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for collecting business data and storing it in a database; A means of analyzing the stored data and identifying issues; A means for generating an improvement proposal optimized for the identified problem; means for displaying the generated improvement suggestions to a user; A system including:

2. The system according to claim 1 , further comprising means for collecting feedback from users and reflecting the feedback in the analysis results.

3. 10. The system of claim 1, further comprising means for converting the collected data into an analyzable format.

Images