system

Abstract

A system is provided.SOLUTION: The system includes a means for automatically collecting the management data of a company, a means for analyzing the management data to calculate a main KPI, a means for generating a management diagnosis report based on the analysis result, a means for analyzing past data and market trends to generate a proposal for future management decision, a means for monitoring the operation status of the company in real time and detecting abnormality, and a means for database-forming the skill and experience of human resources of candidate managers and proposing a training plan.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] The lack of successors that many companies face has a significant impact on management continuity and the survival of the company. This problem is particularly pronounced in small and medium-sized enterprises in rural areas, where the inability to find a suitable successor can lead to stagnation in management decisions, poor performance, and even the risk of the company going bankrupt. To solve this problem, a system is needed to train and support successors and effectively support corporate management decisions. [Means for solving the problem]

[0005] This invention provides a system that automatically collects a company's management data and calculates key KPIs. This system generates a management diagnosis report based on the analysis results, and further analyzes past data and market trends to generate proposals to support future management decisions. It also includes a function to monitor the company's operating status in real time, detect abnormalities, and notify them. Furthermore, by creating a database of the skills and experience of management candidates and proposing appropriate training plans, this system comprehensively solves the issue of a lack of successors.

[0006] "Company management data" refers to data related to the operation of a company, such as sales, inventory, finances, and employee attendance status.

[0007] "Means of collection" refers to technologies such as APIs and sensors that periodically obtain data from a specific data source.

[0008] "Means of analysis" refers to the software algorithms and machine learning models used to analyze collected data and extract useful information from it.

[0009] A "key KPI" is a key performance indicator used to evaluate a company's performance or efficiency.

[0010] A "management diagnosis report" refers to a written or electronic report that shows a company's current situation and future predictions based on analyzed data.

[0011] "Market trends" refers to information that indicates current movements, changes, and trends in the market.

[0012] "Means for generating proposals" refers to technology for proposing specific actions and decisions for future management based on analysis results and market trends.

[0013] "Real-time monitoring measures" refers to systems and technologies that continuously monitor and assess the current state of a company's operations.

[0014] "Anomaly detection methods" refers to algorithms or systems that identify data or events that deviate from normal conditions and generate alerts.

[0015] "Means for creating a database of human resources' skills and experience" refers to technology for collecting, integrating, and storing information such as the skills, experience, and evaluation history of employees or candidates.

[0016] "Means for proposing development plans" refers to systems and algorithms for designing and proposing education and training programs to supplement the necessary skills and experience based on databased human resource information. [Brief explanation of the drawings]

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

[0018] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

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

[0021] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0022] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0023] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0025] [First embodiment]

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

[0027] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0028] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0030] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0034] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0035] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

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

[0038] The present invention is a system that automatically collects and analyzes business data of a company, proposes appropriate business decisions, and also supports the development of successors. Specific embodiments of the present invention will be described below.

[0039] Data collection

[0040] The server periodically collects data from various data sources within the company (ERP system, CRM system, financial system, etc.) For example, it uses APIs to retrieve sales data, inventory data, employee attendance data, and financial data. This data is then stored in a cloud database.

[0041] Data analysis and KPI calculation

[0042] The server analyzes the collected data using machine learning algorithms to calculate important KPIs, such as sales forecasts, cost analysis, inventory turnover, and employee efficiency. This process can be performed by combining multiple analytical models to improve prediction accuracy.

[0043] Generate a management diagnostic report

[0044] Based on the analysis results, the server automatically generates a management diagnosis report, which includes an analysis of the company's current situation, risk predictions, and information on growth opportunities. The report is presented in easy-to-understand graphs and charts using visualization tools.

[0045] Proposal of business decisions

[0046] The server analyzes past data and market trends to generate recommendations for future business decisions, such as optimizing inventory management, changing hiring strategies, and introducing new products to the market. These recommendations are generated using a reinforcement learning algorithm, taking into account past patterns of success and failure.

[0047] Via the terminal, the user can review these proposals and accept or modify them, in which case a recalculation is performed and a new proposal is generated.

[0048] Real-time monitoring and anomaly detection

[0049] The server monitors the company's operations in real time, using data streams to monitor sales, inventory levels, employee attendance, and more, and has the ability to immediately notify users if an abnormality is detected, allowing them to take prompt action.

[0050] Successor development support

[0051] The server creates a database of the skills and experience of potential managers and uses generative AI to propose an appropriate development plan. This may include specific skill training, setting role models, and conducting management simulations. Based on this development plan, users can provide specific training and training to the target employees.

[0052] Specific examples

[0053] For example, suppose a manufacturing company implements a system as follows:

[0054] The server automatically collects sales data, inventory data, and employee attendance data from the ERP system every morning and stores it in a cloud database.

[0055] The server then analyzes this data and calculates KPIs such as sales forecasts and inventory turnover.

[0056] After the monthly settlement, the server generates a management diagnosis report and notifies the user via the terminal, detailing the company's financial health, potential for new market entry, and so on.

[0057] Based on market trends and analysis results, the server will propose product order optimization and new product promotion strategies for the next quarter, and users can review, agree to, or modify these proposals in real time.

[0058] Daily operational status is monitored in real time, and if an abnormality is detected, for example, if inventory suddenly decreases, an alert notification is sent to the user immediately.

[0059] Finally, the server proposes an appropriate development plan for potential future managers, and the user carries out training and education based on that plan.

[0060] This will enable companies to solve the problem of a lack of successors and achieve sustainable management.

[0061] The processing flow will be explained below.

[0062] Step 1:

[0063] The server periodically collects data from various corporate data sources (ERP system, CRM system, financial system), for example using APIs to retrieve sales data, inventory data, employee attendance data, and financial data.

[0064] Step 2:

[0065] The server stores the collected data in a cloud database, where it processes the data and converts it into an appropriate format before storing it in the database.

[0066] Step 3:

[0067] The server feeds data stored in a cloud database into machine learning algorithms to calculate important KPIs, such as sales forecasts, cost analysis, inventory turnover, and employee efficiency.

[0068] Step 4:

[0069] The server generates a management diagnosis report based on the analysis results, converts the KPIs and analysis results into text using natural language generation technology, and creates graphs and charts using visualization tools.

[0070] Step 5:

[0071] The server uploads the generated management diagnosis report to the dashboard and notifies the user, for example, by email or via a mobile app.

[0072] Step 6:

[0073] The server analyzes past data and market trends to generate proposals for future management decisions. It uses a reinforcement learning algorithm to learn past success and failure patterns and generate optimal proposals taking market trends into account.

[0074] Step 7:

[0075] The device displays the generated proposals to the user, who can then view the proposals in the form of a dashboard or report.

[0076] Step 8:

[0077] The user can review the proposed content, agree to it, or make corrections, and can request a recalculation by entering corrections.

[0078] Step 9:

[0079] The server monitors the company's operations in real time, using data streams to monitor sales, inventory levels, employee attendance, and more.

[0080] Step 10:

[0081] The server uses anomaly detection algorithms to detect and alert you to unusual data or trends that deviate from expectations, and sends you a warning via email or SMS.

[0082] Step 11:

[0083] Users can check the alert and decide on appropriate countermeasures, such as immediately placing additional orders or adjusting employee shifts, taking into account the nature of the anomaly.

[0084] Step 12:

[0085] The server creates a database of the skills and experience of potential managers, collecting, integrating, and storing skill sets, career history, and evaluation data from the company's internal personnel database.

[0086] Step 13:

[0087] Based on the databased information, the server uses generative AI to propose appropriate development plans, such as specific skill training, setting up role models, and conducting business simulations.

[0088] Step 14:

[0089] The user reviews and implements the proposed training plan, arranges training programs and workshops based on the proposal, and implements them for the management candidates.

[0090] Example 1

[0091] 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."

[0092] Corporate management requires the efficient collection of data from each department, the calculation of key management indicators, and support for management decisions. However, modern companies must handle complex systems and vast amounts of data, and performing these processes manually is labor-intensive and carries a high risk of error. Important issues remain, such as real-time monitoring, anomaly detection, and the development of management candidates. To address these issues, a consistent automation system and high-precision analysis technology are required.

[0093] 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.

[0094] In this invention, the server includes means for automatically collecting corporate management data, means for analyzing the management data using a machine learning algorithm and calculating key KPIs, means for generating a management diagnosis report using a visualization tool based on the analysis results, means for analyzing past data and market trends and generating proposals for future management decisions using a reinforcement learning algorithm, means for monitoring the corporate operating status in real time using data stream technology and detecting anomalies, and means for using a generative AI model to create a database of the skills and experience of management candidate personnel and propose a training plan. This enables efficient collection and analysis of corporate data, timely and accurate support for management decisions, and automatic proposals for training plans for management candidate personnel.

[0095] "Corporate management data" is a general term for information such as financial data, sales data, inventory data, and employee attendance data that is collected and managed by a company on a daily basis.

[0096] "Automatic collection means" refers to software and hardware components that allow the system to obtain data from various data sources without manual intervention.

[0097] A "machine learning algorithm" is an algorithm that uses technology to have a computer analyze massive amounts of data, recognize patterns and trends in the data, and learn from them.

[0098] "KPI" is an abbreviation for Key Performance Indicator, and refers to a company's key performance indicators, including sales forecasts, cost analysis, inventory turnover, and employee efficiency.

[0099] A "visualization tool" is a tool that displays data in a visual format, such as a graph or chart, making it easier to understand and analyze.

[0100] A "reinforcement learning algorithm" is a machine learning method that uses trial and error to find optimal behavior. It analyzes past data and market trends and automatically improves future behavior.

[0101] "Data stream technology" refers to technology for continuously collecting data in real time and processing it immediately. Apache Kafka is a representative example.

[0102] "Anomaly detection means" refers to software and hardware components that monitor real-time data and detect unexpected events or abnormal values.

[0103] A "generative AI model" is an AI model that uses natural language processing and machine learning techniques and is used to automatically generate new proposals and reports from data.

[0104] "Development plan" means a specific education and training plan to improve the skills and experience of potential management personnel.

[0105] The present invention is a system that automatically collects and analyzes business data of a company, proposes appropriate business decisions, and also supports the development of successors. Specific embodiments of the present invention will be described below.

[0106] Data collection

[0107] The server periodically collects data from various data sources within the company (ERP system, CRM system, financial system, etc.). For example, it uses APIs to obtain sales data, inventory data, employee attendance data, and financial data. This data is stored in a cloud database such as Amazon RDS or Google® Cloud Spanner. Specifically, the server calls functions such as "get_sales_data()" and "get_inventory_data()" and stores the results in the database using the "store_in_database()" function.

[0108] Data analysis and KPI calculation

[0109] The server analyzes the collected data using machine learning algorithms (e.g., TENSORFLOW (registered trademark) or Scikit-learn) to calculate important KPIs. For analysis, the data is preprocessed using the "preprocess_data()" function, and then KPIs are calculated using the "calculate_kpis()" function. Specific KPIs include sales forecasts, cost analysis, inventory turnover, and employee efficiency. This makes it possible to accurately grasp the current situation of the company.

[0110] Generate a management diagnostic report

[0111] Based on the analysis results, the server automatically generates a management diagnosis report. This report includes information on the company's current situation, risk predictions, and growth opportunities, and is presented in graphs and charts using a visualization tool (e.g., Tableau or Power BI). Specifically, the report is generated by the "generate_report()" function, and then notified to the user via the terminal by the "send_report_to_user()" function.

[0112] Proposal of business decisions

[0113] The server analyzes historical data and market trends and generates suggestions for future business decisions using reinforcement learning algorithms (e.g., Deep Q-Learning). These suggestions may include optimizing inventory management, changing recruitment strategies, or launching new products into the market. Suggestions are created using the "generate_suggestions()" function and displayed on the terminal via the "display_suggestions()" function. Users can review and modify the suggestions using the "approve_suggestion()" or "modify_suggestion()" functions.

[0114] Real-time monitoring and anomaly detection

[0115] The server uses data stream technologies such as Apache Kafka to monitor the company's operational status in real time. The server monitors sales, inventory levels, employee attendance, etc., and detects anomalies using the "detect_anomalies()" function. When an anomaly is detected, the user is immediately notified via the "send_alert()" function, allowing the user to take prompt action.

[0116] Successor development support

[0117] The server uses a generative AI model (e.g., GPT-4 (registered trademark)) to create a database of the skills and experience of potential management candidates, and evaluates them using the "analyze_candidate()" function. It then proposes an appropriate development plan using the "generate_development_plan()" function, and sends the plan to the user using the "send_training_plan()" function. This development plan includes specific skill training, role model selection, and management simulations.

[0118] Specific examples

[0119] For example, at a manufacturing company, the server uses the ERP system's API to collect sales data, inventory data, and employee attendance data every morning and stores it in Amazon RDS. The collected data is then analyzed using TensorFlow, preprocessed using the "preprocess_data()" function, and KPIs are calculated using the "calculate_kpis()" function. After monthly settlement, a report is generated using the "generate_report()" function and notified to the user via a terminal using the "send_report_to_user()" function. Furthermore, based on the results of analyzing past data and market trends, the "generate_suggestions()" function makes suggestions for the next quarter. The user can then review and modify the suggestions using the "approve_suggestion()" or "modify_suggestion()" functions. Daily operational status is monitored in real time using the "monitor_operations()" function, and if an anomaly is detected using the "detect_anomalies()" function, the user is immediately notified using the "send_alert()" function. Finally, the skills of potential future managers are evaluated using the "analyze_candidate()" function, a training plan is created using the "generate_development_plan()" function, and the plan is notified to the user using the "send_training_plan()" function.

[0120] Examples of prompts include "Propose a market entry strategy for a new product" or "Generate inventory management optimization recommendations for the next quarter."

[0121] This will enable companies to automate efficient data collection, secure storage, highly accurate analysis, rapid business decision-making, and successor training, all of which will enable them to achieve sustainable management.

[0122] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0123] Step 1: Data collection

[0124] The server collects data from various data sources within the company. Specifically, it uses APIs to retrieve sales data, inventory data, employee attendance data, financial data, etc. from ERP systems, CRM systems, and financial systems. To do this, the server uses authentication information to make API calls and uses functions such as "get_sales_data()" and "get_inventory_data()." The input is the API endpoint of each data source, and the output is the retrieved data, which is then stored in a cloud database (e.g., Amazon RDS or Google Cloud Spanner) using the "store_in_database()" function.

[0125] Step 2: Data Preprocessing

[0126] The server preprocesses the collected data. Specifically, it cleans the data, handles missing values, and standardizes it using the "preprocess_data()" function. The input is the raw data stored in the cloud database, and the output is data formatted in an analyzable format. This creates a dataset suitable for subsequent analysis.

[0127] Step 3: Calculate KPIs

[0128] The server uses the preprocessed data to calculate key KPIs. It uses the "calculate_kpis()" function to apply machine learning algorithms (e.g., TensorFlow, Scikit-learn) to calculate KPIs such as sales forecasts, cost analysis, inventory turnover, and employee efficiency. The input is the preprocessed data, and the output is the numerical values ​​of various KPIs. This provides a concrete representation of the company's important indicators.

[0129] Step 4: Generate a business diagnostic report

[0130] The server creates a management diagnosis report based on the calculated KPIs. It uses the "generate_report()" function and then uses a visualization tool (e.g., Tableau, Power BI) to display the results in graphs and charts. The input is the calculated KPIs and analysis results, and the output is a visualized management diagnosis report. This report is sent to the terminal via the "send_report_to_user()" function and notified to the user.

[0131] Step 5: Propose business decisions

[0132] The server analyzes past data and market trends and uses a reinforcement learning algorithm (e.g., Deep Q-Learning) to generate suggestions for management decisions. Specific suggestions such as optimizing inventory management, changing recruitment strategies, and launching new products into the market are created using the 'generate_suggestions()' function. The input is market trend data and analysis results, and the output is a specific proposal. The user can review the suggestions on their device using the 'display_suggestions()' function, and approve or modify the suggestions using the 'approve_suggestion()' or 'modify_suggestion()' functions.

[0133] Step 6: Real-time monitoring and anomaly detection

[0134] The server uses data streaming technologies such as Apache Kafka to monitor the company's operational status in real time. It monitors data using the 'monitor_operations()' function and detects anomalies using the 'detect_anomalies()' function. The input is real-time operational data, and the output is the detected anomalous data. If an anomaly is found, the user is immediately notified using the 'send_alert()' function.

[0135] Step 7: Support for developing successors

[0136] The server uses a generative AI model (e.g., GPT-4) to create a database of the skills and experience of potential management candidates and proposes a development plan. It evaluates the skills of the candidates using the "analyze_candidate()" function and creates a development plan using the "generate_development_plan()" function. The input is the candidate's skill data and experience data, and the output is a specific development plan. This plan is sent to the user using the "send_training_plan()" function, and specific training and development are carried out.

[0137] (Application example 1)

[0138] 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."

[0139] Conventional corporate management support systems have difficulty automating the regular collection and analysis of management data, resulting in problems such as reduced management efficiency. They also lack the functionality to grasp new market trends and corporate operational status in real time and quickly propose appropriate management decisions. In particular, on industrial production lines, information utilization to improve production efficiency and quality control is insufficient, and rapid response is required when an abnormality occurs. Furthermore, there is also insufficient training for potential successors to management positions, which poses a risk to the long-term sustainability of the company.

[0140] 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.

[0141] In this invention, the server includes the following means: means for automatically collecting corporate management data; means for analyzing the management data to calculate key KPIs; means for generating a management diagnosis report based on the analysis results; means for analyzing past data and market trends to generate proposals for future management decisions; means for monitoring the corporate operations in real time and detecting anomalies; means for creating a database of the skills and experience of management candidates and proposing training plans; means for automatically collecting and saving various sensor data from the factory; means for calculating KPIs for production efficiency and quality control based on the collected data; means for generating a management diagnosis report reporting problems and areas for improvement in the production line; means for optimizing production plans, equipment maintenance schedules, and proposing improvements to quality control; and means for monitoring the production line in real time, detecting anomalies, and notifying the user. This enables efficient and automatic collection and analysis of corporate management data, supporting prompt and appropriate management decisions. It also improves production efficiency and quality control on the production line, allowing for prompt countermeasures to be taken when anomalies occur. Furthermore, data-based skill development for successors ensures the long-term sustainability of the company.

[0142] "Management data" refers to information about a company's business activities, financial status, personnel situation, inventory status, etc.

[0143] "KPI" is an abbreviation for Key Performance Indicator, a specific indicator that shows the degree to which a company has achieved its goals.

[0144] A "management diagnosis report" is a report that summarizes the results of an analysis, including the current situation and problems of a company, and suggestions for improvement.

[0145] A "proposal" is a plan of action for a company's management based on the analysis results and market trends.

[0146] "Real-time monitoring" is a system that constantly monitors a company's operational status and immediately detects any abnormalities that occur.

[0147] "Anomaly detection" refers to the detection of deviations from normal operating conditions.

[0148] "Database of skills and experience" means storing and managing the abilities and past experience of potential managers in a digital format.

[0149] A "development plan" is a specific training or education program designed to improve the skills or careers of specific personnel.

[0150] "Sensor data" refers to various measurement data acquired from factory equipment and production lines.

[0151] "Production efficiency" is an indicator that measures the efficiency of resource utilization in production activities.

[0152] "Quality control" refers to the management activities and methods used to ensure the quality of products and services.

[0153] "Abnormality notification" is an alert function that immediately notifies relevant parties of detected abnormalities.

[0154] The present invention is a system that automatically collects and analyzes business data of a company, proposes appropriate business decisions, and also supports the development of successors. Specific embodiments of the present invention will be described below.

[0155] Data collection

[0156] The server periodically collects data from various data sources within the company (ERP system, CRM system, financial system, etc.) For example, it uses APIs to retrieve sales data, inventory data, employee attendance data, and financial data. This data is then stored in a cloud database.

[0157] Data analysis and KPI calculation

[0158] The server analyzes the collected data using machine learning algorithms (e.g., TensorFlow, scikit-learn) to calculate important KPIs, such as sales forecasts, cost analysis, inventory turnover, and employee efficiency. This process combines multiple analytical models to improve prediction accuracy.

[0159] Generate a management diagnostic report

[0160] Based on the analysis results, the server automatically generates a management diagnosis report, which includes information on the company's current situation, risk predictions, and growth opportunities. The report is presented in easy-to-understand graphs and charts using data visualization tools (e.g., Matplotlib, D3.js).

[0161] Proposal of business decisions

[0162] The server analyzes past data and market trends to generate proposals for future management decisions. For example, it may suggest optimizing inventory management, changing hiring strategies, or launching new products into the market. These proposals are generated using a reinforcement learning algorithm (e.g., OpenAI (registered trademark) Gym) that takes into account past patterns of success and failure. Users can review these proposals via their devices and agree or modify them. If the user makes modifications, a recalculation is performed and a new proposal is generated.

[0163] Real-time monitoring and anomaly detection

[0164] The server monitors the company's operations in real time, using data streams to monitor sales, inventory levels, employee attendance, and more, and has the ability to immediately notify users if an abnormality is detected, allowing them to take prompt action.

[0165] Successor development support

[0166] The server creates a database of the skills and experience of potential managers and uses a generative AI model (e.g., GPT-4) to propose an appropriate development plan. This may include specific skill training, setting role models, and conducting management simulations. Based on this development plan, users can provide specific training and training to the target employees.

[0167] Specific examples

[0168] For example, suppose a manufacturing company implements a system as follows:

[0169] The server automatically collects sales data, inventory data, and employee attendance data from the ERP system every morning and stores it in a cloud database.

[0170] The server then analyzes this data and calculates KPIs such as sales forecasts and inventory turnover.

[0171] After the monthly settlement, the server generates a management diagnosis report and notifies the user via the terminal, detailing the company's financial health, potential for new market entry, and so on.

[0172] Based on market trends and analysis results, the server will propose product order optimization and new product promotion strategies for the next quarter, and users can review, agree to, or modify these proposals in real time.

[0173] Daily operational status is monitored in real time, and if an abnormality is detected, for example, if inventory suddenly decreases, an alert notification is sent to the user immediately.

[0174] Finally, the server proposes an appropriate development plan for potential future managers, and the user carries out training and education based on that plan.

[0175] This will enable companies to solve the problem of a lack of successors and achieve sustainable management.

[0176] Example prompts for generative AI models

[0177] "Analyze the operating rate and defect rate of production line 1 in the factory last month, and if the defect rate has increased, please suggest improvement measures."

[0178] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0179] Step 1:

[0180] The server periodically collects data from various data sources within the company (ERP system, CRM system, financial system, etc.). The hardware used includes a server and a cloud database that retrieves data via API. Input data includes sales data, inventory data, employee attendance data, and financial data. The server collects this data and gets an output that is stored in the cloud database.

[0181] Step 2:

[0182] The server analyzes the collected data using machine learning algorithms (e.g., TensorFlow, scikit-learn) and calculates key KPIs. Input data includes sales data and inventory data stored in a cloud database. Data processing involves filling in missing values ​​and normalizing the data to convert it into a format suitable for machine learning algorithms. Output includes KPIs such as sales forecasts, cost analysis, inventory turnover, and employee efficiency.

[0183] Step 3:

[0184] The server generates a management diagnosis report based on the analysis results. The input data includes calculated KPIs and other analysis results. The server uses data visualization tools (e.g., Matplotlib, D3.js) to visualize the analysis results as graphs and charts and compile them into a report format. The output is an easy-to-read management diagnosis report.

[0185] Step 4:

[0186] The server analyzes past data and market trends to generate proposals for future management decisions. Input data includes past sales data and market trend data. The server uses a reinforcement learning algorithm (e.g., OpenAI Gym) to analyze this data and generate proposals such as optimizing inventory management, changing recruitment strategies, and introducing new products to the market. The output is a concrete proposal for management decisions.

[0187] Step 5:

[0188] The server displays the generated proposals to the user via the terminal. The input data are the generated proposals. The user checks these proposals and accepts or modifies them. If any modifications are made, the server recalculates and generates a new proposal. The output is the user's acceptance or modification.

[0189] Step 6:

[0190] The server monitors the company's operations in real time. Input data includes sales data, inventory levels, and employee attendance data, all of which are acquired in real time. The server uses data stream processing (e.g., Apache Kafka) to monitor this data and immediately notifies the user if an anomaly is detected. The output is the real-time monitoring results and anomaly notification.

[0191] Step 7:

[0192] The server creates a database of the skills and experience of potential management candidates and uses a generative AI model (e.g., GPT-4) to propose an appropriate training plan. Input data includes the skills and past experience of the personnel. The server analyzes this data and generates an optimal training plan. A specific training plan is proposed as the output.

[0193] Example prompts for generative AI models

[0194] "Analyze the operating rate and defect rate of production line 1 in the factory last month, and if the defect rate has increased, please suggest improvement measures."

[0195] 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.

[0196] The present invention is a system that automatically collects and analyzes business data of a company, proposes appropriate business decisions, and further recognizes user emotions and responds based on those emotions to improve the effectiveness of business decisions. An embodiment of the system will be described in detail below.

[0197] Data collection

[0198] The server periodically collects data from various data sources within the company (ERP system, CRM system, financial system, etc.) For example, it uses APIs to retrieve sales data, inventory data, employee attendance data, and financial data. This data is then stored in a cloud database.

[0199] Data analysis and KPI calculation

[0200] The server analyzes the collected data using machine learning algorithms to calculate important KPIs, such as sales forecasts, cost analysis, inventory turnover, and employee efficiency. This process can be performed by combining multiple analytical models to improve prediction accuracy.

[0201] Generate a management diagnostic report

[0202] Based on the analysis results, the server automatically generates a management diagnosis report, which includes an analysis of the company's current situation, risk predictions, and information on growth opportunities. The report is presented in easy-to-understand graphs and charts using visualization tools.

[0203] Proposal of business decisions

[0204] The server analyzes past data and market trends to generate recommendations for future business decisions, such as optimizing inventory management, changing hiring strategies, and introducing new products to the market. These recommendations are generated using a reinforcement learning algorithm, taking into account past patterns of success and failure.

[0205] Via the terminal, the user can review these proposals and accept or modify them, in which case a recalculation is performed and a new proposal is generated.

[0206] Real-time monitoring and anomaly detection

[0207] The server monitors the company's operations in real time, using data streams to monitor sales, inventory levels, employee attendance, and more, and has the ability to immediately notify users if an abnormality is detected, allowing them to take prompt action.

[0208] Successor development support

[0209] The server creates a database of the skills and experience of potential managers and uses generative AI to propose an appropriate development plan. This may include specific skill training, setting role models, and conducting management simulations. Based on this development plan, users can provide specific training and training to the target employees.

[0210] Introducing the Emotion Engine

[0211] The server is equipped with an emotion engine that recognizes the user's emotions and adjusts management decisions and countermeasure proposals based on the user's emotions. The emotion engine analyzes the user's facial expressions, voice, and text input to evaluate their psychological state.

[0212] Tailoring suggestions based on emotions

[0213] The server adjusts the business decision suggestions based on the emotional data obtained by the emotion engine, for example, providing more concise and actionable suggestions when the user is stressed, and more detailed and comprehensive suggestions when the user is relaxed.

[0214] Optimizing notifications based on emotions

[0215] The server detects anomalies and optimizes the content and timing of important notifications according to the user's emotions. For example, if the emotion engine determines that the user is already in a high-stress state, it will delay non-urgent notifications to reduce the burden on the user.

[0216] Specific examples

[0217] For example, suppose a manufacturing company implements a system as follows:

[0218] The server automatically collects sales data, inventory data, and employee attendance data from the ERP system every morning and stores it in a cloud database.

[0219] The server then analyzes this data and calculates KPIs such as sales forecasts and inventory turnover.

[0220] After the monthly settlement, the server generates a management diagnosis report and notifies the user via the terminal, detailing the company's financial health, potential for new market entry, and so on.

[0221] Based on market trends and analysis results, the server will propose product order optimization and new product promotion strategies for the next quarter, and users can review, agree to, or modify these proposals in real time.

[0222] Daily operational status is monitored in real time, and if an abnormality is detected, for example, if inventory suddenly decreases, an alert notification is sent to the user immediately.

[0223] The emotion engine recognizes the user's emotions and makes adjustments such as delaying notifications if the user is in a high stress state.

[0224] Finally, the server proposes an appropriate development plan for potential future managers, and the user carries out training and education based on that plan.

[0225] This will enable companies to solve the problem of a lack of successors, achieve sustainable management, and make more effective management decisions and responses that take into consideration the feelings of users.

[0226] The processing flow will be explained below.

[0227] Step 1:

[0228] The server periodically collects data from various data sources of the company (ERP system, CRM system, financial system), for example, using APIs to retrieve sales data, inventory data, employee attendance data, and financial data.

[0229] Step 2:

[0230] The server stores the collected data in a cloud database, where it processes the data and converts it into an appropriate format before storing it in the database.

[0231] Step 3:

[0232] The server feeds data stored in a cloud database into machine learning algorithms to calculate important KPIs, such as sales forecasts, cost analysis, inventory turnover, and employee efficiency.

[0233] Step 4:

[0234] The server generates a management diagnosis report based on the analysis results, converts the KPIs and analysis results into text using natural language generation technology, and creates graphs and charts using visualization tools.

[0235] Step 5:

[0236] The server uploads the generated management diagnosis report to the dashboard and notifies the user, for example, by email or via a mobile app.

[0237] Step 6:

[0238] The server analyzes past data and market trends to generate proposals for future management decisions. It uses a reinforcement learning algorithm to learn past success and failure patterns and generate optimal proposals taking market trends into account.

[0239] Step 7:

[0240] The device displays the generated proposals to the user, who can then view the proposals in the form of a dashboard or report.

[0241] Step 8:

[0242] The user can review the proposed content, agree to it, or make corrections, and can request a recalculation by entering corrections.

[0243] Step 9:

[0244] The server monitors the company's operations in real time, using data streams to monitor sales, inventory levels, employee attendance, and more.

[0245] Step 10:

[0246] The server uses anomaly detection algorithms to detect and alert you to unusual data or trends that deviate from expectations, and sends you a warning via email or SMS.

[0247] Step 11:

[0248] Users can check the alert and decide on appropriate countermeasures, such as immediately placing additional orders or adjusting employee shifts, taking into account the nature of the anomaly.

[0249] Step 12:

[0250] The server creates a database of the skills and experience of potential managers, collecting, integrating, and storing skill sets, career history, and evaluation data from the company's internal personnel database.

[0251] Step 13:

[0252] Based on the databased information, the server uses generative AI to propose appropriate development plans, such as specific skill training, setting up role models, and conducting business simulations.

[0253] Step 14:

[0254] The user reviews and implements the proposed training plan, arranges training programs and workshops based on the proposal, and implements them for the management candidates.

[0255] Step 15:

[0256] The server uses an emotion engine that recognizes the user's emotions to analyze the user's facial expressions, voice, and text inputs and evaluate their psychological state.

[0257] Step 16:

[0258] The server adjusts the business decision suggestions based on the emotional data obtained by the emotion engine, for example, providing more concise and actionable suggestions when the user is stressed, and more detailed and comprehensive suggestions when the user is relaxed.

[0259] Step 17:

[0260] The server detects anomalies and optimizes the content and timing of important notifications according to the user's emotions. For example, if the emotion engine determines that the user is already in a high-stress state, it will delay non-urgent notifications to reduce the burden on the user.

[0261] Example 2

[0262] 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."

[0263] In corporate management, it is extremely important to effectively collect and analyze large amounts of data to guide appropriate management decisions. However, in conventional systems, data collection and analysis are often done manually, resulting in low efficiency. Furthermore, few systems take user emotions into account when making management decisions, which creates the risk of stress and misjudgment. Furthermore, there is a lack of support for real-time monitoring, anomaly detection, and succession planning. For these reasons, there is a need for the development of a system that provides efficient and comprehensive management support.

[0264] 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.

[0265] In this invention, the server includes means for automatically collecting management data of a company, means for analyzing the management data and calculating major KPIs, means for generating a management diagnosis report based on the analysis results, means for analyzing past data and market trends and generating proposals for future management decisions, means for monitoring the company's operating status in real time and detecting abnormalities, means for creating a database of the skills and experience of management candidate personnel and proposing training plans, and means for recognizing user emotions and adjusting the system's proposals and notification content based on the emotions. This makes it possible to efficiently manage the company's management data while supporting decision-making that takes user emotions into consideration.

[0266] "Management data" refers to various data that indicate the operating status of a company, and specifically includes sales data, inventory data, employee attendance data, financial data, and the like.

[0267] "KPI" stands for Key Performance Indicator and refers to a company's important performance indicators, such as sales forecasts, cost analysis, inventory turnover, and employee efficiency.

[0268] A "management diagnosis report" is a document that comprehensively analyzes a company's business situation and compiles information on current issues, future risks, growth opportunities, etc.

[0269] "Past data" refers to various management data that a company has collected and accumulated in the past.

[0270] "Market Trends" refers to data and information that indicates the current state and future projections of an industry or market.

[0271] "Proposal" refers to a specific action plan for a company's management decisions that the system generates based on analysis results and market trends.

[0272] "Real-time monitoring" is a method for monitoring a company's business situation in real time and responding immediately.

[0273] "Anomalies" refers to unusual data or events that deviate from normal operating conditions, such as a sudden decrease in inventory or an abnormal increase or decrease in sales.

[0274] "Anomaly detection" is a mechanism that detects abnormalities during real-time monitoring and immediately notifies you.

[0275] "Management candidates" refer to employees who have the skills and experience to potentially take on management responsibilities at a company in the future.

[0276] A "development plan" refers to a specific training and education plan designed to develop potential management personnel.

[0277] "User" refers to the people involved in the company who use this system, especially those who are the main actors in making management decisions.

[0278] "Means for recognizing emotions" refers to technology that analyzes a user's facial expressions, voice, and text data to evaluate the user's psychological state.

[0279] "Notification" refers to important information or alerts communicated to the user by the system.

[0280] The present invention is a system that automatically collects and analyzes business data of a company, proposes appropriate business decisions, and further recognizes user emotions and responds based on those emotions to improve the effectiveness of business decisions. An embodiment of the system will be described in detail below.

[0281] Data collection

[0282] The server periodically collects data from various data sources within the company. Specifically, it sends API requests to ERP systems, CRM systems, financial systems, etc. to obtain sales data, inventory data, employee attendance data, and financial data. The obtained data is stored in a cloud database (for example, AWS (registered trademark) DynamoDB).

[0283] Data analysis and KPI calculation

[0284] The server analyzes the collected data using machine learning algorithms (e.g., TensorFlow) and calculates key KPIs, such as sales forecasts, cost analysis, inventory turnover, and employee efficiency. This allows the company's current situation to be quantitatively understood.

[0285] Generate a management diagnostic report

[0286] The server automatically generates a management diagnosis report based on the analysis results. This report includes information on the company's current situation, risk predictions, and growth opportunities. The report is visualized using a visualization tool (e.g., Tableau) to create graphs and charts that are easy for users to understand.

[0287] Proposal of business decisions

[0288] The server generates management decision proposals based on market trends and past company data. These proposals are generated using reinforcement learning algorithms (e.g., OpenAI's reinforcement learning algorithms) and include specific action plans such as optimizing inventory management or introducing new products to the market. The proposals are notified to the user via their terminal, allowing them to review the proposals and agree or modify them.

[0289] Real-time monitoring and anomaly detection

[0290] The server monitors the company's operations in real time and detects anomalies. It uses data streams (e.g., Apache Kafka) to monitor sales, inventory levels, employee attendance, etc., and immediately notifies users if an anomaly is detected. This functionality allows for prompt remedial action to be taken.

[0291] Successor development support

[0292] The server creates a database of the skills and experience of potential managers and uses generative AI (such as OpenAI's GPT-4) to propose an appropriate development plan. The development plan includes specific skill training, role model selection, and management simulations. Users can then implement specific training and training based on the plan.

[0293] Introducing the Emotion Engine

[0294] The server is equipped with an emotion engine (for example, Microsoft® Azure® emotion analysis API) that recognizes the user's emotions. It analyzes the user's facial expressions, voice, and text input, evaluates their psychological state, and adjusts the content of suggestions and notifications.

[0295] Tailoring suggestions based on emotions

[0296] The server then adapts its suggestions based on the emotional data obtained by the emotion engine. For example, if the user is stressed, it will provide more concise and actionable suggestions, whereas if the user is relaxed, it will provide more detailed and comprehensive suggestions.

[0297] Optimizing notifications based on emotions

[0298] The server optimizes the content and timing of anomaly detection and important notifications based on emotional data. If stress levels are judged to be high, non-urgent notifications are delayed to reduce the burden on users.

[0299] Specific examples

[0300] For example, in a manufacturing company, the system is implemented as follows:

[0301] 1. The server automatically collects sales data, inventory data, and employee attendance data from the ERP system every morning and stores them in a cloud database.

[0302] 2. The server analyzes this data and calculates KPIs such as sales forecasts and inventory turnover.

[0303] 3. After the monthly settlement, the server generates a management diagnosis report and notifies the user via the terminal, detailing the company's financial health and potential for new market entry.

[0304] 4. Based on market trends and analysis results, the server will propose product order optimization and new product promotion strategies for the next quarter. The user can review these proposals in real time and agree or modify them.

[0305] 5. Daily operational status is monitored in real time, and if an abnormality is detected, for example, if inventory suddenly decreases, an alert notification is sent to the user immediately.

[0306] 6. The emotion engine recognizes the user's emotions and makes adjustments such as delaying notifications if the user is in a high-stress state.

[0307] 7. Finally, the server proposes an appropriate development plan for potential future managers, and the user carries out training and education based on that plan.

[0308] This will enable companies to solve the problem of a lack of successors, achieve sustainable management, and make more effective management decisions and responses that take into consideration the feelings of users.

[0309] Prompt Sentence Examples

[0310] "Please create a sales forecast for next month based on the sales data and compile the analysis results into a report. Also, please generate improvement suggestions for inventory management based on the current inventory levels."

[0311] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0312] Step 1:

[0313] The server automatically collects data from the company's data sources (ERP system, CRM system, financial system). The server sends API requests to each data source to obtain sales data, inventory data, employee attendance data, and financial data. The obtained data is stored in a cloud database (e.g., AWS DynamoDB).

[0314] Input: API response from the data source

[0315] Data processing: Converts API response data into a format and stores it in a cloud database

[0316] Output: Management data stored in a cloud database

[0317] Step 2:

[0318] The server retrieves the stored management data from the cloud database and analyzes it using machine learning algorithms (e.g., TensorFlow), calculating KPIs such as sales forecasts, cost analysis, inventory turnover, and employee efficiency.

[0319] Input: Management data from cloud database

[0320] Data calculation: Applying machine learning algorithms to calculate KPIs

[0321] Output: Calculated KPIs

[0322] Step 3:

[0323] The server generates a management diagnostic report based on the analysis results. This report includes information on the company's current situation, risk predictions, and growth opportunities. The server uses a visualization tool (e.g., Tableau) to create graphs and charts and display the report in an easy-to-understand manner.

[0324] Input: Analysis results and KPIs

[0325] Data processing: Visualization tools transform analysis results into graphs and charts

[0326] Output: Management diagnosis report

[0327] Step 4:

[0328] The server analyzes historical data and market trends to generate recommendations for future business decisions. These recommendations are generated using a reinforcement learning algorithm and include specific action plans, such as optimizing inventory management or introducing new products to the market.

[0329] Input: Historical data, market trends

[0330] Data computation: Analyzes data using reinforcement learning algorithms and generates recommendations

[0331] Output: Proposal of business decision

[0332] Step 5:

[0333] Through the terminal, the user can review the proposed business decision and agree or modify it. If the user modifies it, the server will recalculate and generate a new proposal.

[0334] Input: User feedback

[0335] Data processing: Reflect feedback and reanalyze

[0336] Output: Corrections or new suggestions

[0337] Step 6:

[0338] The server performs real-time monitoring to monitor the company's operations, using data streams (e.g., Apache Kafka) to monitor sales, inventory levels, employee attendance, etc., and immediately notifies users if an anomaly is detected.

[0339] Input: Real-time data stream

[0340] Data calculation: Runs anomaly detection algorithms to identify anomalies

[0341] Output: Anomaly detection notification

[0342] Step 7:

[0343] The server creates a database of the skills and experience of potential managers and uses generative AI (such as OpenAI's GPT-4) to propose an appropriate training plan, which includes specific skill training, role modeling, and management simulations.

[0344] Input: Skill data and experience of managerial candidates

[0345] Data calculation: Generative AI model is used to generate training plans

[0346] Output: Development plan

[0347] Step 8:

[0348] The server uses an emotion engine (e.g., Microsoft Azure's Emotion Analysis API) to recognize the user's emotions. The server analyzes the user's facial expressions, voice, and text input to evaluate their psychological state.

[0349] Input: User's facial expressions, voice, and text data

[0350] Data Analysis: Analyze sentiment data using the sentiment engine

[0351] Output: Emotion analysis results

[0352] Step 9:

[0353] The server adjusts the management decision suggestions based on the emotional data obtained by the emotion engine. For example, if the user is feeling stressed, it provides simple and easy-to-implement suggestions.

[0354] Input: Sentiment analysis results

[0355] Data processing: Adjust proposal content based on emotion data

[0356] Output: Adjusted proposal

[0357] Step 10:

[0358] The server detects anomalies and optimizes the content and timing of important notifications based on the user's emotions. If the server determines that the user is under high stress, it will delay non-urgent notifications to reduce the burden on the user.

[0359] Input: Anomaly detection data, emotion analysis results

[0360] Data processing: Adjust notification content and timing

[0361] Output: Optimized notification

[0362] (Application example 2)

[0363] 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."

[0364] Conventional management data analysis systems were equipped with functions to monitor a company's operational status, detect abnormalities, and propose management decisions, but they lacked the ability to recognize users' emotions and adjust responses based on them. As a result, they lacked consideration for the psychological state of operators, such as sending important notifications when the operator was in a high-stress state. This often made it difficult for users to respond appropriately, which led to problems with the effectiveness of management decisions.

[0365] 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 automatically collecting corporate management data, means for analyzing the management data to calculate key KPIs, means for generating a management diagnosis report based on the analysis results, means for analyzing past data and market trends to generate proposals for future management decisions, means for monitoring the corporate management situation in real time and detecting abnormalities, means for creating a database of the skills and experience of management candidate personnel and proposing training plans, means for collecting and analyzing various types of data within the factory in real time, means for recognizing operator emotions and adjusting proposals based on those emotions, and means for optimizing the timing and content of notifications based on emotions. This enables appropriate management decisions to be made based on the corporate management situation and enables responses that take into account the psychological state of the operators.

[0366] "Corporate management data" refers to all data generated and acquired by a company in the course of its daily business operations, including sales data, inventory data, employee attendance data, and financial data.

[0367] "Means of collection" refers to the methods and technologies used to obtain target data from various data sources and incorporate it into the system.

[0368] "Means of analysis" refers to techniques and methods for obtaining specific insights by performing statistical analysis, machine learning, data mining, etc. based on collected data.

[0369] "Key KPIs" refer to important indicators for evaluating a company's business performance, including sales forecasts, inventory turnover, and employee efficiency.

[0370] A "management diagnostic report" is a document that includes information on a company's operating status, current situation analysis, risk predictions, and growth opportunities, and is presented using visualization tools such as graphs and charts.

[0371] "Means for generating proposals" refers to technologies and methods that analyze past data and market trends and propose specific actions for future management decisions.

[0372] "Monitoring means" refers to technologies and methods for monitoring and tracking a company's operations in real time and detecting abnormalities or fluctuations.

[0373] "Means for detecting anomalies" refers to methods and technologies for detecting deviations from normal operating patterns or abnormal behavior in real time.

[0374] A "development plan" refers to a plan for providing appropriate training and education based on the skills and experience of potential management personnel.

[0375] "Various data within the factory" refers to production data, inventory data, quality data, machine operation data, etc. generated in the manufacturing industry.

[0376] "Means for recognizing emotions" refers to technologies and methods for analyzing a user's facial expressions, voice, text input, etc. to assess their psychological state.

[0377] "Means for optimizing the timing and content of notifications" refers to technologies and methods for notifying users at appropriate times and in appropriate ways based on their emotional data.

[0378] The present invention is a system that automatically collects and analyzes business data of a company and proposes appropriate business decisions. Furthermore, it recognizes the user's emotions and responds based on those emotions to improve the effectiveness of business decisions. An embodiment of the system is described below in detail.

[0379] Data collection

[0380] The server periodically collects data from various data sources within the company (ERP system, CRM system, financial system, etc.) For example, it uses APIs to retrieve sales data, inventory data, employee attendance data, and financial data. This data is then stored in a cloud database.

[0381] Data analysis and KPI calculation

[0382] The server analyzes the collected data using machine learning algorithms to calculate important KPIs, such as sales forecasts, cost analysis, inventory turnover, and employee efficiency. This process can be performed by combining multiple analytical models to improve prediction accuracy.

[0383] Generate a management diagnostic report

[0384] Based on the analysis results, the server automatically generates a management diagnosis report, which includes an analysis of the company's current situation, risk predictions, and information on growth opportunities. The report is presented in easy-to-understand graphs and charts using visualization tools.

[0385] Proposal of business decisions

[0386] The server analyzes past data and market trends to generate proposals for future management decisions. For example, it makes proposals for optimizing inventory management, changing recruitment strategies, and entering new product markets. These proposals are generated using a reinforcement learning algorithm, taking into account past patterns of success and failure. Users can review these proposals via their devices and agree or modify them. If the user makes modifications, a recalculation is performed and a new proposal is generated.

[0387] Real-time monitoring and anomaly detection

[0388] The server monitors the company's operations in real time, using data streams to monitor sales, inventory levels, employee attendance, and more, and has the ability to immediately notify users if an abnormality is detected, allowing them to take prompt action.

[0389] Successor development support

[0390] The server creates a database of the skills and experience of potential managers and uses generative AI to propose an appropriate development plan. This may include specific skill training, setting role models, and conducting management simulations. Based on this development plan, users can provide specific training and training to the target employees.

[0391] Introducing the Emotion Engine

[0392] The server is equipped with an emotion engine that recognizes the user's emotions and adjusts management decisions and countermeasure proposals based on the user's emotions. The emotion engine analyzes the user's facial expressions, voice, and text input to evaluate their psychological state.

[0393] Tailoring suggestions based on emotions

[0394] The server adjusts the business decision suggestions based on the emotional data obtained by the emotion engine, for example, providing more concise and actionable suggestions when the user is stressed, and more detailed and comprehensive suggestions when the user is relaxed.

[0395] Optimizing notifications based on emotions

[0396] The server detects anomalies and optimizes the content and timing of important notifications according to the user's emotions. For example, if the emotion engine determines that the user is already in a high-stress state, it will delay non-urgent notifications to reduce the burden on the user.

[0397] Specific examples

[0398] For example, suppose a manufacturing company implements a system as follows:

[0399] The server automatically collects sales data, inventory data, and employee attendance data from the ERP system every morning and stores it in a cloud database.

[0400] The server then analyzes this data and calculates KPIs such as sales forecasts and inventory turnover.

[0401] After the monthly settlement, the server generates a management diagnosis report and notifies the user via the terminal, detailing the company's financial health, potential for new market entry, and so on.

[0402] Based on market trends and analysis results, the server will propose product order optimization and new product promotion strategies for the next quarter, and users can review, agree to, or modify these proposals in real time.

[0403] Daily operational status is monitored in real time, and if an abnormality is detected, for example, if inventory suddenly decreases, an alert notification is sent to the user immediately.

[0404] The emotion engine recognizes the user's emotions and makes adjustments such as delaying notifications if the user is in a high stress state.

[0405] Finally, the server proposes an appropriate development plan for potential future managers, and the user implements training based on that plan. This allows companies to solve the problem of a lack of successors, achieve sustainable management, and make more effective management decisions and responses that take users' feelings into consideration.

[0406] Prompt Sentence Examples

[0407] Below is an example of a prompt sentence to input to the generative AI model.

[0408] Analyze the following data to recognize user emotions:

[0409] Facial expression image (e.g., a user's face image taken with a camera)

[0410] Audio data (e.g., user words)

[0411] Text input (e.g., user-entered comments)

[0412] As a result, if the user is exhibiting an emotion (e.g., stress, relaxation, sadness, joy), identify it.

[0413] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0414] Step 1:

[0415] The server periodically collects management data from the company's ERP system, CRM system, financial system, etc. The inputs are sales data, inventory data, employee attendance data, and financial data obtained from each data source. The server obtains this data using an API and stores it in a cloud database. The output is this data stored in the database.

[0416] Step 2:

[0417] The server analyzes the collected data and calculates key KPIs. The input is management data stored in a cloud database. The server uses machine learning algorithms to calculate KPIs such as sales forecasts, cost analysis, inventory turnover, and employee efficiency. The output is the calculated KPIs.

[0418] Step 3:

[0419] The server generates a management diagnosis report based on the analysis results. The input is the calculated KPIs. The server uses visualization tools (e.g., Matplotlib, Seaborn) to generate the management diagnosis report in graph and chart format and saves it in a cloud database. The output is the generated management diagnosis report.

[0420] Step 4:

[0421] The server analyzes past data and market trends to generate proposals for future management decisions. The inputs are past data, market trend data, and calculated KPIs. The server uses a reinforcement learning algorithm to make proposals such as optimizing inventory management, changing recruitment strategies, and entering new product markets. The output is the generated proposals for management decisions.

[0422] Step 5:

[0423] The terminal displays the generated business decision proposals to the user. The input is the business decision proposals sent from the server. The user can review these proposals and agree or modify them. The output is the user's agreement or modified information.

[0424] Step 6:

[0425] The server monitors the company's operations in real time and detects anomalies. The input is a stream of the company's daily operations data. The server analyzes the data stream and records any anomalies it detects. The output is information about the detected anomalies.

[0426] Step 7:

[0427] The server immediately notifies the user if an anomaly is detected. The input is the detected anomaly information. The server sends this information to the terminal so the user can take appropriate countermeasures. The output is the anomaly notification sent to the user.

[0428] Step 8:

[0429] The server creates a database of the skills and experience of management candidates and uses a generative AI model to propose an appropriate training plan. The input is data on the skills and experience of management candidates. The server analyzes this data and generates a training plan. The output is the generated training plan.

[0430] Step 9:

[0431] The server uses an emotion engine that recognizes the user's emotions to adjust management decisions and proposed countermeasures based on the emotions. The inputs are images of the user's facial expressions, voice data, and text input. The server analyzes this data using an emotion engine (e.g., OpenCV, IBM Watson (registered trademark)) to recognize the user's emotions. The output is recognized emotion data.

[0432] Step 10:

[0433] The server optimizes the content of the generated suggestions and the timing of notifications according to the user's emotions. The inputs are the recognized emotion data and the generated business decision suggestions. The server adjusts the suggestions based on the user's psychological state and changes the timing of notifications as needed. The output is the adjusted suggestions and optimized notifications.

[0434] 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.

[0435] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0436] 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.

[0437] [Second embodiment]

[0438] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0439] 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.

[0440] 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).

[0441] 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.

[0442] 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.

[0443] 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).

[0444] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0445] 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.

[0446] 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.

[0447] 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.

[0448] In the smart glasses 214, 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.

[0449] 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."

[0450] The present invention is a system that automatically collects and analyzes business data of a company, proposes appropriate business decisions, and also supports the development of successors. Specific embodiments of the present invention will be described below.

[0451] Data collection

[0452] The server periodically collects data from various data sources within the company (ERP system, CRM system, financial system, etc.) For example, it uses APIs to retrieve sales data, inventory data, employee attendance data, and financial data. This data is then stored in a cloud database.

[0453] Data analysis and KPI calculation

[0454] The server analyzes the collected data using machine learning algorithms to calculate important KPIs, such as sales forecasts, cost analysis, inventory turnover, and employee efficiency. This process can be performed by combining multiple analytical models to improve prediction accuracy.

[0455] Generate a management diagnostic report

[0456] Based on the analysis results, the server automatically generates a management diagnosis report, which includes an analysis of the company's current situation, risk predictions, and information on growth opportunities. The report is presented in easy-to-understand graphs and charts using visualization tools.

[0457] Proposal of business decisions

[0458] The server analyzes past data and market trends to generate recommendations for future business decisions, such as optimizing inventory management, changing hiring strategies, and introducing new products to the market. These recommendations are generated using a reinforcement learning algorithm, taking into account past patterns of success and failure.

[0459] Via the terminal, the user can review these proposals and accept or modify them, in which case a recalculation is performed and a new proposal is generated.

[0460] Real-time monitoring and anomaly detection

[0461] The server monitors the company's operations in real time, using data streams to monitor sales, inventory levels, employee attendance, and more, and has the ability to immediately notify users if an abnormality is detected, allowing them to take prompt action.

[0462] Successor development support

[0463] The server creates a database of the skills and experience of potential managers and uses generative AI to propose an appropriate development plan. This may include specific skill training, setting role models, and conducting management simulations. Based on this development plan, users can provide specific training and training to the target employees.

[0464] Specific examples

[0465] For example, suppose a manufacturing company implements a system as follows:

[0466] The server automatically collects sales data, inventory data, and employee attendance data from the ERP system every morning and stores it in a cloud database.

[0467] The server then analyzes this data and calculates KPIs such as sales forecasts and inventory turnover.

[0468] After the monthly settlement, the server generates a management diagnosis report and notifies the user via the terminal, detailing the company's financial health, potential for new market entry, and so on.

[0469] Based on market trends and analysis results, the server will propose product order optimization and new product promotion strategies for the next quarter, and users can review, agree to, or modify these proposals in real time.

[0470] Daily operational status is monitored in real time, and if an abnormality is detected, for example, if inventory suddenly decreases, an alert notification is sent to the user immediately.

[0471] Finally, the server proposes an appropriate development plan for potential future managers, and the user carries out training and education based on that plan.

[0472] This will enable companies to solve the problem of a lack of successors and achieve sustainable management.

[0473] The processing flow will be explained below.

[0474] Step 1:

[0475] The server periodically collects data from various corporate data sources (ERP system, CRM system, financial system), for example using APIs to retrieve sales data, inventory data, employee attendance data, and financial data.

[0476] Step 2:

[0477] The server stores the collected data in a cloud database, where it processes the data and converts it into an appropriate format before storing it in the database.

[0478] Step 3:

[0479] The server feeds data stored in a cloud database into machine learning algorithms to calculate important KPIs, such as sales forecasts, cost analysis, inventory turnover, and employee efficiency.

[0480] Step 4:

[0481] The server generates a management diagnosis report based on the analysis results, converts the KPIs and analysis results into text using natural language generation technology, and creates graphs and charts using visualization tools.

[0482] Step 5:

[0483] The server uploads the generated management diagnosis report to the dashboard and notifies the user, for example, by email or via a mobile app.

[0484] Step 6:

[0485] The server analyzes past data and market trends to generate proposals for future management decisions. It uses a reinforcement learning algorithm to learn past success and failure patterns and generate optimal proposals taking market trends into account.

[0486] Step 7:

[0487] The device displays the generated proposals to the user, who can then view the proposals in the form of a dashboard or report.

[0488] Step 8:

[0489] The user can review the proposed content, agree to it, or make corrections, and can request a recalculation by entering corrections.

[0490] Step 9:

[0491] The server monitors the company's operations in real time, using data streams to monitor sales, inventory levels, employee attendance, and more.

[0492] Step 10:

[0493] The server uses anomaly detection algorithms to detect and alert you to unusual data or trends that deviate from expectations, and sends you a warning via email or SMS.

[0494] Step 11:

[0495] Users can check the alert and decide on appropriate countermeasures, such as immediately placing additional orders or adjusting employee shifts, taking into account the nature of the anomaly.

[0496] Step 12:

[0497] The server creates a database of the skills and experience of potential managers, collecting, integrating, and storing skill sets, career history, and evaluation data from the company's internal personnel database.

[0498] Step 13:

[0499] Based on the databased information, the server uses generative AI to propose appropriate development plans, such as specific skill training, setting up role models, and conducting business simulations.

[0500] Step 14:

[0501] The user reviews and implements the proposed training plan, arranges training programs and workshops based on the proposal, and implements them for the management candidates.

[0502] Example 1

[0503] 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."

[0504] Corporate management requires the efficient collection of data from each department, the calculation of key management indicators, and support for management decisions. However, modern companies must handle complex systems and vast amounts of data, and performing these processes manually is labor-intensive and carries a high risk of error. Important issues remain, such as real-time monitoring, anomaly detection, and the development of management candidates. To address these issues, a consistent automation system and high-precision analysis technology are required.

[0505] 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.

[0506] In this invention, the server includes means for automatically collecting corporate management data, means for analyzing the management data using a machine learning algorithm and calculating key KPIs, means for generating a management diagnosis report using a visualization tool based on the analysis results, means for analyzing past data and market trends and generating proposals for future management decisions using a reinforcement learning algorithm, means for monitoring the corporate operating status in real time using data stream technology and detecting anomalies, and means for using a generative AI model to create a database of the skills and experience of management candidate personnel and propose a training plan. This enables efficient collection and analysis of corporate data, timely and accurate support for management decisions, and automatic proposals for training plans for management candidate personnel.

[0507] "Corporate management data" is a general term for information such as financial data, sales data, inventory data, and employee attendance data that is collected and managed by a company on a daily basis.

[0508] "Automatic collection means" refers to software and hardware components that allow the system to obtain data from various data sources without manual intervention.

[0509] A "machine learning algorithm" is an algorithm that uses technology to have a computer analyze massive amounts of data, recognize patterns and trends in the data, and learn from them.

[0510] "KPI" is an abbreviation for Key Performance Indicator, and refers to a company's key performance indicators, including sales forecasts, cost analysis, inventory turnover, and employee efficiency.

[0511] A "visualization tool" is a tool that displays data in a visual format, such as a graph or chart, making it easier to understand and analyze.

[0512] A "reinforcement learning algorithm" is a machine learning method that uses trial and error to find optimal behavior. It analyzes past data and market trends and automatically improves future behavior.

[0513] "Data stream technology" refers to technology for continuously collecting data in real time and processing it immediately. Apache Kafka is a representative example.

[0514] "Anomaly detection means" refers to software and hardware components that monitor real-time data and detect unexpected events or abnormal values.

[0515] A "generative AI model" is an AI model that uses natural language processing and machine learning techniques and is used to automatically generate new proposals and reports from data.

[0516] "Development plan" means a specific education and training plan to improve the skills and experience of potential management personnel.

[0517] The present invention is a system that automatically collects and analyzes business data of a company, proposes appropriate business decisions, and also supports the development of successors. Specific embodiments of the present invention will be described below.

[0518] Data collection

[0519] The server periodically collects data from various data sources within the company (ERP system, CRM system, financial system, etc.). For example, it uses APIs to retrieve sales data, inventory data, employee attendance data, and financial data. This data is stored in a cloud database such as Amazon RDS or Google Cloud Spanner. Specifically, the server calls functions such as "get_sales_data()" and "get_inventory_data()" and stores the results in the database using the "store_in_database()" function.

[0520] Data analysis and KPI calculation

[0521] The server analyzes the collected data using machine learning algorithms (e.g., TensorFlow or Scikit-learn) and calculates important KPIs. For analysis, the data is preprocessed using the "preprocess_data()" function, and then KPIs are calculated using the "calculate_kpis()" function. Specific KPIs include sales forecasts, cost analysis, inventory turnover, and employee efficiency. This allows for an accurate understanding of the current situation of the company.

[0522] Generate a management diagnostic report

[0523] Based on the analysis results, the server automatically generates a management diagnosis report. This report includes information on the company's current situation, risk predictions, and growth opportunities, and is presented in graphs and charts using a visualization tool (e.g., Tableau or Power BI). Specifically, the report is generated by the "generate_report()" function, and then notified to the user via the terminal by the "send_report_to_user()" function.

[0524] Proposal of business decisions

[0525] The server analyzes historical data and market trends and generates suggestions for future business decisions using reinforcement learning algorithms (e.g., Deep Q-Learning). These suggestions may include optimizing inventory management, changing recruitment strategies, or launching new products into the market. Suggestions are created using the "generate_suggestions()" function and displayed on the terminal via the "display_suggestions()" function. Users can review and modify the suggestions using the "approve_suggestion()" or "modify_suggestion()" functions.

[0526] Real-time monitoring and anomaly detection

[0527] The server uses data stream technologies such as Apache Kafka to monitor the company's operational status in real time. The server monitors sales, inventory levels, employee attendance, etc., and detects anomalies using the "detect_anomalies()" function. When an anomaly is detected, the user is immediately notified via the "send_alert()" function, allowing the user to take prompt action.

[0528] Successor development support

[0529] The server uses a generative AI model (e.g., GPT-4) to create a database of the skills and experience of potential managers, and evaluates them using the "analyze_candidate()" function. It then proposes an appropriate development plan using the "generate_development_plan()" function, and sends the plan to the user using the "send_training_plan()" function. This development plan includes specific skill training, role model selection, and management simulations.

[0530] Specific examples

[0531] For example, at a manufacturing company, the server uses the ERP system's API to collect sales data, inventory data, and employee attendance data every morning and stores it in Amazon RDS. The collected data is then analyzed using TensorFlow, preprocessed using the "preprocess_data()" function, and KPIs are calculated using the "calculate_kpis()" function. After monthly settlement, a report is generated using the "generate_report()" function and notified to the user via a terminal using the "send_report_to_user()" function. Furthermore, based on the results of analyzing past data and market trends, the "generate_suggestions()" function makes suggestions for the next quarter. The user can then review and modify the suggestions using the "approve_suggestion()" or "modify_suggestion()" functions. Daily operational status is monitored in real time using the "monitor_operations()" function, and if an anomaly is detected using the "detect_anomalies()" function, the user is immediately notified using the "send_alert()" function. Finally, the skills of potential future managers are evaluated using the "analyze_candidate()" function, a training plan is created using the "generate_development_plan()" function, and the plan is notified to the user using the "send_training_plan()" function.

[0532] Examples of prompts include "Propose a market entry strategy for a new product" or "Generate inventory management optimization recommendations for the next quarter."

[0533] This will enable companies to automate efficient data collection, secure storage, highly accurate analysis, rapid business decision-making, and successor training, all of which will enable them to achieve sustainable management.

[0534] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0535] Step 1: Data collection

[0536] The server collects data from various data sources within the company. Specifically, it uses APIs to retrieve sales data, inventory data, employee attendance data, financial data, etc. from ERP systems, CRM systems, and financial systems. To do this, the server uses authentication information to make API calls and uses functions such as "get_sales_data()" and "get_inventory_data()." The input is the API endpoint of each data source, and the output is the retrieved data, which is then stored in a cloud database (e.g., Amazon RDS or Google Cloud Spanner) using the "store_in_database()" function.

[0537] Step 2: Data Preprocessing

[0538] The server preprocesses the collected data. Specifically, it cleans the data, handles missing values, and standardizes it using the "preprocess_data()" function. The input is the raw data stored in the cloud database, and the output is data formatted in an analyzable format. This creates a dataset suitable for subsequent analysis.

[0539] Step 3: Calculate KPIs

[0540] The server uses the preprocessed data to calculate key KPIs. It uses the "calculate_kpis()" function to apply machine learning algorithms (e.g., TensorFlow, Scikit-learn) to calculate KPIs such as sales forecasts, cost analysis, inventory turnover, and employee efficiency. The input is the preprocessed data, and the output is the numerical values ​​of various KPIs. This provides a concrete representation of the company's important indicators.

[0541] Step 4: Generate a business diagnostic report

[0542] The server creates a management diagnosis report based on the calculated KPIs. It uses the "generate_report()" function and then uses a visualization tool (e.g., Tableau, Power BI) to display the results in graphs and charts. The input is the calculated KPIs and analysis results, and the output is a visualized management diagnosis report. This report is sent to the terminal via the "send_report_to_user()" function and notified to the user.

[0543] Step 5: Propose business decisions

[0544] The server analyzes past data and market trends and uses a reinforcement learning algorithm (e.g., Deep Q-Learning) to generate suggestions for management decisions. Specific suggestions such as optimizing inventory management, changing recruitment strategies, and launching new products into the market are created using the 'generate_suggestions()' function. The input is market trend data and analysis results, and the output is a specific proposal. The user can review the suggestions on their device using the 'display_suggestions()' function, and approve or modify the suggestions using the 'approve_suggestion()' or 'modify_suggestion()' functions.

[0545] Step 6: Real-time monitoring and anomaly detection

[0546] The server uses data streaming technologies such as Apache Kafka to monitor the company's operational status in real time. It monitors data using the 'monitor_operations()' function and detects anomalies using the 'detect_anomalies()' function. The input is real-time operational data, and the output is the detected anomalous data. If an anomaly is found, the user is immediately notified using the 'send_alert()' function.

[0547] Step 7: Support for developing successors

[0548] The server uses a generative AI model (e.g., GPT-4) to create a database of the skills and experience of potential management candidates and proposes a development plan. It evaluates the skills of the candidates using the "analyze_candidate()" function and creates a development plan using the "generate_development_plan()" function. The input is the candidate's skill data and experience data, and the output is a specific development plan. This plan is sent to the user using the "send_training_plan()" function, and specific training and development are carried out.

[0549] (Application example 1)

[0550] 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."

[0551] Conventional corporate management support systems have difficulty automating the regular collection and analysis of management data, resulting in problems such as reduced management efficiency. They also lack the functionality to grasp new market trends and corporate operational status in real time and quickly propose appropriate management decisions. In particular, on industrial production lines, information utilization to improve production efficiency and quality control is insufficient, and rapid response is required when an abnormality occurs. Furthermore, there is also insufficient training for potential successors to management positions, which poses a risk to the long-term sustainability of the company.

[0552] 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.

[0553] In this invention, the server includes the following means: means for automatically collecting corporate management data; means for analyzing the management data to calculate key KPIs; means for generating a management diagnosis report based on the analysis results; means for analyzing past data and market trends to generate proposals for future management decisions; means for monitoring the corporate operations in real time and detecting anomalies; means for creating a database of the skills and experience of management candidates and proposing training plans; means for automatically collecting and saving various sensor data from the factory; means for calculating KPIs for production efficiency and quality control based on the collected data; means for generating a management diagnosis report reporting problems and areas for improvement in the production line; means for optimizing production plans, equipment maintenance schedules, and proposing improvements to quality control; and means for monitoring the production line in real time, detecting anomalies, and notifying the user. This enables efficient and automatic collection and analysis of corporate management data, supporting prompt and appropriate management decisions. It also improves production efficiency and quality control on the production line, allowing for prompt countermeasures to be taken when anomalies occur. Furthermore, data-based skill development for successors ensures the long-term sustainability of the company.

[0554] "Management data" refers to information about a company's business activities, financial status, personnel situation, inventory status, etc.

[0555] "KPI" is an abbreviation for Key Performance Indicator, a specific indicator that shows the degree to which a company has achieved its goals.

[0556] A "management diagnosis report" is a report that summarizes the results of an analysis, including the current situation and problems of a company, and suggestions for improvement.

[0557] A "proposal" is a plan of action for a company's management based on the analysis results and market trends.

[0558] "Real-time monitoring" is a system that constantly monitors a company's operational status and immediately detects any abnormalities that occur.

[0559] "Anomaly detection" refers to the detection of deviations from normal operating conditions.

[0560] "Database of skills and experience" means storing and managing the abilities and past experience of potential managers in a digital format.

[0561] A "development plan" is a specific training or education program designed to improve the skills or careers of specific personnel.

[0562] "Sensor data" refers to various measurement data acquired from factory equipment and production lines.

[0563] "Production efficiency" is an indicator that measures the efficiency of resource utilization in production activities.

[0564] "Quality control" refers to the management activities and methods used to ensure the quality of products and services.

[0565] "Abnormality notification" is an alert function that immediately notifies relevant parties of detected abnormalities.

[0566] The present invention is a system that automatically collects and analyzes business data of a company, proposes appropriate business decisions, and also supports the development of successors. Specific embodiments of the present invention will be described below.

[0567] Data collection

[0568] The server periodically collects data from various data sources within the company (ERP system, CRM system, financial system, etc.) For example, it uses APIs to retrieve sales data, inventory data, employee attendance data, and financial data. This data is then stored in a cloud database.

[0569] Data analysis and KPI calculation

[0570] The server analyzes the collected data using machine learning algorithms (e.g., TensorFlow, scikit-learn) to calculate important KPIs, such as sales forecasts, cost analysis, inventory turnover, and employee efficiency. This process combines multiple analytical models to improve prediction accuracy.

[0571] Generate a management diagnostic report

[0572] Based on the analysis results, the server automatically generates a management diagnosis report, which includes information on the company's current situation, risk predictions, and growth opportunities. The report is presented in easy-to-understand graphs and charts using data visualization tools (e.g., Matplotlib, D3.js).

[0573] Proposal of business decisions

[0574] The server analyzes past data and market trends to generate proposals for future management decisions. For example, it may suggest optimizing inventory management, changing hiring strategies, or launching new products into the market. These proposals are generated using a reinforcement learning algorithm (e.g., OpenAI Gym) that takes into account past patterns of success and failure. Users can review these proposals via their devices and agree or modify them. If the user makes modifications, a recalculation is performed and a new proposal is generated.

[0575] Real-time monitoring and anomaly detection

[0576] The server monitors the company's operations in real time, using data streams to monitor sales, inventory levels, employee attendance, and more, and has the ability to immediately notify users if an abnormality is detected, allowing them to take prompt action.

[0577] Successor development support

[0578] The server creates a database of the skills and experience of potential managers and uses a generative AI model (e.g., GPT-4) to propose an appropriate development plan. This may include specific skill training, setting role models, and conducting management simulations. Based on this development plan, users can provide specific training and training to the target employees.

[0579] Specific examples

[0580] For example, suppose a manufacturing company implements a system as follows:

[0581] The server automatically collects sales data, inventory data, and employee attendance data from the ERP system every morning and stores it in a cloud database.

[0582] The server then analyzes this data and calculates KPIs such as sales forecasts and inventory turnover.

[0583] After the monthly settlement, the server generates a management diagnosis report and notifies the user via the terminal, detailing the company's financial health, potential for new market entry, and so on.

[0584] Based on market trends and analysis results, the server will propose product order optimization and new product promotion strategies for the next quarter, and users can review, agree to, or modify these proposals in real time.

[0585] Daily operational status is monitored in real time, and if an abnormality is detected, for example, if inventory suddenly decreases, an alert notification is sent to the user immediately.

[0586] Finally, the server proposes an appropriate development plan for potential future managers, and the user carries out training and education based on that plan.

[0587] This will enable companies to solve the problem of a lack of successors and achieve sustainable management.

[0588] Example prompts for generative AI models

[0589] "Analyze the operating rate and defect rate of production line 1 in the factory last month, and if the defect rate has increased, please suggest improvement measures."

[0590] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0591] Step 1:

[0592] The server periodically collects data from various data sources within the company (ERP system, CRM system, financial system, etc.). The hardware used includes a server and a cloud database that retrieves data via API. Input data includes sales data, inventory data, employee attendance data, and financial data. The server collects this data and gets an output that is stored in the cloud database.

[0593] Step 2:

[0594] The server analyzes the collected data using machine learning algorithms (e.g., TensorFlow, scikit-learn) and calculates key KPIs. Input data includes sales data and inventory data stored in a cloud database. Data processing involves filling in missing values ​​and normalizing the data to convert it into a format suitable for machine learning algorithms. Output includes KPIs such as sales forecasts, cost analysis, inventory turnover, and employee efficiency.

[0595] Step 3:

[0596] The server generates a management diagnosis report based on the analysis results. The input data includes calculated KPIs and other analysis results. The server uses data visualization tools (e.g., Matplotlib, D3.js) to visualize the analysis results as graphs and charts and compile them into a report format. The output is an easy-to-read management diagnosis report.

[0597] Step 4:

[0598] The server analyzes past data and market trends to generate proposals for future management decisions. Input data includes past sales data and market trend data. The server uses a reinforcement learning algorithm (e.g., OpenAI Gym) to analyze this data and generate proposals such as optimizing inventory management, changing recruitment strategies, and introducing new products to the market. The output is a concrete proposal for management decisions.

[0599] Step 5:

[0600] The server displays the generated proposals to the user via the terminal. The input data are the generated proposals. The user checks these proposals and accepts or modifies them. If any modifications are made, the server recalculates and generates a new proposal. The output is the user's acceptance or modification.

[0601] Step 6:

[0602] The server monitors the company's operations in real time. Input data includes sales data, inventory levels, and employee attendance data, all of which are acquired in real time. The server uses data stream processing (e.g., Apache Kafka) to monitor this data and immediately notifies the user if an anomaly is detected. The output is the real-time monitoring results and anomaly notification.

[0603] Step 7:

[0604] The server creates a database of the skills and experience of potential management candidates and uses a generative AI model (e.g., GPT-4) to propose an appropriate training plan. Input data includes the skills and past experience of the personnel. The server analyzes this data and generates an optimal training plan. A specific training plan is proposed as the output.

[0605] Example prompts for generative AI models

[0606] "Analyze the operating rate and defect rate of production line 1 in the factory last month, and if the defect rate has increased, please suggest improvement measures."

[0607] 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.

[0608] The present invention is a system that automatically collects and analyzes business data of a company, proposes appropriate business decisions, and further recognizes user emotions and responds based on those emotions to improve the effectiveness of business decisions. An embodiment of the system will be described in detail below.

[0609] Data collection

[0610] The server periodically collects data from various data sources within the company (ERP system, CRM system, financial system, etc.) For example, it uses APIs to retrieve sales data, inventory data, employee attendance data, and financial data. This data is then stored in a cloud database.

[0611] Data analysis and KPI calculation

[0612] The server analyzes the collected data using machine learning algorithms to calculate important KPIs, such as sales forecasts, cost analysis, inventory turnover, and employee efficiency. This process can be performed by combining multiple analytical models to improve prediction accuracy.

[0613] Generate a management diagnostic report

[0614] Based on the analysis results, the server automatically generates a management diagnosis report, which includes an analysis of the company's current situation, risk predictions, and information on growth opportunities. The report is presented in easy-to-understand graphs and charts using visualization tools.

[0615] Proposal of business decisions

[0616] The server analyzes past data and market trends to generate recommendations for future business decisions, such as optimizing inventory management, changing hiring strategies, and introducing new products to the market. These recommendations are generated using a reinforcement learning algorithm, taking into account past patterns of success and failure.

[0617] Via the terminal, the user can review these proposals and accept or modify them, in which case a recalculation is performed and a new proposal is generated.

[0618] Real-time monitoring and anomaly detection

[0619] The server monitors the company's operations in real time, using data streams to monitor sales, inventory levels, employee attendance, and more, and has the ability to immediately notify users if an abnormality is detected, allowing them to take prompt action.

[0620] Successor development support

[0621] The server creates a database of the skills and experience of potential managers and uses generative AI to propose an appropriate development plan. This may include specific skill training, setting role models, and conducting management simulations. Based on this development plan, users can provide specific training and training to the target employees.

[0622] Introducing the Emotion Engine

[0623] The server is equipped with an emotion engine that recognizes the user's emotions and adjusts management decisions and countermeasure proposals based on the user's emotions. The emotion engine analyzes the user's facial expressions, voice, and text input to evaluate their psychological state.

[0624] Tailoring suggestions based on emotions

[0625] The server adjusts the business decision suggestions based on the emotional data obtained by the emotion engine, for example, providing more concise and actionable suggestions when the user is stressed, and more detailed and comprehensive suggestions when the user is relaxed.

[0626] Optimizing notifications based on emotions

[0627] The server detects anomalies and optimizes the content and timing of important notifications according to the user's emotions. For example, if the emotion engine determines that the user is already in a high-stress state, it will delay non-urgent notifications to reduce the burden on the user.

[0628] Specific examples

[0629] For example, suppose a manufacturing company implements a system as follows:

[0630] The server automatically collects sales data, inventory data, and employee attendance data from the ERP system every morning and stores it in a cloud database.

[0631] The server then analyzes this data and calculates KPIs such as sales forecasts and inventory turnover.

[0632] After the monthly settlement, the server generates a management diagnosis report and notifies the user via the terminal, detailing the company's financial health, potential for new market entry, and so on.

[0633] Based on market trends and analysis results, the server will propose product order optimization and new product promotion strategies for the next quarter, and users can review, agree to, or modify these proposals in real time.

[0634] Daily operational status is monitored in real time, and if an abnormality is detected, for example, if inventory suddenly decreases, an alert notification is sent to the user immediately.

[0635] The emotion engine recognizes the user's emotions and makes adjustments such as delaying notifications if the user is in a high stress state.

[0636] Finally, the server proposes an appropriate development plan for potential future managers, and the user carries out training and education based on that plan.

[0637] This will enable companies to solve the problem of a lack of successors, achieve sustainable management, and make more effective management decisions and responses that take into consideration the feelings of users.

[0638] The processing flow will be explained below.

[0639] Step 1:

[0640] The server periodically collects data from various data sources of the company (ERP system, CRM system, financial system), for example, using APIs to retrieve sales data, inventory data, employee attendance data, and financial data.

[0641] Step 2:

[0642] The server stores the collected data in a cloud database, where it processes the data and converts it into an appropriate format before storing it in the database.

[0643] Step 3:

[0644] The server feeds data stored in a cloud database into machine learning algorithms to calculate important KPIs, such as sales forecasts, cost analysis, inventory turnover, and employee efficiency.

[0645] Step 4:

[0646] The server generates a management diagnosis report based on the analysis results, converts the KPIs and analysis results into text using natural language generation technology, and creates graphs and charts using visualization tools.

[0647] Step 5:

[0648] The server uploads the generated management diagnosis report to the dashboard and notifies the user, for example, by email or via a mobile app.

[0649] Step 6:

[0650] The server analyzes past data and market trends to generate proposals for future management decisions. It uses a reinforcement learning algorithm to learn past success and failure patterns and generate optimal proposals taking market trends into account.

[0651] Step 7:

[0652] The device displays the generated proposals to the user, who can then view the proposals in the form of a dashboard or report.

[0653] Step 8:

[0654] The user can review the proposed content, agree to it, or make corrections, and can request a recalculation by entering corrections.

[0655] Step 9:

[0656] The server monitors the company's operations in real time, using data streams to monitor sales, inventory levels, employee attendance, and more.

[0657] Step 10:

[0658] The server uses anomaly detection algorithms to detect and alert you to unusual data or trends that deviate from expectations, and sends you a warning via email or SMS.

[0659] Step 11:

[0660] Users can check the alert and decide on appropriate countermeasures, such as immediately placing additional orders or adjusting employee shifts, taking into account the nature of the anomaly.

[0661] Step 12:

[0662] The server creates a database of the skills and experience of potential managers, collecting, integrating, and storing skill sets, career history, and evaluation data from the company's internal personnel database.

[0663] Step 13:

[0664] Based on the databased information, the server uses generative AI to propose appropriate development plans, such as specific skill training, setting up role models, and conducting business simulations.

[0665] Step 14:

[0666] The user reviews and implements the proposed training plan, arranges training programs and workshops based on the proposal, and implements them for the management candidates.

[0667] Step 15:

[0668] The server uses an emotion engine that recognizes the user's emotions to analyze the user's facial expressions, voice, and text inputs and evaluate their psychological state.

[0669] Step 16:

[0670] The server adjusts the business decision suggestions based on the emotional data obtained by the emotion engine, for example, providing more concise and actionable suggestions when the user is stressed, and more detailed and comprehensive suggestions when the user is relaxed.

[0671] Step 17:

[0672] The server detects anomalies and optimizes the content and timing of important notifications according to the user's emotions. For example, if the emotion engine determines that the user is already in a high-stress state, it will delay non-urgent notifications to reduce the burden on the user.

[0673] Example 2

[0674] 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."

[0675] In corporate management, it is extremely important to effectively collect and analyze large amounts of data to guide appropriate management decisions. However, in conventional systems, data collection and analysis are often done manually, resulting in low efficiency. Furthermore, few systems take user emotions into account when making management decisions, which creates the risk of stress and misjudgment. Furthermore, there is a lack of support for real-time monitoring, anomaly detection, and succession planning. For these reasons, there is a need for the development of a system that provides efficient and comprehensive management support.

[0676] 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.

[0677] In this invention, the server includes means for automatically collecting management data of a company, means for analyzing the management data and calculating major KPIs, means for generating a management diagnosis report based on the analysis results, means for analyzing past data and market trends and generating proposals for future management decisions, means for monitoring the company's operating status in real time and detecting abnormalities, means for creating a database of the skills and experience of management candidate personnel and proposing training plans, and means for recognizing user emotions and adjusting the system's proposals and notification content based on the emotions. This makes it possible to efficiently manage the company's management data while supporting decision-making that takes user emotions into consideration.

[0678] "Management data" refers to various data that indicate the operating status of a company, and specifically includes sales data, inventory data, employee attendance data, financial data, and the like.

[0679] "KPI" stands for Key Performance Indicator and refers to a company's important performance indicators, such as sales forecasts, cost analysis, inventory turnover, and employee efficiency.

[0680] A "management diagnosis report" is a document that comprehensively analyzes a company's business situation and compiles information on current issues, future risks, growth opportunities, etc.

[0681] "Past data" refers to various management data that a company has collected and accumulated in the past.

[0682] "Market Trends" refers to data and information that indicates the current state and future projections of an industry or market.

[0683] "Proposal" refers to a specific action plan for a company's management decisions that the system generates based on analysis results and market trends.

[0684] "Real-time monitoring" is a method for monitoring a company's business situation in real time and responding immediately.

[0685] "Anomalies" refers to unusual data or events that deviate from normal operating conditions, such as a sudden decrease in inventory or an abnormal increase or decrease in sales.

[0686] "Anomaly detection" is a mechanism that detects abnormalities during real-time monitoring and immediately notifies you.

[0687] "Management candidates" refer to employees who have the skills and experience to potentially take on management responsibilities at a company in the future.

[0688] A "development plan" refers to a specific training and education plan designed to develop potential management personnel.

[0689] "User" refers to the people involved in the company who use this system, especially those who are the main actors in making management decisions.

[0690] "Means for recognizing emotions" refers to technology that analyzes a user's facial expressions, voice, and text data to evaluate the user's psychological state.

[0691] "Notification" refers to important information or alerts communicated to the user by the system.

[0692] The present invention is a system that automatically collects and analyzes business data of a company, proposes appropriate business decisions, and further recognizes user emotions and responds based on those emotions to improve the effectiveness of business decisions. An embodiment of the system will be described in detail below.

[0693] Data collection

[0694] The server periodically collects data from various data sources within the company. Specifically, it sends API requests to ERP systems, CRM systems, financial systems, etc. to obtain sales data, inventory data, employee attendance data, and financial data. The obtained data is stored in a cloud database (for example, AWS DynamoDB).

[0695] Data analysis and KPI calculation

[0696] The server analyzes the collected data using machine learning algorithms (e.g., TensorFlow) and calculates key KPIs, such as sales forecasts, cost analysis, inventory turnover, and employee efficiency. This allows the company's current situation to be quantitatively understood.

[0697] Generate a management diagnostic report

[0698] The server automatically generates a management diagnosis report based on the analysis results. This report includes information on the company's current situation, risk predictions, and growth opportunities. The report is visualized using a visualization tool (e.g., Tableau) to create graphs and charts that are easy for users to understand.

[0699] Proposal of business decisions

[0700] The server generates management decision proposals based on market trends and past company data. These proposals are generated using reinforcement learning algorithms (e.g., OpenAI's reinforcement learning algorithms) and include specific action plans such as optimizing inventory management or introducing new products to the market. The proposals are notified to the user via their terminal, allowing them to review the proposals and agree or modify them.

[0701] Real-time monitoring and anomaly detection

[0702] The server monitors the company's operations in real time and detects anomalies. It uses data streams (e.g., Apache Kafka) to monitor sales, inventory levels, employee attendance, etc., and immediately notifies users if an anomaly is detected. This functionality allows for prompt remedial action to be taken.

[0703] Successor development support

[0704] The server creates a database of the skills and experience of potential managers and uses generative AI (such as OpenAI's GPT-4) to propose an appropriate development plan. The development plan includes specific skill training, role model selection, and management simulations. Users can then implement specific training and training based on the plan.

[0705] Introducing the Emotion Engine

[0706] The server is equipped with an emotion engine (for example, Microsoft Azure's Emotion Analysis API) that recognizes the user's emotions. It analyzes the user's facial expressions, voice, and text input, evaluates their psychological state, and adjusts the content of suggestions and notifications.

[0707] Tailoring suggestions based on emotions

[0708] The server then adapts its suggestions based on the emotional data obtained by the emotion engine. For example, if the user is stressed, it will provide more concise and actionable suggestions, whereas if the user is relaxed, it will provide more detailed and comprehensive suggestions.

[0709] Optimizing notifications based on emotions

[0710] The server optimizes the content and timing of anomaly detection and important notifications based on emotional data. If stress levels are judged to be high, non-urgent notifications are delayed to reduce the burden on users.

[0711] Specific examples

[0712] For example, in a manufacturing company, the system is implemented as follows:

[0713] 1. The server automatically collects sales data, inventory data, and employee attendance data from the ERP system every morning and stores them in a cloud database.

[0714] 2. The server analyzes this data and calculates KPIs such as sales forecasts and inventory turnover.

[0715] 3. After the monthly settlement, the server generates a management diagnosis report and notifies the user via the terminal, detailing the company's financial health and potential for new market entry.

[0716] 4. Based on market trends and analysis results, the server will propose product order optimization and new product promotion strategies for the next quarter. The user can review these proposals in real time and agree or modify them.

[0717] 5. Daily operational status is monitored in real time, and if an abnormality is detected, for example, if inventory suddenly decreases, an alert notification is sent to the user immediately.

[0718] 6. The emotion engine recognizes the user's emotions and makes adjustments such as delaying notifications if the user is in a high-stress state.

[0719] 7. Finally, the server proposes an appropriate development plan for potential future managers, and the user carries out training and education based on that plan.

[0720] This will enable companies to solve the problem of a lack of successors, achieve sustainable management, and make more effective management decisions and responses that take into consideration the feelings of users.

[0721] Prompt Sentence Examples

[0722] "Please create a sales forecast for next month based on the sales data and compile the analysis results into a report. Also, please generate improvement suggestions for inventory management based on the current inventory levels."

[0723] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0724] Step 1:

[0725] The server automatically collects data from the company's data sources (ERP system, CRM system, financial system). The server sends API requests to each data source to obtain sales data, inventory data, employee attendance data, and financial data. The obtained data is stored in a cloud database (e.g., AWS DynamoDB).

[0726] Input: API response from the data source

[0727] Data processing: Converts API response data into a format and stores it in a cloud database

[0728] Output: Management data stored in a cloud database

[0729] Step 2:

[0730] The server retrieves the stored management data from the cloud database and analyzes it using machine learning algorithms (e.g., TensorFlow), calculating KPIs such as sales forecasts, cost analysis, inventory turnover, and employee efficiency.

[0731] Input: Management data from cloud database

[0732] Data calculation: Applying machine learning algorithms to calculate KPIs

[0733] Output: Calculated KPIs

[0734] Step 3:

[0735] The server generates a management diagnostic report based on the analysis results. This report includes information on the company's current situation, risk predictions, and growth opportunities. The server uses a visualization tool (e.g., Tableau) to create graphs and charts and display the report in an easy-to-understand manner.

[0736] Input: Analysis results and KPIs

[0737] Data processing: Visualization tools transform analysis results into graphs and charts

[0738] Output: Management diagnosis report

[0739] Step 4:

[0740] The server analyzes historical data and market trends to generate recommendations for future business decisions. These recommendations are generated using a reinforcement learning algorithm and include specific action plans, such as optimizing inventory management or introducing new products to the market.

[0741] Input: Historical data, market trends

[0742] Data computation: Analyzes data using reinforcement learning algorithms and generates recommendations

[0743] Output: Proposal of business decision

[0744] Step 5:

[0745] Through the terminal, the user can review the proposed business decision and agree or modify it. If the user modifies it, the server will recalculate and generate a new proposal.

[0746] Input: User feedback

[0747] Data processing: Reflect feedback and reanalyze

[0748] Output: Corrections or new suggestions

[0749] Step 6:

[0750] The server performs real-time monitoring to monitor the company's operations, using data streams (e.g., Apache Kafka) to monitor sales, inventory levels, employee attendance, etc., and immediately notifies users if an anomaly is detected.

[0751] Input: Real-time data stream

[0752] Data calculation: Runs anomaly detection algorithms to identify anomalies

[0753] Output: Anomaly detection notification

[0754] Step 7:

[0755] The server creates a database of the skills and experience of potential managers and uses generative AI (such as OpenAI's GPT-4) to propose an appropriate training plan, which includes specific skill training, role modeling, and management simulations.

[0756] Input: Skill data and experience of managerial candidates

[0757] Data calculation: Generative AI model is used to generate training plans

[0758] Output: Development plan

[0759] Step 8:

[0760] The server uses an emotion engine (e.g., Microsoft Azure's Emotion Analysis API) to recognize the user's emotions. The server analyzes the user's facial expressions, voice, and text input to evaluate their psychological state.

[0761] Input: User's facial expressions, voice, and text data

[0762] Data Analysis: Analyze sentiment data using the sentiment engine

[0763] Output: Emotion analysis results

[0764] Step 9:

[0765] The server adjusts the management decision suggestions based on the emotional data obtained by the emotion engine. For example, if the user is feeling stressed, it provides simple and easy-to-implement suggestions.

[0766] Input: Sentiment analysis results

[0767] Data processing: Adjust proposal content based on emotion data

[0768] Output: Adjusted proposal

[0769] Step 10:

[0770] The server detects anomalies and optimizes the content and timing of important notifications based on the user's emotions. If the server determines that the user is under high stress, it will delay non-urgent notifications to reduce the burden on the user.

[0771] Input: Anomaly detection data, emotion analysis results

[0772] Data processing: Adjust notification content and timing

[0773] Output: Optimized notification

[0774] (Application example 2)

[0775] 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."

[0776] Conventional management data analysis systems were equipped with functions to monitor a company's operational status, detect abnormalities, and propose management decisions, but they lacked the ability to recognize users' emotions and adjust responses based on them. As a result, they lacked consideration for the psychological state of operators, such as sending important notifications when the operator was in a high-stress state. This often made it difficult for users to respond appropriately, which led to problems with the effectiveness of management decisions.

[0777] 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 automatically collecting corporate management data, means for analyzing the management data to calculate key KPIs, means for generating a management diagnosis report based on the analysis results, means for analyzing past data and market trends to generate proposals for future management decisions, means for monitoring the corporate management situation in real time and detecting abnormalities, means for creating a database of the skills and experience of management candidate personnel and proposing training plans, means for collecting and analyzing various types of data within the factory in real time, means for recognizing operator emotions and adjusting proposals based on those emotions, and means for optimizing the timing and content of notifications based on emotions. This enables appropriate management decisions to be made based on the corporate management situation and enables responses that take into account the psychological state of the operators.

[0778] "Corporate management data" refers to all data generated and acquired by a company in the course of its daily business operations, including sales data, inventory data, employee attendance data, and financial data.

[0779] "Means of collection" refers to the methods and technologies used to obtain target data from various data sources and incorporate it into the system.

[0780] "Means of analysis" refers to techniques and methods for obtaining specific insights by performing statistical analysis, machine learning, data mining, etc. based on collected data.

[0781] "Key KPIs" refer to important indicators for evaluating a company's business performance, including sales forecasts, inventory turnover, and employee efficiency.

[0782] A "management diagnostic report" is a document that includes information on a company's operating status, current situation analysis, risk predictions, and growth opportunities, and is presented using visualization tools such as graphs and charts.

[0783] "Means for generating proposals" refers to technologies and methods that analyze past data and market trends and propose specific actions for future management decisions.

[0784] "Monitoring means" refers to technologies and methods for monitoring and tracking a company's operations in real time and detecting abnormalities or fluctuations.

[0785] "Means for detecting anomalies" refers to methods and technologies for detecting deviations from normal operating patterns or abnormal behavior in real time.

[0786] A "development plan" refers to a plan for providing appropriate training and education based on the skills and experience of potential management personnel.

[0787] "Various data within the factory" refers to production data, inventory data, quality data, machine operation data, etc. generated in the manufacturing industry.

[0788] "Means for recognizing emotions" refers to technologies and methods for analyzing a user's facial expressions, voice, text input, etc. to assess their psychological state.

[0789] "Means for optimizing the timing and content of notifications" refers to technologies and methods for notifying users at appropriate times and in appropriate ways based on their emotional data.

[0790] The present invention is a system that automatically collects and analyzes business data of a company and proposes appropriate business decisions. Furthermore, it recognizes the user's emotions and responds based on those emotions to improve the effectiveness of business decisions. An embodiment of the system is described below in detail.

[0791] Data collection

[0792] The server periodically collects data from various data sources within the company (ERP system, CRM system, financial system, etc.) For example, it uses APIs to retrieve sales data, inventory data, employee attendance data, and financial data. This data is then stored in a cloud database.

[0793] Data analysis and KPI calculation

[0794] The server analyzes the collected data using machine learning algorithms to calculate important KPIs, such as sales forecasts, cost analysis, inventory turnover, and employee efficiency. This process can be performed by combining multiple analytical models to improve prediction accuracy.

[0795] Generate a management diagnostic report

[0796] Based on the analysis results, the server automatically generates a management diagnosis report, which includes an analysis of the company's current situation, risk predictions, and information on growth opportunities. The report is presented in easy-to-understand graphs and charts using visualization tools.

[0797] Proposal of business decisions

[0798] The server analyzes past data and market trends to generate proposals for future management decisions. For example, it makes proposals for optimizing inventory management, changing recruitment strategies, and entering new product markets. These proposals are generated using a reinforcement learning algorithm, taking into account past patterns of success and failure. Users can review these proposals via their devices and agree or modify them. If the user makes modifications, a recalculation is performed and a new proposal is generated.

[0799] Real-time monitoring and anomaly detection

[0800] The server monitors the company's operations in real time, using data streams to monitor sales, inventory levels, employee attendance, and more, and has the ability to immediately notify users if an abnormality is detected, allowing them to take prompt action.

[0801] Successor development support

[0802] The server creates a database of the skills and experience of potential managers and uses generative AI to propose an appropriate development plan. This may include specific skill training, setting role models, and conducting management simulations. Based on this development plan, users can provide specific training and training to the target employees.

[0803] Introducing the Emotion Engine

[0804] The server is equipped with an emotion engine that recognizes the user's emotions and adjusts management decisions and countermeasure proposals based on the user's emotions. The emotion engine analyzes the user's facial expressions, voice, and text input to evaluate their psychological state.

[0805] Tailoring suggestions based on emotions

[0806] The server adjusts the business decision suggestions based on the emotional data obtained by the emotion engine, for example, providing more concise and actionable suggestions when the user is stressed, and more detailed and comprehensive suggestions when the user is relaxed.

[0807] Optimizing notifications based on emotions

[0808] The server detects anomalies and optimizes the content and timing of important notifications according to the user's emotions. For example, if the emotion engine determines that the user is already in a high-stress state, it will delay non-urgent notifications to reduce the burden on the user.

[0809] Specific examples

[0810] For example, suppose a manufacturing company implements a system as follows:

[0811] The server automatically collects sales data, inventory data, and employee attendance data from the ERP system every morning and stores it in a cloud database.

[0812] The server then analyzes this data and calculates KPIs such as sales forecasts and inventory turnover.

[0813] After the monthly settlement, the server generates a management diagnosis report and notifies the user via the terminal, detailing the company's financial health, potential for new market entry, and so on.

[0814] Based on market trends and analysis results, the server will propose product order optimization and new product promotion strategies for the next quarter, and users can review, agree to, or modify these proposals in real time.

[0815] Daily operational status is monitored in real time, and if an abnormality is detected, for example, if inventory suddenly decreases, an alert notification is sent to the user immediately.

[0816] The emotion engine recognizes the user's emotions and makes adjustments such as delaying notifications if the user is in a high stress state.

[0817] Finally, the server proposes an appropriate development plan for potential future managers, and the user implements training based on that plan. This allows companies to solve the problem of a lack of successors, achieve sustainable management, and make more effective management decisions and responses that take users' feelings into consideration.

[0818] Prompt Sentence Examples

[0819] Below is an example of a prompt sentence to input to the generative AI model.

[0820] Analyze the following data to recognize user emotions:

[0821] Facial expression image (e.g., a user's face image taken with a camera)

[0822] Audio data (e.g., user words)

[0823] Text input (e.g., user-entered comments)

[0824] As a result, if the user is exhibiting an emotion (e.g., stress, relaxation, sadness, joy), identify it.

[0825] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0826] Step 1:

[0827] The server periodically collects management data from the company's ERP system, CRM system, financial system, etc. The inputs are sales data, inventory data, employee attendance data, and financial data obtained from each data source. The server obtains this data using an API and stores it in a cloud database. The output is this data stored in the database.

[0828] Step 2:

[0829] The server analyzes the collected data and calculates key KPIs. The input is management data stored in a cloud database. The server uses machine learning algorithms to calculate KPIs such as sales forecasts, cost analysis, inventory turnover, and employee efficiency. The output is the calculated KPIs.

[0830] Step 3:

[0831] The server generates a management diagnosis report based on the analysis results. The input is the calculated KPIs. The server uses visualization tools (e.g., Matplotlib, Seaborn) to generate the management diagnosis report in graph and chart format and saves it in a cloud database. The output is the generated management diagnosis report.

[0832] Step 4:

[0833] The server analyzes past data and market trends to generate proposals for future management decisions. The inputs are past data, market trend data, and calculated KPIs. The server uses a reinforcement learning algorithm to make proposals such as optimizing inventory management, changing recruitment strategies, and entering new product markets. The output is the generated proposals for management decisions.

[0834] Step 5:

[0835] The terminal displays the generated business decision proposals to the user. The input is the business decision proposals sent from the server. The user can review these proposals and agree or modify them. The output is the user's agreement or modified information.

[0836] Step 6:

[0837] The server monitors the company's operations in real time and detects anomalies. The input is a stream of the company's daily operations data. The server analyzes the data stream and records any anomalies it detects. The output is information about the detected anomalies.

[0838] Step 7:

[0839] The server immediately notifies the user if an anomaly is detected. The input is the detected anomaly information. The server sends this information to the terminal so the user can take appropriate countermeasures. The output is the anomaly notification sent to the user.

[0840] Step 8:

[0841] The server creates a database of the skills and experience of management candidates and uses a generative AI model to propose an appropriate training plan. The input is data on the skills and experience of management candidates. The server analyzes this data and generates a training plan. The output is the generated training plan.

[0842] Step 9:

[0843] The server uses an emotion engine that recognizes the user's emotions to adjust management decisions and proposed countermeasures based on the emotions. The inputs are images of the user's facial expressions, voice data, and text input. The server analyzes this data using an emotion engine (e.g., OpenCV, IBM Watson) to recognize the user's emotions. The output is the recognized emotion data.

[0844] Step 10:

[0845] The server optimizes the content of the generated suggestions and the timing of notifications according to the user's emotions. The inputs are the recognized emotion data and the generated business decision suggestions. The server adjusts the suggestions based on the user's psychological state and changes the timing of notifications as needed. The output is the adjusted suggestions and optimized notifications.

[0846] 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.

[0847] 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.

[0848] 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.

[0849] [Third embodiment]

[0850] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0851] 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.

[0852] 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).

[0853] 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.

[0854] 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.

[0855] 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).

[0856] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0857] 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.

[0858] 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.

[0859] 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.

[0860] 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.

[0861] 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."

[0862] The present invention is a system that automatically collects and analyzes business data of a company, proposes appropriate business decisions, and also supports the development of successors. Specific embodiments of the present invention will be described below.

[0863] Data collection

[0864] The server periodically collects data from various data sources within the company (ERP system, CRM system, financial system, etc.) For example, it uses APIs to retrieve sales data, inventory data, employee attendance data, and financial data. This data is then stored in a cloud database.

[0865] Data analysis and KPI calculation

[0866] The server analyzes the collected data using machine learning algorithms to calculate important KPIs, such as sales forecasts, cost analysis, inventory turnover, and employee efficiency. This process can be performed by combining multiple analytical models to improve prediction accuracy.

[0867] Generate a management diagnostic report

[0868] Based on the analysis results, the server automatically generates a management diagnosis report, which includes an analysis of the company's current situation, risk predictions, and information on growth opportunities. The report is presented in easy-to-understand graphs and charts using visualization tools.

[0869] Proposal of business decisions

[0870] The server analyzes past data and market trends to generate recommendations for future business decisions, such as optimizing inventory management, changing hiring strategies, and introducing new products to the market. These recommendations are generated using a reinforcement learning algorithm, taking into account past patterns of success and failure.

[0871] Via the terminal, the user can review these proposals and accept or modify them, in which case a recalculation is performed and a new proposal is generated.

[0872] Real-time monitoring and anomaly detection

[0873] The server monitors the company's operations in real time, using data streams to monitor sales, inventory levels, employee attendance, and more, and has the ability to immediately notify users if an abnormality is detected, allowing them to take prompt action.

[0874] Successor development support

[0875] The server creates a database of the skills and experience of potential managers and uses generative AI to propose an appropriate development plan. This may include specific skill training, setting role models, and conducting management simulations. Based on this development plan, users can provide specific training and training to the target employees.

[0876] Specific examples

[0877] For example, suppose a manufacturing company implements a system as follows:

[0878] The server automatically collects sales data, inventory data, and employee attendance data from the ERP system every morning and stores it in a cloud database.

[0879] The server then analyzes this data and calculates KPIs such as sales forecasts and inventory turnover.

[0880] After the monthly settlement, the server generates a management diagnosis report and notifies the user via the terminal, detailing the company's financial health, potential for new market entry, and so on.

[0881] Based on market trends and analysis results, the server will propose product order optimization and new product promotion strategies for the next quarter, and users can review, agree to, or modify these proposals in real time.

[0882] Daily operational status is monitored in real time, and if an abnormality is detected, for example, if inventory suddenly decreases, an alert notification is sent to the user immediately.

[0883] Finally, the server proposes an appropriate development plan for potential future managers, and the user carries out training and education based on that plan.

[0884] This will enable companies to solve the problem of a lack of successors and achieve sustainable management.

[0885] The processing flow will be explained below.

[0886] Step 1:

[0887] The server periodically collects data from various corporate data sources (ERP system, CRM system, financial system), for example using APIs to retrieve sales data, inventory data, employee attendance data, and financial data.

[0888] Step 2:

[0889] The server stores the collected data in a cloud database, where it processes the data and converts it into an appropriate format before storing it in the database.

[0890] Step 3:

[0891] The server feeds data stored in a cloud database into machine learning algorithms to calculate important KPIs, such as sales forecasts, cost analysis, inventory turnover, and employee efficiency.

[0892] Step 4:

[0893] The server generates a management diagnosis report based on the analysis results, converts the KPIs and analysis results into text using natural language generation technology, and creates graphs and charts using visualization tools.

[0894] Step 5:

[0895] The server uploads the generated management diagnosis report to the dashboard and notifies the user, for example, by email or via a mobile app.

[0896] Step 6:

[0897] The server analyzes past data and market trends to generate proposals for future management decisions. It uses a reinforcement learning algorithm to learn past success and failure patterns and generate optimal proposals taking market trends into account.

[0898] Step 7:

[0899] The device displays the generated proposals to the user, who can then view the proposals in the form of a dashboard or report.

[0900] Step 8:

[0901] The user can review the proposed content, agree to it, or make corrections, and can request a recalculation by entering corrections.

[0902] Step 9:

[0903] The server monitors the company's operations in real time, using data streams to monitor sales, inventory levels, employee attendance, and more.

[0904] Step 10:

[0905] The server uses anomaly detection algorithms to detect and alert you to unusual data or trends that deviate from expectations, and sends you a warning via email or SMS.

[0906] Step 11:

[0907] Users can check the alert and decide on appropriate countermeasures, such as immediately placing additional orders or adjusting employee shifts, taking into account the nature of the anomaly.

[0908] Step 12:

[0909] The server creates a database of the skills and experience of potential managers, collecting, integrating, and storing skill sets, career history, and evaluation data from the company's internal personnel database.

[0910] Step 13:

[0911] Based on the databased information, the server uses generative AI to propose appropriate development plans, such as specific skill training, setting up role models, and conducting business simulations.

[0912] Step 14:

[0913] The user reviews and implements the proposed training plan, arranges training programs and workshops based on the proposal, and implements them for the management candidates.

[0914] Example 1

[0915] 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."

[0916] Corporate management requires the efficient collection of data from each department, the calculation of key management indicators, and support for management decisions. However, modern companies must handle complex systems and vast amounts of data, and performing these processes manually is labor-intensive and carries a high risk of error. Important issues remain, such as real-time monitoring, anomaly detection, and the development of management candidates. To address these issues, a consistent automation system and high-precision analysis technology are required.

[0917] 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.

[0918] In this invention, the server includes means for automatically collecting corporate management data, means for analyzing the management data using a machine learning algorithm and calculating key KPIs, means for generating a management diagnosis report using a visualization tool based on the analysis results, means for analyzing past data and market trends and generating proposals for future management decisions using a reinforcement learning algorithm, means for monitoring the corporate operating status in real time using data stream technology and detecting anomalies, and means for using a generative AI model to create a database of the skills and experience of management candidate personnel and propose a training plan. This enables efficient collection and analysis of corporate data, timely and accurate support for management decisions, and automatic proposals for training plans for management candidate personnel.

[0919] "Corporate management data" is a general term for information such as financial data, sales data, inventory data, and employee attendance data that is collected and managed by a company on a daily basis.

[0920] "Automatic collection means" refers to software and hardware components that allow the system to obtain data from various data sources without manual intervention.

[0921] A "machine learning algorithm" is an algorithm that uses technology to have a computer analyze massive amounts of data, recognize patterns and trends in the data, and learn from them.

[0922] "KPI" is an abbreviation for Key Performance Indicator, and refers to a company's key performance indicators, including sales forecasts, cost analysis, inventory turnover, and employee efficiency.

[0923] A "visualization tool" is a tool that displays data in a visual format, such as a graph or chart, making it easier to understand and analyze.

[0924] A "reinforcement learning algorithm" is a machine learning method that uses trial and error to find optimal behavior. It analyzes past data and market trends and automatically improves future behavior.

[0925] "Data stream technology" refers to technology for continuously collecting data in real time and processing it immediately. Apache Kafka is a representative example.

[0926] "Anomaly detection means" refers to software and hardware components that monitor real-time data and detect unexpected events or abnormal values.

[0927] A "generative AI model" is an AI model that uses natural language processing and machine learning techniques and is used to automatically generate new proposals and reports from data.

[0928] "Development plan" means a specific education and training plan to improve the skills and experience of potential management personnel.

[0929] The present invention is a system that automatically collects and analyzes business data of a company, proposes appropriate business decisions, and also supports the development of successors. Specific embodiments of the present invention will be described below.

[0930] Data collection

[0931] The server periodically collects data from various data sources within the company (ERP system, CRM system, financial system, etc.). For example, it uses APIs to retrieve sales data, inventory data, employee attendance data, and financial data. This data is stored in a cloud database such as Amazon RDS or Google Cloud Spanner. Specifically, the server calls functions such as "get_sales_data()" and "get_inventory_data()" and stores the results in the database using the "store_in_database()" function.

[0932] Data analysis and KPI calculation

[0933] The server analyzes the collected data using machine learning algorithms (e.g., TensorFlow or Scikit-learn) and calculates important KPIs. For analysis, the data is preprocessed using the "preprocess_data()" function, and then KPIs are calculated using the "calculate_kpis()" function. Specific KPIs include sales forecasts, cost analysis, inventory turnover, and employee efficiency. This allows for an accurate understanding of the current situation of the company.

[0934] Generate a management diagnostic report

[0935] Based on the analysis results, the server automatically generates a management diagnosis report. This report includes information on the company's current situation, risk predictions, and growth opportunities, and is presented in graphs and charts using a visualization tool (e.g., Tableau or Power BI). Specifically, the report is generated by the "generate_report()" function, and then notified to the user via the terminal by the "send_report_to_user()" function.

[0936] Proposal of business decisions

[0937] The server analyzes historical data and market trends and generates suggestions for future business decisions using reinforcement learning algorithms (e.g., Deep Q-Learning). These suggestions may include optimizing inventory management, changing recruitment strategies, or launching new products into the market. Suggestions are created using the "generate_suggestions()" function and displayed on the terminal via the "display_suggestions()" function. Users can review and modify the suggestions using the "approve_suggestion()" or "modify_suggestion()" functions.

[0938] Real-time monitoring and anomaly detection

[0939] The server uses data stream technologies such as Apache Kafka to monitor the company's operational status in real time. The server monitors sales, inventory levels, employee attendance, etc., and detects anomalies using the "detect_anomalies()" function. When an anomaly is detected, the user is immediately notified via the "send_alert()" function, allowing the user to take prompt action.

[0940] Successor development support

[0941] The server uses a generative AI model (e.g., GPT-4) to create a database of the skills and experience of potential managers, and evaluates them using the "analyze_candidate()" function. It then proposes an appropriate development plan using the "generate_development_plan()" function, and sends the plan to the user using the "send_training_plan()" function. This development plan includes specific skill training, role model selection, and management simulations.

[0942] Specific examples

[0943] For example, at a manufacturing company, the server uses the ERP system's API to collect sales data, inventory data, and employee attendance data every morning and stores it in Amazon RDS. The collected data is then analyzed using TensorFlow, preprocessed using the "preprocess_data()" function, and KPIs are calculated using the "calculate_kpis()" function. After monthly settlement, a report is generated using the "generate_report()" function and notified to the user via a terminal using the "send_report_to_user()" function. Furthermore, based on the results of analyzing past data and market trends, the "generate_suggestions()" function makes suggestions for the next quarter. The user can then review and modify the suggestions using the "approve_suggestion()" or "modify_suggestion()" functions. Daily operational status is monitored in real time using the "monitor_operations()" function, and if an anomaly is detected using the "detect_anomalies()" function, the user is immediately notified using the "send_alert()" function. Finally, the skills of potential future managers are evaluated using the "analyze_candidate()" function, a training plan is created using the "generate_development_plan()" function, and the plan is notified to the user using the "send_training_plan()" function.

[0944] Examples of prompts include "Propose a market entry strategy for a new product" or "Generate inventory management optimization recommendations for the next quarter."

[0945] This will enable companies to automate efficient data collection, secure storage, highly accurate analysis, rapid business decision-making, and successor training, all of which will enable them to achieve sustainable management.

[0946] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0947] Step 1: Data collection

[0948] The server collects data from various data sources within the company. Specifically, it uses APIs to retrieve sales data, inventory data, employee attendance data, financial data, etc. from ERP systems, CRM systems, and financial systems. To do this, the server uses authentication information to make API calls and uses functions such as "get_sales_data()" and "get_inventory_data()." The input is the API endpoint of each data source, and the output is the retrieved data, which is then stored in a cloud database (e.g., Amazon RDS or Google Cloud Spanner) using the "store_in_database()" function.

[0949] Step 2: Data Preprocessing

[0950] The server preprocesses the collected data. Specifically, it cleans the data, handles missing values, and standardizes it using the "preprocess_data()" function. The input is the raw data stored in the cloud database, and the output is data formatted in an analyzable format. This creates a dataset suitable for subsequent analysis.

[0951] Step 3: Calculate KPIs

[0952] The server uses the preprocessed data to calculate key KPIs. It uses the "calculate_kpis()" function to apply machine learning algorithms (e.g., TensorFlow, Scikit-learn) to calculate KPIs such as sales forecasts, cost analysis, inventory turnover, and employee efficiency. The input is the preprocessed data, and the output is the numerical values ​​of various KPIs. This provides a concrete representation of the company's important indicators.

[0953] Step 4: Generate a business diagnostic report

[0954] The server creates a management diagnosis report based on the calculated KPIs. It uses the "generate_report()" function and then uses a visualization tool (e.g., Tableau, Power BI) to display the results in graphs and charts. The input is the calculated KPIs and analysis results, and the output is a visualized management diagnosis report. This report is sent to the terminal via the "send_report_to_user()" function and notified to the user.

[0955] Step 5: Propose business decisions

[0956] The server analyzes past data and market trends and uses a reinforcement learning algorithm (e.g., Deep Q-Learning) to generate suggestions for management decisions. Specific suggestions such as optimizing inventory management, changing recruitment strategies, and launching new products into the market are created using the 'generate_suggestions()' function. The input is market trend data and analysis results, and the output is a specific proposal. The user can review the suggestions on their device using the 'display_suggestions()' function, and approve or modify the suggestions using the 'approve_suggestion()' or 'modify_suggestion()' functions.

[0957] Step 6: Real-time monitoring and anomaly detection

[0958] The server uses data streaming technologies such as Apache Kafka to monitor the company's operational status in real time. It monitors data using the 'monitor_operations()' function and detects anomalies using the 'detect_anomalies()' function. The input is real-time operational data, and the output is the detected anomalous data. If an anomaly is found, the user is immediately notified using the 'send_alert()' function.

[0959] Step 7: Support for developing successors

[0960] The server uses a generative AI model (e.g., GPT-4) to create a database of the skills and experience of potential management candidates and proposes a development plan. It evaluates the skills of the candidates using the "analyze_candidate()" function and creates a development plan using the "generate_development_plan()" function. The input is the candidate's skill data and experience data, and the output is a specific development plan. This plan is sent to the user using the "send_training_plan()" function, and specific training and development are carried out.

[0961] (Application example 1)

[0962] 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."

[0963] Conventional corporate management support systems have difficulty automating the regular collection and analysis of management data, resulting in problems such as reduced management efficiency. They also lack the functionality to grasp new market trends and corporate operational status in real time and quickly propose appropriate management decisions. In particular, on industrial production lines, information utilization to improve production efficiency and quality control is insufficient, and rapid response is required when an abnormality occurs. Furthermore, there is also insufficient training for potential successors to management positions, which poses a risk to the long-term sustainability of the company.

[0964] 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.

[0965] In this invention, the server includes the following means: means for automatically collecting corporate management data; means for analyzing the management data to calculate key KPIs; means for generating a management diagnosis report based on the analysis results; means for analyzing past data and market trends to generate proposals for future management decisions; means for monitoring the corporate operations in real time and detecting anomalies; means for creating a database of the skills and experience of management candidates and proposing training plans; means for automatically collecting and saving various sensor data from the factory; means for calculating KPIs for production efficiency and quality control based on the collected data; means for generating a management diagnosis report reporting problems and areas for improvement in the production line; means for optimizing production plans, equipment maintenance schedules, and proposing improvements to quality control; and means for monitoring the production line in real time, detecting anomalies, and notifying the user. This enables efficient and automatic collection and analysis of corporate management data, supporting prompt and appropriate management decisions. It also improves production efficiency and quality control on the production line, allowing for prompt countermeasures to be taken when anomalies occur. Furthermore, data-based skill development for successors ensures the long-term sustainability of the company.

[0966] "Management data" refers to information about a company's business activities, financial status, personnel situation, inventory status, etc.

[0967] "KPI" is an abbreviation for Key Performance Indicator, a specific indicator that shows the degree to which a company has achieved its goals.

[0968] A "management diagnosis report" is a report that summarizes the results of an analysis, including the current situation and problems of a company, and suggestions for improvement.

[0969] A "proposal" is a plan of action for a company's management based on the analysis results and market trends.

[0970] "Real-time monitoring" is a system that constantly monitors a company's operational status and immediately detects any abnormalities that occur.

[0971] "Anomaly detection" refers to the detection of deviations from normal operating conditions.

[0972] "Database of skills and experience" means storing and managing the abilities and past experience of potential managers in a digital format.

[0973] A "development plan" is a specific training or education program designed to improve the skills or careers of specific personnel.

[0974] "Sensor data" refers to various measurement data acquired from factory equipment and production lines.

[0975] "Production efficiency" is an indicator that measures the efficiency of resource utilization in production activities.

[0976] "Quality control" refers to the management activities and methods used to ensure the quality of products and services.

[0977] "Abnormality notification" is an alert function that immediately notifies relevant parties of detected abnormalities.

[0978] The present invention is a system that automatically collects and analyzes business data of a company, proposes appropriate business decisions, and also supports the development of successors. Specific embodiments of the present invention will be described below.

[0979] Data collection

[0980] The server periodically collects data from various data sources within the company (ERP system, CRM system, financial system, etc.) For example, it uses APIs to retrieve sales data, inventory data, employee attendance data, and financial data. This data is then stored in a cloud database.

[0981] Data analysis and KPI calculation

[0982] The server analyzes the collected data using machine learning algorithms (e.g., TensorFlow, scikit-learn) to calculate important KPIs, such as sales forecasts, cost analysis, inventory turnover, and employee efficiency. This process combines multiple analytical models to improve prediction accuracy.

[0983] Generate a management diagnostic report

[0984] Based on the analysis results, the server automatically generates a management diagnosis report, which includes information on the company's current situation, risk predictions, and growth opportunities. The report is presented in easy-to-understand graphs and charts using data visualization tools (e.g., Matplotlib, D3.js).

[0985] Proposal of business decisions

[0986] The server analyzes past data and market trends to generate proposals for future management decisions. For example, it may suggest optimizing inventory management, changing hiring strategies, or launching new products into the market. These proposals are generated using a reinforcement learning algorithm (e.g., OpenAI Gym) that takes into account past patterns of success and failure. Users can review these proposals via their devices and agree or modify them. If the user makes modifications, a recalculation is performed and a new proposal is generated.

[0987] Real-time monitoring and anomaly detection

[0988] The server monitors the company's operations in real time, using data streams to monitor sales, inventory levels, employee attendance, and more, and has the ability to immediately notify users if an abnormality is detected, allowing them to take prompt action.

[0989] Successor development support

[0990] The server creates a database of the skills and experience of potential managers and uses a generative AI model (e.g., GPT-4) to propose an appropriate development plan. This may include specific skill training, setting role models, and conducting management simulations. Based on this development plan, users can provide specific training and training to the target employees.

[0991] Specific examples

[0992] For example, suppose a manufacturing company implements a system as follows:

[0993] The server automatically collects sales data, inventory data, and employee attendance data from the ERP system every morning and stores it in a cloud database.

[0994] The server then analyzes this data and calculates KPIs such as sales forecasts and inventory turnover.

[0995] After the monthly settlement, the server generates a management diagnosis report and notifies the user via the terminal, detailing the company's financial health, potential for new market entry, and so on.

[0996] Based on market trends and analysis results, the server will propose product order optimization and new product promotion strategies for the next quarter, and users can review, agree to, or modify these proposals in real time.

[0997] Daily operational status is monitored in real time, and if an abnormality is detected, for example, if inventory suddenly decreases, an alert notification is sent to the user immediately.

[0998] Finally, the server proposes an appropriate development plan for potential future managers, and the user carries out training and education based on that plan.

[0999] This will enable companies to solve the problem of a lack of successors and achieve sustainable management.

[1000] Example prompts for generative AI models

[1001] "Analyze the operating rate and defect rate of production line 1 in the factory last month, and if the defect rate has increased, please suggest improvement measures."

[1002] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1003] Step 1:

[1004] The server periodically collects data from various data sources within the company (ERP system, CRM system, financial system, etc.). The hardware used includes a server and a cloud database that retrieves data via API. Input data includes sales data, inventory data, employee attendance data, and financial data. The server collects this data and gets an output that is stored in the cloud database.

[1005] Step 2:

[1006] The server analyzes the collected data using machine learning algorithms (e.g., TensorFlow, scikit-learn) and calculates key KPIs. Input data includes sales data and inventory data stored in a cloud database. Data processing involves filling in missing values ​​and normalizing the data to convert it into a format suitable for machine learning algorithms. Output includes KPIs such as sales forecasts, cost analysis, inventory turnover, and employee efficiency.

[1007] Step 3:

[1008] The server generates a management diagnosis report based on the analysis results. The input data includes calculated KPIs and other analysis results. The server uses data visualization tools (e.g., Matplotlib, D3.js) to visualize the analysis results as graphs and charts and compile them into a report format. The output is an easy-to-read management diagnosis report.

[1009] Step 4:

[1010] The server analyzes past data and market trends to generate proposals for future management decisions. Input data includes past sales data and market trend data. The server uses a reinforcement learning algorithm (e.g., OpenAI Gym) to analyze this data and generate proposals such as optimizing inventory management, changing recruitment strategies, and introducing new products to the market. The output is a concrete proposal for management decisions.

[1011] Step 5:

[1012] The server displays the generated proposals to the user via the terminal. The input data are the generated proposals. The user checks these proposals and accepts or modifies them. If any modifications are made, the server recalculates and generates a new proposal. The output is the user's acceptance or modification.

[1013] Step 6:

[1014] The server monitors the company's operations in real time. Input data includes sales data, inventory levels, and employee attendance data, all of which are acquired in real time. The server uses data stream processing (e.g., Apache Kafka) to monitor this data and immediately notifies the user if an anomaly is detected. The output is the real-time monitoring results and anomaly notification.

[1015] Step 7:

[1016] The server creates a database of the skills and experience of potential management candidates and uses a generative AI model (e.g., GPT-4) to propose an appropriate training plan. Input data includes the skills and past experience of the personnel. The server analyzes this data and generates an optimal training plan. A specific training plan is proposed as the output.

[1017] Example prompts for generative AI models

[1018] "Analyze the operating rate and defect rate of production line 1 in the factory last month, and if the defect rate has increased, please suggest improvement measures."

[1019] 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.

[1020] The present invention is a system that automatically collects and analyzes business data of a company, proposes appropriate business decisions, and further recognizes user emotions and responds based on those emotions to improve the effectiveness of business decisions. An embodiment of the system will be described in detail below.

[1021] Data collection

[1022] The server periodically collects data from various data sources within the company (ERP system, CRM system, financial system, etc.) For example, it uses APIs to retrieve sales data, inventory data, employee attendance data, and financial data. This data is then stored in a cloud database.

[1023] Data analysis and KPI calculation

[1024] The server analyzes the collected data using machine learning algorithms to calculate important KPIs, such as sales forecasts, cost analysis, inventory turnover, and employee efficiency. This process can be performed by combining multiple analytical models to improve prediction accuracy.

[1025] Generate a management diagnostic report

[1026] Based on the analysis results, the server automatically generates a management diagnosis report, which includes an analysis of the company's current situation, risk predictions, and information on growth opportunities. The report is presented in easy-to-understand graphs and charts using visualization tools.

[1027] Proposal of business decisions

[1028] The server analyzes past data and market trends to generate recommendations for future business decisions, such as optimizing inventory management, changing hiring strategies, and introducing new products to the market. These recommendations are generated using a reinforcement learning algorithm, taking into account past patterns of success and failure.

[1029] Via the terminal, the user can review these proposals and accept or modify them, in which case a recalculation is performed and a new proposal is generated.

[1030] Real-time monitoring and anomaly detection

[1031] The server monitors the company's operations in real time, using data streams to monitor sales, inventory levels, employee attendance, and more, and has the ability to immediately notify users if an abnormality is detected, allowing them to take prompt action.

[1032] Successor development support

[1033] The server creates a database of the skills and experience of potential managers and uses generative AI to propose an appropriate development plan. This may include specific skill training, setting role models, and conducting management simulations. Based on this development plan, users can provide specific training and training to the target employees.

[1034] Introducing the Emotion Engine

[1035] The server is equipped with an emotion engine that recognizes the user's emotions and adjusts management decisions and countermeasure proposals based on the user's emotions. The emotion engine analyzes the user's facial expressions, voice, and text input to evaluate their psychological state.

[1036] Tailoring suggestions based on emotions

[1037] The server adjusts the business decision suggestions based on the emotional data obtained by the emotion engine, for example, providing more concise and actionable suggestions when the user is stressed, and more detailed and comprehensive suggestions when the user is relaxed.

[1038] Optimizing notifications based on emotions

[1039] The server detects anomalies and optimizes the content and timing of important notifications according to the user's emotions. For example, if the emotion engine determines that the user is already in a high-stress state, it will delay non-urgent notifications to reduce the burden on the user.

[1040] Specific examples

[1041] For example, suppose a manufacturing company implements a system as follows:

[1042] The server automatically collects sales data, inventory data, and employee attendance data from the ERP system every morning and stores it in a cloud database.

[1043] The server then analyzes this data and calculates KPIs such as sales forecasts and inventory turnover.

[1044] After the monthly settlement, the server generates a management diagnosis report and notifies the user via the terminal, detailing the company's financial health, potential for new market entry, and so on.

[1045] Based on market trends and analysis results, the server will propose product order optimization and new product promotion strategies for the next quarter, and users can review, agree to, or modify these proposals in real time.

[1046] Daily operational status is monitored in real time, and if an abnormality is detected, for example, if inventory suddenly decreases, an alert notification is sent to the user immediately.

[1047] The emotion engine recognizes the user's emotions and makes adjustments such as delaying notifications if the user is in a high stress state.

[1048] Finally, the server proposes an appropriate development plan for potential future managers, and the user carries out training and education based on that plan.

[1049] This will enable companies to solve the problem of a lack of successors, achieve sustainable management, and make more effective management decisions and responses that take into consideration the feelings of users.

[1050] The processing flow will be explained below.

[1051] Step 1:

[1052] The server periodically collects data from various data sources of the company (ERP system, CRM system, financial system), for example, using APIs to retrieve sales data, inventory data, employee attendance data, and financial data.

[1053] Step 2:

[1054] The server stores the collected data in a cloud database, where it processes the data and converts it into an appropriate format before storing it in the database.

[1055] Step 3:

[1056] The server feeds data stored in a cloud database into machine learning algorithms to calculate important KPIs, such as sales forecasts, cost analysis, inventory turnover, and employee efficiency.

[1057] Step 4:

[1058] The server generates a management diagnosis report based on the analysis results, converts the KPIs and analysis results into text using natural language generation technology, and creates graphs and charts using visualization tools.

[1059] Step 5:

[1060] The server uploads the generated management diagnosis report to the dashboard and notifies the user, for example, by email or via a mobile app.

[1061] Step 6:

[1062] The server analyzes past data and market trends to generate proposals for future management decisions. It uses a reinforcement learning algorithm to learn past success and failure patterns and generate optimal proposals taking market trends into account.

[1063] Step 7:

[1064] The device displays the generated proposals to the user, who can then view the proposals in the form of a dashboard or report.

[1065] Step 8:

[1066] The user can review the proposed content, agree to it, or make corrections, and can request a recalculation by entering corrections.

[1067] Step 9:

[1068] The server monitors the company's operations in real time, using data streams to monitor sales, inventory levels, employee attendance, and more.

[1069] Step 10:

[1070] The server uses anomaly detection algorithms to detect and alert you to unusual data or trends that deviate from expectations, and sends you a warning via email or SMS.

[1071] Step 11:

[1072] Users can check the alert and decide on appropriate countermeasures, such as immediately placing additional orders or adjusting employee shifts, taking into account the nature of the anomaly.

[1073] Step 12:

[1074] The server creates a database of the skills and experience of potential managers, collecting, integrating, and storing skill sets, career history, and evaluation data from the company's internal personnel database.

[1075] Step 13:

[1076] Based on the databased information, the server uses generative AI to propose appropriate development plans, such as specific skill training, setting up role models, and conducting business simulations.

[1077] Step 14:

[1078] The user reviews and implements the proposed training plan, arranges training programs and workshops based on the proposal, and implements them for the management candidates.

[1079] Step 15:

[1080] The server uses an emotion engine that recognizes the user's emotions to analyze the user's facial expressions, voice, and text inputs and evaluate their psychological state.

[1081] Step 16:

[1082] The server adjusts the business decision suggestions based on the emotional data obtained by the emotion engine, for example, providing more concise and actionable suggestions when the user is stressed, and more detailed and comprehensive suggestions when the user is relaxed.

[1083] Step 17:

[1084] The server detects anomalies and optimizes the content and timing of important notifications according to the user's emotions. For example, if the emotion engine determines that the user is already in a high-stress state, it will delay non-urgent notifications to reduce the burden on the user.

[1085] Example 2

[1086] 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."

[1087] In corporate management, it is extremely important to effectively collect and analyze large amounts of data to guide appropriate management decisions. However, in conventional systems, data collection and analysis are often done manually, resulting in low efficiency. Furthermore, few systems take user emotions into account when making management decisions, which creates the risk of stress and misjudgment. Furthermore, there is a lack of support for real-time monitoring, anomaly detection, and succession planning. For these reasons, there is a need for the development of a system that provides efficient and comprehensive management support.

[1088] 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.

[1089] In this invention, the server includes means for automatically collecting management data of a company, means for analyzing the management data and calculating major KPIs, means for generating a management diagnosis report based on the analysis results, means for analyzing past data and market trends and generating proposals for future management decisions, means for monitoring the company's operating status in real time and detecting abnormalities, means for creating a database of the skills and experience of management candidate personnel and proposing training plans, and means for recognizing user emotions and adjusting the system's proposals and notification content based on the emotions. This makes it possible to efficiently manage the company's management data while supporting decision-making that takes user emotions into consideration.

[1090] "Management data" refers to various data that indicate the operating status of a company, and specifically includes sales data, inventory data, employee attendance data, financial data, and the like.

[1091] "KPI" stands for Key Performance Indicator and refers to a company's important performance indicators, such as sales forecasts, cost analysis, inventory turnover, and employee efficiency.

[1092] A "management diagnosis report" is a document that comprehensively analyzes a company's business situation and compiles information on current issues, future risks, growth opportunities, etc.

[1093] "Past data" refers to various management data that a company has collected and accumulated in the past.

[1094] "Market Trends" refers to data and information that indicates the current state and future projections of an industry or market.

[1095] "Proposal" refers to a specific action plan for a company's management decisions that the system generates based on analysis results and market trends.

[1096] "Real-time monitoring" is a method for monitoring a company's business situation in real time and responding immediately.

[1097] "Anomalies" refers to unusual data or events that deviate from normal operating conditions, such as a sudden decrease in inventory or an abnormal increase or decrease in sales.

[1098] "Anomaly detection" is a mechanism that detects abnormalities during real-time monitoring and immediately notifies you.

[1099] "Management candidates" refer to employees who have the skills and experience to potentially take on management responsibilities at a company in the future.

[1100] A "development plan" refers to a specific training and education plan designed to develop potential management personnel.

[1101] "User" refers to the people involved in the company who use this system, especially those who are the main actors in making management decisions.

[1102] "Means for recognizing emotions" refers to technology that analyzes a user's facial expressions, voice, and text data to evaluate the user's psychological state.

[1103] "Notification" refers to important information or alerts communicated to the user by the system.

[1104] The present invention is a system that automatically collects and analyzes business data of a company, proposes appropriate business decisions, and further recognizes user emotions and responds based on those emotions to improve the effectiveness of business decisions. An embodiment of the system will be described in detail below.

[1105] Data collection

[1106] The server periodically collects data from various data sources within the company. Specifically, it sends API requests to ERP systems, CRM systems, financial systems, etc. to obtain sales data, inventory data, employee attendance data, and financial data. The obtained data is stored in a cloud database (for example, AWS DynamoDB).

[1107] Data analysis and KPI calculation

[1108] The server analyzes the collected data using machine learning algorithms (e.g., TensorFlow) and calculates key KPIs, such as sales forecasts, cost analysis, inventory turnover, and employee efficiency. This allows the company's current situation to be quantitatively understood.

[1109] Generate a management diagnostic report

[1110] The server automatically generates a management diagnosis report based on the analysis results. This report includes information on the company's current situation, risk predictions, and growth opportunities. The report is visualized using a visualization tool (e.g., Tableau) to create graphs and charts that are easy for users to understand.

[1111] Proposal of business decisions

[1112] The server generates management decision proposals based on market trends and past company data. These proposals are generated using reinforcement learning algorithms (e.g., OpenAI's reinforcement learning algorithms) and include specific action plans such as optimizing inventory management or introducing new products to the market. The proposals are notified to the user via their terminal, allowing them to review the proposals and agree or modify them.

[1113] Real-time monitoring and anomaly detection

[1114] The server monitors the company's operations in real time and detects anomalies. It uses data streams (e.g., Apache Kafka) to monitor sales, inventory levels, employee attendance, etc., and immediately notifies users if an anomaly is detected. This functionality allows for prompt remedial action to be taken.

[1115] Successor development support

[1116] The server creates a database of the skills and experience of potential managers and uses generative AI (such as OpenAI's GPT-4) to propose an appropriate development plan. The development plan includes specific skill training, role model selection, and management simulations. Users can then implement specific training and training based on the plan.

[1117] Introducing the Emotion Engine

[1118] The server is equipped with an emotion engine (for example, Microsoft Azure's Emotion Analysis API) that recognizes the user's emotions. It analyzes the user's facial expressions, voice, and text input, evaluates their psychological state, and adjusts the content of suggestions and notifications.

[1119] Tailoring suggestions based on emotions

[1120] The server then adapts its suggestions based on the emotional data obtained by the emotion engine. For example, if the user is stressed, it will provide more concise and actionable suggestions, whereas if the user is relaxed, it will provide more detailed and comprehensive suggestions.

[1121] Optimizing notifications based on emotions

[1122] The server optimizes the content and timing of anomaly detection and important notifications based on emotional data. If stress levels are judged to be high, non-urgent notifications are delayed to reduce the burden on users.

[1123] Specific examples

[1124] For example, in a manufacturing company, the system is implemented as follows:

[1125] 1. The server automatically collects sales data, inventory data, and employee attendance data from the ERP system every morning and stores them in a cloud database.

[1126] 2. The server analyzes this data and calculates KPIs such as sales forecasts and inventory turnover.

[1127] 3. After the monthly settlement, the server generates a management diagnosis report and notifies the user via the terminal, detailing the company's financial health and potential for new market entry.

[1128] 4. Based on market trends and analysis results, the server will propose product order optimization and new product promotion strategies for the next quarter. The user can review these proposals in real time and agree or modify them.

[1129] 5. Daily operational status is monitored in real time, and if an abnormality is detected, for example, if inventory suddenly decreases, an alert notification is sent to the user immediately.

[1130] 6. The emotion engine recognizes the user's emotions and makes adjustments such as delaying notifications if the user is in a high-stress state.

[1131] 7. Finally, the server proposes an appropriate development plan for potential future managers, and the user carries out training and education based on that plan.

[1132] This will enable companies to solve the problem of a lack of successors, achieve sustainable management, and make more effective management decisions and responses that take into consideration the feelings of users.

[1133] Prompt Sentence Examples

[1134] "Please create a sales forecast for next month based on the sales data and compile the analysis results into a report. Also, please generate improvement suggestions for inventory management based on the current inventory levels."

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

[1136] Step 1:

[1137] The server automatically collects data from the company's data sources (ERP system, CRM system, financial system). The server sends API requests to each data source to obtain sales data, inventory data, employee attendance data, and financial data. The obtained data is stored in a cloud database (e.g., AWS DynamoDB).

[1138] Input: API response from the data source

[1139] Data processing: Converts API response data into a format and stores it in a cloud database

[1140] Output: Management data stored in a cloud database

[1141] Step 2:

[1142] The server retrieves the stored management data from the cloud database and analyzes it using machine learning algorithms (e.g., TensorFlow), calculating KPIs such as sales forecasts, cost analysis, inventory turnover, and employee efficiency.

[1143] Input: Management data from cloud database

[1144] Data calculation: Applying machine learning algorithms to calculate KPIs

[1145] Output: Calculated KPIs

[1146] Step 3:

[1147] The server generates a management diagnostic report based on the analysis results. This report includes information on the company's current situation, risk predictions, and growth opportunities. The server uses a visualization tool (e.g., Tableau) to create graphs and charts and display the report in an easy-to-understand manner.

[1148] Input: Analysis results and KPIs

[1149] Data processing: Visualization tools transform analysis results into graphs and charts

[1150] Output: Management diagnosis report

[1151] Step 4:

[1152] The server analyzes historical data and market trends to generate recommendations for future business decisions. These recommendations are generated using a reinforcement learning algorithm and include specific action plans, such as optimizing inventory management or introducing new products to the market.

[1153] Input: Historical data, market trends

[1154] Data computation: Analyzes data using reinforcement learning algorithms and generates recommendations

[1155] Output: Proposal of business decision

[1156] Step 5:

[1157] Through the terminal, the user can review the proposed business decision and agree or modify it. If the user modifies it, the server will recalculate and generate a new proposal.

[1158] Input: User feedback

[1159] Data processing: Reflect feedback and reanalyze

[1160] Output: Corrections or new suggestions

[1161] Step 6:

[1162] The server performs real-time monitoring to monitor the company's operations, using data streams (e.g., Apache Kafka) to monitor sales, inventory levels, employee attendance, etc., and immediately notifies users if an anomaly is detected.

[1163] Input: Real-time data stream

[1164] Data calculation: Runs anomaly detection algorithms to identify anomalies

[1165] Output: Anomaly detection notification

[1166] Step 7:

[1167] The server creates a database of the skills and experience of potential managers and uses generative AI (such as OpenAI's GPT-4) to propose an appropriate training plan, which includes specific skill training, role modeling, and management simulations.

[1168] Input: Skill data and experience of managerial candidates

[1169] Data calculation: Generative AI model is used to generate training plans

[1170] Output: Development plan

[1171] Step 8:

[1172] The server uses an emotion engine (e.g., Microsoft Azure's Emotion Analysis API) to recognize the user's emotions. The server analyzes the user's facial expressions, voice, and text input to evaluate their psychological state.

[1173] Input: User's facial expressions, voice, and text data

[1174] Data Analysis: Analyze sentiment data using the sentiment engine

[1175] Output: Emotion analysis results

[1176] Step 9:

[1177] The server adjusts the management decision suggestions based on the emotional data obtained by the emotion engine. For example, if the user is feeling stressed, it provides simple and easy-to-implement suggestions.

[1178] Input: Sentiment analysis results

[1179] Data processing: Adjust proposal content based on emotion data

[1180] Output: Adjusted proposal

[1181] Step 10:

[1182] The server detects anomalies and optimizes the content and timing of important notifications based on the user's emotions. If the server determines that the user is under high stress, it will delay non-urgent notifications to reduce the burden on the user.

[1183] Input: Anomaly detection data, emotion analysis results

[1184] Data processing: Adjust notification content and timing

[1185] Output: Optimized notification

[1186] (Application example 2)

[1187] 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."

[1188] Conventional management data analysis systems were equipped with functions to monitor a company's operational status, detect abnormalities, and propose management decisions, but they lacked the ability to recognize users' emotions and adjust responses based on them. As a result, they lacked consideration for the psychological state of operators, such as sending important notifications when the operator was in a high-stress state. This often made it difficult for users to respond appropriately, which led to problems with the effectiveness of management decisions.

[1189] 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 automatically collecting corporate management data, means for analyzing the management data to calculate key KPIs, means for generating a management diagnosis report based on the analysis results, means for analyzing past data and market trends to generate proposals for future management decisions, means for monitoring the corporate management situation in real time and detecting abnormalities, means for creating a database of the skills and experience of management candidate personnel and proposing training plans, means for collecting and analyzing various types of data within the factory in real time, means for recognizing operator emotions and adjusting proposals based on those emotions, and means for optimizing the timing and content of notifications based on emotions. This enables appropriate management decisions to be made based on the corporate management situation and enables responses that take into account the psychological state of the operators.

[1190] "Corporate management data" refers to all data generated and acquired by a company in the course of its daily business operations, including sales data, inventory data, employee attendance data, and financial data.

[1191] "Means of collection" refers to the methods and technologies used to obtain target data from various data sources and incorporate it into the system.

[1192] "Means of analysis" refers to techniques and methods for obtaining specific insights by performing statistical analysis, machine learning, data mining, etc. based on collected data.

[1193] "Key KPIs" refer to important indicators for evaluating a company's business performance, including sales forecasts, inventory turnover, and employee efficiency.

[1194] A "management diagnostic report" is a document that includes information on a company's operating status, current situation analysis, risk predictions, and growth opportunities, and is presented using visualization tools such as graphs and charts.

[1195] "Means for generating proposals" refers to technologies and methods that analyze past data and market trends and propose specific actions for future management decisions.

[1196] "Monitoring means" refers to technologies and methods for monitoring and tracking a company's operations in real time and detecting abnormalities or fluctuations.

[1197] "Means for detecting anomalies" refers to methods and technologies for detecting deviations from normal operating patterns or abnormal behavior in real time.

[1198] A "development plan" refers to a plan for providing appropriate training and education based on the skills and experience of potential management personnel.

[1199] "Various data within the factory" refers to production data, inventory data, quality data, machine operation data, etc. generated in the manufacturing industry.

[1200] "Means for recognizing emotions" refers to technologies and methods for analyzing a user's facial expressions, voice, text input, etc. to assess their psychological state.

[1201] "Means for optimizing the timing and content of notifications" refers to technologies and methods for notifying users at appropriate times and in appropriate ways based on their emotional data.

[1202] The present invention is a system that automatically collects and analyzes business data of a company and proposes appropriate business decisions. Furthermore, it recognizes the user's emotions and responds based on those emotions to improve the effectiveness of business decisions. An embodiment of the system is described below in detail.

[1203] Data collection

[1204] The server periodically collects data from various data sources within the company (ERP system, CRM system, financial system, etc.) For example, it uses APIs to retrieve sales data, inventory data, employee attendance data, and financial data. This data is then stored in a cloud database.

[1205] Data analysis and KPI calculation

[1206] The server analyzes the collected data using machine learning algorithms to calculate important KPIs, such as sales forecasts, cost analysis, inventory turnover, and employee efficiency. This process can be performed by combining multiple analytical models to improve prediction accuracy.

[1207] Generate a management diagnostic report

[1208] Based on the analysis results, the server automatically generates a management diagnosis report, which includes an analysis of the company's current situation, risk predictions, and information on growth opportunities. The report is presented in easy-to-understand graphs and charts using visualization tools.

[1209] Proposal of business decisions

[1210] The server analyzes past data and market trends to generate proposals for future management decisions. For example, it makes proposals for optimizing inventory management, changing recruitment strategies, and entering new product markets. These proposals are generated using a reinforcement learning algorithm, taking into account past patterns of success and failure. Users can review these proposals via their devices and agree or modify them. If the user makes modifications, a recalculation is performed and a new proposal is generated.

[1211] Real-time monitoring and anomaly detection

[1212] The server monitors the company's operations in real time, using data streams to monitor sales, inventory levels, employee attendance, and more, and has the ability to immediately notify users if an abnormality is detected, allowing them to take prompt action.

[1213] Successor development support

[1214] The server creates a database of the skills and experience of potential managers and uses generative AI to propose an appropriate development plan. This may include specific skill training, setting role models, and conducting management simulations. Based on this development plan, users can provide specific training and training to the target employees.

[1215] Introducing the Emotion Engine

[1216] The server is equipped with an emotion engine that recognizes the user's emotions and adjusts management decisions and countermeasure proposals based on the user's emotions. The emotion engine analyzes the user's facial expressions, voice, and text input to evaluate their psychological state.

[1217] Tailoring suggestions based on emotions

[1218] The server adjusts the business decision suggestions based on the emotional data obtained by the emotion engine, for example, providing more concise and actionable suggestions when the user is stressed, and more detailed and comprehensive suggestions when the user is relaxed.

[1219] Optimizing notifications based on emotions

[1220] The server detects anomalies and optimizes the content and timing of important notifications according to the user's emotions. For example, if the emotion engine determines that the user is already in a high-stress state, it will delay non-urgent notifications to reduce the burden on the user.

[1221] Specific examples

[1222] For example, suppose a manufacturing company implements a system as follows:

[1223] The server automatically collects sales data, inventory data, and employee attendance data from the ERP system every morning and stores it in a cloud database.

[1224] The server then analyzes this data and calculates KPIs such as sales forecasts and inventory turnover.

[1225] After the monthly settlement, the server generates a management diagnosis report and notifies the user via the terminal, detailing the company's financial health, potential for new market entry, and so on.

[1226] Based on market trends and analysis results, the server will propose product order optimization and new product promotion strategies for the next quarter, and users can review, agree to, or modify these proposals in real time.

[1227] Daily operational status is monitored in real time, and if an abnormality is detected, for example, if inventory suddenly decreases, an alert notification is sent to the user immediately.

[1228] The emotion engine recognizes the user's emotions and makes adjustments such as delaying notifications if the user is in a high stress state.

[1229] Finally, the server proposes an appropriate development plan for potential future managers, and the user implements training based on that plan. This allows companies to solve the problem of a lack of successors, achieve sustainable management, and make more effective management decisions and responses that take users' feelings into consideration.

[1230] Prompt Sentence Examples

[1231] Below is an example of a prompt sentence to input to the generative AI model.

[1232] Analyze the following data to recognize user emotions:

[1233] Facial expression image (e.g., a user's face image taken with a camera)

[1234] Audio data (e.g., user words)

[1235] Text input (e.g., user-entered comments)

[1236] As a result, if the user is exhibiting an emotion (e.g., stress, relaxation, sadness, joy), identify it.

[1237] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1238] Step 1:

[1239] The server periodically collects management data from the company's ERP system, CRM system, financial system, etc. The inputs are sales data, inventory data, employee attendance data, and financial data obtained from each data source. The server obtains this data using an API and stores it in a cloud database. The output is this data stored in the database.

[1240] Step 2:

[1241] The server analyzes the collected data and calculates key KPIs. The input is management data stored in a cloud database. The server uses machine learning algorithms to calculate KPIs such as sales forecasts, cost analysis, inventory turnover, and employee efficiency. The output is the calculated KPIs.

[1242] Step 3:

[1243] The server generates a management diagnosis report based on the analysis results. The input is the calculated KPIs. The server uses visualization tools (e.g., Matplotlib, Seaborn) to generate the management diagnosis report in graph and chart format and saves it in a cloud database. The output is the generated management diagnosis report.

[1244] Step 4:

[1245] The server analyzes past data and market trends to generate proposals for future management decisions. The inputs are past data, market trend data, and calculated KPIs. The server uses a reinforcement learning algorithm to make proposals such as optimizing inventory management, changing recruitment strategies, and entering new product markets. The output is the generated proposals for management decisions.

[1246] Step 5:

[1247] The terminal displays the generated business decision proposals to the user. The input is the business decision proposals sent from the server. The user can review these proposals and agree or modify them. The output is the user's agreement or modified information.

[1248] Step 6:

[1249] The server monitors the company's operations in real time and detects anomalies. The input is a stream of the company's daily operations data. The server analyzes the data stream and records any anomalies it detects. The output is information about the detected anomalies.

[1250] Step 7:

[1251] The server immediately notifies the user if an anomaly is detected. The input is the detected anomaly information. The server sends this information to the terminal so the user can take appropriate countermeasures. The output is the anomaly notification sent to the user.

[1252] Step 8:

[1253] The server creates a database of the skills and experience of management candidates and uses a generative AI model to propose an appropriate training plan. The input is data on the skills and experience of management candidates. The server analyzes this data and generates a training plan. The output is the generated training plan.

[1254] Step 9:

[1255] The server uses an emotion engine that recognizes the user's emotions to adjust management decisions and proposed countermeasures based on the emotions. The inputs are images of the user's facial expressions, voice data, and text input. The server analyzes this data using an emotion engine (e.g., OpenCV, IBM Watson) to recognize the user's emotions. The output is the recognized emotion data.

[1256] Step 10:

[1257] The server optimizes the content of the generated suggestions and the timing of notifications according to the user's emotions. The inputs are the recognized emotion data and the generated business decision suggestions. The server adjusts the suggestions based on the user's psychological state and changes the timing of notifications as needed. The output is the adjusted suggestions and optimized notifications.

[1258] 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.

[1259] 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.

[1260] 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.

[1261] [Fourth embodiment]

[1262] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1263] 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.

[1264] 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).

[1265] 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.

[1266] 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.

[1267] 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).

[1268] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1269] 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.

[1270] 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.

[1271] 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.

[1272] 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.

[1273] 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.

[1274] 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."

[1275] The present invention is a system that automatically collects and analyzes business data of a company, proposes appropriate business decisions, and also supports the development of successors. Specific embodiments of the present invention will be described below.

[1276] Data collection

[1277] The server periodically collects data from various data sources within the company (ERP system, CRM system, financial system, etc.) For example, it uses APIs to retrieve sales data, inventory data, employee attendance data, and financial data. This data is then stored in a cloud database.

[1278] Data analysis and KPI calculation

[1279] The server analyzes the collected data using machine learning algorithms to calculate important KPIs, such as sales forecasts, cost analysis, inventory turnover, and employee efficiency. This process can be performed by combining multiple analytical models to improve prediction accuracy.

[1280] Generate a management diagnostic report

[1281] Based on the analysis results, the server automatically generates a management diagnosis report, which includes an analysis of the company's current situation, risk predictions, and information on growth opportunities. The report is presented in easy-to-understand graphs and charts using visualization tools.

[1282] Proposal of business decisions

[1283] The server analyzes past data and market trends to generate recommendations for future business decisions, such as optimizing inventory management, changing hiring strategies, and introducing new products to the market. These recommendations are generated using a reinforcement learning algorithm, taking into account past patterns of success and failure.

[1284] Via the terminal, the user can review these proposals and accept or modify them, in which case a recalculation is performed and a new proposal is generated.

[1285] Real-time monitoring and anomaly detection

[1286] The server monitors the company's operations in real time, using data streams to monitor sales, inventory levels, employee attendance, and more, and has the ability to immediately notify users if an abnormality is detected, allowing them to take prompt action.

[1287] Successor development support

[1288] The server creates a database of the skills and experience of potential managers and uses generative AI to propose an appropriate development plan. This may include specific skill training, setting role models, and conducting management simulations. Based on this development plan, users can provide specific training and training to the target employees.

[1289] Specific examples

[1290] For example, suppose a manufacturing company implements a system as follows:

[1291] The server automatically collects sales data, inventory data, and employee attendance data from the ERP system every morning and stores it in a cloud database.

[1292] The server then analyzes this data and calculates KPIs such as sales forecasts and inventory turnover.

[1293] After the monthly settlement, the server generates a management diagnosis report and notifies the user via the terminal, detailing the company's financial health, potential for new market entry, and so on.

[1294] Based on market trends and analysis results, the server will propose product order optimization and new product promotion strategies for the next quarter, and users can review, agree to, or modify these proposals in real time.

[1295] Daily operational status is monitored in real time, and if an abnormality is detected, for example, if inventory suddenly decreases, an alert notification is sent to the user immediately.

[1296] Finally, the server proposes an appropriate development plan for potential future managers, and the user carries out training and education based on that plan.

[1297] This will enable companies to solve the problem of a lack of successors and achieve sustainable management.

[1298] The processing flow will be explained below.

[1299] Step 1:

[1300] The server periodically collects data from various corporate data sources (ERP system, CRM system, financial system), for example using APIs to retrieve sales data, inventory data, employee attendance data, and financial data.

[1301] Step 2:

[1302] The server stores the collected data in a cloud database, where it processes the data and converts it into an appropriate format before storing it in the database.

[1303] Step 3:

[1304] The server feeds data stored in a cloud database into machine learning algorithms to calculate important KPIs, such as sales forecasts, cost analysis, inventory turnover, and employee efficiency.

[1305] Step 4:

[1306] The server generates a management diagnosis report based on the analysis results, converts the KPIs and analysis results into text using natural language generation technology, and creates graphs and charts using visualization tools.

[1307] Step 5:

[1308] The server uploads the generated management diagnosis report to the dashboard and notifies the user, for example, by email or via a mobile app.

[1309] Step 6:

[1310] The server analyzes past data and market trends to generate proposals for future management decisions. It uses a reinforcement learning algorithm to learn past success and failure patterns and generate optimal proposals taking market trends into account.

[1311] Step 7:

[1312] The device displays the generated proposals to the user, who can then view the proposals in the form of a dashboard or report.

[1313] Step 8:

[1314] The user can review the proposed content, agree to it, or make corrections, and can request a recalculation by entering corrections.

[1315] Step 9:

[1316] The server monitors the company's operations in real time, using data streams to monitor sales, inventory levels, employee attendance, and more.

[1317] Step 10:

[1318] The server uses anomaly detection algorithms to detect and alert you to unusual data or trends that deviate from expectations, and sends you a warning via email or SMS.

[1319] Step 11:

[1320] Users can check the alert and decide on appropriate countermeasures, such as immediately placing additional orders or adjusting employee shifts, taking into account the nature of the anomaly.

[1321] Step 12:

[1322] The server creates a database of the skills and experience of potential managers, collecting, integrating, and storing skill sets, career history, and evaluation data from the company's internal personnel database.

[1323] Step 13:

[1324] Based on the databased information, the server uses generative AI to propose appropriate development plans, such as specific skill training, setting up role models, and conducting business simulations.

[1325] Step 14:

[1326] The user reviews and implements the proposed training plan, arranges training programs and workshops based on the proposal, and implements them for the management candidates.

[1327] Example 1

[1328] 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."

[1329] Corporate management requires the efficient collection of data from each department, the calculation of key management indicators, and support for management decisions. However, modern companies must handle complex systems and vast amounts of data, and performing these processes manually is labor-intensive and carries a high risk of error. Important issues remain, such as real-time monitoring, anomaly detection, and the development of management candidates. To address these issues, a consistent automation system and high-precision analysis technology are required.

[1330] 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.

[1331] In this invention, the server includes means for automatically collecting corporate management data, means for analyzing the management data using a machine learning algorithm and calculating key KPIs, means for generating a management diagnosis report using a visualization tool based on the analysis results, means for analyzing past data and market trends and generating proposals for future management decisions using a reinforcement learning algorithm, means for monitoring the corporate operating status in real time using data stream technology and detecting anomalies, and means for using a generative AI model to create a database of the skills and experience of management candidate personnel and propose a training plan. This enables efficient collection and analysis of corporate data, timely and accurate support for management decisions, and automatic proposals for training plans for management candidate personnel.

[1332] "Corporate management data" is a general term for information such as financial data, sales data, inventory data, and employee attendance data that is collected and managed by a company on a daily basis.

[1333] "Automatic collection means" refers to software and hardware components that allow the system to obtain data from various data sources without manual intervention.

[1334] A "machine learning algorithm" is an algorithm that uses technology to have a computer analyze massive amounts of data, recognize patterns and trends in the data, and learn from them.

[1335] "KPI" is an abbreviation for Key Performance Indicator, and refers to a company's key performance indicators, including sales forecasts, cost analysis, inventory turnover, and employee efficiency.

[1336] A "visualization tool" is a tool that displays data in a visual format, such as a graph or chart, making it easier to understand and analyze.

[1337] A "reinforcement learning algorithm" is a machine learning method that uses trial and error to find optimal behavior. It analyzes past data and market trends and automatically improves future behavior.

[1338] "Data stream technology" refers to technology for continuously collecting data in real time and processing it immediately. Apache Kafka is a representative example.

[1339] "Anomaly detection means" refers to software and hardware components that monitor real-time data and detect unexpected events or abnormal values.

[1340] A "generative AI model" is an AI model that uses natural language processing and machine learning techniques and is used to automatically generate new proposals and reports from data.

[1341] "Development plan" means a specific education and training plan to improve the skills and experience of potential management personnel.

[1342] The present invention is a system that automatically collects and analyzes business data of a company, proposes appropriate business decisions, and also supports the development of successors. Specific embodiments of the present invention will be described below.

[1343] Data collection

[1344] The server periodically collects data from various data sources within the company (ERP system, CRM system, financial system, etc.). For example, it uses APIs to retrieve sales data, inventory data, employee attendance data, and financial data. This data is stored in a cloud database such as Amazon RDS or Google Cloud Spanner. Specifically, the server calls functions such as "get_sales_data()" and "get_inventory_data()" and stores the results in the database using the "store_in_database()" function.

[1345] Data analysis and KPI calculation

[1346] The server analyzes the collected data using machine learning algorithms (e.g., TensorFlow or Scikit-learn) and calculates important KPIs. For analysis, the data is preprocessed using the "preprocess_data()" function, and then KPIs are calculated using the "calculate_kpis()" function. Specific KPIs include sales forecasts, cost analysis, inventory turnover, and employee efficiency. This allows for an accurate understanding of the current situation of the company.

[1347] Generate a management diagnostic report

[1348] Based on the analysis results, the server automatically generates a management diagnosis report. This report includes information on the company's current situation, risk predictions, and growth opportunities, and is presented in graphs and charts using a visualization tool (e.g., Tableau or Power BI). Specifically, the report is generated by the "generate_report()" function, and then notified to the user via the terminal by the "send_report_to_user()" function.

[1349] Proposal of business decisions

[1350] The server analyzes historical data and market trends and generates suggestions for future business decisions using reinforcement learning algorithms (e.g., Deep Q-Learning). These suggestions may include optimizing inventory management, changing recruitment strategies, or launching new products into the market. Suggestions are created using the "generate_suggestions()" function and displayed on the terminal via the "display_suggestions()" function. Users can review and modify the suggestions using the "approve_suggestion()" or "modify_suggestion()" functions.

[1351] Real-time monitoring and anomaly detection

[1352] The server uses data stream technologies such as Apache Kafka to monitor the company's operational status in real time. The server monitors sales, inventory levels, employee attendance, etc., and detects anomalies using the "detect_anomalies()" function. When an anomaly is detected, the user is immediately notified via the "send_alert()" function, allowing the user to take prompt action.

[1353] Successor development support

[1354] The server uses a generative AI model (e.g., GPT-4) to create a database of the skills and experience of potential managers, and evaluates them using the "analyze_candidate()" function. It then proposes an appropriate development plan using the "generate_development_plan()" function, and sends the plan to the user using the "send_training_plan()" function. This development plan includes specific skill training, role model selection, and management simulations.

[1355] Specific examples

[1356] For example, at a manufacturing company, the server uses the ERP system's API to collect sales data, inventory data, and employee attendance data every morning and stores it in Amazon RDS. The collected data is then analyzed using TensorFlow, preprocessed using the "preprocess_data()" function, and KPIs are calculated using the "calculate_kpis()" function. After monthly settlement, a report is generated using the "generate_report()" function and notified to the user via a terminal using the "send_report_to_user()" function. Furthermore, based on the results of analyzing past data and market trends, the "generate_suggestions()" function makes suggestions for the next quarter. The user can then review and modify the suggestions using the "approve_suggestion()" or "modify_suggestion()" functions. Daily operational status is monitored in real time using the "monitor_operations()" function, and if an anomaly is detected using the "detect_anomalies()" function, the user is immediately notified using the "send_alert()" function. Finally, the skills of potential future managers are evaluated using the "analyze_candidate()" function, a training plan is created using the "generate_development_plan()" function, and the plan is notified to the user using the "send_training_plan()" function.

[1357] Examples of prompts include "Propose a market entry strategy for a new product" or "Generate inventory management optimization recommendations for the next quarter."

[1358] This will enable companies to automate efficient data collection, secure storage, highly accurate analysis, rapid business decision-making, and successor training, all of which will enable them to achieve sustainable management.

[1359] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1360] Step 1: Data collection

[1361] The server collects data from various data sources within the company. Specifically, it uses APIs to retrieve sales data, inventory data, employee attendance data, financial data, etc. from ERP systems, CRM systems, and financial systems. To do this, the server uses authentication information to make API calls and uses functions such as "get_sales_data()" and "get_inventory_data()." The input is the API endpoint of each data source, and the output is the retrieved data, which is then stored in a cloud database (e.g., Amazon RDS or Google Cloud Spanner) using the "store_in_database()" function.

[1362] Step 2: Data Preprocessing

[1363] The server preprocesses the collected data. Specifically, it cleans the data, handles missing values, and standardizes it using the "preprocess_data()" function. The input is the raw data stored in the cloud database, and the output is data formatted in an analyzable format. This creates a dataset suitable for subsequent analysis.

[1364] Step 3: Calculate KPIs

[1365] The server uses the preprocessed data to calculate key KPIs. It uses the "calculate_kpis()" function to apply machine learning algorithms (e.g., TensorFlow, Scikit-learn) to calculate KPIs such as sales forecasts, cost analysis, inventory turnover, and employee efficiency. The input is the preprocessed data, and the output is the numerical values ​​of various KPIs. This provides a concrete representation of the company's important indicators.

[1366] Step 4: Generate a business diagnostic report

[1367] The server creates a management diagnosis report based on the calculated KPIs. It uses the "generate_report()" function and then uses a visualization tool (e.g., Tableau, Power BI) to display the results in graphs and charts. The input is the calculated KPIs and analysis results, and the output is a visualized management diagnosis report. This report is sent to the terminal via the "send_report_to_user()" function and notified to the user.

[1368] Step 5: Propose business decisions

[1369] The server analyzes past data and market trends and uses a reinforcement learning algorithm (e.g., Deep Q-Learning) to generate suggestions for management decisions. Specific suggestions such as optimizing inventory management, changing recruitment strategies, and launching new products into the market are created using the 'generate_suggestions()' function. The input is market trend data and analysis results, and the output is a specific proposal. The user can review the suggestions on their device using the 'display_suggestions()' function, and approve or modify the suggestions using the 'approve_suggestion()' or 'modify_suggestion()' functions.

[1370] Step 6: Real-time monitoring and anomaly detection

[1371] The server uses data streaming technologies such as Apache Kafka to monitor the company's operational status in real time. It monitors data using the 'monitor_operations()' function and detects anomalies using the 'detect_anomalies()' function. The input is real-time operational data, and the output is the detected anomalous data. If an anomaly is found, the user is immediately notified using the 'send_alert()' function.

[1372] Step 7: Support for developing successors

[1373] The server uses a generative AI model (e.g., GPT-4) to create a database of the skills and experience of potential management candidates and proposes a development plan. It evaluates the skills of the candidates using the "analyze_candidate()" function and creates a development plan using the "generate_development_plan()" function. The input is the candidate's skill data and experience data, and the output is a specific development plan. This plan is sent to the user using the "send_training_plan()" function, and specific training and development are carried out.

[1374] (Application example 1)

[1375] 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."

[1376] Conventional corporate management support systems have difficulty automating the regular collection and analysis of management data, resulting in problems such as reduced management efficiency. They also lack the functionality to grasp new market trends and corporate operational status in real time and quickly propose appropriate management decisions. In particular, on industrial production lines, information utilization to improve production efficiency and quality control is insufficient, and rapid response is required when an abnormality occurs. Furthermore, there is also insufficient training for potential successors to management positions, which poses a risk to the long-term sustainability of the company.

[1377] 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.

[1378] In this invention, the server includes the following means: means for automatically collecting corporate management data; means for analyzing the management data to calculate key KPIs; means for generating a management diagnosis report based on the analysis results; means for analyzing past data and market trends to generate proposals for future management decisions; means for monitoring the corporate operations in real time and detecting anomalies; means for creating a database of the skills and experience of management candidates and proposing training plans; means for automatically collecting and saving various sensor data from the factory; means for calculating KPIs for production efficiency and quality control based on the collected data; means for generating a management diagnosis report reporting problems and areas for improvement in the production line; means for optimizing production plans, equipment maintenance schedules, and proposing improvements to quality control; and means for monitoring the production line in real time, detecting anomalies, and notifying the user. This enables efficient and automatic collection and analysis of corporate management data, supporting prompt and appropriate management decisions. It also improves production efficiency and quality control on the production line, allowing for prompt countermeasures to be taken when anomalies occur. Furthermore, data-based skill development for successors ensures the long-term sustainability of the company.

[1379] "Management data" refers to information about a company's business activities, financial status, personnel situation, inventory status, etc.

[1380] "KPI" is an abbreviation for Key Performance Indicator, a specific indicator that shows the degree to which a company has achieved its goals.

[1381] A "management diagnosis report" is a report that summarizes the results of an analysis, including the current situation and problems of a company, and suggestions for improvement.

[1382] A "proposal" is a plan of action for a company's management based on the analysis results and market trends.

[1383] "Real-time monitoring" is a system that constantly monitors a company's operational status and immediately detects any abnormalities that occur.

[1384] "Anomaly detection" refers to the detection of deviations from normal operating conditions.

[1385] "Database of skills and experience" means storing and managing the abilities and past experience of potential managers in a digital format.

[1386] A "development plan" is a specific training or education program designed to improve the skills or careers of specific personnel.

[1387] "Sensor data" refers to various measurement data acquired from factory equipment and production lines.

[1388] "Production efficiency" is an indicator that measures the efficiency of resource utilization in production activities.

[1389] "Quality control" refers to the management activities and methods used to ensure the quality of products and services.

[1390] "Abnormality notification" is an alert function that immediately notifies relevant parties of detected abnormalities.

[1391] The present invention is a system that automatically collects and analyzes business data of a company, proposes appropriate business decisions, and also supports the development of successors. Specific embodiments of the present invention will be described below.

[1392] Data collection

[1393] The server periodically collects data from various data sources within the company (ERP system, CRM system, financial system, etc.) For example, it uses APIs to retrieve sales data, inventory data, employee attendance data, and financial data. This data is then stored in a cloud database.

[1394] Data analysis and KPI calculation

[1395] The server analyzes the collected data using machine learning algorithms (e.g., TensorFlow, scikit-learn) to calculate important KPIs, such as sales forecasts, cost analysis, inventory turnover, and employee efficiency. This process combines multiple analytical models to improve prediction accuracy.

[1396] Generate a management diagnostic report

[1397] Based on the analysis results, the server automatically generates a management diagnosis report, which includes information on the company's current situation, risk predictions, and growth opportunities. The report is presented in easy-to-understand graphs and charts using data visualization tools (e.g., Matplotlib, D3.js).

[1398] Proposal of business decisions

[1399] The server analyzes past data and market trends to generate proposals for future management decisions. For example, it may suggest optimizing inventory management, changing hiring strategies, or launching new products into the market. These proposals are generated using a reinforcement learning algorithm (e.g., OpenAI Gym) that takes into account past patterns of success and failure. Users can review these proposals via their devices and agree or modify them. If the user makes modifications, a recalculation is performed and a new proposal is generated.

[1400] Real-time monitoring and anomaly detection

[1401] The server monitors the company's operations in real time, using data streams to monitor sales, inventory levels, employee attendance, and more, and has the ability to immediately notify users if an abnormality is detected, allowing them to take prompt action.

[1402] Successor development support

[1403] The server creates a database of the skills and experience of potential managers and uses a generative AI model (e.g., GPT-4) to propose an appropriate development plan. This may include specific skill training, setting role models, and conducting management simulations. Based on this development plan, users can provide specific training and training to the target employees.

[1404] Specific examples

[1405] For example, suppose a manufacturing company implements a system as follows:

[1406] The server automatically collects sales data, inventory data, and employee attendance data from the ERP system every morning and stores it in a cloud database.

[1407] The server then analyzes this data and calculates KPIs such as sales forecasts and inventory turnover.

[1408] After the monthly settlement, the server generates a management diagnosis report and notifies the user via the terminal, detailing the company's financial health, potential for new market entry, and so on.

[1409] Based on market trends and analysis results, the server will propose product order optimization and new product promotion strategies for the next quarter, and users can review, agree to, or modify these proposals in real time.

[1410] Daily operational status is monitored in real time, and if an abnormality is detected, for example, if inventory suddenly decreases, an alert notification is sent to the user immediately.

[1411] Finally, the server proposes an appropriate development plan for potential future managers, and the user carries out training and education based on that plan.

[1412] This will enable companies to solve the problem of a lack of successors and achieve sustainable management.

[1413] Example prompts for generative AI models

[1414] "Analyze the operating rate and defect rate of production line 1 in the factory last month, and if the defect rate has increased, please suggest improvement measures."

[1415] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1416] Step 1:

[1417] The server periodically collects data from various data sources within the company (ERP system, CRM system, financial system, etc.). The hardware used includes a server and a cloud database that retrieves data via API. Input data includes sales data, inventory data, employee attendance data, and financial data. The server collects this data and gets an output that is stored in the cloud database.

[1418] Step 2:

[1419] The server analyzes the collected data using machine learning algorithms (e.g., TensorFlow, scikit-learn) and calculates key KPIs. Input data includes sales data and inventory data stored in a cloud database. Data processing involves filling in missing values ​​and normalizing the data to convert it into a format suitable for machine learning algorithms. Output includes KPIs such as sales forecasts, cost analysis, inventory turnover, and employee efficiency.

[1420] Step 3:

[1421] The server generates a management diagnosis report based on the analysis results. The input data includes calculated KPIs and other analysis results. The server uses data visualization tools (e.g., Matplotlib, D3.js) to visualize the analysis results as graphs and charts and compile them into a report format. The output is an easy-to-read management diagnosis report.

[1422] Step 4:

[1423] The server analyzes past data and market trends to generate proposals for future management decisions. Input data includes past sales data and market trend data. The server uses a reinforcement learning algorithm (e.g., OpenAI Gym) to analyze this data and generate proposals such as optimizing inventory management, changing recruitment strategies, and introducing new products to the market. The output is a concrete proposal for management decisions.

[1424] Step 5:

[1425] The server displays the generated proposals to the user via the terminal. The input data are the generated proposals. The user checks these proposals and accepts or modifies them. If any modifications are made, the server recalculates and generates a new proposal. The output is the user's acceptance or modification.

[1426] Step 6:

[1427] The server monitors the company's operations in real time. Input data includes sales data, inventory levels, and employee attendance data, all of which are acquired in real time. The server uses data stream processing (e.g., Apache Kafka) to monitor this data and immediately notifies the user if an anomaly is detected. The output is the real-time monitoring results and anomaly notification.

[1428] Step 7:

[1429] The server creates a database of the skills and experience of potential management candidates and uses a generative AI model (e.g., GPT-4) to propose an appropriate training plan. Input data includes the skills and past experience of the personnel. The server analyzes this data and generates an optimal training plan. A specific training plan is proposed as the output.

[1430] Example prompts for generative AI models

[1431] "Analyze the operating rate and defect rate of production line 1 in the factory last month, and if the defect rate has increased, please suggest improvement measures."

[1432] 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.

[1433] The present invention is a system that automatically collects and analyzes business data of a company, proposes appropriate business decisions, and further recognizes user emotions and responds based on those emotions to improve the effectiveness of business decisions. An embodiment of the system will be described in detail below.

[1434] Data collection

[1435] The server periodically collects data from various data sources within the company (ERP system, CRM system, financial system, etc.) For example, it uses APIs to retrieve sales data, inventory data, employee attendance data, and financial data. This data is then stored in a cloud database.

[1436] Data analysis and KPI calculation

[1437] The server analyzes the collected data using machine learning algorithms to calculate important KPIs, such as sales forecasts, cost analysis, inventory turnover, and employee efficiency. This process can be performed by combining multiple analytical models to improve prediction accuracy.

[1438] Generate a management diagnostic report

[1439] Based on the analysis results, the server automatically generates a management diagnosis report, which includes an analysis of the company's current situation, risk predictions, and information on growth opportunities. The report is presented in easy-to-understand graphs and charts using visualization tools.

[1440] Proposal of business decisions

[1441] The server analyzes past data and market trends to generate recommendations for future business decisions, such as optimizing inventory management, changing hiring strategies, and introducing new products to the market. These recommendations are generated using a reinforcement learning algorithm, taking into account past patterns of success and failure.

[1442] Via the terminal, the user can review these proposals and accept or modify them, in which case a recalculation is performed and a new proposal is generated.

[1443] Real-time monitoring and anomaly detection

[1444] The server monitors the company's operations in real time, using data streams to monitor sales, inventory levels, employee attendance, and more, and has the ability to immediately notify users if an abnormality is detected, allowing them to take prompt action.

[1445] Successor development support

[1446] The server creates a database of the skills and experience of potential managers and uses generative AI to propose an appropriate development plan. This may include specific skill training, setting role models, and conducting management simulations. Based on this development plan, users can provide specific training and training to the target employees.

[1447] Introducing the Emotion Engine

[1448] The server is equipped with an emotion engine that recognizes the user's emotions and adjusts management decisions and countermeasure proposals based on the user's emotions. The emotion engine analyzes the user's facial expressions, voice, and text input to evaluate their psychological state.

[1449] Tailoring suggestions based on emotions

[1450] The server adjusts the business decision suggestions based on the emotional data obtained by the emotion engine, for example, providing more concise and actionable suggestions when the user is stressed, and more detailed and comprehensive suggestions when the user is relaxed.

[1451] Optimizing notifications based on emotions

[1452] The server detects anomalies and optimizes the content and timing of important notifications according to the user's emotions. For example, if the emotion engine determines that the user is already in a high-stress state, it will delay non-urgent notifications to reduce the burden on the user.

[1453] Specific examples

[1454] For example, suppose a manufacturing company implements a system as follows:

[1455] The server automatically collects sales data, inventory data, and employee attendance data from the ERP system every morning and stores it in a cloud database.

[1456] The server then analyzes this data and calculates KPIs such as sales forecasts and inventory turnover.

[1457] After the monthly settlement, the server generates a management diagnosis report and notifies the user via the terminal, detailing the company's financial health, potential for new market entry, and so on.

[1458] Based on market trends and analysis results, the server will propose product order optimization and new product promotion strategies for the next quarter, and users can review, agree to, or modify these proposals in real time.

[1459] Daily operational status is monitored in real time, and if an abnormality is detected, for example, if inventory suddenly decreases, an alert notification is sent to the user immediately.

[1460] The emotion engine recognizes the user's emotions and makes adjustments such as delaying notifications if the user is in a high stress state.

[1461] Finally, the server proposes an appropriate development plan for potential future managers, and the user carries out training and education based on that plan.

[1462] This will enable companies to solve the problem of a lack of successors, achieve sustainable management, and make more effective management decisions and responses that take into consideration the feelings of users.

[1463] The processing flow will be explained below.

[1464] Step 1:

[1465] The server periodically collects data from various data sources of the company (ERP system, CRM system, financial system), for example, using APIs to retrieve sales data, inventory data, employee attendance data, and financial data.

[1466] Step 2:

[1467] The server stores the collected data in a cloud database, where it processes the data and converts it into an appropriate format before storing it in the database.

[1468] Step 3:

[1469] The server feeds data stored in a cloud database into machine learning algorithms to calculate important KPIs, such as sales forecasts, cost analysis, inventory turnover, and employee efficiency.

[1470] Step 4:

[1471] The server generates a management diagnosis report based on the analysis results, converts the KPIs and analysis results into text using natural language generation technology, and creates graphs and charts using visualization tools.

[1472] Step 5:

[1473] The server uploads the generated management diagnosis report to the dashboard and notifies the user, for example, by email or via a mobile app.

[1474] Step 6:

[1475] The server analyzes past data and market trends to generate proposals for future management decisions. It uses a reinforcement learning algorithm to learn past success and failure patterns and generate optimal proposals taking market trends into account.

[1476] Step 7:

[1477] The device displays the generated proposals to the user, who can then view the proposals in the form of a dashboard or report.

[1478] Step 8:

[1479] The user can review the proposed content, agree to it, or make corrections, and can request a recalculation by entering corrections.

[1480] Step 9:

[1481] The server monitors the company's operations in real time, using data streams to monitor sales, inventory levels, employee attendance, and more.

[1482] Step 10:

[1483] The server uses anomaly detection algorithms to detect and alert you to unusual data or trends that deviate from expectations, and sends you a warning via email or SMS.

[1484] Step 11:

[1485] Users can check the alert and decide on appropriate countermeasures, such as immediately placing additional orders or adjusting employee shifts, taking into account the nature of the anomaly.

[1486] Step 12:

[1487] The server creates a database of the skills and experience of potential managers, collecting, integrating, and storing skill sets, career history, and evaluation data from the company's internal personnel database.

[1488] Step 13:

[1489] Based on the databased information, the server uses generative AI to propose appropriate development plans, such as specific skill training, setting up role models, and conducting business simulations.

[1490] Step 14:

[1491] The user reviews and implements the proposed training plan, arranges training programs and workshops based on the proposal, and implements them for the management candidates.

[1492] Step 15:

[1493] The server uses an emotion engine that recognizes the user's emotions to analyze the user's facial expressions, voice, and text inputs and evaluate their psychological state.

[1494] Step 16:

[1495] The server adjusts the business decision suggestions based on the emotional data obtained by the emotion engine, for example, providing more concise and actionable suggestions when the user is stressed, and more detailed and comprehensive suggestions when the user is relaxed.

[1496] Step 17:

[1497] The server detects anomalies and optimizes the content and timing of important notifications according to the user's emotions. For example, if the emotion engine determines that the user is already in a high-stress state, it will delay non-urgent notifications to reduce the burden on the user.

[1498] Example 2

[1499] 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."

[1500] In corporate management, it is extremely important to effectively collect and analyze large amounts of data to guide appropriate management decisions. However, in conventional systems, data collection and analysis are often done manually, resulting in low efficiency. Furthermore, few systems take user emotions into account when making management decisions, which creates the risk of stress and misjudgment. Furthermore, there is a lack of support for real-time monitoring, anomaly detection, and succession planning. For these reasons, there is a need for the development of a system that provides efficient and comprehensive management support.

[1501] 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.

[1502] In this invention, the server includes means for automatically collecting management data of a company, means for analyzing the management data and calculating major KPIs, means for generating a management diagnosis report based on the analysis results, means for analyzing past data and market trends and generating proposals for future management decisions, means for monitoring the company's operating status in real time and detecting abnormalities, means for creating a database of the skills and experience of management candidate personnel and proposing training plans, and means for recognizing user emotions and adjusting the system's proposals and notification content based on the emotions. This makes it possible to efficiently manage the company's management data while supporting decision-making that takes user emotions into consideration.

[1503] "Management data" refers to various data that indicate the operating status of a company, and specifically includes sales data, inventory data, employee attendance data, financial data, and the like.

[1504] "KPI" stands for Key Performance Indicator and refers to a company's important performance indicators, such as sales forecasts, cost analysis, inventory turnover, and employee efficiency.

[1505] A "management diagnosis report" is a document that comprehensively analyzes a company's business situation and compiles information on current issues, future risks, growth opportunities, etc.

[1506] "Past data" refers to various management data that a company has collected and accumulated in the past.

[1507] "Market Trends" refers to data and information that indicates the current state and future projections of an industry or market.

[1508] "Proposal" refers to a specific action plan for a company's management decisions that the system generates based on analysis results and market trends.

[1509] "Real-time monitoring" is a method for monitoring a company's business situation in real time and responding immediately.

[1510] "Anomalies" refers to unusual data or events that deviate from normal operating conditions, such as a sudden decrease in inventory or an abnormal increase or decrease in sales.

[1511] "Anomaly detection" is a mechanism that detects abnormalities during real-time monitoring and immediately notifies you.

[1512] "Management candidates" refer to employees who have the skills and experience to potentially take on management responsibilities at a company in the future.

[1513] A "development plan" refers to a specific training and education plan designed to develop potential management personnel.

[1514] "User" refers to the people involved in the company who use this system, especially those who are the main actors in making management decisions.

[1515] "Means for recognizing emotions" refers to technology that analyzes a user's facial expressions, voice, and text data to evaluate the user's psychological state.

[1516] "Notification" refers to important information or alerts communicated to the user by the system.

[1517] The present invention is a system that automatically collects and analyzes business data of a company, proposes appropriate business decisions, and further recognizes user emotions and responds based on those emotions to improve the effectiveness of business decisions. An embodiment of the system will be described in detail below.

[1518] Data collection

[1519] The server periodically collects data from various data sources within the company. Specifically, it sends API requests to ERP systems, CRM systems, financial systems, etc. to obtain sales data, inventory data, employee attendance data, and financial data. The obtained data is stored in a cloud database (for example, AWS DynamoDB).

[1520] Data analysis and KPI calculation

[1521] The server analyzes the collected data using machine learning algorithms (e.g., TensorFlow) and calculates key KPIs, such as sales forecasts, cost analysis, inventory turnover, and employee efficiency. This allows the company's current situation to be quantitatively understood.

[1522] Generate a management diagnostic report

[1523] The server automatically generates a management diagnosis report based on the analysis results. This report includes information on the company's current situation, risk predictions, and growth opportunities. The report is visualized using a visualization tool (e.g., Tableau) to create graphs and charts that are easy for users to understand.

[1524] Proposal of business decisions

[1525] The server generates management decision proposals based on market trends and past company data. These proposals are generated using reinforcement learning algorithms (e.g., OpenAI's reinforcement learning algorithms) and include specific action plans such as optimizing inventory management or introducing new products to the market. The proposals are notified to the user via their terminal, allowing them to review the proposals and agree or modify them.

[1526] Real-time monitoring and anomaly detection

[1527] The server monitors the company's operations in real time and detects anomalies. It uses data streams (e.g., Apache Kafka) to monitor sales, inventory levels, employee attendance, etc., and immediately notifies users if an anomaly is detected. This functionality allows for prompt remedial action to be taken.

[1528] Successor development support

[1529] The server creates a database of the skills and experience of potential managers and uses generative AI (such as OpenAI's GPT-4) to propose an appropriate development plan. The development plan includes specific skill training, role model selection, and management simulations. Users can then implement specific training and training based on the plan.

[1530] Introducing the Emotion Engine

[1531] The server is equipped with an emotion engine (for example, Microsoft Azure's Emotion Analysis API) that recognizes the user's emotions. It analyzes the user's facial expressions, voice, and text input, evaluates their psychological state, and adjusts the content of suggestions and notifications.

[1532] Tailoring suggestions based on emotions

[1533] The server then adapts its suggestions based on the emotional data obtained by the emotion engine. For example, if the user is stressed, it will provide more concise and actionable suggestions, whereas if the user is relaxed, it will provide more detailed and comprehensive suggestions.

[1534] Optimizing notifications based on emotions

[1535] The server optimizes the content and timing of anomaly detection and important notifications based on emotional data. If stress levels are judged to be high, non-urgent notifications are delayed to reduce the burden on users.

[1536] Specific examples

[1537] For example, in a manufacturing company, the system is implemented as follows:

[1538] 1. The server automatically collects sales data, inventory data, and employee attendance data from the ERP system every morning and stores them in a cloud database.

[1539] 2. The server analyzes this data and calculates KPIs such as sales forecasts and inventory turnover.

[1540] 3. After the monthly settlement, the server generates a management diagnosis report and notifies the user via the terminal, detailing the company's financial health and potential for new market entry.

[1541] 4. Based on market trends and analysis results, the server will propose product order optimization and new product promotion strategies for the next quarter. The user can review these proposals in real time and agree or modify them.

[1542] 5. Daily operational status is monitored in real time, and if an abnormality is detected, for example, if inventory suddenly decreases, an alert notification is sent to the user immediately.

[1543] 6. The emotion engine recognizes the user's emotions and makes adjustments such as delaying notifications if the user is in a high-stress state.

[1544] 7. Finally, the server proposes an appropriate development plan for potential future managers, and the user carries out training and education based on that plan.

[1545] This will enable companies to solve the problem of a lack of successors, achieve sustainable management, and make more effective management decisions and responses that take into consideration the feelings of users.

[1546] Prompt Sentence Examples

[1547] "Please create a sales forecast for next month based on the sales data and compile the analysis results into a report. Also, please generate improvement suggestions for inventory management based on the current inventory levels."

[1548] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1549] Step 1:

[1550] The server automatically collects data from the company's data sources (ERP system, CRM system, financial system). The server sends API requests to each data source to obtain sales data, inventory data, employee attendance data, and financial data. The obtained data is stored in a cloud database (e.g., AWS DynamoDB).

[1551] Input: API response from the data source

[1552] Data processing: Converts API response data into a format and stores it in a cloud database

[1553] Output: Management data stored in a cloud database

[1554] Step 2:

[1555] The server retrieves the stored management data from the cloud database and analyzes it using machine learning algorithms (e.g., TensorFlow), calculating KPIs such as sales forecasts, cost analysis, inventory turnover, and employee efficiency.

[1556] Input: Management data from cloud database

[1557] Data calculation: Applying machine learning algorithms to calculate KPIs

[1558] Output: Calculated KPIs

[1559] Step 3:

[1560] The server generates a management diagnostic report based on the analysis results. This report includes information on the company's current situation, risk predictions, and growth opportunities. The server uses a visualization tool (e.g., Tableau) to create graphs and charts and display the report in an easy-to-understand manner.

[1561] Input: Analysis results and KPIs

[1562] Data processing: Visualization tools transform analysis results into graphs and charts

[1563] Output: Management diagnosis report

[1564] Step 4:

[1565] The server analyzes historical data and market trends to generate recommendations for future business decisions. These recommendations are generated using a reinforcement learning algorithm and include specific action plans, such as optimizing inventory management or introducing new products to the market.

[1566] Input: Historical data, market trends

[1567] Data computation: Analyzes data using reinforcement learning algorithms and generates recommendations

[1568] Output: Proposal of business decision

[1569] Step 5:

[1570] Through the terminal, the user can review the proposed business decision and agree or modify it. If the user modifies it, the server will recalculate and generate a new proposal.

[1571] Input: User feedback

[1572] Data processing: Reflect feedback and reanalyze

[1573] Output: Corrections or new suggestions

[1574] Step 6:

[1575] The server performs real-time monitoring t...

Claims

1. A means of automatically collecting business data of a company; A means for analyzing the management data and calculating major KPIs; A means for generating a management diagnosis report based on the analysis results; A means of analyzing historical data and market trends to generate proposals for future business decisions; A means of monitoring the company's operations in real time and detecting abnormalities, A system that includes a database of the skills and experience of potential management personnel and a means to propose development plans.

2. 10. The system of claim 1, further comprising means for displaying the proposed business decision to a user and allowing the user to agree or modify the decision.

3. 2. The system according to claim 1, further comprising means for notifying a user of an abnormality detected by said abnormality detection means, so that the user can determine an appropriate countermeasure.

Images