system

Abstract

We provide the system. [Solution] Means of collecting information, A means of integrating and processing the collected information, A means of formulating and executing work plans based on integrated information, Means for monitoring and coordinating the progress of the work, Means for detecting anomalies and providing information, A system that includes this.

Description

Technical Field

[0005] ,

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] Each department within an enterprise conducts its operations using its own independent system and data format, resulting in information fragmentation and potential delays in business collaboration. Additionally, tasks may progress in a state where priorities are unclear, potentially inhibiting productivity. To address these issues, an integrated approach across departments is required.

Means for Solving the Problems

[0005] This invention provides a means for collecting information provided in different data formats from various departments, and for centrally integrating and processing it. This eliminates data isolation and improves overall operational efficiency. Furthermore, it enables optimal resource allocation by formulating and executing work plans based on the integrated data, and by autonomously and dynamically adjusting priorities during the process. It also provides a means for monitoring work progress in real time and making adjustments as needed, enabling quick and accurate responses.

[0006] "Information" refers to elements that include data and knowledge, and is content that is used within a specific context.

[0007] "Means of collection" refers to the processes and technologies used to obtain necessary data from diverse sources.

[0008] "Means of integration" refers to a system that centralizes and organizes various forms of data into an easily understandable format.

[0009] "Processing methods" refer to techniques for analyzing data and performing operations or calculations to derive results that are appropriate for a specific purpose or role.

[0010] A "work plan" refers to the process of systematically determining the actions and steps necessary to achieve a specific goal.

[0011] "Means of planning and execution" refers to the method of formulating a plan and carrying out specific tasks based on that plan.

[0012] "Means of monitoring and adjusting" refers to the process of observing progress and status in real time and making appropriate changes or corrections as needed. [Brief explanation of the drawing]

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

Embodiments for Carrying Out the Invention

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

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

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

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

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

[0019] In the following embodiments, a numbered communication I / F (Interface) is an interface including a communication processor and 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), or Bluetooth (registered trademark), and the like.

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

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

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

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

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

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0030] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

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

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

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

[0034] The "cross-operational AI agent" system according to the present invention integrates information and tasks managed by various departments within a company, enabling efficient business execution. This system integrates and operates functions for information gathering and processing, work planning and execution, and progress monitoring and adjustment on a central system.

[0035] First, the server collects data in various formats provided by each department. It allows for centralized access to data from databases, spreadsheets, and specialized software. The collected data is standardized and integrated into the company's internal data warehouse for storage. This eliminates data inconsistencies across departments, enabling cross-departmental data analysis.

[0036] Next, the AI ​​agent uses this integrated data to analyze the priorities of each task and develop a work plan. The AI ​​uses machine learning algorithms to assess the importance and urgency of tasks and allocate resources efficiently. This ensures that internal operations are not carried out in isolation by individual departments, but rather optimized across the entire company.

[0037] On the device, users can check the progress of their work plan in real time. By monitoring whether the work is progressing as scheduled and taking action as needed, delays and problems can be detected early. This monitoring function also includes suggesting optimal solutions based on analysis results provided by AI.

[0038] For example, feedback data from the product development department is shared with the sales department in real time, and an AI agent analyzes it to optimize the timing of new product market launches and promotional activities. This facilitates smoother communication between departments and improves overall operational efficiency.

[0039] In this way, by having servers and AI agents autonomously perform a series of data processing and analysis, as well as work planning and monitoring, the present invention can streamline interdepartmental coordination work and drastically improve the productivity of the entire company.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The server automatically collects data from each department's systems. Data sources include databases, spreadsheets, and cloud services, and this information is centralized through an ETL process. The server standardizes the data format and stores it in a central data warehouse.

[0043] Step 2:

[0044] The server provides integrated data to the AI ​​agent. The AI ​​agent analyzes the data using machine learning algorithms to assess the importance and urgency of the tasks. This generates a priority list for each task.

[0045] Step 3:

[0046] The server automatically constructs work plans for each department based on the priority list generated by the AI ​​agent. It calculates the required resources, makes optimal allocations, and formulates work plans. The formulated plans are automatically distributed to the terminals of the relevant parties.

[0047] Step 4:

[0048] On their devices, users can view the distributed work plans and update the progress of their tasks in real time. Users can also see the overall project status on the dashboard and update it when new information is added.

[0049] Step 5:

[0050] The server collects progress data sent from the terminals in real time and feeds it back to the AI ​​agent. The AI ​​analyzes the data and automatically generates warnings and improvement suggestions for areas where progress is lagging.

[0051] Step 6:

[0052] Based on the AI ​​agent's analysis results, the server prioritizes tasks and readjusts the work plan. If necessary, it issues emergency alerts to stakeholders to support the smooth progress of the project.

[0053] (Example 1)

[0054] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0055] The aim is to eliminate data inconsistencies and inefficiencies that arise when each department within a company independently manages information and tasks, and to optimize company-wide operations. In particular, it is difficult to centrally manage and utilize data when the data formats differ, and it is also a challenge to appropriately analyze and dynamically adjust task priorities.

[0056] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0057] In this invention, the server includes means for collecting information, means for integrating the collected information and standardizing the data format, and means for analyzing task priorities using a machine learning algorithm based on the standardized information. This enables centralized management of information across departments and effective task prioritization.

[0058] "Means of collecting information" refers to devices or functions for collecting information provided in different data formats from various departments within a company.

[0059] "Means of standardizing data formats" refers to devices or functions that convert collected information into a specific format and ensure consistency.

[0060] "Means of using machine learning algorithms" refers to devices or functions that utilize machine learning techniques for data analysis and task prioritization.

[0061] "Means for analyzing task priorities" refers to a device or function that evaluates each task performed within a company and prioritizes them based on their importance and urgency.

[0062] "Means for efficient resource allocation" refers to devices or functions that optimally allocate appropriate resources such as personnel, time, and equipment according to the priority of the analyzed tasks.

[0063] "Means for monitoring work progress" refers to devices or functions for tracking the status of ongoing tasks in real time and verifying whether they are progressing as planned.

[0064] "Means for early problem detection and solution provision" refers to a device or function that detects potential problems that may arise based on the progress of work and provides appropriate solutions to them.

[0065] As a means of implementing the invention, this system optimizes business operations by efficiently collecting, integrating, and analyzing information from multiple departments within a company.

[0066] First, the server collects information from each department. It connects to the databases, spreadsheets, and specialized software provided by each department via database connection tools and APIs to retrieve the necessary data. Because this collected data may be in different formats, a data conversion tool is used to consolidate it into a standard format (e.g., JSON or CSV).

[0067] The program utilizes machine learning frameworks such as Python's scikit-learn library for processing. This allows the server to analyze integrated data and evaluate the priority of each task. Since this priority is a crucial element directly related to improving operational efficiency, the server uses the analysis results to formulate a work plan and allocate resources appropriately.

[0068] On their devices, users can check the progress of their work plans in real time through a web browser. By using a front-end framework (e.g., React or Angular) to visually display the progress in a dashboard format, users can identify problems early. Furthermore, an AI agent suggests the optimal solution based on the analysis results, facilitating rapid problem resolution.

[0069] One concrete example is the process of sharing the launch date of a new product with the sales department based on feedback from the product development department. By having the AI ​​agent analyze the feedback and suggest an appropriate launch date and timing for promotional activities, interdepartmental communication is streamlined, and overall work efficiency is improved. An example of a prompt message is, "Based on feedback from the product development department, please analyze the appropriate timing for the next promotional activity."

[0070] This configuration enables the centralization and optimal management of information and tasks across the entire company.

[0071] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0072] Step 1:

[0073] The server collects information from various departments within the company. Inputs include data in various formats obtained from databases, spreadsheets, and specialized software. The server uses APIs and database connection tools to extract the necessary information from these sources. The output is a collection of the retrieved information.

[0074] Step 2:

[0075] The server standardizes the data format of the collected information. The input consists of data in different formats collected in Step 1. The server uses an ETL (Extract, Transform, Load) tool to convert the data into a standard format, unifying it into JSON or CSV. The output is the standardized, integrated data.

[0076] Step 3:

[0077] The server analyzes task priorities using standardized, integrated data. The input is the integrated data obtained in step 2. The server applies machine learning algorithms to analyze the data and evaluate the importance and urgency of the tasks. Specifically, it builds a model using the Python scikit-learn library and assigns priority labels to the tasks. The output is a priority list for each task.

[0078] Step 4:

[0079] The server develops a work plan and allocates resources optimally based on the priority list. The input is the priority list analyzed in step 3. The server uses a planning algorithm to create an efficient schedule and allocate resources appropriately. The output generates a detailed work plan and resource allocation list.

[0080] Step 5:

[0081] On the terminal, the user monitors how the work plan is progressing. The input is real-time progress data provided by the server. The user can view the progress information and address issues as needed by viewing a dashboard via a web browser. The output shows the latest progress and suggested solutions.

[0082] Step 6:

[0083] When a user checks their progress, the server presents problem-solving solutions generated by an AI agent. Input includes data on problem occurrences based on progress checks and a history of past solutions. The server uses a generative AI model to generate optimized prompts and solutions, providing feedback to the user. The output presents the most suitable problem-solving solution, enabling a rapid response.

[0084] (Application Example 1)

[0085] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0086] In production environments such as factories, data integration and work planning are complex, making efficient work execution difficult. Furthermore, while rapid response is required when anomalies occur, insufficient real-time information provision can lead to delays in response. To solve these problems, a system is needed that effectively integrates data, optimizes work plans, monitors progress, and detects and provides information on anomalies.

[0087] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0088] In this invention, the server includes means for collecting information, means for integrating and processing the collected information, means for formulating and executing work plans based on the integrated information, means for monitoring and adjusting the progress of work, and means for detecting anomalies and providing information. This enables centralized data management and efficient work planning in production activities, as well as real-time progress monitoring and anomaly response.

[0089] "Means of collecting information" refers to devices or software that acquire necessary data from various data sources inside and outside the factory.

[0090] "Means of integration and processing" refers to devices or software that standardize acquired data, aggregate and store it in a database, and perform any necessary analysis.

[0091] "Means for formulating and executing work plans" refers to devices or software that create an optimal work plan based on collected data and execute actions according to that plan.

[0092] "Means for monitoring and adjusting the progress of work" refers to devices or software that continuously monitor the progress of work being performed and adjust the plan as necessary.

[0093] "Means for detecting anomalies and providing information" refers to devices or software that detect problems or anomalies within a system and the work environment and suggest appropriate countermeasures.

[0094] The system for implementing this invention aims to enable efficient work schedule generation and execution, as well as rapid response to abnormalities, in production environments such as factories. The server collects information from various data sources inside and outside the factory, standardizes it, and integrates it into a data warehouse. The database used can be PostgreSQL or MongoDB.

[0095] The server utilizes the collected data and employs machine learning algorithms such as TENSORFLOW® or PyTorch to develop work plans. These plans are optimized for production efficiency and designed to maximize the use of internal resources. The server also monitors work progress in real time, detects anomalies if problems occur, and provides users with appropriate countermeasures. This enables factory workers to immediately perform optimal operations.

[0096] The terminal provides users with work plans and progress data in an easy-to-understand format. This allows workers to grasp the progress of work on-site in real time and get help revising work plans as needed. Users can also take quick countermeasures by following recommendations from the AI ​​agent when an anomaly occurs.

[0097] As a concrete example, when manufacturing a new product begins at a factory, a server aggregates data from each process in real time, and an AI agent generates an optimal work plan. This plan, based on recommendations from a computationally powerful AI, adjusts the supply chain and production lines as needed. An example of a prompt provided to the generating AI model is, "Generate an efficient work schedule based on factory production data. Provide real-time information if any anomalies occur."

[0098] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0099] Step 1:

[0100] The server collects information from various data sources both inside and outside the factory. It uses data provided by sensors, ERP systems, and logistics platforms as input, standardizes the data, and stores it in PostgreSQL or MongoDB. This integrates data that previously existed in disparate formats, making it centrally accessible.

[0101] Step 2:

[0102] The server generates an optimal work plan using machine learning algorithms based on the collected data. Here, TensorFlow or PyTorch is used for pattern recognition and predictive analytics on the data to determine the optimal resource allocation and work sequence. The output of this process is an optimized work plan, which is used to maximize factory productivity.

[0103] Step 3:

[0104] The terminal displays the generated work plan and the real-time progress of the factory. Inputs are work plan data received from the server and progress data from each process, while output is a visual interface provided to the user. This allows the user to instantly understand which processes are on schedule and adjust on-site operations accordingly.

[0105] Step 4:

[0106] The server analyzes the progress in real time as the work progresses and notifies the user if any anomalies occur. This includes a process to detect anomalies by comparing them with pre-configured criteria and predictions derived from historical data. When an anomaly is detected, the server generates a recommended solution and sends a notification to the user with a prompt.

[0107] Step 5:

[0108] Based on the information provided via the terminal, users take necessary actions. This includes manual adjustments and the execution of automated corrective procedures recommended by AI. This ensures factory stability and safety, minimizing production disruptions.

[0109] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0110] By combining the "cross-operational AI agent" system according to the present invention with an emotion engine that recognizes user emotions, even more advanced business management can be achieved. This makes it possible to provide a flexible work environment that not only improves the efficiency of operations but also takes into account the emotional aspects of the user.

[0111] The server collects information from each department while simultaneously acquiring user emotional data using an emotion engine. This emotional data is analyzed in real time using the user's voice tone and facial recognition technology. This information is integrated with business data, enabling further optimization of task prioritization and work plans.

[0112] The AI ​​agent analyzes data obtained from the emotion engine to assess the user's stress level and motivation. This enables flexible, emotion-based work adjustments, such as redistributing tasks when the user is overloaded or offering rewards when the user is highly motivated.

[0113] On their devices, users can receive feedback that reflects their emotional data. For example, if the AI ​​determines that a user is stressed, it may suggest taking a break or recommend access to support resources. Furthermore, by analyzing the emotional trends of the entire team and presenting areas for communication improvement to all members, team cohesion can be enhanced.

[0114] For example, if some members of a project team are feeling intense pressure due to a tight deadline, the AI ​​agent can sense this emotion and automatically suggest distributing tasks to other members. This not only balances the overall workload but also maintains the psychological well-being of individual employees.

[0115] Thus, this system, centered around a server and an AI agent, can improve operational efficiency while also enabling adaptive support that takes into account the user's emotional needs, thereby increasing the overall productivity of the organization.

[0116] The following describes the processing flow.

[0117] Step 1:

[0118] The server automatically collects information from the data systems of each business unit. The collected data includes progress, resource usage, and task details. This data is converted to a standard format and integrated into the data warehouse.

[0119] Step 2:

[0120] The server uses an emotion engine to acquire audio and image data from the user's device. This data is analyzed in real time to generate parameters (e.g., stress level, motivation index) for recognizing the user's emotional state.

[0121] Step 3:

[0122] The AI ​​agent calculates task priorities based on integrated business data and emotional parameters. It also considers the impact of tasks on the user's emotions while developing the optimal work plan.

[0123] Step 4:

[0124] On the device, users receive generated work plans and emotion-based feedback. Users can review task reallocation suggestions tailored to their emotional state and adjust the plan as needed.

[0125] Step 5:

[0126] The server periodically monitors user feedback and activity using an emotion engine to detect changes. This allows it to readjust work plans in real time if necessary, maintaining an efficient and comfortable work environment.

[0127] Step 6:

[0128] The AI ​​agent analyzes the emotional dynamics of the entire team and proposes specific improvement measures to enhance teamwork. This includes recommending workshops to improve communication and implementing stress reduction measures.

[0129] (Example 2)

[0130] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0131] Traditional business management systems have struggled to provide work adjustments and support that take into account the emotional aspects of users. This resulted in problems not only with improving work efficiency but also with properly managing user stress and motivation. This posed a risk of decreased overall organizational productivity and team cohesion.

[0132] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0133] In this invention, the server includes means for collecting information, means for integrating and processing the collected information, means for analyzing voice tone and facial expressions to acquire emotional data, means for integrating the acquired emotional data with work information, means for formulating and executing work plans based on the integrated information, means for monitoring and adjusting the progress of work, means for providing feedback to the user, and means for autonomously adjusting work based on the user's stress level and motivation. This enables flexible work adjustment and support that takes into account the emotional aspects of the user.

[0134] "Means of collecting information" refers to the function of obtaining business-related data from each department and storing it in a database or similar system.

[0135] "Means for integrating and processing information" refers to functions that centralize collected data and convert it into a format that can be analyzed and utilized.

[0136] "Methods for acquiring emotional data by analyzing voice tone and facial expressions" refer to technologies that analyze a user's voice and video data to understand their emotional state.

[0137] "Means for integrating emotional data with business information" refers to a function that combines information about users' emotions with business-related data to improve and streamline operations.

[0138] "Means for formulating and executing work plans" refers to the function of formulating work plans based on integrated information and carrying out tasks according to those plans.

[0139] "Means for monitoring and adjusting work progress" refers to functions for checking the status of ongoing work and modifying plans and resources as needed.

[0140] "Means of providing feedback to users" refers to functions that provide users with evaluations and advice based on emotional data and work performance.

[0141] "Means of autonomously adjusting tasks based on user stress levels and motivation" refers to technologies that analyze the user's emotional state and optimize the allocation of workload and task priorities in real time.

[0142] This invention specifically describes a method for implementing a "cross-operational AI agent" system that adjusts tasks based on the user's emotional state.

[0143] The server uses data collection software to gather business information from each department and store it in a database. A SQL-based data management system is used for this purpose. The server also utilizes speech recognition AI and facial recognition AI as emotion engines to acquire emotional data in real time from the user's voice tone and facial expressions. Specific tools used include standard cloud-based speech recognition APIs and facial recognition APIs.

[0144] The server integrates acquired emotional data with business data and uses data mining techniques to quantify user stress levels and motivation. This utilizes libraries such as Python's pandas and scikit-learn. This allows the server to consider the user's emotional state, develop optimal work plans, and prioritize tasks accordingly.

[0145] The AI ​​agent utilizes a generative AI model to redistribute tasks when a user is overloaded, and offers suggestions for special projects or rewards when the user is highly motivated. In this way, flexible work adjustments based on the user's emotions are possible.

[0146] On their devices, users receive feedback generated based on emotional data. This is provided through dashboards built with web application frameworks such as React and Angular. Users can visually understand their stress and motivation levels and receive suggestions tailored to their work situation. For example, feedback such as "It would be good to take a short break" might be included.

[0147] As a concrete example, when some members of a project team are feeling pressured by a tight deadline, the AI ​​agent can be prompted with a message such as, "I would like to ask the AI ​​agent for advice on how to deal with the situation where some members of the project team are feeling stressed due to the tight deadline." This will automatically suggest a redistribution of tasks. This allows for a balance in workload while maintaining the user's psychological well-being.

[0148] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0149] Step 1:

[0150] The server collects business information from each department. The input received through the data collection software is in a different format for each department. The server stores this data in a centralized database. An SQL-based management system is used for data storage. This provides information that allows for an overview of the entire business.

[0151] Step 2:

[0152] The server uses an emotion engine to acquire emotional data from the user. The input for this process is the user's voice and video data. The server uses speech recognition AI and facial recognition AI to analyze voice tone and facial expressions, measuring the user's emotional state in real time. The output is quantified data on the user's stress level and motivation.

[0153] Step 3:

[0154] The server integrates the collected business data and emotional data. The input is the data obtained in steps 1 and 2, and the output is business information that takes emotional aspects into account. Data mining techniques are used to identify and analyze business risks and motivational factors for each user. This analysis utilizes Python's pandas and scikit-learn libraries.

[0155] Step 4:

[0156] The AI ​​agent develops a work plan based on integrated data. The output data from step 3 is used as input. The AI ​​agent utilizes a generative AI model to prioritize and dynamically adjust tasks. As output, an optimized work plan is generated, with tasks tailored to each user.

[0157] Step 5:

[0158] On the device, the user receives feedback from an AI agent. The input is feedback data generated by the AI ​​agent. The output on the device includes specific work suggestions that reflect stress levels and motivation, as well as alerts regarding the need for breaks. The feedback content is visualized through a dashboard created with React or Angular.

[0159] Step 6:

[0160] Users adjust their work based on feedback. By following the AI ​​agent's suggestions and modifying workload distribution and task priorities, they achieve both work efficiency and psychological well-being. The inputs in this step are feedback data and user decisions. The output is an adjusted work schedule and an improved work environment.

[0161] (Application Example 2)

[0162] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0163] In today's work environment, fluctuations in workers' emotions and motivation have a significant impact on work efficiency and productivity. However, traditional systems have failed to consider these emotional aspects when planning work and allocating tasks, which can lead to imbalances in workload and excessive burdens on workers. Furthermore, there have been insufficient means to understand and appropriately respond to the emotional flow throughout the organization.

[0164] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0165] In this invention, the server includes means for collecting information, means for integrating and processing the collected information, and means for recognizing the user's emotions and adjusting the work environment based on this recognition. This makes it possible to provide not only increased work efficiency but also a flexible work environment that takes into account the emotional aspects of the worker.

[0166] "Means for collecting information" refers to devices or methods for obtaining necessary information from each business department and related data sources.

[0167] "Means for integrating and processing collected information" refers to a device or method for centralizing information acquired in different formats and processing it in a way that is useful for business operations.

[0168] "Means for formulating and executing work plans based on integrated information" refers to a device or method for formulating an optimal work plan based on processed information and putting it into concrete action.

[0169] "Means for monitoring and adjusting work progress" refers to devices or methods for understanding the actual progress against a work plan and adjusting the plan or tasks as necessary.

[0170] "Means for recognizing user emotions and adjusting the work environment based on this recognition" refers to a device or method that analyzes user emotions in real time and optimizes the work environment based on the analysis results.

[0171] The system implementing this invention utilizes a server, an emotion recognition camera, a microphone, and dedicated emotion analysis software. The server collects user facial expression data and voice data in real time from the emotion recognition camera and microphone installed in the work environment. This data is analyzed using, for example, the Microsoft® Azure® emotion analysis API. The analysis results are compiled as information reflecting the user's emotional state.

[0172] The server integrates this emotional data and works with work management software to dynamically control work plans. Specifically, if a user is experiencing stress, it can redistribute tasks to other workers or robots. Furthermore, when a user is highly motivated, it can offer specific rewards to improve work efficiency. This makes it possible to improve productivity while maintaining the user's psychological well-being.

[0173] As a concrete example, in a robot used in a factory, if a worker exhibits fluctuations in performance, the system can instantly sense this and adjust the work task. For instance, if a worker is fatigued after lunch, the system might suggest adjusting the work speed or switching to a simpler task.

[0174] An example of a prompt to input into the generating AI model is: "In a factory environment, please tell me how to measure stress levels from workers' facial expressions and voice tone, and automate efficient task management."

[0175] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0176] Step 1:

[0177] The server collects user facial and audio data in real time through emotion recognition cameras and microphones installed in the work environment. The user's facial image and audio are acquired as input, and this data is prepared to be sent to the emotion analysis platform as output.

[0178] Step 2:

[0179] The server sends the collected data to an emotion analysis API to analyze the user's emotional state. Facial expression data and voice data are sent to the API as input, and the user's emotional state (e.g., stress level and motivation level) is obtained as output. Here, data analysis is performed to infer emotions from changes in facial expressions and tone of voice.

[0180] Step 3:

[0181] The server integrates the analyzed emotional information into the work management software. Emotional data is used as input, and information for adjusting work plans is generated as output. Specifically, if stress levels are high, suggestions for reducing workload are created.

[0182] Step 4:

[0183] The server redistributes tasks and adjusts work plans based on business management information. Integrated business data and sentiment data are used as input, and optimized work plans and task instructions are generated as output. This is a process that dynamically distributes tasks according to the user's state.

[0184] Step 5:

[0185] The server notifies the terminal of the adjusted work plan and provides feedback to the user. The input is an optimized work plan, and the output provides the user with actionable tasks and break suggestions. Specifically, the user receives a break alert and can use that time to recover.

[0186] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0187] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0188] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0189] [Second Embodiment]

[0190] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0191] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0192] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0193] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0194] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0195] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0196] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0197] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0198] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0199] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0200] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0201] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0202] The "cross-operational AI agent" system according to the present invention integrates information and tasks managed by various departments within a company, enabling efficient business execution. This system integrates and operates functions for information gathering and processing, work planning and execution, and progress monitoring and adjustment on a central system.

[0203] First, the server collects data in various formats provided by each department. It allows for centralized access to data from databases, spreadsheets, and specialized software. The collected data is standardized and integrated into the company's internal data warehouse for storage. This eliminates data inconsistencies across departments, enabling cross-departmental data analysis.

[0204] Next, the AI ​​agent uses this integrated data to analyze the priorities of each task and develop a work plan. The AI ​​uses machine learning algorithms to assess the importance and urgency of tasks and allocate resources efficiently. This ensures that internal operations are not carried out in isolation by individual departments, but rather optimized across the entire company.

[0205] On the device, users can check the progress of their work plan in real time. By monitoring whether the work is progressing as scheduled and taking action as needed, delays and problems can be detected early. This monitoring function also includes suggesting optimal solutions based on analysis results provided by AI.

[0206] For example, feedback data from the product development department is shared with the sales department in real time, and an AI agent analyzes it to optimize the timing of new product market launches and promotional activities. This facilitates smoother communication between departments and improves overall operational efficiency.

[0207] In this way, by having servers and AI agents autonomously perform a series of data processing and analysis, as well as work planning and monitoring, the present invention can streamline interdepartmental coordination work and drastically improve the productivity of the entire company.

[0208] The following describes the processing flow.

[0209] Step 1:

[0210] The server automatically collects data from each department's systems. Data sources include databases, spreadsheets, and cloud services, and this information is centralized through an ETL process. The server standardizes the data format and stores it in a central data warehouse.

[0211] Step 2:

[0212] The server provides integrated data to the AI ​​agent. The AI ​​agent analyzes the data using machine learning algorithms to assess the importance and urgency of the tasks. This generates a priority list for each task.

[0213] Step 3:

[0214] The server automatically constructs work plans for each department based on the priority list generated by the AI ​​agent. It calculates the required resources, makes optimal allocations, and formulates work plans. The formulated plans are automatically distributed to the terminals of the relevant parties.

[0215] Step 4:

[0216] On their devices, users can view the distributed work plans and update the progress of their tasks in real time. Users can also see the overall project status on the dashboard and update it when new information is added.

[0217] Step 5:

[0218] The server collects progress data sent from the terminals in real time and feeds it back to the AI ​​agent. The AI ​​analyzes the data and automatically generates warnings and improvement suggestions for areas where progress is lagging.

[0219] Step 6:

[0220] Based on the AI ​​agent's analysis results, the server prioritizes tasks and readjusts the work plan. If necessary, it issues emergency alerts to stakeholders to support the smooth progress of the project.

[0221] (Example 1)

[0222] Next, we will describe Example 1. 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."

[0223] The aim is to eliminate data inconsistencies and inefficiencies that arise when each department within a company independently manages information and tasks, and to optimize company-wide operations. In particular, it is difficult to centrally manage and utilize data when the data formats differ, and it is also a challenge to appropriately analyze and dynamically adjust task priorities.

[0224] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0225] In this invention, the server includes means for collecting information, means for integrating the collected information and standardizing the data format, and means for analyzing task priorities using a machine learning algorithm based on the standardized information. This enables centralized management of information across departments and effective task prioritization.

[0226] "Means of collecting information" refers to devices or functions for collecting information provided in different data formats from various departments within a company.

[0227] "Means of standardizing data formats" refers to devices or functions that convert collected information into a specific format and ensure consistency.

[0228] "Means of using machine learning algorithms" refers to devices or functions that utilize machine learning techniques for data analysis and task prioritization.

[0229] "Means for analyzing task priorities" refers to a device or function that evaluates each task performed within a company and prioritizes them based on their importance and urgency.

[0230] "Means for efficient resource allocation" refers to devices or functions that optimally allocate appropriate resources such as personnel, time, and equipment according to the priority of the analyzed tasks.

[0231] "Means for monitoring work progress" refers to devices or functions for tracking the status of ongoing tasks in real time and verifying whether they are progressing as planned.

[0232] "Means for early problem detection and solution provision" refers to a device or function that detects potential problems that may arise based on the progress of work and provides appropriate solutions to them.

[0233] As a means of implementing the invention, this system optimizes business operations by efficiently collecting, integrating, and analyzing information from multiple departments within a company.

[0234] First, the server collects information from each department. It connects to the databases, spreadsheets, and specialized software provided by each department via database connection tools and APIs to retrieve the necessary data. Because this collected data may be in different formats, a data conversion tool is used to consolidate it into a standard format (e.g., JSON or CSV).

[0235] The program utilizes machine learning frameworks such as Python's scikit-learn library for processing. This allows the server to analyze integrated data and evaluate the priority of each task. Since this priority is a crucial element directly related to improving operational efficiency, the server uses the analysis results to formulate a work plan and allocate resources appropriately.

[0236] On their devices, users can check the progress of their work plans in real time through a web browser. By using a front-end framework (e.g., React or Angular) to visually display the progress in a dashboard format, users can identify problems early. Furthermore, an AI agent suggests the optimal solution based on the analysis results, facilitating rapid problem resolution.

[0237] One concrete example is the process of sharing the launch date of a new product with the sales department based on feedback from the product development department. By having the AI ​​agent analyze the feedback and suggest an appropriate launch date and timing for promotional activities, interdepartmental communication is streamlined, and overall work efficiency is improved. An example of a prompt message is, "Based on feedback from the product development department, please analyze the appropriate timing for the next promotional activity."

[0238] This configuration enables the centralization and optimal management of information and tasks across the entire company.

[0239] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0240] Step 1:

[0241] The server collects information from various departments within the company. Inputs include data in various formats obtained from databases, spreadsheets, and specialized software. The server uses APIs and database connection tools to extract the necessary information from these sources. The output is a collection of the retrieved information.

[0242] Step 2:

[0243] The server standardizes the data format of the collected information. The input consists of data in different formats collected in Step 1. The server uses an ETL (Extract, Transform, Load) tool to convert the data into a standard format, unifying it into JSON or CSV. The output is the standardized, integrated data.

[0244] Step 3:

[0245] The server analyzes task priorities using standardized, integrated data. The input is the integrated data obtained in step 2. The server applies machine learning algorithms to analyze the data and evaluate the importance and urgency of the tasks. Specifically, it builds a model using the Python scikit-learn library and assigns priority labels to the tasks. The output is a priority list for each task.

[0246] Step 4:

[0247] The server develops a work plan and allocates resources optimally based on the priority list. The input is the priority list analyzed in step 3. The server uses a planning algorithm to create an efficient schedule and allocate resources appropriately. The output generates a detailed work plan and resource allocation list.

[0248] Step 5:

[0249] On the terminal, the user monitors how the work plan is progressing. The input is real-time progress data provided by the server. The user can view the progress information and address issues as needed by viewing a dashboard via a web browser. The output shows the latest progress and suggested solutions.

[0250] Step 6:

[0251] When a user checks their progress, the server presents problem-solving solutions generated by an AI agent. Input includes data on problem occurrences based on progress checks and a history of past solutions. The server uses a generative AI model to generate optimized prompts and solutions, providing feedback to the user. The output presents the most suitable problem-solving solution, enabling a rapid response.

[0252] (Application Example 1)

[0253] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0254] In production environments such as factories, data integration and work planning are complex, making efficient work execution difficult. Furthermore, while rapid response is required when anomalies occur, insufficient real-time information provision can lead to delays in response. To solve these problems, a system is needed that effectively integrates data, optimizes work plans, monitors progress, and detects and provides information on anomalies.

[0255] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0256] In this invention, the server includes means for collecting information, means for integrating and processing the collected information, means for formulating and executing work plans based on the integrated information, means for monitoring and adjusting the progress of work, and means for detecting anomalies and providing information. This enables centralized data management and efficient work planning in production activities, as well as real-time progress monitoring and anomaly response.

[0257] "Means of collecting information" refers to devices or software that acquire necessary data from various data sources inside and outside the factory.

[0258] "Means of integration and processing" refers to devices or software that standardize acquired data, aggregate and store it in a database, and perform any necessary analysis.

[0259] "Means for formulating and executing work plans" refers to devices or software that create an optimal work plan based on collected data and execute actions according to that plan.

[0260] "Means for monitoring and adjusting the progress of work" refers to devices or software that continuously monitor the progress of work being performed and adjust the plan as necessary.

[0261] "Means for detecting anomalies and providing information" refers to devices or software that detect problems or anomalies within a system and the work environment and suggest appropriate countermeasures.

[0262] The system for implementing this invention aims to enable efficient work schedule generation and execution, as well as rapid response to abnormalities, in production environments such as factories. The server collects information from various data sources inside and outside the factory, standardizes it, and integrates it into a data warehouse. The database used can be PostgreSQL or MongoDB.

[0263] The server utilizes collected data and employs machine learning algorithms such as TensorFlow or PyTorch to develop work plans. These plans are optimized for production efficiency and designed to maximize the use of internal resources. The server also monitors work progress in real time, detects anomalies if problems occur, and provides users with appropriate countermeasures. This allows factory workers to immediately perform optimal operations.

[0264] The terminal provides users with work plans and progress data in an easy-to-understand format. This allows workers to grasp the progress of work on-site in real time and get help revising work plans as needed. Users can also take quick countermeasures by following recommendations from the AI ​​agent when an anomaly occurs.

[0265] As a concrete example, when manufacturing a new product begins at a factory, a server aggregates data from each process in real time, and an AI agent generates an optimal work plan. This plan, based on recommendations from a computationally powerful AI, adjusts the supply chain and production lines as needed. An example of a prompt provided to the generating AI model is, "Generate an efficient work schedule based on factory production data. Provide real-time information if any anomalies occur."

[0266] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0267] Step 1:

[0268] The server collects information from various data sources both inside and outside the factory. It uses data provided by sensors, ERP systems, and logistics platforms as input, standardizes the data, and stores it in PostgreSQL or MongoDB. This integrates data that previously existed in disparate formats, making it centrally accessible.

[0269] Step 2:

[0270] The server generates an optimal work plan using machine learning algorithms based on the collected data. Here, TensorFlow or PyTorch is used for pattern recognition and predictive analytics on the data to determine the optimal resource allocation and work sequence. The output of this process is an optimized work plan, which is used to maximize factory productivity.

[0271] Step 3:

[0272] The terminal displays the generated work plan and the real-time progress of the factory. Inputs are work plan data received from the server and progress data from each process, while output is a visual interface provided to the user. This allows the user to instantly understand which processes are on schedule and adjust on-site operations accordingly.

[0273] Step 4:

[0274] The server analyzes the progress in real time as the work progresses and notifies the user if any anomalies occur. This includes a process to detect anomalies by comparing them with pre-configured criteria and predictions derived from historical data. When an anomaly is detected, the server generates a recommended solution and sends a notification to the user with a prompt.

[0275] Step 5:

[0276] Based on the information provided via the terminal, users take necessary actions. This includes manual adjustments and the execution of automated corrective procedures recommended by AI. This ensures factory stability and safety, minimizing production disruptions.

[0277] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0278] By combining the "cross-operational AI agent" system according to the present invention with an emotion engine that recognizes user emotions, even more advanced business management can be achieved. This makes it possible to provide a flexible work environment that not only improves the efficiency of operations but also takes into account the emotional aspects of the user.

[0279] The server collects information from each department and simultaneously obtains the user's emotional data using an emotion engine. The emotional data is analyzed in real time using the user's voice tone and facial recognition technology. By integrating this information with business data, it becomes possible to prioritize tasks and further optimize work plans.

[0280] The AI agent analyzes the data obtained from the emotion engine and evaluates the user's stress level and motivation. This enables flexible business adjustments based on emotions, such as redistributing tasks when the user is under excessive load and proposing rewards when the user is motivated.

[0281] On the terminal, the user can receive feedback that reflects the emotional data. For example, if the user is judged to be in a stressed state, the AI recommends taking a break or accessing support resources. Also, by analyzing the emotional trends of the entire team and presenting improvement points for communication to all members, the cohesion of the team can be enhanced.

[0282] As a specific example, when some members of a project team are strongly feeling the pressure of a short delivery period, the AI agent senses that emotion and automatically proposes task distribution to other members. This not only achieves an overall business balance but also maintains the mental health of individual employees.

[0283] In this way, this system centered around the server and the AI agent enables adaptive support that takes into account the emotional aspects of users while improving business efficiency, thereby enhancing the productivity of the entire organization. [[ID=M17]]

[0284] The following describes the processing flow.

[0285] Step 1:

[0286] The server automatically collects information from the data systems of each business department. The data collected includes progress status, resource usage status, and task details. These data are converted into a standard format and integrated into the data warehouse.

[0287] Step 2:

[0288] The server uses an emotion engine to obtain voice and image data from the user's terminal. These data are analyzed in real-time to generate parameters (e.g., stress level, motivation index) for recognizing the user's emotional state.

[0289] Step 3:

[0290] The AI agent calculates the priority of tasks based on the integrated business data and emotional parameters. Considering the impact of tasks on the user's emotions, it formulates an optimal work plan.

[0291] Step 4:

[0292] On the terminal, the user receives the generated work plan and feedback based on emotions. The user can view the proposed reallocation of tasks according to their emotional state and adjust the plan if necessary.

[0293] Step 5:

[0294] The server periodically monitors the user's feedback and activity status with the emotion engine to detect changes. Thereby, if necessary, it readjusts the work plan in real-time to maintain an efficient and comfortable working environment.

[0295] Step 6:

[0296] The AI ​​agent analyzes the emotional dynamics of the entire team and proposes specific improvement measures to enhance teamwork. This includes recommending workshops to improve communication and implementing stress reduction measures.

[0297] (Example 2)

[0298] Next, we will describe Example 2. 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".

[0299] Traditional business management systems have struggled to provide work adjustments and support that take into account the emotional aspects of users. This resulted in problems not only with improving work efficiency but also with properly managing user stress and motivation. This posed a risk of decreased overall organizational productivity and team cohesion.

[0300] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0301] In this invention, the server includes means for collecting information, means for integrating and processing the collected information, means for analyzing voice tone and facial expressions to acquire emotional data, means for integrating the acquired emotional data with work information, means for formulating and executing work plans based on the integrated information, means for monitoring and adjusting the progress of work, means for providing feedback to the user, and means for autonomously adjusting work based on the user's stress level and motivation. This enables flexible work adjustment and support that takes into account the emotional aspects of the user.

[0302] "Means of collecting information" refers to the function of obtaining business-related data from each department and storing it in a database or similar system.

[0303] "Means for integrating and processing information" refers to functions that centralize collected data and convert it into a format that can be analyzed and utilized.

[0304] The means for "analyzing voice tones and expressions to obtain emotion data" is a technology for analyzing a user's voice and video data to grasp the emotional state.

[0305] The means for "integrating emotion data with business information" is a function for combining information related to a user's emotions and data related to business to improve the efficiency and quality of business operations.

[0306] The means for "formulating and executing a work plan" is a function for formulating a work plan based on integrated information and performing business operations according to the plan.

[0307] The means for "monitoring and adjusting the progress of work" is a function for checking the ongoing work status and changing plans and resources as needed.

[0308] The means for "providing feedback to the user" is a function for providing the user with evaluations and advice based on emotion data and business status.

[0309] The means for "autonomously adjusting business operations based on the user's stress level and motivation" is a technology for analyzing the user's emotional state and optimizing the distribution of business load and task priorities in real time.

[0310] This invention discloses a method for specifically implementing a "Cross-Operational AI Agent" system that adjusts business operations based on the emotional state of the user.

[0311] The server uses data collection software to collect business information from each department and store it in a database. At this time, an SQL-based data management system is used. The server also utilizes voice recognition AI and facial expression recognition AI as an emotion engine to obtain emotion data from the user's voice tone and facial expression in real time. As specific tools, standard cloud voice recognition APIs and face recognition APIs are used.

[0312] The server integrates acquired emotional data with business data and uses data mining techniques to quantify user stress levels and motivation. This utilizes libraries such as Python's pandas and scikit-learn. This allows the server to consider the user's emotional state, develop optimal work plans, and prioritize tasks accordingly.

[0313] The AI ​​agent utilizes a generative AI model to redistribute tasks when a user is overloaded, and offers suggestions for special projects or rewards when the user is highly motivated. In this way, flexible work adjustments based on the user's emotions are possible.

[0314] On their devices, users receive feedback generated based on emotional data. This is provided through dashboards built with web application frameworks such as React and Angular. Users can visually understand their stress and motivation levels and receive suggestions tailored to their work situation. For example, feedback such as "It would be good to take a short break" might be included.

[0315] As a concrete example, when some members of a project team are feeling pressured by a tight deadline, the AI ​​agent can be prompted with a message such as, "I would like to ask the AI ​​agent for advice on how to deal with the situation where some members of the project team are feeling stressed due to the tight deadline." This will automatically suggest a redistribution of tasks. This allows for a balance in workload while maintaining the user's psychological well-being.

[0316] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0317] Step 1:

[0318] The server collects business information from each department. The input received through the data collection software is in a different format for each department. The server stores this data in a centralized database. An SQL-based management system is used for data storage. This provides information that allows for an overview of the entire business.

[0319] Step 2:

[0320] The server uses an emotion engine to acquire emotional data from the user. The input for this process is the user's voice and video data. The server uses speech recognition AI and facial recognition AI to analyze voice tone and facial expressions, measuring the user's emotional state in real time. The output is quantified data on the user's stress level and motivation.

[0321] Step 3:

[0322] The server integrates the collected business data and emotional data. The input is the data obtained in steps 1 and 2, and the output is business information that takes emotional aspects into account. Data mining techniques are used to identify and analyze business risks and motivational factors for each user. This analysis utilizes Python's pandas and scikit-learn libraries.

[0323] Step 4:

[0324] The AI ​​agent develops a work plan based on integrated data. The output data from step 3 is used as input. The AI ​​agent utilizes a generative AI model to prioritize and dynamically adjust tasks. As output, an optimized work plan is generated, with tasks tailored to each user.

[0325] Step 5:

[0326] On the device, the user receives feedback from an AI agent. The input is feedback data generated by the AI ​​agent. The output on the device includes specific work suggestions that reflect stress levels and motivation, as well as alerts regarding the need for breaks. The feedback content is visualized through a dashboard created with React or Angular.

[0327] Step 6:

[0328] Users adjust their work based on feedback. By following the AI ​​agent's suggestions and modifying workload distribution and task priorities, they achieve both work efficiency and psychological well-being. The inputs in this step are feedback data and user decisions. The output is an adjusted work schedule and an improved work environment.

[0329] (Application Example 2)

[0330] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0331] In today's work environment, fluctuations in workers' emotions and motivation have a significant impact on work efficiency and productivity. However, traditional systems have failed to consider these emotional aspects when planning work and allocating tasks, which can lead to imbalances in workload and excessive burdens on workers. Furthermore, there have been insufficient means to understand and appropriately respond to the emotional flow throughout the organization.

[0332] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0333] In this invention, the server includes means for collecting information, means for integrating and processing the collected information, and means for recognizing the user's emotions and adjusting the work environment based on this recognition. This makes it possible to provide not only increased work efficiency but also a flexible work environment that takes into account the emotional aspects of the worker.

[0334] "Means for collecting information" refers to devices or methods for obtaining necessary information from each business department and related data sources.

[0335] "Means for integrating and processing collected information" refers to a device or method for unifying information acquired in different formats and processing it in a way that is useful for business operations.

[0336] "Means for formulating and executing work plans based on integrated information" refers to a device or method for formulating an optimal work plan based on processed information and putting it into concrete action.

[0337] "Means for monitoring and adjusting work progress" refers to devices or methods for understanding the actual progress against a work plan and adjusting the plan or tasks as necessary.

[0338] "Means for recognizing user emotions and adjusting the work environment based on this recognition" refers to a device or method that analyzes user emotions in real time and optimizes the work environment based on the analysis results.

[0339] The system implementing this invention utilizes a server, an emotion-recognition camera, a microphone, and dedicated emotion analysis software. The server collects user facial expression data and voice data in real time from the emotion-recognition camera and microphone installed in the work environment. This data is analyzed using, for example, the Microsoft Azure Emotion Analysis API. The analysis results are compiled as information reflecting the user's emotional state.

[0340] The server integrates this emotional data and works with work management software to dynamically control work plans. Specifically, if a user is experiencing stress, it can redistribute tasks to other workers or robots. Furthermore, when a user is highly motivated, it can offer specific rewards to improve work efficiency. This makes it possible to improve productivity while maintaining the user's psychological well-being.

[0341] As a concrete example, in a robot used in a factory, if a worker exhibits fluctuations in performance, the system can instantly sense this and adjust the work task. For instance, if a worker is fatigued after lunch, the system might suggest adjusting the work speed or switching to a simpler task.

[0342] An example of a prompt sentence to input into the generating AI model is: "In a factory environment, please tell me how to measure stress levels from workers' facial expressions and voice tone, and automate efficient task management."

[0343] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0344] Step 1:

[0345] The server collects user facial and audio data in real time through emotion recognition cameras and microphones installed in the work environment. The user's facial image and audio are acquired as input, and this data is prepared to be sent to the emotion analysis platform as output.

[0346] Step 2:

[0347] The server sends the collected data to an emotion analysis API to analyze the user's emotional state. Facial expression data and voice data are sent to the API as input, and the user's emotional state (e.g., stress level and motivation level) is obtained as output. Here, data analysis is performed to infer emotions from changes in facial expressions and tone of voice.

[0348] Step 3:

[0349] The server integrates the analyzed emotional information into the work management software. Emotional data is used as input, and information for adjusting work plans is generated as output. Specifically, if stress levels are high, suggestions for reducing workload are created.

[0350] Step 4:

[0351] The server redistributes tasks and adjusts work plans based on business management information. Integrated business data and sentiment data are used as input, and optimized work plans and task instructions are generated as output. This is a process that dynamically distributes tasks according to the user's state.

[0352] Step 5:

[0353] The server notifies the terminal of the adjusted work plan and provides feedback to the user. The input is an optimized work plan, and the output provides the user with actionable tasks and break suggestions. Specifically, the user receives a break alert and can use that time to recover.

[0354] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0355] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0356] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0357] [Third Embodiment]

[0358] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0359] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0360] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0361] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0362] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0363] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0364] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0365] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0366] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0367] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0368] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0369] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0370] The "cross-operational AI agent" system according to the present invention integrates information and tasks managed by various departments within a company, enabling efficient business execution. This system integrates and operates functions for information gathering and processing, work planning and execution, and progress monitoring and adjustment on a central system.

[0371] First, the server collects data in various formats provided by each department. It allows for centralized access to data from databases, spreadsheets, and specialized software. The collected data is standardized and integrated into the company's internal data warehouse for storage. This eliminates data inconsistencies across departments, enabling cross-departmental data analysis.

[0372] Next, the AI ​​agent uses this integrated data to analyze the priorities of each task and develop a work plan. The AI ​​uses machine learning algorithms to assess the importance and urgency of tasks and allocate resources efficiently. This ensures that internal operations are not carried out in isolation by individual departments, but rather optimized across the entire company.

[0373] On the device, users can check the progress of their work plan in real time. By monitoring whether the work is progressing as scheduled and taking action as needed, delays and problems can be detected early. This monitoring function also includes suggesting optimal solutions based on analysis results provided by AI.

[0374] For example, feedback data from the product development department is shared with the sales department in real time, and an AI agent analyzes it to optimize the timing of new product market launches and promotional activities. This facilitates smoother communication between departments and improves overall operational efficiency.

[0375] In this way, by having servers and AI agents autonomously perform a series of data processing and analysis, as well as work planning and monitoring, the present invention can streamline interdepartmental coordination work and drastically improve the productivity of the entire company.

[0376] The following describes the processing flow.

[0377] Step 1:

[0378] The server automatically collects data from each department's systems. Data sources include databases, spreadsheets, and cloud services, and this information is centralized through an ETL process. The server standardizes the data format and stores it in a central data warehouse.

[0379] Step 2:

[0380] The server provides integrated data to the AI ​​agent. The AI ​​agent analyzes the data using machine learning algorithms to assess the importance and urgency of the tasks. This generates a priority list for each task.

[0381] Step 3:

[0382] The server automatically constructs work plans for each department based on the priority list generated by the AI ​​agent. It calculates the required resources, makes optimal allocations, and formulates work plans. The formulated plans are automatically distributed to the terminals of the relevant parties.

[0383] Step 4:

[0384] On their devices, users can view the distributed work plans and update the progress of their tasks in real time. Users can also see the overall project status on the dashboard and update it when new information is added.

[0385] Step 5:

[0386] The server collects progress data sent from the terminals in real time and feeds it back to the AI ​​agent. The AI ​​analyzes the data and automatically generates warnings and improvement suggestions for areas where progress is lagging.

[0387] Step 6:

[0388] Based on the AI ​​agent's analysis results, the server prioritizes tasks and readjusts the work plan. If necessary, it issues emergency alerts to stakeholders to support the smooth progress of the project.

[0389] (Example 1)

[0390] Next, we will describe Example 1. 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."

[0391] The aim is to eliminate data inconsistencies and inefficiencies that arise when each department within a company independently manages information and tasks, and to optimize company-wide operations. In particular, it is difficult to centrally manage and utilize data when the data formats differ, and it is also a challenge to appropriately analyze and dynamically adjust task priorities.

[0392] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0393] In this invention, the server includes means for collecting information, means for integrating the collected information and standardizing the data format, and means for analyzing task priorities using a machine learning algorithm based on the standardized information. This enables centralized management of information across departments and effective task prioritization.

[0394] "Means of collecting information" refers to devices or functions for collecting information provided in different data formats from various departments within a company.

[0395] "Means of standardizing data formats" refers to devices or functions that convert collected information into a specific format and ensure consistency.

[0396] "Means of using machine learning algorithms" refers to devices or functions that utilize machine learning techniques for data analysis and task prioritization.

[0397] "Means for analyzing task priorities" refers to a device or function that evaluates each task performed within a company and prioritizes them based on their importance and urgency.

[0398] "Means for efficient resource allocation" refers to devices or functions that optimally allocate appropriate resources such as personnel, time, and equipment according to the priority of the analyzed tasks.

[0399] "Means for monitoring work progress" refers to devices or functions for tracking the status of ongoing tasks in real time and verifying whether they are progressing as planned.

[0400] "Means for early problem detection and solution provision" refers to a device or function that detects potential problems that may arise based on the progress of work and provides appropriate solutions to them.

[0401] As a means of implementing the invention, this system optimizes business operations by efficiently collecting, integrating, and analyzing information from multiple departments within a company.

[0402] First, the server collects information from each department. It connects to the databases, spreadsheets, and specialized software provided by each department via database connection tools and APIs to retrieve the necessary data. Because this collected data may be in different formats, a data conversion tool is used to consolidate it into a standard format (e.g., JSON or CSV).

[0403] The program utilizes machine learning frameworks such as Python's scikit-learn library for processing. This allows the server to analyze integrated data and evaluate the priority of each task. Since this priority is a crucial element directly related to improving operational efficiency, the server uses the analysis results to formulate a work plan and allocate resources appropriately.

[0404] On their devices, users can check the progress of their work plans in real time through a web browser. By using a front-end framework (e.g., React or Angular) to visually display the progress in a dashboard format, users can identify problems early. Furthermore, an AI agent suggests the optimal solution based on the analysis results, facilitating rapid problem resolution.

[0405] One concrete example is the process of sharing the launch date of a new product with the sales department based on feedback from the product development department. By having the AI ​​agent analyze the feedback and suggest an appropriate launch date and timing for promotional activities, interdepartmental communication is streamlined, and overall work efficiency is improved. An example of a prompt message is, "Based on feedback from the product development department, please analyze the appropriate timing for the next promotional activity."

[0406] This configuration enables the centralization and optimal management of information and tasks across the entire company.

[0407] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0408] Step 1:

[0409] The server collects information from various departments within the company. Inputs include data in various formats obtained from databases, spreadsheets, and specialized software. The server uses APIs and database connection tools to extract the necessary information from these sources. The output is a collection of the retrieved information.

[0410] Step 2:

[0411] The server standardizes the data format of the collected information. The input consists of data in different formats collected in Step 1. The server uses an ETL (Extract, Transform, Load) tool to convert the data into a standard format, unifying it into JSON or CSV. The output is the standardized, integrated data.

[0412] Step 3:

[0413] The server analyzes task priorities using standardized, integrated data. The input is the integrated data obtained in step 2. The server applies machine learning algorithms to analyze the data and evaluate the importance and urgency of the tasks. Specifically, it builds a model using the Python scikit-learn library and assigns priority labels to the tasks. The output is a priority list for each task.

[0414] Step 4:

[0415] The server develops a work plan and allocates resources optimally based on the priority list. The input is the priority list analyzed in step 3. The server uses a planning algorithm to create an efficient schedule and allocate resources appropriately. The output generates a detailed work plan and resource allocation list.

[0416] Step 5:

[0417] On the terminal, the user monitors how the work plan is progressing. The input is real-time progress data provided by the server. The user can view the progress information and address issues as needed by viewing a dashboard via a web browser. The output shows the latest progress and suggested solutions.

[0418] Step 6:

[0419] When a user checks their progress, the server presents problem-solving solutions generated by an AI agent. Input includes data on problem occurrences based on progress checks and a history of past solutions. The server uses a generative AI model to generate optimized prompts and solutions, providing feedback to the user. The output presents the most suitable problem-solving solution, enabling a rapid response.

[0420] (Application Example 1)

[0421] Next, we will explain Application Example 1. In the following explanation, 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."

[0422] In production environments such as factories, data integration and work planning are complex, making efficient work execution difficult. Furthermore, while rapid response is required when anomalies occur, insufficient real-time information provision can lead to delays in response. To solve these problems, a system is needed that effectively integrates data, optimizes work plans, monitors progress, and detects and provides information on anomalies.

[0423] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0424] In this invention, the server includes means for collecting information, means for integrating and processing the collected information, means for formulating and executing work plans based on the integrated information, means for monitoring and adjusting the progress of work, and means for detecting anomalies and providing information. This enables centralized data management and efficient work planning in production activities, as well as real-time progress monitoring and anomaly response.

[0425] "Means of collecting information" refers to devices or software that acquire necessary data from various data sources inside and outside the factory.

[0426] "Means of integration and processing" refers to devices or software that standardize acquired data, aggregate and store it in a database, and perform any necessary analysis.

[0427] "Means for formulating and executing work plans" refers to devices or software that create an optimal work plan based on collected data and execute actions according to that plan.

[0428] "Means for monitoring and adjusting the progress of work" refers to devices or software that continuously monitor the progress of work being performed and adjust the plan as necessary.

[0429] "Means for detecting anomalies and providing information" refers to devices or software that detect problems or anomalies within a system and the work environment and suggest appropriate countermeasures.

[0430] The system for implementing this invention aims to enable efficient work schedule generation and execution, as well as rapid response to abnormalities, in production environments such as factories. The server collects information from various data sources inside and outside the factory, standardizes it, and integrates it into a data warehouse. The database used can be PostgreSQL or MongoDB.

[0431] The server utilizes collected data and employs machine learning algorithms such as TensorFlow or PyTorch to develop work plans. These plans are optimized for production efficiency and designed to maximize the use of internal resources. The server also monitors work progress in real time, detects anomalies if problems occur, and provides users with appropriate countermeasures. This allows factory workers to immediately perform optimal operations.

[0432] The terminal provides users with work plans and progress data in an easy-to-understand format. This allows workers to grasp the progress of work on-site in real time and get help revising work plans as needed. Users can also take quick countermeasures by following recommendations from the AI ​​agent when an anomaly occurs.

[0433] As a concrete example, when manufacturing a new product begins at a factory, a server aggregates data from each process in real time, and an AI agent generates an optimal work plan. This plan, based on recommendations from a computationally powerful AI, adjusts the supply chain and production lines as needed. An example of a prompt provided to the generating AI model is, "Generate an efficient work schedule based on factory production data. Provide real-time information if any anomalies occur."

[0434] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0435] Step 1:

[0436] The server collects information from various data sources both inside and outside the factory. It uses data provided by sensors, ERP systems, and logistics platforms as input, standardizes the data, and stores it in PostgreSQL or MongoDB. This integrates data that previously existed in disparate formats, making it centrally accessible.

[0437] Step 2:

[0438] The server generates an optimal work plan using machine learning algorithms based on the collected data. Here, TensorFlow or PyTorch is used for pattern recognition and predictive analytics on the data to determine the optimal resource allocation and work sequence. The output of this process is an optimized work plan, which is used to maximize factory productivity.

[0439] Step 3:

[0440] The terminal displays the generated work plan and the real-time progress of the factory. Inputs are work plan data received from the server and progress data from each process, while output is a visual interface provided to the user. This allows the user to instantly understand which processes are on schedule and adjust on-site operations accordingly.

[0441] Step 4:

[0442] The server analyzes the progress in real time as the work progresses and notifies the user if any anomalies occur. This includes a process to detect anomalies by comparing them with pre-configured criteria and predictions derived from historical data. When an anomaly is detected, the server generates a recommended solution and sends a notification to the user with a prompt.

[0443] Step 5:

[0444] Based on the information provided via the terminal, users take necessary actions. This includes manual adjustments and the execution of automated corrective procedures recommended by AI. This ensures factory stability and safety, minimizing production disruptions.

[0445] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0446] By combining the "cross-operational AI agent" system according to the present invention with an emotion engine that recognizes user emotions, even more advanced business management can be achieved. This makes it possible to provide a flexible work environment that not only improves the efficiency of operations but also takes into account the emotional aspects of the user.

[0447] The server collects information from each department while simultaneously acquiring user emotional data using an emotion engine. This emotional data is analyzed in real time using the user's voice tone and facial recognition technology. This information is integrated with business data, enabling further optimization of task prioritization and work plans.

[0448] The AI ​​agent analyzes data obtained from the emotion engine to assess the user's stress level and motivation. This enables flexible, emotion-based work adjustments, such as redistributing tasks when the user is overloaded or offering rewards when the user is highly motivated.

[0449] On their devices, users can receive feedback that reflects their emotional data. For example, if the AI ​​determines that a user is stressed, it may suggest taking a break or recommend access to support resources. Furthermore, by analyzing the emotional trends of the entire team and presenting areas for communication improvement to all members, team cohesion can be enhanced.

[0450] For example, if some members of a project team are feeling intense pressure due to a tight deadline, the AI ​​agent can sense this emotion and automatically suggest distributing tasks to other members. This not only balances the overall workload but also maintains the psychological well-being of individual employees.

[0451] Thus, this system, centered around a server and an AI agent, can improve operational efficiency while also enabling adaptive support that takes into account the user's emotional needs, thereby increasing the overall productivity of the organization.

[0452] The following describes the processing flow.

[0453] Step 1:

[0454] The server automatically collects information from the data systems of each business unit. The collected data includes progress, resource usage, and task details. This data is converted to a standard format and integrated into the data warehouse.

[0455] Step 2:

[0456] The server uses an emotion engine to acquire audio and image data from the user's device. This data is analyzed in real time to generate parameters (e.g., stress level, motivation index) for recognizing the user's emotional state.

[0457] Step 3:

[0458] The AI ​​agent calculates task priorities based on integrated business data and emotional parameters. It also considers the impact of tasks on the user's emotions while developing the optimal work plan.

[0459] Step 4:

[0460] On the device, users receive generated work plans and emotion-based feedback. Users can review task reallocation suggestions tailored to their emotional state and adjust the plan as needed.

[0461] Step 5:

[0462] The server periodically monitors user feedback and activity using an emotion engine to detect changes. This allows it to readjust work plans in real time if necessary, maintaining an efficient and comfortable work environment.

[0463] Step 6:

[0464] The AI ​​agent analyzes the emotional dynamics of the entire team and proposes specific improvement measures to enhance teamwork. This includes recommending workshops to improve communication and implementing stress reduction measures.

[0465] (Example 2)

[0466] Next, we will describe Example 2. 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."

[0467] Traditional business management systems have struggled to provide work adjustments and support that take into account the emotional aspects of users. This resulted in problems not only with improving work efficiency but also with properly managing user stress and motivation. This posed a risk of decreased overall organizational productivity and team cohesion.

[0468] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0469] In this invention, the server includes means for collecting information, means for integrating and processing the collected information, means for analyzing voice tone and facial expressions to acquire emotional data, means for integrating the acquired emotional data with work information, means for formulating and executing work plans based on the integrated information, means for monitoring and adjusting the progress of work, means for providing feedback to the user, and means for autonomously adjusting work based on the user's stress level and motivation. This enables flexible work adjustment and support that takes into account the emotional aspects of the user.

[0470] "Means of collecting information" refers to the function of obtaining business-related data from each department and storing it in a database or similar system.

[0471] "Means for integrating and processing information" refers to functions that centralize collected data and convert it into a format that can be analyzed and utilized.

[0472] "Methods for acquiring emotional data by analyzing voice tone and facial expressions" refers to technologies that analyze a user's voice and video data to understand their emotional state.

[0473] "Means for integrating emotional data with business information" refers to a function that combines information about users' emotions with business-related data to improve and streamline operations.

[0474] "Means for formulating and executing work plans" refers to the function of formulating work plans based on integrated information and carrying out tasks according to those plans.

[0475] "Means for monitoring and adjusting work progress" refers to functions for checking the status of ongoing work and modifying plans and resources as needed.

[0476] "Means of providing feedback to users" refers to functions that provide users with evaluations and advice based on emotional data and work performance.

[0477] "Means of autonomously adjusting tasks based on user stress levels and motivation" refers to technologies that analyze the user's emotional state and optimize the allocation of workload and task priorities in real time.

[0478] This invention specifically describes a method for implementing a "cross-operational AI agent" system that adjusts tasks based on the user's emotional state.

[0479] The server uses data collection software to gather business information from each department and store it in a database. A SQL-based data management system is used for this purpose. The server also utilizes speech recognition AI and facial recognition AI as emotion engines to acquire emotional data in real time from the user's voice tone and facial expressions. Specific tools used include standard cloud-based speech recognition APIs and facial recognition APIs.

[0480] The server integrates acquired emotional data with business data and uses data mining techniques to quantify user stress levels and motivation. This utilizes libraries such as Python's pandas and scikit-learn. This allows the server to consider the user's emotional state, develop optimal work plans, and prioritize tasks accordingly.

[0481] The AI ​​agent utilizes a generative AI model to redistribute tasks when a user is overloaded, and offers suggestions for special projects or rewards when the user is highly motivated. In this way, flexible work adjustments based on the user's emotions are possible.

[0482] On their devices, users receive feedback generated based on emotional data. This is provided through dashboards built with web application frameworks such as React and Angular. Users can visually understand their stress and motivation levels and receive suggestions tailored to their work situation. For example, feedback such as "It would be good to take a short break" might be included.

[0483] As a concrete example, when some members of a project team are feeling pressured by a tight deadline, the AI ​​agent can be prompted with a message such as, "I would like to ask the AI ​​agent for advice on how to deal with the situation where some members of the project team are feeling stressed due to the tight deadline." This will automatically suggest a redistribution of tasks. This allows for a balance in workload while maintaining the user's psychological well-being.

[0484] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0485] Step 1:

[0486] The server collects business information from each department. The input received through the data collection software is in a different format for each department. The server stores this data in a centralized database. An SQL-based management system is used for data storage. This provides information that allows for an overview of the entire business.

[0487] Step 2:

[0488] The server uses an emotion engine to acquire emotional data from the user. The input for this process is the user's voice and video data. The server uses speech recognition AI and facial recognition AI to analyze voice tone and facial expressions, measuring the user's emotional state in real time. The output is quantified data on the user's stress level and motivation.

[0489] Step 3:

[0490] The server integrates the collected business data and emotional data. The input is the data obtained in steps 1 and 2, and the output is business information that takes emotional aspects into account. Data mining techniques are used to identify and analyze business risks and motivational factors for each user. This analysis utilizes Python's pandas and scikit-learn libraries.

[0491] Step 4:

[0492] The AI ​​agent develops a work plan based on integrated data. The output data from step 3 is used as input. The AI ​​agent utilizes a generative AI model to prioritize and dynamically adjust tasks. As output, an optimized work plan is generated, with tasks tailored to each user.

[0493] Step 5:

[0494] On the device, the user receives feedback from an AI agent. The input is feedback data generated by the AI ​​agent. The output on the device includes specific work suggestions that reflect stress levels and motivation, as well as alerts regarding the need for breaks. The feedback content is visualized through a dashboard created with React or Angular.

[0495] Step 6:

[0496] Users adjust their work based on feedback. By following the AI ​​agent's suggestions and modifying workload distribution and task priorities, they achieve both work efficiency and psychological well-being. The inputs in this step are feedback data and user decisions. The output is an adjusted work schedule and an improved work environment.

[0497] (Application Example 2)

[0498] Next, we will explain application example 2. In the following explanation, 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."

[0499] In today's work environment, fluctuations in workers' emotions and motivation have a significant impact on work efficiency and productivity. However, traditional systems have failed to consider these emotional aspects when planning work and allocating tasks, which can lead to imbalances in workload and excessive burdens on workers. Furthermore, there have been insufficient means to understand and appropriately respond to the emotional flow throughout the organization.

[0500] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0501] In this invention, the server includes means for collecting information, means for integrating and processing the collected information, and means for recognizing the user's emotions and adjusting the work environment based on this recognition. This makes it possible to provide not only increased work efficiency but also a flexible work environment that takes into account the emotional aspects of the worker.

[0502] "Means for collecting information" refers to devices or methods for obtaining necessary information from each business department and related data sources.

[0503] "Means for integrating and processing collected information" refers to a device or method for unifying information acquired in different formats and processing it in a way that is useful for business operations.

[0504] "Means for formulating and executing work plans based on integrated information" refers to a device or method for formulating an optimal work plan based on processed information and putting it into concrete action.

[0505] "Means for monitoring and adjusting work progress" refers to devices or methods for understanding the actual progress against a work plan and adjusting the plan or tasks as necessary.

[0506] "Means for recognizing user emotions and adjusting the work environment based on this recognition" refers to a device or method that analyzes user emotions in real time and optimizes the work environment based on the analysis results.

[0507] The system implementing this invention utilizes a server, an emotion-recognition camera, a microphone, and dedicated emotion analysis software. The server collects user facial expression data and voice data in real time from the emotion-recognition camera and microphone installed in the work environment. This data is analyzed using, for example, the Microsoft Azure Emotion Analysis API. The analysis results are compiled as information reflecting the user's emotional state.

[0508] The server integrates this emotional data and works with work management software to dynamically control work plans. Specifically, if a user is experiencing stress, it can redistribute tasks to other workers or robots. Furthermore, when a user is highly motivated, it can offer specific rewards to improve work efficiency. This makes it possible to improve productivity while maintaining the user's psychological well-being.

[0509] As a concrete example, in a robot used in a factory, if a worker exhibits fluctuations in performance, the system can instantly sense this and adjust the work task. For instance, if a worker is fatigued after lunch, the system might suggest adjusting the work speed or switching to a simpler task.

[0510] An example of a prompt sentence to input into the generating AI model is: "In a factory environment, please tell me how to measure stress levels from workers' facial expressions and voice tone, and automate efficient task management."

[0511] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0512] Step 1:

[0513] The server collects user facial and audio data in real time through emotion recognition cameras and microphones installed in the work environment. The user's facial image and audio are acquired as input, and this data is prepared to be sent to the emotion analysis platform as output.

[0514] Step 2:

[0515] The server sends the collected data to an emotion analysis API to analyze the user's emotional state. Facial expression data and voice data are sent to the API as input, and the user's emotional state (e.g., stress level and motivation level) is obtained as output. Here, data analysis is performed to infer emotions from changes in facial expressions and tone of voice.

[0516] Step 3:

[0517] The server integrates the analyzed emotional information into the work management software. Emotional data is used as input, and information for adjusting work plans is generated as output. Specifically, if stress levels are high, suggestions for reducing workload are created.

[0518] Step 4:

[0519] The server redistributes tasks and adjusts work plans based on business management information. Integrated business data and sentiment data are used as input, and optimized work plans and task instructions are generated as output. This is a process that dynamically distributes tasks according to the user's state.

[0520] Step 5:

[0521] The server notifies the terminal of the adjusted work plan and provides feedback to the user. The input is an optimized work plan, and the output provides the user with actionable tasks and break suggestions. Specifically, the user receives a break alert and can use that time to recover.

[0522] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0523] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0524] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0525] [Fourth Embodiment]

[0526] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0527] As shown in Figure 7, the 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.

[0528] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0529] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0530] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0531] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0532] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0533] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0534] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0535] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0536] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0537] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0538] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0539] The "cross-operational AI agent" system according to the present invention integrates information and tasks managed by various departments within a company, enabling efficient business execution. This system integrates and operates functions for information gathering and processing, work planning and execution, and progress monitoring and adjustment on a central system.

[0540] First, the server collects data in various formats provided by each department. It allows for centralized access to data from databases, spreadsheets, and specialized software. The collected data is standardized and integrated into the company's internal data warehouse for storage. This eliminates data inconsistencies across departments, enabling cross-departmental data analysis.

[0541] Next, the AI ​​agent uses this integrated data to analyze the priorities of each task and develop a work plan. The AI ​​uses machine learning algorithms to assess the importance and urgency of tasks and allocate resources efficiently. This ensures that internal operations are not carried out in isolation by individual departments, but rather optimized across the entire company.

[0542] On the device, users can check the progress of their work plan in real time. By monitoring whether the work is progressing as scheduled and taking action as needed, delays and problems can be detected early. This monitoring function also includes suggesting optimal solutions based on analysis results provided by AI.

[0543] For example, feedback data from the product development department is shared with the sales department in real time, and an AI agent analyzes it to optimize the timing of new product market launches and promotional activities. This facilitates smoother communication between departments and improves overall operational efficiency.

[0544] In this way, by having servers and AI agents autonomously perform a series of data processing and analysis, as well as work planning and monitoring, the present invention can streamline interdepartmental coordination work and drastically improve the productivity of the entire company.

[0545] The following describes the processing flow.

[0546] Step 1:

[0547] The server automatically collects data from each department's systems. Data sources include databases, spreadsheets, and cloud services, and this information is centralized through an ETL process. The server standardizes the data format and stores it in a central data warehouse.

[0548] Step 2:

[0549] The server provides integrated data to the AI ​​agent. The AI ​​agent analyzes the data using machine learning algorithms to assess the importance and urgency of the tasks. This generates a priority list for each task.

[0550] Step 3:

[0551] The server automatically constructs work plans for each department based on the priority list generated by the AI ​​agent. It calculates the required resources, makes optimal allocations, and formulates work plans. The formulated plans are automatically distributed to the terminals of the relevant parties.

[0552] Step 4:

[0553] On their devices, users can view the distributed work plans and update the progress of their tasks in real time. Users can also see the overall project status on the dashboard and update it when new information is added.

[0554] Step 5:

[0555] The server collects progress data sent from the terminals in real time and feeds it back to the AI ​​agent. The AI ​​analyzes the data and automatically generates warnings and improvement suggestions for areas where progress is lagging.

[0556] Step 6:

[0557] Based on the AI ​​agent's analysis results, the server prioritizes tasks and readjusts the work plan. If necessary, it issues emergency alerts to stakeholders to support the smooth progress of the project.

[0558] (Example 1)

[0559] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0560] The aim is to eliminate data inconsistencies and inefficiencies that arise when each department within a company independently manages information and tasks, and to optimize company-wide operations. In particular, it is difficult to centrally manage and utilize data when the data formats differ, and it is also a challenge to appropriately analyze and dynamically adjust task priorities.

[0561] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0562] In this invention, the server includes means for collecting information, means for integrating the collected information and standardizing the data format, and means for analyzing task priorities using a machine learning algorithm based on the standardized information. This enables centralized management of information across departments and effective task prioritization.

[0563] "Means of collecting information" refers to devices or functions for collecting information provided in different data formats from various departments within a company.

[0564] "Means of standardizing data formats" refers to devices or functions that convert collected information into a specific format and ensure consistency.

[0565] "Means of using machine learning algorithms" refers to devices or functions that utilize machine learning techniques for data analysis and task prioritization.

[0566] "Means for analyzing task priorities" refers to a device or function that evaluates each task performed within a company and prioritizes them based on their importance and urgency.

[0567] "Means for efficient resource allocation" refers to devices or functions that optimally allocate appropriate resources such as personnel, time, and equipment according to the priority of the analyzed tasks.

[0568] "Means for monitoring work progress" refers to devices or functions for tracking the status of ongoing tasks in real time and verifying whether they are progressing as planned.

[0569] "Means for early problem detection and solution provision" refers to a device or function that detects potential problems that may arise based on the progress of work and provides appropriate solutions to them.

[0570] As a means of implementing the invention, this system optimizes business operations by efficiently collecting, integrating, and analyzing information from multiple departments within a company.

[0571] First, the server collects information from each department. It connects to the databases, spreadsheets, and specialized software provided by each department via database connection tools and APIs to retrieve the necessary data. Because this collected data may be in different formats, a data conversion tool is used to consolidate it into a standard format (e.g., JSON or CSV).

[0572] The program utilizes machine learning frameworks such as Python's scikit-learn library for processing. This allows the server to analyze integrated data and evaluate the priority of each task. Since this priority is a crucial element directly related to improving operational efficiency, the server uses the analysis results to formulate a work plan and allocate resources appropriately.

[0573] On their devices, users can check the progress of their work plans in real time through a web browser. By using a front-end framework (e.g., React or Angular) to visually display the progress in a dashboard format, users can identify problems early. Furthermore, an AI agent suggests the optimal solution based on the analysis results, facilitating rapid problem resolution.

[0574] One concrete example is the process of sharing the launch date of a new product with the sales department based on feedback from the product development department. By having the AI ​​agent analyze the feedback and suggest an appropriate launch date and timing for promotional activities, interdepartmental communication is streamlined, and overall work efficiency is improved. An example of a prompt message is, "Based on feedback from the product development department, please analyze the appropriate timing for the next promotional activity."

[0575] This configuration enables the centralization and optimal management of information and tasks across the entire company.

[0576] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0577] Step 1:

[0578] The server collects information from various departments within the company. Inputs include data in various formats obtained from databases, spreadsheets, and specialized software. The server uses APIs and database connection tools to extract the necessary information from these sources. The output is a collection of the retrieved information.

[0579] Step 2:

[0580] The server standardizes the data format of the collected information. The input consists of data in different formats collected in Step 1. The server uses an ETL (Extract, Transform, Load) tool to convert the data into a standard format, unifying it into JSON or CSV. The output is the standardized, integrated data.

[0581] Step 3:

[0582] The server analyzes task priorities using standardized, integrated data. The input is the integrated data obtained in step 2. The server applies machine learning algorithms to analyze the data and evaluate the importance and urgency of the tasks. Specifically, it builds a model using the Python scikit-learn library and assigns priority labels to the tasks. The output is a priority list for each task.

[0583] Step 4:

[0584] The server develops a work plan and allocates resources optimally based on the priority list. The input is the priority list analyzed in step 3. The server uses a planning algorithm to create an efficient schedule and allocate resources appropriately. The output generates a detailed work plan and resource allocation list.

[0585] Step 5:

[0586] On the terminal, the user monitors how the work plan is progressing. The input is real-time progress data provided by the server. The user can view the progress information and address issues as needed by viewing a dashboard via a web browser. The output shows the latest progress and suggested solutions.

[0587] Step 6:

[0588] When a user checks their progress, the server presents problem-solving solutions generated by an AI agent. Input includes data on problem occurrences based on progress checks and a history of past solutions. The server uses a generative AI model to generate optimized prompts and solutions, providing feedback to the user. The output presents the most suitable problem-solving solution, enabling a rapid response.

[0589] (Application Example 1)

[0590] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0591] In production environments such as factories, data integration and work planning are complex, making efficient work execution difficult. Furthermore, while rapid response is required when anomalies occur, insufficient real-time information provision can lead to delays in response. To solve these problems, a system is needed that effectively integrates data, optimizes work plans, monitors progress, and detects and provides information on anomalies.

[0592] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0593] In this invention, the server includes means for collecting information, means for integrating and processing the collected information, means for formulating and executing work plans based on the integrated information, means for monitoring and adjusting the progress of work, and means for detecting anomalies and providing information. This enables centralized data management and efficient work planning in production activities, as well as real-time progress monitoring and anomaly response.

[0594] "Means of collecting information" refers to devices or software that acquire necessary data from various data sources inside and outside the factory.

[0595] "Means of integration and processing" refers to devices or software that standardize acquired data, aggregate and store it in a database, and perform any necessary analysis.

[0596] "Means for formulating and executing work plans" refers to devices or software that create an optimal work plan based on collected data and execute actions according to that plan.

[0597] "Means for monitoring and adjusting the progress of work" refers to devices or software that continuously monitor the progress of work being performed and adjust the plan as necessary.

[0598] "Means for detecting anomalies and providing information" refers to devices or software that detect problems or anomalies within a system and the work environment and suggest appropriate countermeasures.

[0599] The system for implementing this invention aims to enable efficient work schedule generation and execution, as well as rapid response to abnormalities, in production environments such as factories. The server collects information from various data sources inside and outside the factory, standardizes it, and integrates it into a data warehouse. The database used can be PostgreSQL or MongoDB.

[0600] The server utilizes collected data and employs machine learning algorithms such as TensorFlow or PyTorch to develop work plans. These plans are optimized for production efficiency and designed to maximize the use of internal resources. The server also monitors work progress in real time, detects anomalies if problems occur, and provides users with appropriate countermeasures. This allows factory workers to immediately perform optimal operations.

[0601] The terminal provides users with work plans and progress data in an easy-to-understand format. This allows workers to grasp the progress of work on-site in real time and get help revising work plans as needed. Users can also take quick countermeasures by following recommendations from the AI ​​agent when an anomaly occurs.

[0602] As a concrete example, when manufacturing a new product begins at a factory, a server aggregates data from each process in real time, and an AI agent generates an optimal work plan. This plan, based on recommendations from a computationally powerful AI, adjusts the supply chain and production lines as needed. An example of a prompt provided to the generating AI model is, "Generate an efficient work schedule based on factory production data. Provide real-time information if any anomalies occur."

[0603] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0604] Step 1:

[0605] The server collects information from various data sources both inside and outside the factory. It uses data provided by sensors, ERP systems, and logistics platforms as input, standardizes the data, and stores it in PostgreSQL or MongoDB. This integrates data that previously existed in disparate formats, making it centrally accessible.

[0606] Step 2:

[0607] The server generates an optimal work plan using machine learning algorithms based on the collected data. Here, TensorFlow or PyTorch is used for pattern recognition and predictive analytics on the data to determine the optimal resource allocation and work sequence. The output of this process is an optimized work plan, which is used to maximize factory productivity.

[0608] Step 3:

[0609] The terminal displays the generated work plan and the real-time progress of the factory. Inputs are work plan data received from the server and progress data from each process, while output is a visual interface provided to the user. This allows the user to instantly understand which processes are on schedule and adjust on-site operations accordingly.

[0610] Step 4:

[0611] The server analyzes the progress in real time as the work progresses and notifies the user if any anomalies occur. This includes a process to detect anomalies by comparing them with pre-configured criteria and predictions derived from historical data. When an anomaly is detected, the server generates a recommended solution and sends a notification to the user with a prompt.

[0612] Step 5:

[0613] Based on the information provided via the terminal, users take necessary actions. This includes manual adjustments and the execution of automated corrective procedures recommended by AI. This ensures factory stability and safety, minimizing production disruptions.

[0614] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0615] By combining the "cross-operational AI agent" system according to the present invention with an emotion engine that recognizes user emotions, even more advanced business management can be achieved. This makes it possible to provide a flexible work environment that not only improves the efficiency of operations but also takes into account the emotional aspects of the user.

[0616] The server collects information from each department while simultaneously acquiring user emotional data using an emotion engine. This emotional data is analyzed in real time using the user's voice tone and facial recognition technology. This information is integrated with business data, enabling further optimization of task prioritization and work plans.

[0617] The AI ​​agent analyzes data obtained from the emotion engine to assess the user's stress level and motivation. This enables flexible, emotion-based work adjustments, such as redistributing tasks when the user is overloaded or offering rewards when the user is highly motivated.

[0618] On their devices, users can receive feedback that reflects their emotional data. For example, if the AI ​​determines that a user is stressed, it may suggest taking a break or recommend access to support resources. Furthermore, by analyzing the emotional trends of the entire team and presenting areas for communication improvement to all members, team cohesion can be enhanced.

[0619] For example, if some members of a project team are feeling intense pressure due to a tight deadline, the AI ​​agent can sense this emotion and automatically suggest distributing tasks to other members. This not only balances the overall workload but also maintains the psychological well-being of individual employees.

[0620] Thus, this system, centered around a server and an AI agent, can improve operational efficiency while also enabling adaptive support that takes into account the user's emotional needs, thereby increasing the overall productivity of the organization.

[0621] The following describes the processing flow.

[0622] Step 1:

[0623] The server automatically collects information from the data systems of each business unit. The collected data includes progress, resource usage, and task details. This data is converted to a standard format and integrated into the data warehouse.

[0624] Step 2:

[0625] The server uses an emotion engine to acquire audio and image data from the user's device. This data is analyzed in real time to generate parameters (e.g., stress level, motivation index) for recognizing the user's emotional state.

[0626] Step 3:

[0627] The AI ​​agent calculates task priorities based on integrated business data and emotional parameters. It also considers the impact of tasks on the user's emotions while developing the optimal work plan.

[0628] Step 4:

[0629] On the device, users receive generated work plans and emotion-based feedback. Users can review task reallocation suggestions tailored to their emotional state and adjust the plan as needed.

[0630] Step 5:

[0631] The server periodically monitors user feedback and activity using an emotion engine to detect changes. This allows it to readjust work plans in real time if necessary, maintaining an efficient and comfortable work environment.

[0632] Step 6:

[0633] The AI ​​agent analyzes the emotional dynamics of the entire team and proposes specific improvement measures to enhance teamwork. This includes recommending workshops to improve communication and implementing stress reduction measures.

[0634] (Example 2)

[0635] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0636] Traditional business management systems have struggled to provide work adjustments and support that take into account the emotional aspects of users. This resulted in problems not only with improving work efficiency but also with properly managing user stress and motivation. This posed a risk of decreased overall organizational productivity and team cohesion.

[0637] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0638] In this invention, the server includes means for collecting information, means for integrating and processing the collected information, means for analyzing voice tone and facial expressions to acquire emotional data, means for integrating the acquired emotional data with work information, means for formulating and executing work plans based on the integrated information, means for monitoring and adjusting the progress of work, means for providing feedback to the user, and means for autonomously adjusting work based on the user's stress level and motivation. This enables flexible work adjustment and support that takes into account the emotional aspects of the user.

[0639] "Means of collecting information" refers to the function of obtaining business-related data from each department and storing it in a database or similar system.

[0640] "Means for integrating and processing information" refers to functions that centralize collected data and convert it into a format that can be analyzed and utilized.

[0641] "Methods for acquiring emotional data by analyzing voice tone and facial expressions" refers to technologies that analyze a user's voice and video data to understand their emotional state.

[0642] "Means for integrating emotional data with business information" refers to a function that combines information about users' emotions with business-related data to improve and streamline operations.

[0643] "Means for formulating and executing work plans" refers to the function of formulating work plans based on integrated information and carrying out tasks according to those plans.

[0644] "Means for monitoring and adjusting work progress" refers to functions for checking the status of ongoing work and modifying plans and resources as needed.

[0645] "Means of providing feedback to users" refers to functions that provide users with evaluations and advice based on emotional data and work performance.

[0646] "Means of autonomously adjusting tasks based on user stress levels and motivation" refers to technologies that analyze the user's emotional state and optimize the allocation of workload and task priorities in real time.

[0647] This invention specifically describes a method for implementing a "cross-operational AI agent" system that adjusts tasks based on the user's emotional state.

[0648] The server uses data collection software to gather business information from each department and store it in a database. A SQL-based data management system is used for this purpose. The server also utilizes speech recognition AI and facial recognition AI as emotion engines to acquire emotional data in real time from the user's voice tone and facial expressions. Specific tools used include standard cloud-based speech recognition APIs and facial recognition APIs.

[0649] The server integrates acquired emotional data with business data and uses data mining techniques to quantify user stress levels and motivation. This utilizes libraries such as Python's pandas and scikit-learn. This allows the server to consider the user's emotional state, develop optimal work plans, and prioritize tasks accordingly.

[0650] The AI ​​agent utilizes a generative AI model to redistribute tasks when a user is overloaded, and offers suggestions for special projects or rewards when the user is highly motivated. In this way, flexible work adjustments based on the user's emotions are possible.

[0651] On their devices, users receive feedback generated based on emotional data. This is provided through dashboards built with web application frameworks such as React and Angular. Users can visually understand their stress and motivation levels and receive suggestions tailored to their work situation. For example, feedback such as "It would be good to take a short break" might be included.

[0652] As a concrete example, when some members of a project team are feeling pressured by a tight deadline, the AI ​​agent can be prompted with a message such as, "I would like to ask the AI ​​agent for advice on how to deal with the situation where some members of the project team are feeling stressed due to the tight deadline." This will automatically suggest a redistribution of tasks. This allows for a balance in workload while maintaining the user's psychological well-being.

[0653] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0654] Step 1:

[0655] The server collects business information from each department. The input received through the data collection software is in a different format for each department. The server stores this data in a centralized database. An SQL-based management system is used for data storage. This provides information that allows for an overview of the entire business.

[0656] Step 2:

[0657] The server uses an emotion engine to acquire emotional data from the user. The input for this process is the user's voice and video data. The server uses speech recognition AI and facial recognition AI to analyze voice tone and facial expressions, measuring the user's emotional state in real time. The output is quantified data on the user's stress level and motivation.

[0658] Step 3:

[0659] The server integrates the collected business data and emotional data. The input is the data obtained in steps 1 and 2, and the output is business information that takes emotional aspects into account. Data mining techniques are used to identify and analyze business risks and motivational factors for each user. This analysis utilizes Python's pandas and scikit-learn libraries.

[0660] Step 4:

[0661] The AI ​​agent develops a work plan based on integrated data. The output data from step 3 is used as input. The AI ​​agent utilizes a generative AI model to prioritize and dynamically adjust tasks. As output, an optimized work plan is generated, with tasks tailored to each user.

[0662] Step 5:

[0663] On the device, the user receives feedback from an AI agent. The input is feedback data generated by the AI ​​agent. The output on the device includes specific work suggestions that reflect stress levels and motivation, as well as alerts regarding the need for breaks. The feedback content is visualized through a dashboard created with React or Angular.

[0664] Step 6:

[0665] Users adjust their work based on feedback. By following the AI ​​agent's suggestions and modifying workload distribution and task priorities, they achieve both work efficiency and psychological well-being. The inputs in this step are feedback data and user decisions. The output is an adjusted work schedule and an improved work environment.

[0666] (Application Example 2)

[0667] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0668] In today's work environment, fluctuations in workers' emotions and motivation have a significant impact on work efficiency and productivity. However, traditional systems have failed to consider these emotional aspects when planning work and allocating tasks, which can lead to imbalances in workload and excessive burdens on workers. Furthermore, there have been insufficient means to understand and appropriately respond to the emotional flow throughout the organization.

[0669] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0670] In this invention, the server includes means for collecting information, means for integrating and processing the collected information, and means for recognizing the user's emotions and adjusting the work environment based on this recognition. This makes it possible to provide not only increased work efficiency but also a flexible work environment that takes into account the emotional aspects of the worker.

[0671] "Means for collecting information" refers to devices or methods for obtaining necessary information from each business department and related data sources.

[0672] "Means for integrating and processing collected information" refers to a device or method for unifying information acquired in different formats and processing it in a way that is useful for business operations.

[0673] "Means for formulating and executing work plans based on integrated information" refers to a device or method for formulating an optimal work plan based on processed information and putting it into concrete action.

[0674] "Means for monitoring and adjusting work progress" refers to devices or methods for understanding the actual progress against a work plan and adjusting the plan or tasks as necessary.

[0675] "Means for recognizing user emotions and adjusting the work environment based on this recognition" refers to a device or method that analyzes user emotions in real time and optimizes the work environment based on the analysis results.

[0676] The system implementing this invention utilizes a server, an emotion-recognition camera, a microphone, and dedicated emotion analysis software. The server collects user facial expression data and voice data in real time from the emotion-recognition camera and microphone installed in the work environment. This data is analyzed using, for example, the Microsoft Azure Emotion Analysis API. The analysis results are compiled as information reflecting the user's emotional state.

[0677] The server integrates this emotional data and works with work management software to dynamically control work plans. Specifically, if a user is experiencing stress, it can redistribute tasks to other workers or robots. Furthermore, when a user is highly motivated, it can offer specific rewards to improve work efficiency. This makes it possible to improve productivity while maintaining the user's psychological well-being.

[0678] As a concrete example, in a robot used in a factory, if a worker exhibits fluctuations in performance, the system can instantly sense this and adjust the work task. For instance, if a worker is fatigued after lunch, the system might suggest adjusting the work speed or switching to a simpler task.

[0679] An example of a prompt sentence to input into the generating AI model is: "In a factory environment, please tell me how to measure stress levels from workers' facial expressions and voice tone, and automate efficient task management."

[0680] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0681] Step 1:

[0682] The server collects user facial and audio data in real time through emotion recognition cameras and microphones installed in the work environment. The user's facial image and audio are acquired as input, and this data is prepared to be sent to the emotion analysis platform as output.

[0683] Step 2:

[0684] The server sends the collected data to an emotion analysis API to analyze the user's emotional state. Facial expression data and voice data are sent to the API as input, and the user's emotional state (e.g., stress level and motivation level) is obtained as output. Here, data analysis is performed to infer emotions from changes in facial expressions and tone of voice.

[0685] Step 3:

[0686] The server integrates the analyzed emotional information into the work management software. Emotional data is used as input, and information for adjusting work plans is generated as output. Specifically, if stress levels are high, suggestions for reducing workload are created.

[0687] Step 4:

[0688] The server redistributes tasks and adjusts work plans based on business management information. Integrated business data and sentiment data are used as input, and optimized work plans and task instructions are generated as output. This is a process that dynamically distributes tasks according to the user's state.

[0689] Step 5:

[0690] The server notifies the terminal of the adjusted work plan and provides feedback to the user. The input is an optimized work plan, and the output provides the user with actionable tasks and break suggestions. Specifically, the user receives a break alert and can use that time to recover.

[0691] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0692] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0693] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0694] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0695] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0696] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0697] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0698] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0699] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0700] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0701] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0702] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0703] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0704] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0705] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0706] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0707] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0708] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0709] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0710] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0711] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0712] The following is further disclosed regarding the embodiments described above.

[0713] (Claim 1)

[0714] Means of collecting information,

[0715] A means of integrating and processing the collected information,

[0716] A means of formulating and executing work plans based on integrated information,

[0717] Means for monitoring and coordinating the progress of the work,

[0718] A system that includes this.

[0719] (Claim 2)

[0720] The system according to claim 1, comprising means for centralizing data received from each business department in different data formats.

[0721] (Claim 3)

[0722] The system according to claim 1, comprising means for autonomously and dynamically adjusting the priorities of a work plan.

[0723] "Example 1"

[0724] (Claim 1)

[0725] Means of collecting information,

[0726] A means of integrating the collected information and standardizing the data format,

[0727] A method for analyzing task priorities using machine learning algorithms based on standardized information,

[0728] A means of formulating a work plan based on the analysis results and efficiently allocating resources,

[0729] A means of monitoring work progress, enabling real-time early detection of problems and the presentation of solutions,

[0730] A system that includes this.

[0731] (Claim 2)

[0732] The system according to claim 1, comprising means for centralizing information received from various business departments in different data formats, and for integrating and standardizing it using a data conversion tool.

[0733] (Claim 3)

[0734] The system according to claim 1, comprising means for autonomously and dynamically adjusting the priorities of a work plan using a machine learning algorithm.

[0735] "Application Example 1"

[0736] (Claim 1)

[0737] Means of collecting information,

[0738] A means of integrating and processing the collected information,

[0739] A means of formulating and executing work plans based on integrated information,

[0740] Means for monitoring and coordinating the progress of the work,

[0741] Means for detecting anomalies and providing information,

[0742] A system that includes this.

[0743] (Claim 2)

[0744] The system according to claim 1, comprising means for centralizing data received from each business department in different data formats.

[0745] (Claim 3)

[0746] The system according to claim 1, comprising means for displaying the progress of production activities in real time.

[0747] "Example 2 of combining an emotion engine"

[0748] (Claim 1)

[0749] Means of collecting information,

[0750] A means of integrating and processing the collected information,

[0751] A method for obtaining emotional data by analyzing voice tone and facial expressions,

[0752] A means of integrating acquired emotional data with business information,

[0753] A means of formulating and executing work plans based on integrated information,

[0754] Means for monitoring and coordinating the progress of the work,

[0755] Means of providing feedback to users,

[0756] A means of autonomously adjusting tasks based on the user's stress level and motivation,

[0757] A system that includes this.

[0758] (Claim 2)

[0759] The system according to claim 1, comprising means for centralizing data received from each business department in different data formats.

[0760] (Claim 3)

[0761] The system according to claim 1, comprising means for autonomously and dynamically adjusting the priorities of a work plan.

[0762] "Application example 2 when combining with an emotional engine"

[0763] (Claim 1)

[0764] Means of collecting information,

[0765] A means of integrating and processing the collected information,

[0766] A means of formulating and executing work plans based on integrated information,

[0767] Means for monitoring and coordinating the progress of the work,

[0768] A means of recognizing user emotions and adjusting the work environment based on this recognition,

[0769] A system that includes this.

[0770] (Claim 2)

[0771] The system according to claim 1, comprising means for centralizing data received from each business department in different data formats.

[0772] (Claim 3)

[0773] The system according to claim 1, comprising means for autonomously and dynamically adjusting the priorities of a work plan. [Explanation of Symbols]

[0774] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means of collecting information, A means of integrating and processing the collected information, A means of formulating and executing work plans based on integrated information, Means for monitoring and coordinating the progress of the work, Means for detecting anomalies and providing information, A system that includes this.

2. The system according to claim 1, comprising means for centralizing data received from each business department in different data formats.

3. The system according to claim 1, comprising means for displaying the progress of production activities in real time.

Images