system

Abstract

We provide the system. [Solution] A data collection method for obtaining user activity logs and task information, A problem analysis method that analyzes acquired data and identifies problems, A means for generating and displaying countermeasures for identified issues, An execution mechanism that configures and executes measures based on the measures selected by the user, A reporting mechanism that monitors the progress of execution and generates reports periodically, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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] In a modern business environment, there are problems that it is difficult for users to efficiently manage a large amount of business information and tasks they face daily and extract essential issues from them. Also, since there is a lack of support for users to utilize generative artificial intelligence to find appropriate countermeasures and execute them promptly, there are problems of a decrease in business efficiency and a delay in problem-solving. There is a demand for providing an effective and automated support tool to address such a situation.

Means for Solving the Problems

[0005] This invention aggregates business information using data collection means to acquire user activity logs and task information, and identifies potential problems using problem analysis means that analyze the acquired data. Furthermore, it supports planned problem solving by using a countermeasure generation means that generates and displays countermeasures for the identified problems. It also provides an execution means that allows the user to select the optimal countermeasure from those presented and then sets and executes it based on that selection, thereby enabling a rapid response to problems. In addition, it provides a reporting means that monitors the progress of execution and generates reports periodically, thereby providing feedback to the user and aiming to improve business efficiency and problem-solving ability.

[0006] "Data collection means" refers to technical means for obtaining user activity logs and task information.

[0007] "Problem analysis methods" are technical means for analyzing acquired data and identifying potential problems.

[0008] A "solution generation method" is a technical means for generating solutions to identified problems and displaying them to the user.

[0009] "Implementation means" refers to the technical means for setting an implementation plan based on the measures selected by the user and for executing those measures according to that plan.

[0010] A "reporting mechanism" is a technical means for monitoring the progress of implemented measures and periodically reporting progress and problems to the user.

[0011] A "machine learning model" is an algorithm or system used to analyze large amounts of data and learn patterns and trends in that data.

[0012] "Evaluation tools" are technical means for evaluating the effectiveness and feasibility of the generated countermeasures and for prioritizing them. [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] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This 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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This 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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This 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] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

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

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

[0016] In the following embodiments, a processor with a reference numeral (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 RAM (Random Access Memory) with a reference numeral 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 storage with a reference numeral 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, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[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] To implement this invention, it is necessary to construct a system that integrates data collection means, problem analysis means, countermeasure generation means, implementation means, and reporting means. The following describes how this system is configured and operates.

[0035] System configuration and operation

[0036] Data acquisition methods

[0037] The server automatically collects data from user activity logs and task management tools. It retrieves logs and task progress generated by users in their daily work via API or direct connection, and stores this information in a database. For example, when a user registers a task using project management software, that information is sent to the server.

[0038] Problem analysis means

[0039] The server utilizes natural language processing techniques and machine learning algorithms to analyze the collected data. This highlights frequently occurring problems and potential challenges in the user's work. Specifically, the server extracts keywords such as "progress delays" and "resource shortages" from the logs and classifies these problems.

[0040] Countermeasure generation means

[0041] Once a problem is identified, the server uses generative AI to generate solutions. These solutions are designed to be the most feasible and effective for the user. For example, if the problem is identified as "insufficient task progress management," the server will generate countermeasures such as "strengthening reminder settings" or "suggesting task splitting."

[0042] Execution method

[0043] When the user selects what they believe to be the most suitable solution from several options displayed, the server configures the specific settings to implement that solution. Based on the selected solution, the necessary tools are automatically installed and scripts are executed. For example, if the user selects "set automatic task reminders," the server will set up the corresponding reminders.

[0044] Reporting method

[0045] The server monitors the implementation status of configured measures in real time and periodically generates progress reports. These reports are delivered to the user's dashboard and via email, clearly indicating the level of achievement and any newly discovered issues. This allows users to always understand their work status and make adjustments as needed.

[0046] This system enables users to efficiently manage and resolve issues, supporting the smooth execution of daily tasks.

[0047] The following describes the processing flow.

[0048] Step 1:

[0049] The server collects the latest data from user activity logs and task management tools. Log collection is performed by querying information from the database using HTTP requests. It communicates with task management tools via API to retrieve task information.

[0050] Step 2:

[0051] The server analyzes the collected data. Using natural language processing, it extracts keywords from the logs, and a machine learning model performs data analysis to identify potential user issues. The analysis results are organized into issues such as "project delays" and "resource imbalances."

[0052] Step 3:

[0053] The server generates solutions to address the issues. Using generation AI, it generates specific solutions tailored to the user's work situation and lists them as proposed solutions. The generated solutions may be specific, such as "redistributing resources" or "setting up progress review meetings."

[0054] Step 4:

[0055] The user selects the most appropriate solution from several options provided by the server. A selection interface is provided on the terminal to make the selection process easy for the user.

[0056] Step 5:

[0057] The server will begin processing to implement the selected countermeasures. Specifically, it will automatically execute scripts to configure necessary tools and adjust system parameters. It will also modify the settings of project management tools and notification systems.

[0058] Step 6:

[0059] The server monitors the effectiveness of implemented measures and periodically generates progress reports. These reports are provided to users via their terminals, allowing them to visualize their progress and any newly discovered issues.

[0060] (Example 1)

[0061] 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."

[0062] Traditionally, identifying problems and proposing solutions in business management and project progress relied on human judgment, making efficient and rapid problem-solving difficult. Furthermore, the lack of measurement of the effectiveness of proposed solutions and prioritization hindered effective business improvement.

[0063] 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.

[0064] In this invention, the server includes data collection means for acquiring human operation information and business information, problem analysis means for analyzing the acquired information and identifying problems, and solution generation means for generating and displaying solutions to the identified problems. This makes it possible to quickly identify problems in business operations and automatically propose effective solutions.

[0065] "Human operation information" refers to action data generated when a human operates a computer system, and includes input information, clicks, and operation history.

[0066] "Business information" refers to information such as the progress of tasks and projects related to the activities of a company or organization, resource allocation, and performance indicators.

[0067] "Data collection means" refers to methods or devices for incorporating human operation information and business information into a system, and includes mechanisms for acquiring information through APIs, sensors, etc.

[0068] "Problem analysis tools" are methods or devices used to analyze acquired data and identify business problems from it, employing machine learning or data mining techniques.

[0069] A "solution generation means" is a method or apparatus used to devise and present solutions to an identified problem, and may utilize generative AI models or rule-based systems.

[0070] A "generative AI model" refers to an algorithm or model that uses artificial intelligence technology to generate results or suggestions based on data to achieve human instructions or goals.

[0071] A "prompt" is an instruction or question given to a generative AI model, providing specific guidelines to elicit the desired generation result.

[0072] This invention provides a system that enables humans to efficiently manage their daily tasks and automatically generate solutions to problems that are discovered. Specific embodiments of the system are described below.

[0073] The server collects human operation information and business information using data collection methods. This includes obtaining information from project management tools and task management systems using APIs. Specifically, the server retrieves data from project management software, which is a typical example of a business management tool, and stores it in a database stored within the system.

[0074] Next, the server uses machine learning and natural language processing techniques as problem analysis tools. Specifically, it extracts keywords from the data using a natural language processing library, and then uses machine learning algorithms to identify problems. Based on this process, the server can identify frequent problems and resource shortages that occur in the business.

[0075] Solutions to identified problems are generated by the server using a generative AI model. At this stage, the server generates prompts to solve the identified problems and inputs these prompts into the generative AI model to obtain effective solutions. For example, if the problem is identified as "the task is behind schedule," an example of a generated prompt might be, "Please provide specific solutions to improve the progress."

[0076] The server presents the generated solutions to the user and configures the execution settings based on the user's chosen solution. The user selects the best option from the presented choices, and the server automatically executes specific actions such as setting reminders. This allows the server to provide the user with direct support to improve work efficiency.

[0077] This system allows users to deepen their understanding of their work and solve problems efficiently. This makes it easy to identify business processes that need change or improvement, enabling quick responses.

[0078] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0079] Step 1:

[0080] The server retrieves user work information via the project management tool's API. This includes data on task creation, updates, and completion. The server converts the raw data retrieved from the API into a unified format and stores it in the database. The input is work data from the API, and the output is formatted work data.

[0081] Step 2:

[0082] The server analyzes stored business data using natural language processing techniques. Specifically, the server scans the text volume within the data and extracts specific keywords and phrases (e.g., delay in progress, change in priority). The input is formatted business data, and the output is the analyzed keywords and their frequency information.

[0083] Step 3:

[0084] The server generates prompt sentences to input into the AI ​​model based on the keywords obtained through analysis. This lays the foundation for extracting specific solutions. The input is the analyzed keyword information, and the output is the prompt sentences.

[0085] Step 4:

[0086] The server inputs a prompt message into the AI ​​model, which then generates possible solutions. The AI ​​model outputs multiple solutions in text format. The input is the prompt message, and the output is a list of proposed solutions.

[0087] Step 5:

[0088] The user receives a list of solutions provided by the server and selects the most appropriate solution based on their own judgment. This selection is fed back into the system and forms the basis for the next step. The input is the list of proposed solutions, and the output is the solution selected by the user.

[0089] Step 6:

[0090] The server automatically configures and implements the necessary settings and tools based on the user's chosen solution. For example, to set a reminder, it might integrate with a calendar app to schedule notifications. The input is the user's chosen solution, and the output is the specific configuration or execution procedure.

[0091] (Application Example 1)

[0092] 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."

[0093] In modern data centers and business management, the challenge of efficient operation is hampered by excessive tasks and inefficient resource allocation. This leads to data bottlenecks and delays in business progress, placing a significant burden on administrators. Therefore, there is a need for methods to effectively allocate resources and improve efficiency through data analysis and optimization.

[0094] 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.

[0095] In this invention, the server includes information gathering means for acquiring user behavior data and business information, analysis means for analyzing the acquired information and identifying problems, solution generation means for generating and displaying effective solutions to the identified problems, and means for supporting the optimization of computing tasks using clustering technology. This makes it possible to quickly analyze and efficiently resolve task overload and resource shortage problems in the data center.

[0096] "Information gathering means" refers to methods for acquiring user behavior data and business information, and enables the automatic collection of data.

[0097] "Analysis methods" refer to methods for identifying problems from collected information, and specifically to analytical techniques for extracting problems from data.

[0098] "Solution generation method" refers to a method of generating effective solutions to identified problems and presenting them to the user.

[0099] "Implementation methods" refer to the means by which a procedure is set based on the solution selected by the user and then actually carried out.

[0100] A "reporting system" is a means that monitors the status of implementation and periodically generates reports on progress and results.

[0101] Clustering is a technique for optimizing computational tasks by classifying data into several groups.

[0102] A "machine learning algorithm" is a computational method that allows computers to learn patterns based on data and perform predictions and analyses.

[0103] To implement this invention, a system is constructed to improve the operational efficiency of a data center. This system is server-centric and integrates information gathering means, analysis means, solution generation means, implementation means, and reporting means to function.

[0104] The server first acquires user behavior data and business information as a means of information gathering. This involves using hardware and software that automatically collects data by utilizing various sensors and APIs connected to the network.

[0105] Next, the collected information is analyzed using analytical tools. This analysis employs machine learning algorithms to extract and classify problems from the data. Specifically, clustering techniques using the Python scikit-learn library are used to support the optimization of computational tasks.

[0106] Once a problem is identified, a solution generation mechanism utilizes an AI model to devise countermeasures, which are then presented to the user. The generated solutions can be viewed and implemented through the user's terminal or the management screen.

[0107] Once the user selects a solution, it is implemented using the appropriate means. The server automatically configures the selected procedure and performs actions such as resource reallocation and task adjustment.

[0108] Finally, the server continuously monitors implementation status through reporting mechanisms and periodically reports progress and effectiveness to administrators. This includes a process of generating reports and notifying administrators via email or the administrator dashboard.

[0109] For example, if a particular server becomes overloaded, this system offers a solution such as "redistributing resources." By selecting this option, administrators can automatically redistribute resources appropriately, reducing the server load.

[0110] An example of a prompt that utilizes a generative AI model is as follows:

[0111] "Please tell me how to propose solutions to server overload problems within a data center."

[0112] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0113] Step 1:

[0114] The server automatically acquires user behavior data and work information from network-connected sensors and APIs using information gathering methods. This process involves collecting daily work logs and task progress through database access and API calls. Input is data from sensors and APIs, while output is structured information stored in the database.

[0115] Step 2:

[0116] The server analyzes the collected data using machine learning algorithms. This analysis utilizes the scikit-learn library to identify problems through clustering. The input is stored business data, and the output is the identified issues and discovered data patterns. In this process, the server performs data classification and problem extraction.

[0117] Step 3:

[0118] The server uses a generative AI model to generate solutions to the identified problem and presents them on the terminal using a solution generation mechanism. The input here is the problem identified in step 2, and the output is a list of solutions proposed to the user. The server calculates the optimal solution and displays it in the user interface.

[0119] Step 4:

[0120] The user selects the most suitable solution from those presented on the terminal. Based on this selection, the server implements the solution using various means, such as reallocating resources or adjusting tasks. The input is the user's solution selection, and the output is the implemented configuration changes and resource adjustments. The server automatically updates the configuration and puts the changes into action.

[0121] Step 5:

[0122] The server continuously monitors the execution status using reporting mechanisms and periodically reports progress and results to the administrator. Input is system execution data, and output is information notified via email or the management dashboard in the form of reports. The server checks the status and makes further adjustments as needed.

[0123] 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.

[0124] To implement this invention, it is necessary to construct a system that combines data collection means, problem analysis means, countermeasure generation means, execution means, and reporting means with an emotion engine that recognizes and utilizes user emotions in the analysis. The following details how this system is configured and operates.

[0125] System configuration and operation

[0126] Data acquisition methods

[0127] The server collects not only user activity logs and task information, but also user emotional data. Emotional data is obtained by analyzing facial expression data and voice data acquired from sensors such as cameras installed on the device. This data is collected with the user's consent and is managed securely.

[0128] Problem analysis means

[0129] The server comprehensively analyzes the acquired activity logs, task information, and emotional data. In particular, by utilizing the emotional engine to evaluate the user's current emotional state, it can identify emotionally-related issues such as stress and decreased motivation. This allows for the identification of human-factor-related problems that were difficult to detect with traditional data alone.

[0130] Countermeasure generation means

[0131] The server uses AI to generate optimal countermeasures, taking emotional data into consideration. These countermeasures are adjusted according to the user's emotional state; for example, if the user is experiencing high stress, the suggestions might include "increase rest time" or "suggest a relaxation session."

[0132] Execution method

[0133] Once the user selects a solution from the presented options, the server prepares to implement the chosen solution. If the solution is related to emotions, it sets up appropriate psychological intervention tools and provides notifications. For example, it might set the server to play relaxation music in response to the user's selection.

[0134] Reporting method

[0135] The server monitors user emotional changes and progress in response to implemented measures, and periodically generates comprehensive reports. These reports visualize the shift in emotions and the progress of the issues at that point in time, supporting user self-management.

[0136] This system allows users to comprehensively understand emotions and business data, promoting problem-solving from a more human-centered perspective.

[0137] The following describes the processing flow.

[0138] Step 1:

[0139] The server collects user activity logs, task information, and emotional data. Emotional data is extracted from the user's facial expressions captured through a camera connected to the device, and from voice data obtained through speech recognition. This data is stored in a secure database.

[0140] Step 2:

[0141] The server analyzes the collected data. Using natural language processing and machine learning models, it identifies operational issues from activity logs and task information. Furthermore, an emotion engine analyzes the user's real-time emotional state to evaluate stress levels and engagement. These results are integrated to clarify potential issues.

[0142] Step 3:

[0143] The server uses AI to generate specific countermeasures based on the analysis results. These countermeasures are optimized and displayed while taking into account the user's emotional state. For example, if high stress levels are detected, countermeasures such as "introduction to relaxation techniques" or "adjustment of the work environment" will be suggested.

[0144] Step 4:

[0145] The user selects the most suitable solution from the presented options. The selection is made through the terminal's user interface, and the selection information is sent to the server. This process is designed to be intuitive and easy to complete.

[0146] Step 5:

[0147] Based on the user's selection, the server initiates the process of executing the chosen action. For example, if the chosen action is "start a relaxation session," music or guided audio will be played through a dedicated app. If necessary, settings for the digital calendar and notification system will be changed.

[0148] Step 6:

[0149] The server monitors performance and changes in user sentiment, and periodically generates progress reports. These reports are sent to terminals, allowing users to visually review past sentiment trends and the effectiveness of countermeasures. Based on this information, users can adapt their own work strategies.

[0150] (Example 2)

[0151] 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".

[0152] In today's information environment, the stress and decreased motivation that users experience on a daily basis have a significant impact on work performance and productivity. Furthermore, traditional systems have insufficient measures to address the emotional aspects of users, hindering effective problem-solving. This has resulted in difficulties in maintaining work efficiency and the mental well-being of users.

[0153] 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.

[0154] In this invention, the server includes data collection means for acquiring user activity records, work information, and emotional information; problem analysis means for analyzing the acquired data and identifying issues, including the user's emotional state; and countermeasure generation means for generating and presenting countermeasures using a generated AI model based on the identified issues and the user's emotional state. This makes it possible to propose and implement effective countermeasures that take the user's emotional state into consideration in real time.

[0155] A "user" refers to an individual who uses the system to provide activity records and emotional information.

[0156] "Activity log" refers to the history of specific actions and inputs that occur when a user performs their daily tasks.

[0157] "Business information" refers to detailed data related to the tasks and projects that the user is working on.

[0158] "Emotional information" refers to data that represents the user's psychological state, obtained from their facial expressions and voice.

[0159] "Data collection methods" refer to the technologies and processes used to acquire user activity records, work information, and emotional information.

[0160] "Problem analysis methods" refer to the techniques and processes used to evaluate and identify users' problems and emotional states from collected data.

[0161] A "generative AI model" refers to an algorithm and model that uses artificial intelligence to generate optimal solutions based on data.

[0162] "Countermeasure generation method" refers to the technology and process that creates and presents countermeasures using a generation AI model, taking into account the identified problem and the user's emotional state.

[0163] "Real-time" refers to the ability of a system to process information instantly and reflect the results immediately.

[0164] "Effective measures" refer to appropriate action suggestions and environmental adjustments aimed at improving users' work efficiency and psychological well-being.

[0165] To implement this invention, a comprehensive configuration is required to support the entire system flow, from data collection, analysis, and countermeasure generation to implementation and evaluation. The details are described below.

[0166] First, the user's device is equipped with sensors necessary to collect activity and emotional data. Specifically, cameras and microphones are used to capture facial and voice data in real time. This data is transferred to a server with the user's permission. The server acts as a data collection system and stores the data transmitted from the device. The data is managed securely, and mechanisms are in place to protect user privacy.

[0167] Next, the server analyzes the collected data as a means of problem analysis. Emotion engines and machine learning algorithms are used to identify the user's emotional state and challenges. This analysis is crucial for making comprehensive judgments, including the user's stress level and motivation, utilizing artificial intelligence (AI) technology. This process also employs techniques for pattern recognition and correlation evaluation of the data.

[0168] Subsequently, a process takes place in which a generative AI model is run to generate countermeasures. The server inputs prompt sentences into the generative AI model based on the analysis results. For example, a possible prompt sentence might be, "If the user is showing high stress levels, suggest appropriate countermeasures." This prompt sentence serves as the basic information for the AI ​​model to suggest the optimal countermeasures. The model generates specific action plans based on the user's emotional state. These plans are presented to the user, who can then use them as options.

[0169] Once a user selects a course of action, the server coordinates its implementation. Especially when psychological intervention is needed, the system automatically launches appropriate music or applications on the device. For example, it might configure the system to play relaxation music, ensuring that music plays on the user's device.

[0170] The server continuously monitors changes in user emotions and the effectiveness of countermeasures, and generates reports to evaluate the results. These reports include a visual representation of user progress and emotional improvement, and support self-management.

[0171] In this way, the invention integrates digital and human elements to achieve comprehensive problem-solving for the user.

[0172] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0173] Step 1:

[0174] The server collects user activity records, work information, and emotional information from the terminal. The terminal's camera and microphone capture the user's facial expressions and voice, and transmit this information to the server. Using this data as input, the server stores the information in a database.

[0175] Step 2:

[0176] The server analyzes the collected data. Using an emotion engine, it analyzes facial expression and voice data to evaluate the user's emotional state. For example, it detects the presence or absence of a smile using a facial expression recognition algorithm. As output of this process, data is generated as an index related to the user's emotional state.

[0177] Step 3:

[0178] The server identifies issues based on the analysis results. It uses machine learning algorithms to determine stress levels and decreased motivation. Here, it identifies the current emotional state by comparing it with past data. The identified issues are generated as output.

[0179] Step 4:

[0180] The server inputs a prompt message into the AI ​​model for the identified problem. This prompt message might read, for example, "If the user is showing high stress levels, suggest appropriate countermeasures." Based on this input, the AI ​​model generates optimal countermeasures and outputs a list of solutions.

[0181] Step 5:

[0182] The user selects their desired solution from the presented list of solutions. For example, the user might select "Play relaxation music." This selection is sent to the server, and that information is generated as output data.

[0183] Step 6:

[0184] The server prepares to execute the action selected by the user. It sends a command to the terminal corresponding to the selected action. Specifically, it sets the terminal to play relaxation music. The input for this process is the output of step 5, which shows that the specific settings necessary for executing the process have been completed.

[0185] Step 7:

[0186] The server continuously monitors the user's emotional changes while the countermeasures are being implemented. It then collects data again to evaluate the extent of the emotional changes. This data is collected and analyzed, and a report is generated. This report visually displays which countermeasures were effective and for how long.

[0187] (Application Example 2)

[0188] 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".

[0189] Traditionally, problem analysis was performed based on user activity logs and task information, but problem analysis and solution generation did not take into account the user's emotional state. As a result, more humane support could not be provided, and issues related to emotions such as stress and decreased motivation were not adequately addressed. This presents a challenge in providing optimal support and a comfortable environment for users.

[0190] 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.

[0191] In this invention, the server includes data collection means for acquiring user activity logs, task information, and emotional data; problem analysis means for analyzing the acquired data and identifying problems; and countermeasure generation means for generating and presenting countermeasures for the identified problems while evaluating the user's emotional state. This enables more appropriate and humane problem solving while taking the user's emotions into consideration.

[0192] A "user" refers to an individual or representative of an organization that uses this system, and is the entity whose activity logs, task information, and sentiment data are collected and analyzed.

[0193] An "activity log" is data that records a user's actions and operations, and is information that the system uses to understand the user's situation.

[0194] "Task information" is data that indicates the tasks and schedules that a user should perform, and it is the basic data that the system uses to identify problems.

[0195] "Emotional data" refers to data that reflects the user's emotional state and is obtained through facial expression analysis and voice analysis.

[0196] "Data collection means" refers to technical means for acquiring user activity logs, task information, and sentiment data, and includes devices such as sensors and input devices.

[0197] "Problem analysis methods" are technical means that analyze acquired activity logs, task information, and sentiment data to identify the challenges that users face.

[0198] A "solution generation method" is a technical means that uses a generation AI to generate and present the most suitable solution to the user based on analyzed problem and sentiment data.

[0199] "Execution means" refers to the technical means by which the system takes specific actions based on the measures selected by the user and provides feedback as needed.

[0200] A "reporting mechanism" is a technical means of monitoring the implementation status of countermeasures and changes in user sentiment, and reporting the results to the user.

[0201] A "generative AI model" is an artificial intelligence model that generates optimal suggestions and responses for the user based on recorded data.

[0202] To implement this invention, an interactive robot assistant deployed in a smart home environment is used. This robot collects user activity logs, task information, and emotional data in real time and transmits the data to a server located in the cloud. For data collection, sensors such as cameras and microphones are used to analyze the user's movements and voice to obtain facial expression data and voice tone.

[0203] Based on the received data, the server evaluates the user's current emotional state using problem analysis tools and identifies any issues. In particular, it uses an emotion engine to analyze in detail the user's emotions, such as stress and motivation. The generative AI model then generates suggestions optimized for the user's state based on the identified issues and emotional data. Accordingly, prompts such as "If the user's emotional state is high stress, generate suggestions to promote relaxation" are used.

[0204] Based on the user's selection, the robot automatically performs actions such as playing relaxation music or adjusting smart home lighting. This includes integration with music service APIs and smart lighting devices. After execution, it monitors the user's emotional changes and the effectiveness of the actions, providing regular feedback through reporting mechanisms. Through this process, the goal is to improve the user's lifestyle for greater comfort.

[0205] As a concrete example, if a user is experiencing increased stress due to long hours of working from home, the robot might suggest, "You seem a little tired today, would you mind listening to some relaxing music?" and then proceed to do so after receiving the user's approval. This allows the user to refresh both mentally and physically, enabling them to work more efficiently.

[0206] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0207] Step 1:

[0208] The device collects user activity logs, task information, and sentiment data. Input is raw data acquired from sensors such as cameras and microphones. The device organizes this data and converts it into a format for transmission to the server. Output is a standardized dataset.

[0209] Step 2:

[0210] The server analyzes the received data using a problem analysis tool. The input is a standardized dataset sent from the terminal. The server processes the data using an emotion engine and machine learning models to evaluate the user's current emotional state and identify the problem. The output is the user's emotional state and the identified problem.

[0211] Step 3:

[0212] The server generates countermeasures based on the identified issues and emotional states. The input is the user's emotional state and issues obtained through issue analysis. The server uses a generative AI model to create optimal countermeasures and constructs suggestions for the user based on the prompt "Generate suggestions to promote relaxation." The output is a customized set of countermeasures.

[0213] Step 4:

[0214] The user receives proposed solutions from the server and selects the most appropriate solution. The input is the proposed solutions sent from the server. The user selects the suggestion best suited to their situation and provides feedback to the server. The output is information about the solution selected by the user.

[0215] Step 5:

[0216] The server sends instructions to the terminal or associated device to execute the action selected by the user. The input is the action selected by the user. The server utilizes music service APIs and smart home devices to play relaxation music or send signals to adjust lighting. The output is the specific relaxation action that was performed.

[0217] Step 6:

[0218] After the countermeasures are implemented, the server re-evaluates the user's emotional changes and monitors progress and effectiveness. The input is the user's emotional data, which is acquired again. The server provides feedback on the results of the implementation to the user through reporting mechanisms and prepares the next countermeasures as needed. This output serves as feedback to the user and guidance for the next action.

[0219] 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.

[0220] Data generation model 58 is a 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.

[0221] 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.

[0222] [Second Embodiment]

[0223] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0224] 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.

[0225] 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).

[0226] 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.

[0227] 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.

[0228] 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).

[0229] 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.

[0230] 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.

[0231] 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.

[0232] 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.

[0233] 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.

[0234] 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".

[0235] To implement this invention, it is necessary to construct a system that integrates data collection means, problem analysis means, countermeasure generation means, implementation means, and reporting means. The following describes how this system is configured and operates.

[0236] System configuration and operation

[0237] Data acquisition methods

[0238] The server automatically collects data from user activity logs and task management tools. It retrieves logs and task progress generated by users in their daily work via API or direct connection, and stores this information in a database. For example, when a user registers a task using project management software, that information is sent to the server.

[0239] Problem analysis means

[0240] The server utilizes natural language processing techniques and machine learning algorithms to analyze the collected data. This highlights frequently occurring problems and potential challenges in the user's work. Specifically, the server extracts keywords such as "progress delays" and "resource shortages" from the logs and classifies these problems.

[0241] Countermeasure generation means

[0242] Once a problem is identified, the server uses generative AI to generate solutions. These solutions are designed to be the most feasible and effective for the user. For example, if the problem is identified as "insufficient task progress management," the server will generate countermeasures such as "strengthening reminder settings" or "suggesting task splitting."

[0243] Execution method

[0244] When the user selects what they believe to be the most suitable solution from several options displayed, the server configures the specific settings to implement that solution. Based on the selected solution, the necessary tools are automatically installed and scripts are executed. For example, if the user selects "set automatic task reminders," the server will set up the corresponding reminders.

[0245] Reporting method

[0246] The server monitors the implementation status of configured measures in real time and periodically generates progress reports. These reports are delivered to the user's dashboard and via email, clearly indicating the level of achievement and any newly discovered issues. This allows users to always understand their work status and make adjustments as needed.

[0247] This system enables users to efficiently manage and resolve issues, supporting the smooth execution of daily tasks.

[0248] The following describes the processing flow.

[0249] Step 1:

[0250] The server collects the latest data from user activity logs and task management tools. Log collection is performed by querying information from the database using HTTP requests. It communicates with task management tools via API to retrieve task information.

[0251] Step 2:

[0252] The server analyzes the collected data. Using natural language processing, it extracts keywords from the logs, and a machine learning model performs data analysis to identify potential user issues. The analysis results are organized into issues such as "project delays" and "resource imbalances."

[0253] Step 3:

[0254] The server generates solutions to address the issues. Using generation AI, it generates specific solutions tailored to the user's work situation and lists them as proposed solutions. The generated solutions may be specific, such as "redistributing resources" or "setting up progress review meetings."

[0255] Step 4:

[0256] The user selects the most appropriate solution from several options provided by the server. A selection interface is provided on the terminal to make the selection process easy for the user.

[0257] Step 5:

[0258] The server will begin processing to implement the selected countermeasures. Specifically, it will automatically execute scripts to configure necessary tools and adjust system parameters. It will also modify the settings of project management tools and notification systems.

[0259] Step 6:

[0260] The server monitors the effectiveness of implemented measures and periodically generates progress reports. These reports are provided to users via their terminals, allowing them to visualize their progress and any newly discovered issues.

[0261] (Example 1)

[0262] 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."

[0263] Traditionally, identifying problems and proposing solutions in business management and project progress relied on human judgment, making efficient and rapid problem-solving difficult. Furthermore, the lack of measurement of the effectiveness of proposed solutions and prioritization hindered effective business improvement.

[0264] 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.

[0265] In this invention, the server includes data collection means for acquiring human operation information and business information, problem analysis means for analyzing the acquired information and identifying problems, and solution generation means for generating and displaying solutions to the identified problems. This makes it possible to quickly identify problems in business operations and automatically propose effective solutions.

[0266] "Human operation information" refers to action data generated when a human operates a computer system, and includes input information, clicks, and operation history.

[0267] "Business information" refers to information such as the progress of tasks and projects related to the activities of a company or organization, resource allocation, and performance indicators.

[0268] "Data collection means" refers to methods or devices for incorporating human operation information and business information into a system, and includes mechanisms for acquiring information through APIs, sensors, etc.

[0269] "Problem analysis tools" are methods or devices used to analyze acquired data and identify business problems from it, employing machine learning or data mining techniques.

[0270] A "solution generation means" is a method or apparatus used to devise and present solutions to an identified problem, and may utilize generative AI models or rule-based systems.

[0271] A "generative AI model" refers to an algorithm or model that uses artificial intelligence technology to generate results or suggestions based on data to achieve human instructions or goals.

[0272] A "prompt" is an instruction or question given to a generative AI model, providing specific guidelines to elicit the desired generation result.

[0273] This invention provides a system that enables humans to efficiently manage their daily tasks and automatically generate solutions to problems that are discovered. Specific embodiments of the system are described below.

[0274] The server collects human operation information and business information using data collection methods. This includes obtaining information from project management tools and task management systems using APIs. Specifically, the server retrieves data from project management software, which is a typical example of a business management tool, and stores it in a database stored within the system.

[0275] Next, the server uses machine learning and natural language processing techniques as problem analysis tools. Specifically, it extracts keywords from the data using a natural language processing library, and then uses machine learning algorithms to identify problems. Based on this process, the server can identify frequent problems and resource shortages that occur in the business.

[0276] Solutions to identified problems are generated by the server using a generative AI model. At this stage, the server generates prompts to solve the identified problems and inputs these prompts into the generative AI model to obtain effective solutions. For example, if the problem is identified as "the task is behind schedule," an example of a generated prompt might be, "Please provide specific solutions to improve the progress."

[0277] The server presents the generated solutions to the user and configures the execution settings based on the user's chosen solution. The user selects the best option from the presented choices, and the server automatically executes specific actions such as setting reminders. This allows the server to provide the user with direct support to improve work efficiency.

[0278] By using this system, users can deepen their understanding of their own business and solve problems efficiently. As a result, it becomes possible to easily identify business processes that require changes or improvements and to achieve prompt responses.

[0279] The flow of the specific process in Example 1 will be described with reference to FIG. 11.

[0280] Step 1:

[0281] The server obtains the user's business information via the API of the project management tool. This includes data on task creation, update, and completion. The server converts the raw data obtained from the API into a unified format and stores it in the database. The input is the business data from the API, and the output is the formatted business data.

[0282] Step 2:

[0283] The server analyzes the stored business data using natural language processing technology. Specifically, the server scans the text volume in the data and extracts specific keywords and phrases (e.g., progress delay, priority change). The input is the formatted business data, and the output is the analyzed keywords and their frequency information.

[0284] Step 3:

[0285] The server generates a prompt sentence for inputting into the AI model based on the keywords obtained by the analysis. This provides a basis for extracting specific solutions. The input is the analyzed keyword information, and the output is the prompt sentence.

[0286] Step 4:

[0287] The server inputs the prompt sentence into the generative AI model to generate possible solutions. The AI model outputs a list of proposed solutions in text format. The input is the prompt sentence, and the output is the list of proposed solutions.

[0288] Step 5:

[0289] The user receives a list of solutions provided by the server and selects the most appropriate solution based on their own judgment. This selection is fed back into the system and forms the basis for the next step. The input is the list of proposed solutions, and the output is the solution selected by the user.

[0290] Step 6:

[0291] The server automatically configures and implements the necessary settings and tools based on the user's chosen solution. For example, to set a reminder, it might integrate with a calendar app to schedule notifications. The input is the user's chosen solution, and the output is the specific configuration or execution procedure.

[0292] (Application Example 1)

[0293] 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."

[0294] In modern data centers and business management, the challenge of efficient operation is hampered by excessive tasks and inefficient resource allocation. This leads to data bottlenecks and delays in business progress, placing a significant burden on administrators. Therefore, there is a need for methods to effectively allocate resources and improve efficiency through data analysis and optimization.

[0295] 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.

[0296] In this invention, the server includes information gathering means for acquiring user behavior data and business information, analysis means for analyzing the acquired information and identifying problems, solution generation means for generating and displaying effective solutions to the identified problems, and means for supporting the optimization of computing tasks using clustering technology. This makes it possible to quickly analyze and efficiently resolve task overload and resource shortage problems in the data center.

[0297] "Information gathering means" refers to methods for acquiring user behavior data and business information, and enables the automatic collection of data.

[0298] "Analysis methods" refer to methods for identifying problems from collected information, and specifically to analytical techniques for extracting problems from data.

[0299] "Solution generation method" refers to a method of generating effective solutions to identified problems and presenting them to the user.

[0300] "Implementation methods" refer to the means by which a procedure is set based on the solution selected by the user and then actually carried out.

[0301] A "reporting system" is a means that monitors the status of implementation and periodically generates reports on progress and results.

[0302] Clustering is a technique for optimizing computational tasks by classifying data into several groups.

[0303] A "machine learning algorithm" is a computational method that allows computers to learn patterns based on data and perform predictions and analyses.

[0304] To implement this invention, a system is constructed to improve the operational efficiency of a data center. This system is server-centric and integrates information gathering means, analysis means, solution generation means, implementation means, and reporting means to function.

[0305] First, as an information collection means, the server acquires the user's behavioral data and business information. For this, it uses hardware and software that utilize various sensors and APIs connected to the network to automatically collect data.

[0306] Next, the collected information is analyzed by the analysis means. In this analysis, by using machine learning algorithms, problems are extracted and classified from the data. Specifically, clustering techniques using the scikit - learn library in Python are used to assist in the optimization of computational tasks.

[0307] When the issues are identified, countermeasures are devised using the generated AI model by the solution generation means and presented to the user. The generated solutions can be confirmed through the user terminal or the management screen and are in an executable state.

[0308] When the user selects a solution, it is transferred to execution by the implementation means. The server automatically sets the selected procedure and performs implementations such as resource redistribution and task adjustment.

[0309] Finally, by the reporting means, the server continuously monitors the implementation status and regularly reports the progress and effects to the administrator. This includes the process of generating reports and notifying them via email or the administrator dashboard.

[0310] As a specific example, when a specific server becomes overloaded, this system provides solutions such as "resource redistribution". By selecting this, the administrator can automatically have the resources appropriately redistributed and the server load reduced.

[0311] Examples of prompt sentences for utilizing the generated AI model are as follows.

[0312] "Please teach me how to propose countermeasures for the server overload problem in the data center."

[0313] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0314] Step 1:

[0315] The server automatically acquires user behavior data and work information from network-connected sensors and APIs using information gathering methods. This process involves collecting daily work logs and task progress through database access and API calls. Input is data from sensors and APIs, while output is structured information stored in the database.

[0316] Step 2:

[0317] The server analyzes the collected data using machine learning algorithms. This analysis utilizes the scikit-learn library to identify problems through clustering. The input is stored business data, and the output is the identified issues and discovered data patterns. In this process, the server performs data classification and problem extraction.

[0318] Step 3:

[0319] The server uses a generative AI model to generate solutions to the identified problem and presents them on the terminal using a solution generation mechanism. The input here is the problem identified in step 2, and the output is a list of solutions proposed to the user. The server calculates the optimal solution and displays it in the user interface.

[0320] Step 4:

[0321] The user selects the most suitable solution from those presented on the terminal. Based on this selection, the server implements the solution using various means, such as reallocating resources or adjusting tasks. The input is the user's solution selection, and the output is the implemented configuration changes and resource adjustments. The server automatically updates the configuration and puts the changes into action.

[0322] Step 5:

[0323] The server continuously monitors the execution status using reporting mechanisms and periodically reports progress and results to the administrator. Input is system execution data, and output is information notified via email or the management dashboard in the form of reports. The server checks the status and makes further adjustments as needed.

[0324] 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.

[0325] To implement this invention, it is necessary to construct a system that combines data collection means, problem analysis means, countermeasure generation means, execution means, and reporting means with an emotion engine that recognizes and utilizes user emotions in the analysis. The following details how this system is configured and operates.

[0326] System configuration and operation

[0327] Data acquisition methods

[0328] The server collects not only user activity logs and task information, but also user emotional data. Emotional data is obtained by analyzing facial expression data and voice data acquired from sensors such as cameras installed on the device. This data is collected with the user's consent and is managed securely.

[0329] Problem analysis means

[0330] The server comprehensively analyzes the acquired activity logs, task information, and emotional data. In particular, by utilizing the emotional engine to evaluate the user's current emotional state, it can identify emotionally-related issues such as stress and decreased motivation. This allows for the identification of human-factor-related problems that were difficult to detect with traditional data alone.

[0331] Countermeasure generation means

[0332] The server uses AI to generate optimal countermeasures, taking emotional data into consideration. These countermeasures are adjusted according to the user's emotional state; for example, if the user is experiencing high stress, the suggestions might include "increase rest time" or "suggest a relaxation session."

[0333] Execution method

[0334] Once the user selects a solution from the presented options, the server prepares to implement the chosen solution. If the solution is related to emotions, it sets up appropriate psychological intervention tools and provides notifications. For example, it might set the server to play relaxation music in response to the user's selection.

[0335] Reporting method

[0336] The server monitors user emotional changes and progress in response to implemented measures, and periodically generates comprehensive reports. These reports visualize the shift in emotions and the progress of the issues at that point in time, supporting user self-management.

[0337] This system allows users to comprehensively understand emotions and business data, promoting problem-solving from a more human-centered perspective.

[0338] The following describes the processing flow.

[0339] Step 1:

[0340] The server collects user activity logs, task information, and emotional data. Emotional data is extracted from the user's facial expressions captured through a camera connected to the device, and from voice data obtained through speech recognition. This data is stored in a secure database.

[0341] Step 2:

[0342] The server analyzes the collected data. Using natural language processing and machine learning models, it identifies operational issues from activity logs and task information. Furthermore, an emotion engine analyzes the user's real-time emotional state to evaluate stress levels and engagement. These results are integrated to clarify potential issues.

[0343] Step 3:

[0344] The server uses AI to generate specific countermeasures based on the analysis results. These countermeasures are optimized and displayed while taking into account the user's emotional state. For example, if high stress levels are detected, countermeasures such as "introduction to relaxation techniques" or "adjustment of the work environment" will be suggested.

[0345] Step 4:

[0346] The user selects the most suitable solution from the presented options. The selection is made through the terminal's user interface, and the selection information is sent to the server. This process is designed to be intuitive and easy to complete.

[0347] Step 5:

[0348] Based on the user's selection, the server initiates the process of executing the chosen action. For example, if the chosen action is "start a relaxation session," music or guided audio will be played through a dedicated app. If necessary, settings for the digital calendar and notification system will be changed.

[0349] Step 6:

[0350] The server monitors performance and changes in user sentiment, and periodically generates progress reports. These reports are sent to terminals, allowing users to visually review past sentiment trends and the effectiveness of countermeasures. Based on this information, users can adapt their own work strategies.

[0351] (Example 2)

[0352] 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".

[0353] In today's information environment, the stress and decreased motivation that users experience on a daily basis have a significant impact on work performance and productivity. Furthermore, traditional systems have insufficient measures to address the emotional aspects of users, hindering effective problem-solving. This has resulted in difficulties in maintaining work efficiency and the mental well-being of users.

[0354] 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.

[0355] In this invention, the server includes data collection means for acquiring user activity records, work information, and emotional information; problem analysis means for analyzing the acquired data and identifying issues, including the user's emotional state; and countermeasure generation means for generating and presenting countermeasures using a generated AI model based on the identified issues and the user's emotional state. This makes it possible to propose and implement effective countermeasures that take the user's emotional state into consideration in real time.

[0356] A "user" refers to an individual who uses the system to provide activity records and emotional information.

[0357] "Activity log" refers to the history of specific actions and inputs that occur when a user performs their daily tasks.

[0358] "Business information" refers to detailed data related to the tasks and projects that the user is working on.

[0359] "Emotional information" refers to data that represents the user's psychological state, obtained from their facial expressions and voice.

[0360] "Data collection methods" refer to the technologies and processes used to acquire user activity records, work information, and emotional information.

[0361] "Problem analysis methods" refer to the techniques and processes used to evaluate and identify users' problems and emotional states from collected data.

[0362] A "generative AI model" refers to an algorithm and model that uses artificial intelligence to generate optimal solutions based on data.

[0363] "Countermeasure generation method" refers to the technology and process that creates and presents countermeasures using a generation AI model, taking into account the identified problem and the user's emotional state.

[0364] "Real-time" refers to the ability of a system to process information instantly and reflect the results immediately.

[0365] "Effective measures" refer to appropriate action suggestions and environmental adjustments aimed at improving users' work efficiency and psychological well-being.

[0366] To implement this invention, a comprehensive configuration is required to support the entire system flow, from data collection, analysis, and countermeasure generation to implementation and evaluation. The details are described below.

[0367] First, the user's device is equipped with sensors necessary to collect activity and emotional data. Specifically, cameras and microphones are used to capture facial and voice data in real time. This data is transferred to a server with the user's permission. The server acts as a data collection system and stores the data transmitted from the device. The data is managed securely, and mechanisms are in place to protect user privacy.

[0368] Next, the server analyzes the collected data as a means of problem analysis. Emotion engines and machine learning algorithms are used to identify the user's emotional state and challenges. This analysis is crucial for making comprehensive judgments, including the user's stress level and motivation, utilizing artificial intelligence (AI) technology. This process also employs techniques for pattern recognition and correlation evaluation of the data.

[0369] Subsequently, a process takes place in which a generative AI model is run to generate countermeasures. The server inputs prompt sentences into the generative AI model based on the analysis results. For example, a possible prompt sentence might be, "If the user is showing high stress levels, suggest appropriate countermeasures." This prompt sentence serves as the basic information for the AI ​​model to suggest the optimal countermeasures. The model generates specific action plans based on the user's emotional state. These plans are presented to the user, who can then use them as options.

[0370] Once a user selects a course of action, the server coordinates its implementation. Especially when psychological intervention is needed, the system automatically launches appropriate music or applications on the device. For example, it might configure the system to play relaxation music, ensuring that music plays on the user's device.

[0371] The server continuously monitors changes in user emotions and the effectiveness of countermeasures, and generates reports to evaluate the results. These reports include a visual representation of user progress and emotional improvement, and support self-management.

[0372] In this way, the invention integrates digital and human elements to achieve comprehensive problem-solving for the user.

[0373] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0374] Step 1:

[0375] The server collects user activity records, work information, and emotional information from the terminal. The terminal's camera and microphone capture the user's facial expressions and voice, and transmit this information to the server. Using this data as input, the server stores the information in a database.

[0376] Step 2:

[0377] The server analyzes the collected data. Using an emotion engine, it analyzes facial expression and voice data to evaluate the user's emotional state. For example, it detects the presence or absence of a smile using a facial expression recognition algorithm. As output of this process, data is generated as an index related to the user's emotional state.

[0378] Step 3:

[0379] The server identifies issues based on the analysis results. It uses machine learning algorithms to determine stress levels and decreased motivation. Here, it identifies the current emotional state by comparing it with past data. The identified issues are generated as output.

[0380] Step 4:

[0381] The server inputs a prompt message into the AI ​​model for the identified problem. This prompt message might read, for example, "If the user is showing high stress levels, suggest appropriate countermeasures." Based on this input, the AI ​​model generates optimal countermeasures and outputs a list of solutions.

[0382] Step 5:

[0383] The user selects their desired solution from the presented list of solutions. For example, the user might select "Play relaxation music." This selection is sent to the server, and that information is generated as output data.

[0384] Step 6:

[0385] The server prepares to execute the action selected by the user. It sends a command to the terminal corresponding to the selected action. Specifically, it sets the terminal to play relaxation music. The input for this process is the output of step 5, which shows that the specific settings necessary for executing the process have been completed.

[0386] Step 7:

[0387] The server continuously monitors the user's emotional changes while the countermeasures are being implemented. It then collects data again to evaluate the extent of the emotional changes. This data is collected and analyzed, and a report is generated. This report visually displays which countermeasures were effective and for how long.

[0388] (Application Example 2)

[0389] 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."

[0390] Traditionally, problem analysis was performed based on user activity logs and task information, but problem analysis and solution generation did not take into account the user's emotional state. As a result, more humane support could not be provided, and issues related to emotions such as stress and decreased motivation were not adequately addressed. This presents a challenge in providing optimal support and a comfortable environment for users.

[0391] 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.

[0392] In this invention, the server includes data collection means for acquiring user activity logs, task information, and emotional data; problem analysis means for analyzing the acquired data and identifying problems; and countermeasure generation means for generating and presenting countermeasures for the identified problems while evaluating the user's emotional state. This enables more appropriate and humane problem solving while taking the user's emotions into consideration.

[0393] A "user" refers to an individual or representative of an organization that uses this system, and is the entity whose activity logs, task information, and sentiment data are collected and analyzed.

[0394] An "activity log" is data that records a user's actions and operations, and is information that the system uses to understand the user's situation.

[0395] "Task information" is data that indicates the tasks and schedules that a user should perform, and it is the basic data that the system uses to identify problems.

[0396] "Emotional data" refers to data that reflects the user's emotional state and is obtained through facial expression analysis and voice analysis.

[0397] "Data collection means" refers to technical means for acquiring user activity logs, task information, and sentiment data, and includes devices such as sensors and input devices.

[0398] "Problem analysis methods" are technical means that analyze acquired activity logs, task information, and sentiment data to identify the challenges that users face.

[0399] A "solution generation method" is a technical means that uses a generation AI to generate and present the most suitable solution to the user based on analyzed problem and sentiment data.

[0400] "Execution means" refers to the technical means by which the system takes specific actions based on the measures selected by the user and provides feedback as needed.

[0401] A "reporting mechanism" is a technical means of monitoring the implementation status of countermeasures and changes in user sentiment, and reporting the results to the user.

[0402] A "generative AI model" is an artificial intelligence model that generates optimal suggestions and responses for the user based on recorded data.

[0403] To implement this invention, an interactive robot assistant deployed in a smart home environment is used. This robot collects user activity logs, task information, and emotional data in real time and transmits the data to a server located in the cloud. For data collection, sensors such as cameras and microphones are used to analyze the user's movements and voice to obtain facial expression data and voice tone.

[0404] Based on the received data, the server evaluates the user's current emotional state using problem analysis tools and identifies any issues. In particular, it uses an emotion engine to analyze in detail the user's emotions, such as stress and motivation. The generative AI model then generates suggestions optimized for the user's state based on the identified issues and emotional data. Accordingly, prompts such as "If the user's emotional state is high stress, generate suggestions to promote relaxation" are used.

[0405] Based on the user's selection, the robot automatically performs actions such as playing relaxation music or adjusting smart home lighting. This includes integration with music service APIs and smart lighting devices. After execution, it monitors the user's emotional changes and the effectiveness of the actions, providing regular feedback through reporting mechanisms. Through this process, the goal is to improve the user's lifestyle for greater comfort.

[0406] As a concrete example, if a user is experiencing increased stress due to long hours of working from home, the robot might suggest, "You seem a little tired today, would you mind listening to some relaxing music?" and then proceed to do so after receiving the user's approval. This allows the user to refresh both mentally and physically, enabling them to work more efficiently.

[0407] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0408] Step 1:

[0409] The device collects user activity logs, task information, and sentiment data. Input is raw data acquired from sensors such as cameras and microphones. The device organizes this data and converts it into a format for transmission to the server. Output is a standardized dataset.

[0410] Step 2:

[0411] The server analyzes the received data using a problem analysis tool. The input is a standardized dataset sent from the terminal. The server processes the data using an emotion engine and machine learning models to evaluate the user's current emotional state and identify the problem. The output is the user's emotional state and the identified problem.

[0412] Step 3:

[0413] The server generates countermeasures based on the identified issues and emotional states. The input is the user's emotional state and issues obtained through issue analysis. The server uses a generative AI model to create optimal countermeasures and constructs suggestions for the user based on the prompt "Generate suggestions to promote relaxation." The output is a customized set of countermeasures.

[0414] Step 4:

[0415] The user receives proposed solutions from the server and selects the most appropriate solution. The input is the proposed solutions sent from the server. The user selects the suggestion best suited to their situation and provides feedback to the server. The output is information about the solution selected by the user.

[0416] Step 5:

[0417] The server sends instructions to the terminal or associated device to execute the action selected by the user. The input is the action selected by the user. The server utilizes music service APIs and smart home devices to play relaxation music or send signals to adjust lighting. The output is the specific relaxation action that was performed.

[0418] Step 6:

[0419] After the countermeasures are implemented, the server re-evaluates the user's emotional changes and monitors progress and effectiveness. The input is the user's emotional data, which is acquired again. The server provides feedback on the results of the implementation to the user through reporting mechanisms and prepares the next countermeasures as needed. This output serves as feedback to the user and guidance for the next action.

[0420] 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.

[0421] 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.

[0422] 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.

[0423] [Third Embodiment]

[0424] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0425] 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.

[0426] 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).

[0427] 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.

[0428] 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.

[0429] 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).

[0430] 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.

[0431] 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.

[0432] 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.

[0433] 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.

[0434] 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.

[0435] 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".

[0436] To implement this invention, it is necessary to construct a system that integrates data collection means, problem analysis means, countermeasure generation means, implementation means, and reporting means. The following describes how this system is configured and operates.

[0437] System configuration and operation

[0438] Data acquisition methods

[0439] The server automatically collects data from user activity logs and task management tools. It retrieves logs and task progress generated by users in their daily work via API or direct connection, and stores this information in a database. For example, when a user registers a task using project management software, that information is sent to the server.

[0440] Problem analysis means

[0441] The server utilizes natural language processing techniques and machine learning algorithms to analyze the collected data. This highlights frequently occurring problems and potential challenges in the user's work. Specifically, the server extracts keywords such as "progress delays" and "resource shortages" from the logs and classifies these problems.

[0442] Countermeasure generation means

[0443] Once a problem is identified, the server uses generative AI to generate solutions. These solutions are designed to be the most feasible and effective for the user. For example, if the problem is identified as "insufficient task progress management," the server will generate countermeasures such as "strengthening reminder settings" or "suggesting task splitting."

[0444] Execution method

[0445] When the user selects what they believe to be the most suitable solution from several options displayed, the server configures the specific settings to implement that solution. Based on the selected solution, the necessary tools are automatically installed and scripts are executed. For example, if the user selects "set automatic task reminders," the server will set up the corresponding reminders.

[0446] Reporting method

[0447] The server monitors the implementation status of configured measures in real time and periodically generates progress reports. These reports are delivered to the user's dashboard and via email, clearly indicating the level of achievement and any newly discovered issues. This allows users to always understand their work status and make adjustments as needed.

[0448] This system enables users to efficiently manage and resolve issues, supporting the smooth execution of daily tasks.

[0449] The following describes the processing flow.

[0450] Step 1:

[0451] The server collects the latest data from user activity logs and task management tools. Log collection is performed by querying information from the database using HTTP requests. It communicates with task management tools via API to retrieve task information.

[0452] Step 2:

[0453] The server analyzes the collected data. Using natural language processing, it extracts keywords from the logs, and a machine learning model performs data analysis to identify potential user issues. The analysis results are organized into issues such as "project delays" and "resource imbalances."

[0454] Step 3:

[0455] The server generates solutions to address the issues. Using generation AI, it generates specific solutions tailored to the user's work situation and lists them as proposed solutions. The generated solutions may be specific, such as "redistributing resources" or "setting up progress review meetings."

[0456] Step 4:

[0457] The user selects the most appropriate solution from several options provided by the server. A selection interface is provided on the terminal to make the selection process easy for the user.

[0458] Step 5:

[0459] The server will begin processing to implement the selected countermeasures. Specifically, it will automatically execute scripts to configure necessary tools and adjust system parameters. It will also modify the settings of project management tools and notification systems.

[0460] Step 6:

[0461] The server monitors the effectiveness of implemented measures and periodically generates progress reports. These reports are provided to users via their terminals, allowing them to visualize their progress and any newly discovered issues.

[0462] (Example 1)

[0463] 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."

[0464] Traditionally, identifying problems and proposing solutions in business management and project progress relied on human judgment, making efficient and rapid problem-solving difficult. Furthermore, the lack of measurement of the effectiveness of proposed solutions and prioritization hindered effective business improvement.

[0465] 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.

[0466] In this invention, the server includes data collection means for acquiring human operation information and business information, problem analysis means for analyzing the acquired information and identifying problems, and solution generation means for generating and displaying solutions to the identified problems. This makes it possible to quickly identify problems in business operations and automatically propose effective solutions.

[0467] "Human operation information" refers to action data generated when a human operates a computer system, and includes input information, clicks, and operation history.

[0468] "Business information" refers to information such as the progress of tasks and projects related to the activities of a company or organization, resource allocation, and performance indicators.

[0469] "Data collection means" refers to methods or devices for incorporating human operation information and business information into a system, and includes mechanisms for acquiring information through APIs, sensors, etc.

[0470] "Problem analysis tools" are methods or devices used to analyze acquired data and identify business problems from it, employing machine learning or data mining techniques.

[0471] A "solution generation means" is a method or apparatus used to devise and present solutions to an identified problem, and may utilize generative AI models or rule-based systems.

[0472] A "generative AI model" refers to an algorithm or model that uses artificial intelligence technology to generate results or suggestions based on data to achieve human instructions or goals.

[0473] A "prompt" is an instruction or question given to a generative AI model, providing specific guidelines to elicit the desired generation result.

[0474] This invention provides a system that enables humans to efficiently manage their daily tasks and automatically generate solutions to problems that are discovered. Specific embodiments of the system are described below.

[0475] The server collects human operation information and business information using data collection methods. This includes obtaining information from project management tools and task management systems using APIs. Specifically, the server retrieves data from project management software, which is a typical example of a business management tool, and stores it in a database stored within the system.

[0476] Next, the server uses machine learning and natural language processing techniques as problem analysis tools. Specifically, it extracts keywords from the data using a natural language processing library, and then uses machine learning algorithms to identify problems. Based on this process, the server can identify frequent problems and resource shortages that occur in the business.

[0477] Solutions to identified problems are generated by the server using a generative AI model. At this stage, the server generates prompts to solve the identified problems and inputs these prompts into the generative AI model to obtain effective solutions. For example, if the problem is identified as "the task is behind schedule," an example of a generated prompt might be, "Please provide specific solutions to improve the progress."

[0478] The server presents the generated solutions to the user and configures the execution settings based on the user's chosen solution. The user selects the best option from the presented choices, and the server automatically executes specific actions such as setting reminders. This allows the server to provide the user with direct support to improve work efficiency.

[0479] This system allows users to deepen their understanding of their work and solve problems efficiently. This makes it easy to identify business processes that need change or improvement, enabling quick responses.

[0480] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0481] Step 1:

[0482] The server retrieves user work information via the project management tool's API. This includes data on task creation, updates, and completion. The server converts the raw data retrieved from the API into a unified format and stores it in the database. The input is work data from the API, and the output is formatted work data.

[0483] Step 2:

[0484] The server analyzes stored business data using natural language processing techniques. Specifically, the server scans the text volume within the data and extracts specific keywords and phrases (e.g., delay in progress, change in priority). The input is formatted business data, and the output is the analyzed keywords and their frequency information.

[0485] Step 3:

[0486] The server generates prompt sentences to input into the AI ​​model based on the keywords obtained through analysis. This lays the foundation for extracting specific solutions. The input is the analyzed keyword information, and the output is the prompt sentences.

[0487] Step 4:

[0488] The server inputs a prompt message into the AI ​​model, which then generates possible solutions. The AI ​​model outputs multiple solutions in text format. The input is the prompt message, and the output is a list of proposed solutions.

[0489] Step 5:

[0490] The user receives a list of solutions provided by the server and selects the most appropriate solution based on their own judgment. This selection is fed back into the system and forms the basis for the next step. The input is the list of proposed solutions, and the output is the solution selected by the user.

[0491] Step 6:

[0492] The server automatically configures and implements the necessary settings and tools based on the user's chosen solution. For example, to set a reminder, it might integrate with a calendar app to schedule notifications. The input is the user's chosen solution, and the output is the specific configuration or execution procedure.

[0493] (Application Example 1)

[0494] 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."

[0495] In modern data centers and business management, the challenge of efficient operation is hampered by excessive tasks and inefficient resource allocation. This leads to data bottlenecks and delays in business progress, placing a significant burden on administrators. Therefore, there is a need for methods to effectively allocate resources and improve efficiency through data analysis and optimization.

[0496] 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.

[0497] In this invention, the server includes information gathering means for acquiring user behavior data and business information, analysis means for analyzing the acquired information and identifying problems, solution generation means for generating and displaying effective solutions to the identified problems, and means for supporting the optimization of computing tasks using clustering technology. This makes it possible to quickly analyze and efficiently resolve task overload and resource shortage problems in the data center.

[0498] "Information gathering means" refers to methods for acquiring user behavior data and business information, and enables the automatic collection of data.

[0499] "Analysis methods" refer to methods for identifying problems from collected information, and specifically to analytical techniques for extracting problems from data.

[0500] "Solution generation method" refers to a method of generating effective solutions to identified problems and presenting them to the user.

[0501] "Implementation methods" refer to the means by which a procedure is set based on the solution selected by the user and then actually carried out.

[0502] A "reporting system" is a means that monitors the status of implementation and periodically generates reports on progress and results.

[0503] Clustering is a technique for optimizing computational tasks by classifying data into several groups.

[0504] A "machine learning algorithm" is a computational method that allows computers to learn patterns based on data and perform predictions and analyses.

[0505] To implement this invention, a system is constructed to improve the operational efficiency of a data center. This system is server-centric and integrates information gathering means, analysis means, solution generation means, implementation means, and reporting means to function.

[0506] The server first acquires user behavior data and business information as a means of information gathering. This involves using hardware and software that automatically collects data by utilizing various sensors and APIs connected to the network.

[0507] Next, the collected information is analyzed using analytical tools. This analysis employs machine learning algorithms to extract and classify problems from the data. Specifically, clustering techniques using the Python scikit-learn library are used to support the optimization of computational tasks.

[0508] Once a problem is identified, a solution generation mechanism utilizes an AI model to devise countermeasures, which are then presented to the user. The generated solutions can be viewed and implemented through the user's terminal or the management screen.

[0509] Once the user selects a solution, it is implemented using the appropriate means. The server automatically configures the selected procedure and performs actions such as resource reallocation and task adjustment.

[0510] Finally, the server continuously monitors implementation status through reporting mechanisms and periodically reports progress and effectiveness to administrators. This includes a process of generating reports and notifying administrators via email or the administrator dashboard.

[0511] For example, if a particular server becomes overloaded, this system offers a solution such as "redistributing resources." By selecting this option, administrators can automatically redistribute resources appropriately, reducing the server load.

[0512] An example of a prompt that utilizes a generative AI model is as follows:

[0513] "Please tell me how to propose solutions to server overload problems within a data center."

[0514] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0515] Step 1:

[0516] The server automatically acquires user behavior data and work information from network-connected sensors and APIs using information gathering methods. This process involves collecting daily work logs and task progress through database access and API calls. Input is data from sensors and APIs, while output is structured information stored in the database.

[0517] Step 2:

[0518] The server analyzes the collected data using machine learning algorithms. This analysis utilizes the scikit-learn library to identify problems through clustering. The input is stored business data, and the output is the identified issues and discovered data patterns. In this process, the server performs data classification and problem extraction.

[0519] Step 3:

[0520] The server uses a generative AI model to generate solutions to the identified problem and presents them on the terminal using a solution generation mechanism. The input here is the problem identified in step 2, and the output is a list of solutions proposed to the user. The server calculates the optimal solution and displays it in the user interface.

[0521] Step 4:

[0522] The user selects the most suitable solution from those presented on the terminal. Based on this selection, the server implements the solution using various means, such as reallocating resources or adjusting tasks. The input is the user's solution selection, and the output is the implemented configuration changes and resource adjustments. The server automatically updates the configuration and puts the changes into action.

[0523] Step 5:

[0524] The server continuously monitors the execution status using reporting mechanisms and periodically reports progress and results to the administrator. Input is system execution data, and output is information notified via email or the management dashboard in the form of reports. The server checks the status and makes further adjustments as needed.

[0525] 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.

[0526] To implement this invention, it is necessary to construct a system that combines data collection means, problem analysis means, countermeasure generation means, execution means, and reporting means with an emotion engine that recognizes and utilizes user emotions in the analysis. The following details how this system is configured and operates.

[0527] System configuration and operation

[0528] Data acquisition methods

[0529] The server collects not only user activity logs and task information, but also user emotional data. Emotional data is obtained by analyzing facial expression data and voice data acquired from sensors such as cameras installed on the device. This data is collected with the user's consent and is managed securely.

[0530] Problem analysis means

[0531] The server comprehensively analyzes the acquired activity logs, task information, and emotional data. In particular, by utilizing the emotional engine to evaluate the user's current emotional state, it can identify emotionally-related issues such as stress and decreased motivation. This allows for the identification of human-factor-related problems that were difficult to detect with traditional data alone.

[0532] Countermeasure generation means

[0533] The server uses AI to generate optimal countermeasures, taking emotional data into consideration. These countermeasures are adjusted according to the user's emotional state; for example, if the user is experiencing high stress, the suggestions might include "increase rest time" or "suggest a relaxation session."

[0534] Execution method

[0535] Once the user selects a solution from the presented options, the server prepares to implement the chosen solution. If the solution is related to emotions, it sets up appropriate psychological intervention tools and provides notifications. For example, it might set the server to play relaxation music in response to the user's selection.

[0536] Reporting method

[0537] The server monitors user emotional changes and progress in response to implemented measures, and periodically generates comprehensive reports. These reports visualize the shift in emotions and the progress of the issues at that point in time, supporting user self-management.

[0538] This system allows users to comprehensively understand emotions and business data, promoting problem-solving from a more human-centered perspective.

[0539] The following describes the processing flow.

[0540] Step 1:

[0541] The server collects user activity logs, task information, and emotional data. Emotional data is extracted from the user's facial expressions captured through a camera connected to the device, and from voice data obtained through speech recognition. This data is stored in a secure database.

[0542] Step 2:

[0543] The server analyzes the collected data. Using natural language processing and machine learning models, it identifies operational issues from activity logs and task information. Furthermore, an emotion engine analyzes the user's real-time emotional state to evaluate stress levels and engagement. These results are integrated to clarify potential issues.

[0544] Step 3:

[0545] The server uses AI to generate specific countermeasures based on the analysis results. These countermeasures are optimized and displayed while taking into account the user's emotional state. For example, if high stress levels are detected, countermeasures such as "introduction to relaxation techniques" or "adjustment of the work environment" will be suggested.

[0546] Step 4:

[0547] The user selects the most suitable solution from the presented options. The selection is made through the terminal's user interface, and the selection information is sent to the server. This process is designed to be intuitive and easy to complete.

[0548] Step 5:

[0549] Based on the user's selection, the server initiates the process of executing the chosen action. For example, if the chosen action is "start a relaxation session," music or guided audio will be played through a dedicated app. If necessary, settings for the digital calendar and notification system will be changed.

[0550] Step 6:

[0551] The server monitors performance and changes in user sentiment, and periodically generates progress reports. These reports are sent to terminals, allowing users to visually review past sentiment trends and the effectiveness of countermeasures. Based on this information, users can adapt their own work strategies.

[0552] (Example 2)

[0553] 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."

[0554] In today's information environment, the stress and decreased motivation that users experience on a daily basis have a significant impact on work performance and productivity. Furthermore, traditional systems have insufficient measures to address the emotional aspects of users, hindering effective problem-solving. This has resulted in difficulties in maintaining work efficiency and the mental well-being of users.

[0555] 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.

[0556] In this invention, the server includes data collection means for acquiring user activity records, work information, and emotional information; problem analysis means for analyzing the acquired data and identifying issues, including the user's emotional state; and countermeasure generation means for generating and presenting countermeasures using a generated AI model based on the identified issues and the user's emotional state. This makes it possible to propose and implement effective countermeasures that take the user's emotional state into consideration in real time.

[0557] A "user" refers to an individual who uses the system to provide activity records and emotional information.

[0558] "Activity log" refers to the history of specific actions and inputs that occur when a user performs their daily tasks.

[0559] "Business information" refers to detailed data related to the tasks and projects that the user is working on.

[0560] "Emotional information" refers to data that represents the user's psychological state, obtained from their facial expressions and voice.

[0561] "Data collection methods" refer to the technologies and processes used to acquire user activity records, work information, and emotional information.

[0562] "Problem analysis methods" refer to the techniques and processes used to evaluate and identify users' problems and emotional states from collected data.

[0563] A "generative AI model" refers to an algorithm and model that uses artificial intelligence to generate optimal solutions based on data.

[0564] "Countermeasure generation method" refers to the technology and process that creates and presents countermeasures using a generation AI model, taking into account the identified problem and the user's emotional state.

[0565] "Real-time" refers to the ability of a system to process information instantly and reflect the results immediately.

[0566] "Effective measures" refer to appropriate action suggestions and environmental adjustments aimed at improving users' work efficiency and psychological well-being.

[0567] To implement this invention, a comprehensive configuration is required to support the entire system flow, from data collection, analysis, and countermeasure generation to implementation and evaluation. The details are described below.

[0568] First, the user's device is equipped with sensors necessary to collect activity and emotional data. Specifically, cameras and microphones are used to capture facial and voice data in real time. This data is transferred to a server with the user's permission. The server acts as a data collection system and stores the data transmitted from the device. The data is managed securely, and mechanisms are in place to protect user privacy.

[0569] Next, the server analyzes the collected data as a means of problem analysis. Emotion engines and machine learning algorithms are used to identify the user's emotional state and challenges. This analysis is crucial for making comprehensive judgments, including the user's stress level and motivation, utilizing artificial intelligence (AI) technology. This process also employs techniques for pattern recognition and correlation evaluation of the data.

[0570] Subsequently, a process takes place in which a generative AI model is run to generate countermeasures. The server inputs prompt sentences into the generative AI model based on the analysis results. For example, a possible prompt sentence might be, "If the user is showing high stress levels, suggest appropriate countermeasures." This prompt sentence serves as the basic information for the AI ​​model to suggest the optimal countermeasures. The model generates specific action plans based on the user's emotional state. These plans are presented to the user, who can then use them as options.

[0571] Once a user selects a course of action, the server coordinates its implementation. Especially when psychological intervention is needed, the system automatically launches appropriate music or applications on the device. For example, it might configure the system to play relaxation music, ensuring that music plays on the user's device.

[0572] The server continuously monitors changes in user emotions and the effectiveness of countermeasures, and generates reports to evaluate the results. These reports include a visual representation of user progress and emotional improvement, and support self-management.

[0573] In this way, the invention integrates digital and human elements to achieve comprehensive problem-solving for the user.

[0574] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0575] Step 1:

[0576] The server collects user activity records, work information, and emotional information from the terminal. The terminal's camera and microphone capture the user's facial expressions and voice, and transmit this information to the server. Using this data as input, the server stores the information in a database.

[0577] Step 2:

[0578] The server analyzes the collected data. Using an emotion engine, it analyzes facial expression and voice data to evaluate the user's emotional state. For example, it detects the presence or absence of a smile using a facial expression recognition algorithm. As output of this process, data is generated as an index related to the user's emotional state.

[0579] Step 3:

[0580] The server identifies issues based on the analysis results. It uses machine learning algorithms to determine stress levels and decreased motivation. Here, it identifies the current emotional state by comparing it with past data. The identified issues are generated as output.

[0581] Step 4:

[0582] The server inputs a prompt message into the AI ​​model for the identified problem. This prompt message might read, for example, "If the user is showing high stress levels, suggest appropriate countermeasures." Based on this input, the AI ​​model generates optimal countermeasures and outputs a list of solutions.

[0583] Step 5:

[0584] The user selects their desired solution from the presented list of solutions. For example, the user might select "Play relaxation music." This selection is sent to the server, and that information is generated as output data.

[0585] Step 6:

[0586] The server prepares to execute the action selected by the user. It sends a command to the terminal corresponding to the selected action. Specifically, it sets the terminal to play relaxation music. The input for this process is the output of step 5, which shows that the specific settings necessary for executing the process have been completed.

[0587] Step 7:

[0588] The server continuously monitors the user's emotional changes while the countermeasures are being implemented. It then collects data again to evaluate the extent of the emotional changes. This data is collected and analyzed, and a report is generated. This report visually displays which countermeasures were effective and for how long.

[0589] (Application Example 2)

[0590] 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."

[0591] Traditionally, problem analysis was performed based on user activity logs and task information, but problem analysis and solution generation did not take into account the user's emotional state. As a result, more humane support could not be provided, and issues related to emotions such as stress and decreased motivation were not adequately addressed. This presents a challenge in providing optimal support and a comfortable environment for users.

[0592] 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.

[0593] In this invention, the server includes data collection means for acquiring user activity logs, task information, and emotional data; problem analysis means for analyzing the acquired data and identifying problems; and countermeasure generation means for generating and presenting countermeasures for the identified problems while evaluating the user's emotional state. This enables more appropriate and humane problem solving while taking the user's emotions into consideration.

[0594] A "user" refers to an individual or representative of an organization that uses this system, and is the entity whose activity logs, task information, and sentiment data are collected and analyzed.

[0595] An "activity log" is data that records a user's actions and operations, and is information that the system uses to understand the user's situation.

[0596] "Task information" is data that indicates the tasks and schedules that a user should perform, and it is the basic data that the system uses to identify problems.

[0597] "Emotional data" refers to data that reflects the user's emotional state and is obtained through facial expression analysis and voice analysis.

[0598] "Data collection means" refers to technical means for acquiring user activity logs, task information, and sentiment data, and includes devices such as sensors and input devices.

[0599] "Problem analysis methods" are technical means that analyze acquired activity logs, task information, and sentiment data to identify the challenges that users face.

[0600] A "solution generation method" is a technical means that uses a generation AI to generate and present the most suitable solution to the user based on analyzed problem and sentiment data.

[0601] "Execution means" refers to the technical means by which the system takes specific actions based on the measures selected by the user and provides feedback as needed.

[0602] A "reporting mechanism" is a technical means of monitoring the implementation status of countermeasures and changes in user sentiment, and reporting the results to the user.

[0603] A "generative AI model" is an artificial intelligence model that generates optimal suggestions and responses for the user based on recorded data.

[0604] To implement this invention, an interactive robot assistant deployed in a smart home environment is used. This robot collects user activity logs, task information, and emotional data in real time and transmits the data to a server located in the cloud. For data collection, sensors such as cameras and microphones are used to analyze the user's movements and voice to obtain facial expression data and voice tone.

[0605] Based on the received data, the server evaluates the user's current emotional state using problem analysis tools and identifies any issues. In particular, it uses an emotion engine to analyze in detail the user's emotions, such as stress and motivation. The generative AI model then generates suggestions optimized for the user's state based on the identified issues and emotional data. Accordingly, prompts such as "If the user's emotional state is high stress, generate suggestions to promote relaxation" are used.

[0606] Based on the user's selection, the robot automatically performs actions such as playing relaxation music or adjusting smart home lighting. This includes integration with music service APIs and smart lighting devices. After execution, it monitors the user's emotional changes and the effectiveness of the actions, providing regular feedback through reporting mechanisms. Through this process, the goal is to improve the user's lifestyle for greater comfort.

[0607] As a concrete example, if a user is experiencing increased stress due to long hours of working from home, the robot might suggest, "You seem a little tired today, would you mind listening to some relaxing music?" and then proceed to do so after receiving the user's approval. This allows the user to refresh both mentally and physically, enabling them to work more efficiently.

[0608] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0609] Step 1:

[0610] The device collects user activity logs, task information, and sentiment data. Input is raw data acquired from sensors such as cameras and microphones. The device organizes this data and converts it into a format for transmission to the server. Output is a standardized dataset.

[0611] Step 2:

[0612] The server analyzes the received data using a problem analysis tool. The input is a standardized dataset sent from the terminal. The server processes the data using an emotion engine and machine learning models to evaluate the user's current emotional state and identify the problem. The output is the user's emotional state and the identified problem.

[0613] Step 3:

[0614] The server generates countermeasures based on the identified issues and emotional states. The input is the user's emotional state and issues obtained through issue analysis. The server uses a generative AI model to create optimal countermeasures and constructs suggestions for the user based on the prompt "Generate suggestions to promote relaxation." The output is a customized set of countermeasures.

[0615] Step 4:

[0616] The user receives proposed solutions from the server and selects the most appropriate solution. The input is the proposed solutions sent from the server. The user selects the suggestion best suited to their situation and provides feedback to the server. The output is information about the solution selected by the user.

[0617] Step 5:

[0618] The server sends instructions to the terminal or associated device to execute the action selected by the user. The input is the action selected by the user. The server utilizes music service APIs and smart home devices to play relaxation music or send signals to adjust lighting. The output is the specific relaxation action that was performed.

[0619] Step 6:

[0620] After the countermeasures are implemented, the server re-evaluates the user's emotional changes and monitors progress and effectiveness. The input is the user's emotional data, which is acquired again. The server provides feedback on the results of the implementation to the user through reporting mechanisms and prepares the next countermeasures as needed. This output serves as feedback to the user and guidance for the next action.

[0621] 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.

[0622] 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.

[0623] 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.

[0624] [Fourth Embodiment]

[0625] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0626] 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.

[0627] 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).

[0628] 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.

[0629] 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.

[0630] 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).

[0631] 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.

[0632] 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.

[0633] 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.

[0634] 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.

[0635] 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.

[0636] 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.

[0637] 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".

[0638] To implement this invention, it is necessary to construct a system that integrates data collection means, problem analysis means, countermeasure generation means, implementation means, and reporting means. The following describes how this system is configured and operates.

[0639] System configuration and operation

[0640] Data acquisition methods

[0641] The server automatically collects data from user activity logs and task management tools. It retrieves logs and task progress generated by users in their daily work via API or direct connection, and stores this information in a database. For example, when a user registers a task using project management software, that information is sent to the server.

[0642] Problem analysis means

[0643] The server utilizes natural language processing techniques and machine learning algorithms to analyze the collected data. This highlights frequently occurring problems and potential challenges in the user's work. Specifically, the server extracts keywords such as "progress delays" and "resource shortages" from the logs and classifies these problems.

[0644] Countermeasure generation means

[0645] Once a problem is identified, the server uses generative AI to generate solutions. These solutions are designed to be the most feasible and effective for the user. For example, if the problem is identified as "insufficient task progress management," the server will generate countermeasures such as "strengthening reminder settings" or "suggesting task splitting."

[0646] Execution method

[0647] When the user selects what they believe to be the most suitable solution from several options displayed, the server configures the specific settings to implement that solution. Based on the selected solution, the necessary tools are automatically installed and scripts are executed. For example, if the user selects "set automatic task reminders," the server will set up the corresponding reminders.

[0648] Reporting method

[0649] The server monitors the implementation status of configured measures in real time and periodically generates progress reports. These reports are delivered to the user's dashboard and via email, clearly indicating the level of achievement and any newly discovered issues. This allows users to always understand their work status and make adjustments as needed.

[0650] This system enables users to efficiently manage and resolve issues, supporting the smooth execution of daily tasks.

[0651] The following describes the processing flow.

[0652] Step 1:

[0653] The server collects the latest data from user activity logs and task management tools. Log collection is performed by querying information from the database using HTTP requests. It communicates with task management tools via API to retrieve task information.

[0654] Step 2:

[0655] The server analyzes the collected data. Using natural language processing, it extracts keywords from the logs, and a machine learning model performs data analysis to identify potential user issues. The analysis results are organized into issues such as "project delays" and "resource imbalances."

[0656] Step 3:

[0657] The server generates solutions to address the issues. Using generation AI, it generates specific solutions tailored to the user's work situation and lists them as proposed solutions. The generated solutions may be specific, such as "redistributing resources" or "setting up progress review meetings."

[0658] Step 4:

[0659] The user selects the most appropriate solution from several options provided by the server. A selection interface is provided on the terminal to make the selection process easy for the user.

[0660] Step 5:

[0661] The server will begin processing to implement the selected countermeasures. Specifically, it will automatically execute scripts to configure necessary tools and adjust system parameters. It will also modify the settings of project management tools and notification systems.

[0662] Step 6:

[0663] The server monitors the effectiveness of implemented measures and periodically generates progress reports. These reports are provided to users via their terminals, allowing them to visualize their progress and any newly discovered issues.

[0664] (Example 1)

[0665] 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".

[0666] Traditionally, identifying problems and proposing solutions in business management and project progress relied on human judgment, making efficient and rapid problem-solving difficult. Furthermore, the lack of measurement of the effectiveness of proposed solutions and prioritization hindered effective business improvement.

[0667] 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.

[0668] In this invention, the server includes data collection means for acquiring human operation information and business information, problem analysis means for analyzing the acquired information and identifying problems, and solution generation means for generating and displaying solutions to the identified problems. This makes it possible to quickly identify problems in business operations and automatically propose effective solutions.

[0669] "Human operation information" refers to action data generated when a human operates a computer system, and includes input information, clicks, and operation history.

[0670] "Business information" refers to information such as the progress of tasks and projects related to the activities of a company or organization, resource allocation, and performance indicators.

[0671] "Data collection means" refers to methods or devices for incorporating human operation information and business information into a system, and includes mechanisms for acquiring information through APIs, sensors, etc.

[0672] "Problem analysis tools" are methods or devices used to analyze acquired data and identify business problems from it, employing machine learning or data mining techniques.

[0673] A "solution generation means" is a method or apparatus used to devise and present solutions to an identified problem, and may utilize generative AI models or rule-based systems.

[0674] A "generative AI model" refers to an algorithm or model that uses artificial intelligence technology to generate results or suggestions based on data to achieve human instructions or goals.

[0675] A "prompt" is an instruction or question given to a generative AI model, providing specific guidelines to elicit the desired generation result.

[0676] This invention provides a system that enables humans to efficiently manage their daily tasks and automatically generate solutions to problems that are discovered. Specific embodiments of the system are described below.

[0677] The server collects human operation information and business information using data collection methods. This includes obtaining information from project management tools and task management systems using APIs. Specifically, the server retrieves data from project management software, which is a typical example of a business management tool, and stores it in a database stored within the system.

[0678] Next, the server uses machine learning and natural language processing techniques as problem analysis tools. Specifically, it extracts keywords from the data using a natural language processing library, and then uses machine learning algorithms to identify problems. Based on this process, the server can identify frequent problems and resource shortages that occur in the business.

[0679] Solutions to identified problems are generated by the server using a generative AI model. At this stage, the server generates prompts to solve the identified problems and inputs these prompts into the generative AI model to obtain effective solutions. For example, if the problem is identified as "the task is behind schedule," an example of a generated prompt might be, "Please provide specific solutions to improve the progress."

[0680] The server presents the generated solutions to the user and configures the execution settings based on the user's chosen solution. The user selects the best option from the presented choices, and the server automatically executes specific actions such as setting reminders. This allows the server to provide the user with direct support to improve work efficiency.

[0681] This system allows users to deepen their understanding of their work and solve problems efficiently. This makes it easy to identify business processes that need change or improvement, enabling quick responses.

[0682] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0683] Step 1:

[0684] The server retrieves user work information via the project management tool's API. This includes data on task creation, updates, and completion. The server converts the raw data retrieved from the API into a unified format and stores it in the database. The input is work data from the API, and the output is formatted work data.

[0685] Step 2:

[0686] The server analyzes stored business data using natural language processing techniques. Specifically, the server scans the text volume within the data and extracts specific keywords and phrases (e.g., delay in progress, change in priority). The input is formatted business data, and the output is the analyzed keywords and their frequency information.

[0687] Step 3:

[0688] The server generates prompt sentences to input into the AI ​​model based on the keywords obtained through analysis. This lays the foundation for extracting specific solutions. The input is the analyzed keyword information, and the output is the prompt sentences.

[0689] Step 4:

[0690] The server inputs a prompt message into the AI ​​model, which then generates possible solutions. The AI ​​model outputs multiple solutions in text format. The input is the prompt message, and the output is a list of proposed solutions.

[0691] Step 5:

[0692] The user receives a list of solutions provided by the server and selects the most appropriate solution based on their own judgment. This selection is fed back into the system and forms the basis for the next step. The input is the list of proposed solutions, and the output is the solution selected by the user.

[0693] Step 6:

[0694] The server automatically configures and implements the necessary settings and tools based on the user's chosen solution. For example, to set a reminder, it might integrate with a calendar app to schedule notifications. The input is the user's chosen solution, and the output is the specific configuration or execution procedure.

[0695] (Application Example 1)

[0696] 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".

[0697] In modern data centers and business management, the challenge of efficient operation is hampered by excessive tasks and inefficient resource allocation. This leads to data bottlenecks and delays in business progress, placing a significant burden on administrators. Therefore, there is a need for methods to effectively allocate resources and improve efficiency through data analysis and optimization.

[0698] 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.

[0699] In this invention, the server includes information gathering means for acquiring user behavior data and business information, analysis means for analyzing the acquired information and identifying problems, solution generation means for generating and displaying effective solutions to the identified problems, and means for supporting the optimization of computing tasks using clustering technology. This makes it possible to quickly analyze and efficiently resolve task overload and resource shortage problems in the data center.

[0700] "Information gathering means" refers to methods for acquiring user behavior data and business information, and enables the automatic collection of data.

[0701] "Analysis methods" refer to methods for identifying problems from collected information, and specifically to analytical techniques for extracting problems from data.

[0702] "Solution generation method" refers to a method of generating effective solutions to identified problems and presenting them to the user.

[0703] "Implementation methods" refer to the means by which a procedure is set based on the solution selected by the user and then actually carried out.

[0704] A "reporting system" is a means that monitors the status of implementation and periodically generates reports on progress and results.

[0705] Clustering is a technique for optimizing computational tasks by classifying data into several groups.

[0706] A "machine learning algorithm" is a computational method that allows computers to learn patterns based on data and perform predictions and analyses.

[0707] To implement this invention, a system is constructed to improve the operational efficiency of a data center. This system is server-centric and integrates information gathering means, analysis means, solution generation means, implementation means, and reporting means to function.

[0708] The server first acquires user behavior data and business information as a means of information gathering. This involves using hardware and software that automatically collects data by utilizing various sensors and APIs connected to the network.

[0709] Next, the collected information is analyzed using analytical tools. This analysis employs machine learning algorithms to extract and classify problems from the data. Specifically, clustering techniques using the Python scikit-learn library are used to support the optimization of computational tasks.

[0710] Once a problem is identified, a solution generation mechanism utilizes an AI model to devise countermeasures, which are then presented to the user. The generated solutions can be viewed and implemented through the user's terminal or the management screen.

[0711] Once the user selects a solution, it is implemented using the appropriate means. The server automatically configures the selected procedure and performs actions such as resource reallocation and task adjustment.

[0712] Finally, the server continuously monitors implementation status through reporting mechanisms and periodically reports progress and effectiveness to administrators. This includes a process of generating reports and notifying administrators via email or the administrator dashboard.

[0713] For example, if a particular server becomes overloaded, this system offers a solution such as "redistributing resources." By selecting this option, administrators can automatically redistribute resources appropriately, reducing the server load.

[0714] An example of a prompt that utilizes a generative AI model is as follows:

[0715] "Please tell me how to propose solutions to server overload problems within a data center."

[0716] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0717] Step 1:

[0718] The server automatically acquires user behavior data and work information from network-connected sensors and APIs using information gathering methods. This process involves collecting daily work logs and task progress through database access and API calls. Input is data from sensors and APIs, while output is structured information stored in the database.

[0719] Step 2:

[0720] The server analyzes the collected data using machine learning algorithms. This analysis utilizes the scikit-learn library to identify problems through clustering. The input is stored business data, and the output is the identified issues and discovered data patterns. In this process, the server performs data classification and problem extraction.

[0721] Step 3:

[0722] The server uses a generative AI model to generate solutions to the identified problem and presents them on the terminal using a solution generation mechanism. The input here is the problem identified in step 2, and the output is a list of solutions proposed to the user. The server calculates the optimal solution and displays it in the user interface.

[0723] Step 4:

[0724] The user selects the most suitable solution from those presented on the terminal. Based on this selection, the server implements the solution using various means, such as reallocating resources or adjusting tasks. The input is the user's solution selection, and the output is the implemented configuration changes and resource adjustments. The server automatically updates the configuration and puts the changes into action.

[0725] Step 5:

[0726] The server continuously monitors the execution status using reporting mechanisms and periodically reports progress and results to the administrator. Input is system execution data, and output is information notified via email or the management dashboard in the form of reports. The server checks the status and makes further adjustments as needed.

[0727] 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.

[0728] To implement this invention, it is necessary to construct a system that combines data collection means, problem analysis means, countermeasure generation means, execution means, and reporting means with an emotion engine that recognizes and utilizes user emotions in the analysis. The following details how this system is configured and operates.

[0729] System configuration and operation

[0730] Data acquisition methods

[0731] The server collects not only user activity logs and task information, but also user emotional data. Emotional data is obtained by analyzing facial expression data and voice data acquired from sensors such as cameras installed on the device. This data is collected with the user's consent and is managed securely.

[0732] Problem analysis means

[0733] The server comprehensively analyzes the acquired activity logs, task information, and emotional data. In particular, by utilizing the emotional engine to evaluate the user's current emotional state, it can identify emotionally-related issues such as stress and decreased motivation. This allows for the identification of human-factor-related problems that were difficult to detect with traditional data alone.

[0734] Countermeasure generation means

[0735] The server uses AI to generate optimal countermeasures, taking emotional data into consideration. These countermeasures are adjusted according to the user's emotional state; for example, if the user is experiencing high stress, the suggestions might include "increase rest time" or "suggest a relaxation session."

[0736] Execution method

[0737] Once the user selects a solution from the presented options, the server prepares to implement the chosen solution. If the solution is related to emotions, it sets up appropriate psychological intervention tools and provides notifications. For example, it might set the server to play relaxation music in response to the user's selection.

[0738] Reporting method

[0739] The server monitors user emotional changes and progress in response to implemented measures, and periodically generates comprehensive reports. These reports visualize the shift in emotions and the progress of the issues at that point in time, supporting user self-management.

[0740] This system allows users to comprehensively understand emotions and business data, promoting problem-solving from a more human-centered perspective.

[0741] The following describes the processing flow.

[0742] Step 1:

[0743] The server collects user activity logs, task information, and emotional data. Emotional data is extracted from the user's facial expressions captured through a camera connected to the device, and from voice data obtained through speech recognition. This data is stored in a secure database.

[0744] Step 2:

[0745] The server analyzes the collected data. Using natural language processing and machine learning models, it identifies operational issues from activity logs and task information. Furthermore, an emotion engine analyzes the user's real-time emotional state to evaluate stress levels and engagement. These results are integrated to clarify potential issues.

[0746] Step 3:

[0747] The server uses AI to generate specific countermeasures based on the analysis results. These countermeasures are optimized and displayed while taking into account the user's emotional state. For example, if high stress levels are detected, countermeasures such as "introduction to relaxation techniques" or "adjustment of the work environment" will be suggested.

[0748] Step 4:

[0749] The user selects the most suitable solution from the presented options. The selection is made through the terminal's user interface, and the selection information is sent to the server. This process is designed to be intuitive and easy to complete.

[0750] Step 5:

[0751] Based on the user's selection, the server initiates the process of executing the chosen action. For example, if the chosen action is "start a relaxation session," music or guided audio will be played through a dedicated app. If necessary, settings for the digital calendar and notification system will be changed.

[0752] Step 6:

[0753] The server monitors performance and changes in user sentiment, and periodically generates progress reports. These reports are sent to terminals, allowing users to visually review past sentiment trends and the effectiveness of countermeasures. Based on this information, users can adapt their own work strategies.

[0754] (Example 2)

[0755] 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".

[0756] In today's information environment, the stress and decreased motivation that users experience on a daily basis have a significant impact on work performance and productivity. Furthermore, traditional systems have insufficient measures to address the emotional aspects of users, hindering effective problem-solving. This has resulted in difficulties in maintaining work efficiency and the mental well-being of users.

[0757] 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.

[0758] In this invention, the server includes data collection means for acquiring user activity records, work information, and emotional information; problem analysis means for analyzing the acquired data and identifying issues, including the user's emotional state; and countermeasure generation means for generating and presenting countermeasures using a generated AI model based on the identified issues and the user's emotional state. This makes it possible to propose and implement effective countermeasures that take the user's emotional state into consideration in real time.

[0759] A "user" refers to an individual who uses the system to provide activity records and emotional information.

[0760] "Activity log" refers to the history of specific actions and inputs that occur when a user performs their daily tasks.

[0761] "Business information" refers to detailed data related to the tasks and projects that the user is working on.

[0762] "Emotional information" refers to data that represents the user's psychological state, obtained from their facial expressions and voice.

[0763] "Data collection methods" refer to the technologies and processes used to acquire user activity records, work information, and emotional information.

[0764] "Problem analysis methods" refer to the techniques and processes used to evaluate and identify users' problems and emotional states from collected data.

[0765] A "generative AI model" refers to an algorithm and model that uses artificial intelligence to generate optimal solutions based on data.

[0766] "Countermeasure generation method" refers to the technology and process that creates and presents countermeasures using a generation AI model, taking into account the identified problem and the user's emotional state.

[0767] "Real-time" refers to the ability of a system to process information instantly and reflect the results immediately.

[0768] "Effective measures" refer to appropriate action suggestions and environmental adjustments aimed at improving users' work efficiency and psychological well-being.

[0769] To implement this invention, a comprehensive configuration is required to support the entire system flow, from data collection, analysis, and countermeasure generation to implementation and evaluation. The details are described below.

[0770] First, the user's device is equipped with sensors necessary to collect activity and emotional data. Specifically, cameras and microphones are used to capture facial and voice data in real time. This data is transferred to a server with the user's permission. The server acts as a data collection system and stores the data transmitted from the device. The data is managed securely, and mechanisms are in place to protect user privacy.

[0771] Next, the server analyzes the collected data as a means of problem analysis. Emotion engines and machine learning algorithms are used to identify the user's emotional state and challenges. This analysis is crucial for making comprehensive judgments, including the user's stress level and motivation, utilizing artificial intelligence (AI) technology. This process also employs techniques for pattern recognition and correlation evaluation of the data.

[0772] Subsequently, a process takes place in which a generative AI model is run to generate countermeasures. The server inputs prompt sentences into the generative AI model based on the analysis results. For example, a possible prompt sentence might be, "If the user is showing high stress levels, suggest appropriate countermeasures." This prompt sentence serves as the basic information for the AI ​​model to suggest the optimal countermeasures. The model generates specific action plans based on the user's emotional state. These plans are presented to the user, who can then use them as options.

[0773] Once a user selects a course of action, the server coordinates its implementation. Especially when psychological intervention is needed, the system automatically launches appropriate music or applications on the device. For example, it might configure the system to play relaxation music, ensuring that music plays on the user's device.

[0774] The server continuously monitors changes in user emotions and the effectiveness of countermeasures, and generates reports to evaluate the results. These reports include a visual representation of user progress and emotional improvement, and support self-management.

[0775] In this way, the invention integrates digital and human elements to achieve comprehensive problem-solving for the user.

[0776] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0777] Step 1:

[0778] The server collects user activity records, work information, and emotional information from the terminal. The terminal's camera and microphone capture the user's facial expressions and voice, and transmit this information to the server. Using this data as input, the server stores the information in a database.

[0779] Step 2:

[0780] The server analyzes the collected data. Using an emotion engine, it analyzes facial expression and voice data to evaluate the user's emotional state. For example, it detects the presence or absence of a smile using a facial expression recognition algorithm. As output of this process, data is generated as an index related to the user's emotional state.

[0781] Step 3:

[0782] The server identifies issues based on the analysis results. It uses machine learning algorithms to determine stress levels and decreased motivation. Here, it identifies the current emotional state by comparing it with past data. The identified issues are generated as output.

[0783] Step 4:

[0784] The server inputs a prompt message into the AI ​​model for the identified problem. This prompt message might read, for example, "If the user is showing high stress levels, suggest appropriate countermeasures." Based on this input, the AI ​​model generates optimal countermeasures and outputs a list of solutions.

[0785] Step 5:

[0786] The user selects their desired solution from the presented list of solutions. For example, the user might select "Play relaxation music." This selection is sent to the server, and that information is generated as output data.

[0787] Step 6:

[0788] The server prepares to execute the action selected by the user. It sends a command to the terminal corresponding to the selected action. Specifically, it sets the terminal to play relaxation music. The input for this process is the output of step 5, which shows that the specific settings necessary for executing the process have been completed.

[0789] Step 7:

[0790] The server continuously monitors the user's emotional changes while the countermeasures are being implemented. It then collects data again to evaluate the extent of the emotional changes. This data is collected and analyzed, and a report is generated. This report visually displays which countermeasures were effective and for how long.

[0791] (Application Example 2)

[0792] 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".

[0793] Traditionally, problem analysis was performed based on user activity logs and task information, but problem analysis and solution generation did not take into account the user's emotional state. As a result, more humane support could not be provided, and issues related to emotions such as stress and decreased motivation were not adequately addressed. This presents a challenge in providing optimal support and a comfortable environment for users.

[0794] 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.

[0795] In this invention, the server includes data collection means for acquiring user activity logs, task information, and emotional data; problem analysis means for analyzing the acquired data and identifying problems; and countermeasure generation means for generating and presenting countermeasures for the identified problems while evaluating the user's emotional state. This enables more appropriate and humane problem solving while taking the user's emotions into consideration.

[0796] A "user" refers to an individual or representative of an organization that uses this system, and is the entity whose activity logs, task information, and sentiment data are collected and analyzed.

[0797] An "activity log" is data that records a user's actions and operations, and is information that the system uses to understand the user's situation.

[0798] "Task information" is data that indicates the tasks and schedules that a user should perform, and it is the basic data that the system uses to identify problems.

[0799] "Emotional data" refers to data that reflects the user's emotional state and is obtained through facial expression analysis and voice analysis.

[0800] "Data collection means" refers to technical means for acquiring user activity logs, task information, and sentiment data, and includes devices such as sensors and input devices.

[0801] "Problem analysis methods" are technical means that analyze acquired activity logs, task information, and sentiment data to identify the challenges that users face.

[0802] A "solution generation method" is a technical means that uses a generation AI to generate and present the most suitable solution to the user based on analyzed problem and sentiment data.

[0803] "Execution means" refers to the technical means by which the system takes specific actions based on the measures selected by the user and provides feedback as needed.

[0804] A "reporting mechanism" is a technical means of monitoring the implementation status of countermeasures and changes in user sentiment, and reporting the results to the user.

[0805] A "generative AI model" is an artificial intelligence model that generates optimal suggestions and responses for the user based on recorded data.

[0806] To implement this invention, an interactive robot assistant deployed in a smart home environment is used. This robot collects user activity logs, task information, and emotional data in real time and transmits the data to a server located in the cloud. For data collection, sensors such as cameras and microphones are used to analyze the user's movements and voice to obtain facial expression data and voice tone.

[0807] Based on the received data, the server evaluates the user's current emotional state using problem analysis tools and identifies any issues. In particular, it uses an emotion engine to analyze in detail the user's emotions, such as stress and motivation. The generative AI model then generates suggestions optimized for the user's state based on the identified issues and emotional data. Accordingly, prompts such as "If the user's emotional state is high stress, generate suggestions to promote relaxation" are used.

[0808] Based on the user's selection, the robot automatically performs actions such as playing relaxation music or adjusting smart home lighting. This includes integration with music service APIs and smart lighting devices. After execution, it monitors the user's emotional changes and the effectiveness of the actions, providing regular feedback through reporting mechanisms. Through this process, the goal is to improve the user's lifestyle for greater comfort.

[0809] As a concrete example, if a user is experiencing increased stress due to long hours of working from home, the robot might suggest, "You seem a little tired today, would you mind listening to some relaxing music?" and then proceed to do so after receiving the user's approval. This allows the user to refresh both mentally and physically, enabling them to work more efficiently.

[0810] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0811] Step 1:

[0812] The device collects user activity logs, task information, and sentiment data. Input is raw data acquired from sensors such as cameras and microphones. The device organizes this data and converts it into a format for transmission to the server. Output is a standardized dataset.

[0813] Step 2:

[0814] The server analyzes the received data using a problem analysis tool. The input is a standardized dataset sent from the terminal. The server processes the data using an emotion engine and machine learning models to evaluate the user's current emotional state and identify the problem. The output is the user's emotional state and the identified problem.

[0815] Step 3:

[0816] The server generates countermeasures based on the identified issues and emotional states. The input is the user's emotional state and issues obtained through issue analysis. The server uses a generative AI model to create optimal countermeasures and constructs suggestions for the user based on the prompt "Generate suggestions to promote relaxation." The output is a customized set of countermeasures.

[0817] Step 4:

[0818] The user receives proposed solutions from the server and selects the most appropriate solution. The input is the proposed solutions sent from the server. The user selects the suggestion best suited to their situation and provides feedback to the server. The output is information about the solution selected by the user.

[0819] Step 5:

[0820] The server sends instructions to the terminal or associated device to execute the action selected by the user. The input is the action selected by the user. The server utilizes music service APIs and smart home devices to play relaxation music or send signals to adjust lighting. The output is the specific relaxation action that was performed.

[0821] Step 6:

[0822] After the countermeasures are implemented, the server re-evaluates the user's emotional changes and monitors progress and effectiveness. The input is the user's emotional data, which is acquired again. The server provides feedback on the results of the implementation to the user through reporting mechanisms and prepares the next countermeasures as needed. This output serves as feedback to the user and guidance for the next action.

[0823] 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.

[0824] 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.

[0825] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0826] 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.

[0827] 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.

[0828] 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.

[0829] 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.

[0830] 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.

[0831] 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."

[0832] 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.

[0833] 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.

[0834] 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.

[0835] 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.

[0836] 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.

[0837] 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.

[0838] 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.

[0839] 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.

[0840] 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.

[0841] 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.

[0842] 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.

[0843] 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.

[0844] The following is further disclosed regarding the embodiments described above.

[0845] (Claim 1)

[0846] A data collection method for obtaining user activity logs and task information,

[0847] A problem analysis method that analyzes acquired data and identifies problems,

[0848] A means for generating and displaying countermeasures for identified issues,

[0849] An execution mechanism that configures and executes measures based on the measures selected by the user,

[0850] A reporting mechanism that monitors the progress of execution and generates reports periodically,

[0851] A system that includes this.

[0852] (Claim 2)

[0853] The system according to claim 1, comprising means for analyzing a problem using a machine learning model.

[0854] (Claim 3)

[0855] The system according to claim 1, comprising an evaluation means for evaluating the effectiveness of the generated countermeasures and prioritizing them.

[0856] "Example 1"

[0857] (Claim 1)

[0858] A data collection means for acquiring human operation information and business information,

[0859] A problem analysis method that analyzes acquired information and identifies problems,

[0860] A solution generation means for generating and displaying solutions to identified problems,

[0861] An execution means that configures and executes based on a solution selected by a human,

[0862] A reporting mechanism that monitors the progress of execution and generates reports periodically,

[0863] A generative AI model for generating solutions,

[0864] A means for generating a prompt statement to generate a solution to the aforementioned problem,

[0865] An information processing system that includes this.

[0866] (Claim 2)

[0867] The information processing system according to claim 1, comprising means for analyzing a problem using machine learning techniques.

[0868] (Claim 3)

[0869] The information processing system according to claim 1, comprising evaluation means for evaluating the effectiveness of generated solutions and prioritizing them.

[0870] "Application Example 1"

[0871] (Claim 1)

[0872] Information gathering means for acquiring user behavior data and business information,

[0873] Analytical means to analyze acquired information and identify problems,

[0874] A solution generation means for generating and displaying effective solutions to identified problems,

[0875] An implementation method for setting and carrying out procedures based on the solution selected by the user,

[0876] A reporting means that monitors the status of implementation and generates reports periodically,

[0877] A means to support the optimization of computational tasks using clustering technology,

[0878] A system that includes this.

[0879] (Claim 2)

[0880] The system according to claim 1, comprising means for analyzing a problem using a machine learning algorithm.

[0881] (Claim 3)

[0882] The system according to claim 1, comprising evaluation means for evaluating the effectiveness of the generated solutions and setting priorities.

[0883] "Example 2 of combining an emotion engine"

[0884] (Claim 1)

[0885] A data collection method for acquiring user activity records, work information, and emotional information,

[0886] A problem analysis method that analyzes acquired data to identify issues, including the user's emotional state,

[0887] A means for generating and presenting countermeasures using an AI model based on identified issues and the user's emotional state,

[0888] Based on the measures selected by the user, the execution means to be set up and executed,

[0889] A reporting mechanism that monitors the progress of execution and changes in emotions, and generates reports periodically.

[0890] A system that includes this.

[0891] (Claim 2)

[0892] The system according to claim 1, comprising means for analyzing a problem using a machine learning algorithm and evaluating the user's emotional state.

[0893] (Claim 3)

[0894] The system according to claim 1, comprising means for evaluating the effectiveness of the generated countermeasures and prioritizing them.

[0895] "Application example 2 when combining with an emotional engine"

[0896] (Claim 1)

[0897] A data collection method for acquiring user activity logs, task information, and sentiment data,

[0898] A problem analysis method that analyzes acquired data to identify problems,

[0899] A means for generating and presenting countermeasures for identified issues while evaluating the user's emotional state,

[0900] An implementation mechanism that takes action based on the measures selected by the user and provides feedback,

[0901] A reporting mechanism that monitors the progress of the execution and changes in emotions, and provides regular reports,

[0902] A system that includes this.

[0903] (Claim 2)

[0904] The system according to claim 1, comprising means for analyzing a problem using a machine learning model and a generative AI model.

[0905] (Claim 3)

[0906] The system according to claim 1, comprising an evaluation means for evaluating the effectiveness of the generated countermeasures and prioritizing them according to changes in emotional state. [Explanation of symbols]

[0907] 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. A data collection method for obtaining user activity logs and task information, A problem analysis method that analyzes acquired data and identifies problems, A means for generating and displaying countermeasures for identified issues, An execution mechanism that configures and executes measures based on the measures selected by the user, A reporting mechanism that monitors the progress of execution and generates reports periodically, A system that includes this.

2. The system according to claim 1, comprising means for analyzing a problem using a machine learning model.

3. The system according to claim 1, comprising an evaluation means for evaluating the effectiveness of the generated countermeasures and prioritizing them.

Images