system

Abstract

Provide a system. 【Solution means】 Means for collecting industry-specific data, Means for preprocessing the data and performing cleansing, Means for training a machine learning model using the preprocessed data, Means for customizing the trained model for customers, Means for distributing the customized model to terminals, Means for processing business data in real time at the terminal and providing business support, Means for collecting feedback from users and updating the training model, A system including the above.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern corporate activities, effectively and feasibly applying industry-specific expertise to business operations is an important issue in improving productivity and business efficiency. However, many companies face problems such as a lack of expertise and difficulty in aggregating know-how, resulting in inefficiency in business operations or the continuation of inefficient business processes.

Means for Solving the Problems

[0005] This invention proposes a system that provides AI agents embodying expertise by collecting industry-specific data and training machine learning models. This system collects industry-specific data from partner organizations, preprocesses it, and then trains machine learning models. Furthermore, it customizes the trained models for customers and distributes them to terminals to support the operations of customer companies. These terminals can use this model to process business data in real time and provide users with insights for business improvement. In addition, by collecting user feedback and continuously updating the trained models, the system can sustainably improve operational efficiency.

[0006] "Industry-specific data" refers to data that contains specialized knowledge and information specific to a particular industry or field.

[0007] "Cleaning" refers to the process of organizing and removing noise from data to improve its accuracy and consistency.

[0008] A "machine learning model" is a collection of algorithms that allow computers to learn patterns and rules from data, enabling them to automate future data analysis and decision-making.

[0009] A "trained model" is a model that has undergone machine learning using a specific dataset and is ready to perform specific functions such as prediction or classification.

[0010] "Customization" is the process of adjusting and optimizing a system or service to suit a specific customer or use case.

[0011] A "terminal" is an electronic device that is connected to a network and can send and receive data.

[0012] "Processing business data in real time" refers to the process of instantly analyzing business-related data and providing users with useful information.

[0013] "Feedback" refers to response information based on the results of using a system or service and user opinions, used to improve the performance of that system or service. [Brief explanation of the drawing]

[0014] [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]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0018] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0020] 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).

[0021] 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."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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".

[0035] This invention is an industry-specific AI dispatch system that leverages specialized industry knowledge to support the operational efficiency of companies. This system operates based on the cooperation of three parties: a server, terminals, and users.

[0036] First, the server receives industry-specific data from partner specialized organizations. This includes industry best practices and process management information, which are stored in a database. The server securely receives business data from users and integrates that data with the know-how.

[0037] The server preprocesses and cleanses the received data, removing noise and incomplete information to optimize the dataset for training machine learning models. Next, the server uses machine learning algorithms to create a trained AI model, which then possesses expertise in a specific industry.

[0038] Once the AI ​​model is trained, it is customized according to the user's specific needs. The server then distributes this customized model to the customer's terminal. On the terminal, the AI ​​agent runs, processing data related to the user's work in real time and supporting business improvement. As a concrete example, in manufacturing, the AI ​​agent can monitor the status of equipment and provide advance warnings of signs of failure.

[0039] Subsequently, the user provides feedback based on the AI ​​system's performance. This feedback is sent to the server and used to improve the AI ​​model. The server continuously optimizes the model and redistributes the new version to the terminal. As a result, the system continues to evolve according to the user's work environment, leading to continuously improved business results.

[0040] In this way, the system of the present invention achieves sustainable operational efficiency for companies through AI agents with specialized industry knowledge.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The server receives industry-specific data from partner specialist organizations and stores it in a database. This includes industry best practices and relevant information.

[0044] Step 2:

[0045] Users upload company-specific business data to the server. This data is encrypted and transmitted via a secure protocol.

[0046] Step 3:

[0047] The server cleanses the received data, removing inaccurate data and noise. At this stage, the data format is also standardized, making it suitable for machine learning.

[0048] Step 4:

[0049] The server uses organized data to train a machine learning model. This model is designed to learn industry-specific knowledge and expertise.

[0050] Step 5:

[0051] The trained model is customized according to the user's business needs. The server then transfers this customized model to the terminal.

[0052] Step 6:

[0053] The AI ​​agent installed on the device processes business data in real time and provides users with insights for business improvement. For example, in a manufacturing plant, it monitors the status of equipment and detects anomalies.

[0054] Step 7:

[0055] Users provide feedback to the server regarding the AI ​​agent's behavior. This feedback is used to improve the model.

[0056] Step 8:

[0057] The server updates the AI ​​model based on user feedback and newly acquired data. This updated model is then distributed back to the terminals, ensuring continuous system optimization.

[0058] (Example 1)

[0059] 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."

[0060] In modern business environments, there is a growing demand to improve efficiency by leveraging specific expertise and know-how. However, existing systems have limited the effectiveness of productivity improvements and support due to insufficient detailed data processing and advanced business support tailored to specific tasks. Solving this problem is crucial.

[0061] 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.

[0062] In this invention, the server includes means for collecting business-domain specific information, means for preprocessing the information and performing data improvement, and means for training a generated AI model using the improved information. This enables accurate information provision and real-time business support using a business-specific AI model.

[0063] "Business-specific information" refers to data that includes specialized knowledge and know-how related to a particular business.

[0064] "Preprocessing" refers to the process of preparing raw data into a format suitable for analysis and model training.

[0065] "Data refinement" refers to the process of removing noise and incomplete information from a dataset to make it suitable for analysis.

[0066] A "generative AI model" refers to an artificial intelligence program designed to learn from data and perform predictions and classifications for specific tasks.

[0067] "Teaching" refers to the process by which a model learns specific patterns or rules using machine learning algorithms.

[0068] "Adjusting" refers to the process of changing the parameters and settings of a model to suit specific needs and requirements.

[0069] "Device" refers to equipment that includes hardware or software environments for running AI models and providing business support.

[0070] "Real-time" refers to data processing and analysis that provides results immediately, without any time delay.

[0071] "Opinions" refer to feedback and evaluations provided by users, and are information that can be used to improve the system or model.

[0072] "Insights" refer to new knowledge and understanding gained through data analysis and AI models, which support business decision-making.

[0073] This invention is an AI-powered dispatch system specialized for specific business areas, designed to streamline corporate operations by leveraging specialized knowledge. The system consists of a server, terminals, and users, and each component works in coordination with the others.

[0074] The server first collects business-specific information from partner specialized organizations and stores it in a database. This information includes industry best practices and process management information, and a dataset is formed based on this to analyze business operations. Next, the server receives business data from users and securely retrieves it through encrypted communication using the SSL / TLS protocol. The collected data is preprocessed and data improvement is performed. In this process, the dataset is cleaned up from noise and missing values ​​using libraries such as Pandas, and prepared in a format suitable for training machine learning models.

[0075] The server trains generative AI models using machine learning frameworks such as TENSORFLOW® and PyTorch. These models learn expertise within the business domain and are tailored to specific business needs. The tailored AI models are then distributed to user terminals, where AI agents run. These terminals process business-related data in real time to support business improvement. For example, in manufacturing, a terminal might process equipment sensor data and predict signs of failure.

[0076] Users provide feedback based on the AI ​​system's performance. This feedback is sent to the server and used to improve the AI ​​model. The server optimizes the model based on this feedback and redistributes it to the terminal as a new version. This allows the system to continuously evolve and always provide support that is compatible with the latest business environment.

[0077] A concrete example of a prompt might be: "Create an AI model that proposes the optimal delivery routes to reduce fuel consumption for the logistics industry. Real-time route optimization considering traffic and weather data is required."

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

[0079] Step 1:

[0080] The server collects domain-specific information from partner specialized organizations. It receives industry data digitally via APIs and data feeds as input. This received data is stored in the server's database. The output is a dataset of organized and stored industry information.

[0081] Step 2:

[0082] The server receives business data from users. As input, it receives encrypted business-related data sent via a REST API. The server adds this data to a database, forming an integrated dataset as output.

[0083] Step 3:

[0084] The server performs preprocessing and data refinement. It receives an integrated dataset as input and uses the Pandas library to denoise and impute missing values. This improves data quality, resulting in clean data suitable for training machine learning models as output.

[0085] Step 4:

[0086] The server trains the generated AI model. It feeds a clean dataset as input to a machine learning algorithm (e.g., TensorFlow) to train the model. The output is a trained AI model with knowledge specific to a particular business domain.

[0087] Step 5:

[0088] The server adjusts the trained model and distributes it to the terminal. As input, it adjusts the model considering user requests and prompts to generate a customized model. The server then sends this customized model to the terminal. The output is a customized AI model that meets the user's specific needs.

[0089] Step 6:

[0090] The terminal processes business data in real time. It supplies various types of data generated from business activities (e.g., sensor data) to the model as input. The terminal uses an AI agent to process the data and provides the user with predictions and optimized suggestions as output.

[0091] Step 7:

[0092] Users provide feedback on the AI ​​system's results. As input, they send opinions and evaluations to the server that reflect the system's output and their experience. The server receives this feedback and, as output, obtains information necessary for improving the model. Based on this feedback, the model is then optimized.

[0093] (Application Example 1)

[0094] 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."

[0095] Detecting equipment malfunctions and providing real-time administrator notifications in factory and other workplace settings is inefficient with conventional technologies, making timely responses difficult. In particular, the decline in productivity caused by equipment failures and reduced operational efficiency is a major problem, and effective measures to prevent this are needed.

[0096] 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.

[0097] In this invention, the server includes means for acquiring industry-specific data, means for pre-processing and cleansing the data, and means for detecting equipment abnormalities and notifying the administrator. This makes it possible to improve work efficiency at the factory floor and prevent equipment failures.

[0098] "Industry-specific materials" are collections of data containing know-how and best practices specific to a particular industrial sector.

[0099] "Preprocessing" is the process of removing and organizing noise and missing information in order to improve the accuracy of the data.

[0100] "Data cleansing" is the process of correcting outliers and invalid data to ensure data quality.

[0101] A "machine learning model" is a mathematical model that uses algorithms to learn patterns and rules from data.

[0102] "Training" in machine learning is the process of optimizing a model using data.

[0103] "Customization" refers to the process of adjusting a product or service to meet specific needs or requirements.

[0104] An "information processing device" is an electronic device used for inputting, processing, and outputting data.

[0105] "Real-time" refers to information being processed and provided to the user immediately the moment it is generated.

[0106] "Work support" refers to activities that provide information and advice to improve the efficiency and accuracy of work.

[0107] "Feedback" refers to the backflow of opinions and information based on the output and usage of a system.

[0108] Anomaly detection is a technology that identifies malfunctions in equipment or systems that deviate from their normal state.

[0109] "Administrator notification" refers to the act of promptly informing the person in charge when important information arises.

[0110] In the system that implements this application, a server plays a central role. The server first retrieves industry-specific data from partner specialized organizations. This includes best practices and technical information that are updated in real time using an edge computing framework. The retrieved data is preprocessed and cleansed and organized into a high-quality dataset. This process removes noise and imputes missing values.

[0111] Next, the server trains a machine learning model using the pre-processed data. This primarily uses Python's Scikit-learn library to build models using algorithms such as random forests and neural networks. This trained model is then customized to meet the customer's specific needs.

[0112] Customized models are distributed to information processing devices, enabling terminals to provide real-time support for on-site work. The terminals use data acquired from equipment within the factory to detect anomalies and generate insights into the equipment. This information is notified to administrators in real time to support rapid response. Furthermore, feedback is sent to the server based on the information received by the terminals, allowing the system to continuously improve.

[0113] As a concrete example, on a manufacturing line, AI can identify the reason for a machine malfunction and prompt the manager with "Which part of the manufacturing line is currently malfunctioning?", allowing for immediate countermeasures to be suggested. At this time, the manager will be shown a prompt message such as "What equipment status should be monitored most closely on this manufacturing line right now?" This enables the AI ​​to quickly analyze the situation on site and propose the optimal solution.

[0114] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0115] Step 1:

[0116] The server retrieves industry-specific data from partner specialized organizations. As input, it receives data periodically downloaded from the specialized organizations' APIs and databases. As output, the collected data is stored in a local database. This operation uses HTTP requests to retrieve the latest information.

[0117] Step 2:

[0118] The server preprocesses and cleanses the acquired data. Raw data stored in a local database is used as input. Data processing uses the Python Pandas library to impute missing values ​​and remove noise. The output is a high-quality dataset. This process ensures that only valid data proceeds to the next step.

[0119] Step 3:

[0120] The server trains a machine learning model using pre-processed data. The input is a normalized dataset. The server uses Scikit-learn to build and train random forest or neural network models. The output is a trained model optimized for a specific industry. Through this process, the model learns patterns from the data and gains predictive power.

[0121] Step 4:

[0122] The server customizes the trained model to meet customer needs and distributes it to the information processing unit. It receives customer requirements and model parameters as input. Data processing is performed by tuning the model's hyperparameters. The customized model is installed on the information processing unit as output. This process makes the optimized model available for field use.

[0123] Step 5:

[0124] The terminal provides real-time work support on-site. Input consists of data from on-site equipment and sensors. The terminal uses a model to detect anomalies and performs analysis using a generated AI model. The output is the notification of necessary information to the administrator. This operation uses prompt messages to provide suggestions and warnings to the administrator.

[0125] Step 6:

[0126] The server collects user feedback and updates the training model. Inputs include terminal usage data and administrator evaluations. Data calculations retrain the model based on the new data. The output is an improved model. This process enhances the overall accuracy and efficiency of the system.

[0127] 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.

[0128] This invention aims to provide more effective business support by combining an industry-specific AI dispatch system with an emotion engine that recognizes user emotions. This system is based on servers, terminals, and users, and aims to improve operational efficiency through their coordination.

[0129] First, the server collects industry-specific data and know-how from partner specialized organizations and stores it in a database. Then, users upload company-specific business data to the server via a secure protocol. The server cleanses the received data, converts it to a unified format, and uses it to train machine learning models.

[0130] The emotion engine allows the device to analyze the user's emotional state in real time. This enables the system to collect feedback data based on the user's emotions. This data is used to adjust parameters to reduce the user's stress level, among other things.

[0131] The server creates a trained AI model and customizes it to meet the user's business needs. This customized model is then distributed to the terminal and provides business support to the user as an AI agent. As a specific example, in manufacturing, the AI ​​agent continuously monitors the efficiency and quality of equipment and suggests improvements when anomalies are detected. It also adjusts the interface to match the user's emotional state.

[0132] Users provide feedback based on the AI ​​system's performance and operational efficiency. Emotional data obtained through the emotion engine complements this feedback and helps in updating the AI ​​model on the server. This feedback allows the server to continuously improve and retrain the AI ​​model, redistributing the new model to terminals and evolving the entire system.

[0133] Throughout this entire system, the present invention, which incorporates emotion recognition, enables support that balances user job satisfaction and efficiency, thereby contributing to improved productivity for companies.

[0134] The following describes the processing flow.

[0135] Step 1:

[0136] The server receives industry-specific data and know-how from partner specialized organizations and stores it in a database. This information includes the latest industry trends and best practices.

[0137] Step 2:

[0138] Users collect company-specific business data and send it to the server via a secure protocol. This data includes production data, sales data, customer inquiry information, and more.

[0139] Step 3:

[0140] The server cleanses the received data, removing noise and inaccurate information to improve data quality. This process converts the data into a unified format.

[0141] Step 4:

[0142] The server uses the cleansed data to train a machine learning model. This model learns industry-specific expertise and builds a foundation for trend prediction and optimization.

[0143] Step 5:

[0144] By utilizing an emotion engine, the device analyzes the user's emotional state in real time. Based on this analysis, the user's stress level can be determined.

[0145] Step 6:

[0146] The trained AI models are customized based on the user's specific business needs and distributed from the server to the terminal. This allows the AI ​​agent to provide support tailored to the company's workflow.

[0147] Step 7:

[0148] The AI ​​agent on the terminal monitors business processes and provides insights for business improvement in a way that is sensitive to the user's emotions. For example, in a manufacturing environment, it provides real-time alerts regarding equipment inefficiency and quality issues.

[0149] Step 8:

[0150] Users send feedback to the server based on the AI ​​agent's performance and interactions. This feedback includes user sentiment data, which is a crucial element for improving the model.

[0151] Step 9:

[0152] The server updates the AI ​​model using feedback and new data. It then retrains the updated model and redistributes the optimized version to the terminals, supporting continuous improvement of operations.

[0153] (Example 2)

[0154] 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".

[0155] In today's business environment, there is a need for systems that support operations efficiently and flexibly based on industry-specific information. However, existing systems struggle to provide real-time support that takes into account the emotional state of users. This challenge makes it difficult to improve operational efficiency and maximize user satisfaction.

[0156] 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.

[0157] In this invention, the server includes means for collecting industry-specific information, means for organizing the information and performing data cleanup, and means for training a learning algorithm using the organized information. This enables highly accurate business support that leverages industry-specific knowledge. Furthermore, flexible business responses based on the user's emotional state are realized, leading to improved business efficiency and increased user satisfaction.

[0158] "Industry-specific information" refers to data and knowledge specific to a particular industry or field, and includes specialized information necessary for business support.

[0159] "Data cleansing" is the process of preparing raw data, a procedure to remove inaccurate data and ensure consistency and accuracy.

[0160] A "learning algorithm" refers to a computational process that uses data to find patterns and rules, enabling problem-solving and prediction.

[0161] "User-specific customization" refers to the process of optimizing the system to meet the unique needs and requirements of each user, ensuring they achieve the best possible performance.

[0162] "Evaluation" refers to the feedback and opinions that users provide to the system, and includes information that helps improve the system.

[0163] "Emotional state" refers to the user's psychological and emotional state, and is a factor considered by the system to provide the user with the best possible support.

[0164] The following describes embodiments for carrying out the invention.

[0165] This system is implemented through collaboration between the server, terminals, and users. The server has a database for collecting and maintaining industry-specific information. The server receives information from partner specialized organizations and performs data cleansing to generate accurate and consistent data. Then, existing machine learning platforms and libraries (e.g., TensorFlow and PyTorch) are utilized to train learning algorithms using this refined data.

[0166] The device features an emotion engine that recognizes the user's emotional state in real time during work. This engine utilizes hardware sensors such as cameras and microphones to analyze the user's facial expressions and voice. This allows the system to understand in real time whether the user is stressed or satisfied. The user's emotions and work data interact to improve the quality of work support.

[0167] As a concrete example, in the manufacturing industry, the terminal can monitor efficiency and quality while equipment is running, and immediately suggest corrective actions if an anomaly is detected. Furthermore, by adjusting the interface according to the user's emotional state, it's possible to reduce stress. The terminal sends this information to a server, which then uses it to improve its algorithms.

[0168] Examples of specific prompt messages include the following:

[0169] "Monitor the efficiency of manufacturing equipment and propose corrective measures if any abnormalities occur."

[0170] "Analyze the user's stress level using an emotion engine and adjust the interface accordingly."

[0171] Based on these prompts, the generated AI model can provide users with personalized work support, thereby improving work efficiency and user satisfaction.

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

[0173] Step 1:

[0174] The server collects industry-specific information from partner specialized organizations. This information input consists of cases and data sets related to a specific industry. The server stores this in a database and makes the information available for use as needed.

[0175] Step 2:

[0176] The server cleans and preprocesses the collected industry-specific information. Inputs include raw and unorganized data, and the output generates consistent and accurate data. This process includes removing incorrect data, imputing missing values, and standardizing the format.

[0177] Step 3:

[0178] The server trains learning algorithms using pre-processed data. The input is cleaned data, and the output includes generative AI models based on pattern detection and prediction. This process involves using a machine learning platform to build an optimal model by adjusting the algorithm's parameters.

[0179] Step 4:

[0180] The server customizes the trained model according to the user's needs. The input is the generated AI model, and the output is the customized model that meets the user's business requirements. Specifically, it considers industry-specific use cases and fine-tunes the model and enhances the algorithms.

[0181] Step 5:

[0182] The server distributes customized models to the terminals. The input is the adjusted AI model, and the output is the terminal environment that received it. This enables business support functions on the terminals.

[0183] Step 6:

[0184] The terminal processes user work data sequentially and provides work support. Input data includes real-time collected work metrics and the user's emotional state. Output provides the user with improvement suggestions and feedback to improve work efficiency.

[0185] Step 7:

[0186] Users submit feedback based on the work results provided by the AI. This feedback is input to a server, which then prompts continuous improvement of the model and is used as retraining data. This feedback loop allows the AI ​​system to continuously evolve.

[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] Modern households require support to efficiently handle various tasks, but conventional technologies have struggled to provide dynamic support that takes user emotions into account. Furthermore, addressing individual household needs often requires massive data processing and model updates, making them impractical. To solve this problem, a system is needed that can grasp the user's emotional state in real time and provide task support accordingly.

[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 means for acquiring business information, means for preparing and purifying the information before processing, and means for training an automated learning model using the prepared information. This enables the analysis of the user's emotional state, business support based on that analysis, and further evolution of the entire system through continuous feedback.

[0192] "Means for acquiring business information" refers to methods and technologies for collecting business-related information, which effectively gather the data required by the system.

[0193] "Preprocessing" refers to the process of preparing acquired information before processing it, correcting inconsistencies to improve accuracy, and converting it to the required format.

[0194] "Purification" refers to the process of removing defects and unnecessary parts from data, and is a method for improving the transparency and accuracy of information.

[0195] "Methods for training automated learning models" refer to methods of using large amounts of data to train machine learning algorithms and build foundational computational models for making predictions and decisions.

[0196] "Means of providing to the device" refers to the process of delivering a model created or improved by the system to a specific device or terminal, making it directly available to the user.

[0197] "Means for processing business information and providing business support" refers to technologies or functions that analyze information according to the user's needs and perform various processes to assist in the optimal execution of business operations.

[0198] "Analyzing emotional state" refers to the process of monitoring a user's facial expressions, tone of voice, and behavioral patterns to evaluate their emotional state and psychological characteristics.

[0199] "Means of collecting feedback" refers to methods of systematically gathering opinions and usage-based responses from users, which are then used to improve the system.

[0200] This invention is a system that analyzes user emotions in real time and provides business support. The server acquires business information and performs preprocessing and purification. For example, it corrects inconsistencies in the information and converts it to the required format. This ensures that the automated learning model is accurately trained. The server also refines this trained model and distributes it to devices. In this process, it is possible to provide the model directly to specific devices or terminals.

[0201] The terminal uses software such as OpenCV and TensorFlow to run models within the device and analyze the user's emotional state. This allows for real-time capture of the user's facial expressions and tone of voice, and an assessment of their emotional state. Based on the evaluation results, the system can provide work support tailored to the user's needs, thereby improving work efficiency. Furthermore, the feedback is compiled and used to improve the system.

[0202] As a concrete example, considering a busy morning at home, the device can individually sense the tension in the user's mood and suggest things like playing music or assisting with breakfast preparation. To support such user interactions, a feedback function based on emotional data will drive the overall evolution of the system.

[0203] Example of a prompt:

[0204] "What kind of robot support would be ideal for the whole family getting ready to leave in the morning?"

[0205] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0206] Step 1:

[0207] The server retrieves business information. This information includes user activity logs and past feedback, providing data that offers hints for improving business efficiency. The server receives data uploaded from the user's device as input and organizes it. The organized data is then passed as output to the preprocessing step.

[0208] Step 2:

[0209] The server preprocesses and cleans the received data. This process uses normalization and filtering techniques to correct inconsistent data and remove noise. The input is the data sorted in step 1, and the output is the data converted into a format acceptable to the model.

[0210] Step 3:

[0211] The server trains an automated learning model using pre-processed data. By feeding the data into a specific learning algorithm and allowing it to learn patterns and trends, it generates a trained model as output. This improves the overall accuracy of the system.

[0212] Step 4:

[0213] The server provides the trained model to the terminal. This process transfers the trained model to the user's device, enabling real-time business support. The input is the trained model, and the output is the model in a format executable on the terminal.

[0214] Step 5:

[0215] The device uses a model to analyze emotional states. It captures the user's facial expressions and voice via the device's built-in camera and microphone, and analyzes them using the model. The input is real-time emotional data, and the output is an analysis result indicating the user's emotional state.

[0216] Step 6:

[0217] The terminal provides business support based on the analysis results. It offers appropriate suggestions and assistance according to the user's emotional state, streamlining the business process. For example, if the user is experiencing excessive stress, the system will suggest playing relaxing music.

[0218] Step 7:

[0219] Users provide feedback on the business support services offered, and the terminal collects this feedback. The input is user feedback, which is sent to the server and used for future model updates. The output is feedback data, which is used to better adjust the server's AI model.

[0220] 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.

[0221] 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.

[0222] 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.

[0223] [Second Embodiment]

[0224] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0225] 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.

[0226] 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).

[0227] 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.

[0228] 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.

[0229] 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).

[0230] 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.

[0231] 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.

[0232] 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.

[0233] 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.

[0234] 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.

[0235] 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".

[0236] This invention is an industry-specific AI dispatch system that leverages specialized industry knowledge to support the operational efficiency of companies. This system operates based on the cooperation of three parties: a server, terminals, and users.

[0237] First, the server receives industry-specific data from partner specialized organizations. This includes industry best practices and process management information, which are stored in a database. The server securely receives business data from users and integrates that data with the know-how.

[0238] The server preprocesses and cleanses the received data, removing noise and incomplete information to optimize the dataset for training machine learning models. Next, the server uses machine learning algorithms to create a trained AI model, which then possesses expertise in a specific industry.

[0239] Once the AI ​​model is trained, it is customized according to the user's specific needs. The server then distributes this customized model to the customer's terminal. On the terminal, the AI ​​agent runs, processing data related to the user's work in real time and supporting business improvement. As a concrete example, in manufacturing, the AI ​​agent can monitor the status of equipment and provide advance warnings of signs of failure.

[0240] Subsequently, the user provides feedback based on the AI ​​system's performance. This feedback is sent to the server and used to improve the AI ​​model. The server continuously optimizes the model and redistributes the new version to the terminal. As a result, the system continues to evolve according to the user's work environment, leading to continuously improved business results.

[0241] In this way, the system of the present invention achieves sustainable operational efficiency for companies through AI agents with specialized industry knowledge.

[0242] The following describes the processing flow.

[0243] Step 1:

[0244] The server receives industry-specific data from partner specialist organizations and stores it in a database. This includes industry best practices and relevant information.

[0245] Step 2:

[0246] Users upload company-specific business data to the server. This data is encrypted and transmitted via a secure protocol.

[0247] Step 3:

[0248] The server cleanses the received data, removing inaccurate data and noise. At this stage, the data format is also standardized, making it suitable for machine learning.

[0249] Step 4:

[0250] The server uses organized data to train a machine learning model. This model is designed to learn industry-specific knowledge and expertise.

[0251] Step 5:

[0252] The trained model is customized according to the user's business needs. The server then transfers this customized model to the terminal.

[0253] Step 6:

[0254] The AI ​​agent installed on the device processes business data in real time and provides users with insights for business improvement. For example, in a manufacturing plant, it monitors the status of equipment and detects anomalies.

[0255] Step 7:

[0256] Users provide feedback to the server regarding the AI ​​agent's behavior. This feedback is used to improve the model.

[0257] Step 8:

[0258] The server updates the AI ​​model based on user feedback and newly acquired data. This updated model is then distributed back to the terminals, ensuring continuous system optimization.

[0259] (Example 1)

[0260] 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."

[0261] In modern business environments, there is a growing demand to improve efficiency by leveraging specific expertise and know-how. However, existing systems have limited the effectiveness of productivity improvements and support due to insufficient detailed data processing and advanced business support tailored to specific tasks. Solving this problem is crucial.

[0262] 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.

[0263] In this invention, the server includes means for collecting business-domain specific information, means for preprocessing the information and performing data improvement, and means for training a generated AI model using the improved information. This enables accurate information provision and real-time business support using a business-specific AI model.

[0264] "Business-specific information" refers to data that includes specialized knowledge and know-how related to a particular business.

[0265] "Preprocessing" refers to the process of preparing raw data into a format suitable for analysis and model training.

[0266] "Data refinement" refers to the process of removing noise and incomplete information from a dataset to make it suitable for analysis.

[0267] A "generative AI model" refers to an artificial intelligence program designed to learn from data and perform predictions and classifications for specific tasks.

[0268] "Teaching" refers to the process by which a model learns specific patterns or rules using machine learning algorithms.

[0269] "Adjusting" refers to the process of changing the parameters and settings of a model to suit specific needs and requirements.

[0270] "Device" refers to equipment that includes hardware or software environments for running AI models and providing business support.

[0271] "Real-time" refers to data processing and analysis that provides results immediately, without any time delay.

[0272] "Opinions" refer to feedback and evaluations provided by users, and are information that can be used to improve the system or model.

[0273] "Insights" refer to new knowledge and understanding gained through data analysis and AI models, which support business decision-making.

[0274] This invention is an AI-powered dispatch system specialized for specific business areas, designed to streamline corporate operations by leveraging specialized knowledge. The system consists of a server, terminals, and users, and each component works in coordination with the others.

[0275] The server first collects business-specific information from partner specialized organizations and stores it in a database. This information includes industry best practices and process management information, and a dataset is formed based on this to analyze business operations. Next, the server receives business data from users and securely retrieves it through encrypted communication using the SSL / TLS protocol. The collected data is preprocessed and data improvement is performed. In this process, the dataset is cleaned up from noise and missing values ​​using libraries such as Pandas, and prepared in a format suitable for training machine learning models.

[0276] The server uses machine learning frameworks such as TensorFlow and PyTorch to train generative AI models. These models learn expertise in the business domain and are tailored to specific business needs. The tailored AI models are distributed to user terminals, where AI agents run. On the terminals, business data is processed in real time to support business improvement. For example, in manufacturing, a terminal processes sensor data from equipment and predicts signs of failure.

[0277] Users provide feedback based on the AI ​​system's performance. This feedback is sent to the server and used to improve the AI ​​model. The server optimizes the model based on this feedback and redistributes it to the terminal as a new version. This allows the system to continuously evolve and always provide support that is compatible with the latest business environment.

[0278] A concrete example of a prompt might be: "Create an AI model that proposes the optimal delivery routes to reduce fuel consumption for the logistics industry. Real-time route optimization considering traffic and weather data is required."

[0279] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0280] Step 1:

[0281] The server collects industry-specific information from partnering specialized institutions. As input, it receives industry data provided digitally via APIs and data feeds. This received data is stored in the server's database. The output is a dataset of organized and stored industry information.

[0282] Step 2:

[0283] The server receives business data from users. As input, it receives encrypted business-related data sent through a REST API. The server adds it to the database and, as output, forms an integrated dataset.

[0284] Step 3:

[0285] The server performs preprocessing and data improvement. As input, it receives the integrated dataset and uses the Pandas library to remove noise and fill in missing values. This improves the data quality and, as output, obtains clean data suitable for training a machine learning model.

[0286] Step 4:

[0287] The server trains a generative AI model. As input, it supplies the clean dataset to a machine learning algorithm (e.g., TensorFlow) to train the model. As output, it obtains a trained AI model with knowledge specialized in a specific business area.

[0288] Step 5:

[0289] The server adjusts the trained model and distributes it to the terminal. As input, it adjusts the model considering the user's requests and prompt text to generate a customized model. The server sends this to the terminal. The output is a customized AI model that meets the user's specific needs.

[0290] Step 6:

[0291] The terminal processes business data in real time. It supplies various types of data generated from business activities (e.g., sensor data) to the model as input. The terminal uses an AI agent to process the data and provides the user with predictions and optimized suggestions as output.

[0292] Step 7:

[0293] Users provide feedback on the AI ​​system's results. As input, they send opinions and evaluations to the server that reflect the system's output and their experience. The server receives this feedback and, as output, obtains information necessary for improving the model. Based on this feedback, the model is then optimized.

[0294] (Application Example 1)

[0295] 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."

[0296] Detecting equipment malfunctions and providing real-time administrator notifications in factory and other workplace settings is inefficient with conventional technologies, making timely responses difficult. In particular, the decline in productivity caused by equipment failures and reduced operational efficiency is a major problem, and effective measures to prevent this are needed.

[0297] 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.

[0298] In this invention, the server includes means for acquiring industry-specific data, means for pre-processing and cleansing the data, and means for detecting equipment abnormalities and notifying the administrator. This makes it possible to improve work efficiency at the factory floor and prevent equipment failures.

[0299] "Industry-specific materials" are collections of data containing know-how and best practices specific to a particular industrial sector.

[0300] "Pretreatment" refers to the process of removing and organizing noise and missing information in order to improve the accuracy of data.

[0301] "Cleaning" refers to the operation of correcting outliers and invalid data to ensure the quality of data.

[0302] "Machine learning model" refers to a mathematical model that utilizes an algorithm for learning patterns and rules from data.

[0303] "Training" refers to the process of optimizing a model using data in machine learning.

[0304] "Customization" refers to the operation of adjusting products or services according to specific needs and conditions.

[0305] "Information processing device" refers to an electronic device for inputting, processing, and outputting data.

[0306] "Real-time" refers to the situation where information is processed immediately at the moment it is generated and provided to users.

[0307] "Work support" refers to activities that provide information and advice to enhance the efficiency and accuracy of work.

[0308] "Feedback" refers to the reverse flow of opinions and information based on the output and usage status of a system.

[0309] "Anomaly detection" refers to a technology for identifying malfunctions in equipment and systems that deviate from normal conditions.

[0310] "Administrator notification" refers to the act of promptly informing the responsible person when important information occurs.

[0311] In the system that implements this application, a server plays a central role. The server first retrieves industry-specific data from partner specialized organizations. This includes best practices and technical information that are updated in real time using an edge computing framework. The retrieved data is preprocessed and cleansed and organized into a high-quality dataset. This process removes noise and imputes missing values.

[0312] Next, the server trains a machine learning model using the pre-processed data. This primarily uses Python's Scikit-learn library to build models using algorithms such as random forests and neural networks. This trained model is then customized to meet the customer's specific needs.

[0313] Customized models are distributed to information processing devices, enabling terminals to provide real-time support for on-site work. The terminals use data acquired from equipment within the factory to detect anomalies and generate insights into the equipment. This information is notified to administrators in real time to support rapid response. Furthermore, feedback is sent to the server based on the information received by the terminals, allowing the system to continuously improve.

[0314] As a concrete example, on a manufacturing line, AI can identify the reason for a machine malfunction and prompt the manager with "Which part of the manufacturing line is currently malfunctioning?", allowing for immediate countermeasures to be suggested. At this time, the manager will be shown a prompt message such as "What equipment status should be monitored most closely on this manufacturing line right now?" This enables the AI ​​to quickly analyze the situation on site and propose the optimal solution.

[0315] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0316] Step 1:

[0317] The server retrieves industry-specific data from partner specialized organizations. As input, it receives data periodically downloaded from the specialized organizations' APIs and databases. As output, the collected data is stored in a local database. This operation uses HTTP requests to retrieve the latest information.

[0318] Step 2:

[0319] The server preprocesses and cleanses the acquired data. Raw data stored in a local database is used as input. Data processing uses the Python Pandas library to impute missing values ​​and remove noise. The output is a high-quality dataset. This process ensures that only valid data proceeds to the next step.

[0320] Step 3:

[0321] The server trains a machine learning model using pre-processed data. The input is a normalized dataset. The server uses Scikit-learn to build and train random forest or neural network models. The output is a trained model optimized for a specific industry. Through this process, the model learns patterns from the data and gains predictive power.

[0322] Step 4:

[0323] The server customizes the trained model to meet customer needs and distributes it to the information processing unit. It receives customer requirements and model parameters as input. Data processing is performed by tuning the model's hyperparameters. The customized model is installed on the information processing unit as output. This process makes the optimized model available for field use.

[0324] Step 5:

[0325] The terminal provides real-time work support on-site. Input consists of data from on-site equipment and sensors. The terminal uses a model to detect anomalies and performs analysis using a generated AI model. The output is the notification of necessary information to the administrator. This operation uses prompt messages to provide suggestions and warnings to the administrator.

[0326] Step 6:

[0327] The server collects user feedback and updates the training model. Inputs include terminal usage data and administrator evaluations. Data calculations retrain the model based on the new data. The output is an improved model. This process enhances the overall accuracy and efficiency of the system.

[0328] 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.

[0329] This invention aims to provide more effective business support by combining an industry-specific AI dispatch system with an emotion engine that recognizes user emotions. This system is based on servers, terminals, and users, and aims to improve operational efficiency through their coordination.

[0330] First, the server collects industry-specific data and know-how from partner specialized organizations and stores it in a database. Then, users upload company-specific business data to the server via a secure protocol. The server cleanses the received data, converts it to a unified format, and uses it to train machine learning models.

[0331] The emotion engine allows the device to analyze the user's emotional state in real time. This enables the system to collect feedback data based on the user's emotions. This data is used to adjust parameters to reduce the user's stress level, among other things.

[0332] The server creates a trained AI model and customizes it to meet the user's business needs. This customized model is then distributed to the terminal and provides business support to the user as an AI agent. As a specific example, in manufacturing, the AI ​​agent continuously monitors the efficiency and quality of equipment and suggests improvements when anomalies are detected. It also adjusts the interface to match the user's emotional state.

[0333] Users provide feedback based on the AI ​​system's performance and operational efficiency. Emotional data obtained through the emotion engine complements this feedback and helps in updating the AI ​​model on the server. This feedback allows the server to continuously improve and retrain the AI ​​model, redistributing the new model to terminals and evolving the entire system.

[0334] Throughout this entire system, the present invention, which incorporates emotion recognition, enables support that balances user job satisfaction and efficiency, thereby contributing to improved productivity for companies.

[0335] The following describes the processing flow.

[0336] Step 1:

[0337] The server receives industry-specific data and know-how from partner specialized organizations and stores it in a database. This information includes the latest industry trends and best practices.

[0338] Step 2:

[0339] Users collect company-specific business data and send it to the server via a secure protocol. This data includes production data, sales data, customer inquiry information, and more.

[0340] Step 3:

[0341] The server cleanses the received data, removing noise and inaccurate information to improve data quality. This process converts the data into a unified format.

[0342] Step 4:

[0343] The server uses the cleansed data to train a machine learning model. This model learns industry-specific expertise and builds a foundation for trend prediction and optimization.

[0344] Step 5:

[0345] By utilizing an emotion engine, the device analyzes the user's emotional state in real time. Based on this analysis, the user's stress level can be determined.

[0346] Step 6:

[0347] The trained AI models are customized based on the user's specific business needs and distributed from the server to the terminal. This allows the AI ​​agent to provide support tailored to the company's workflow.

[0348] Step 7:

[0349] The AI ​​agent on the terminal monitors business processes and provides insights for business improvement in a way that is sensitive to the user's emotions. For example, in a manufacturing environment, it provides real-time alerts regarding equipment inefficiency and quality issues.

[0350] Step 8:

[0351] Users send feedback to the server based on the AI ​​agent's performance and interactions. This feedback includes user sentiment data, which is a crucial element for improving the model.

[0352] Step 9:

[0353] The server updates the AI ​​model using feedback and new data. It then retrains the updated model and redistributes the optimized version to the terminals, supporting continuous improvement of operations.

[0354] (Example 2)

[0355] 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".

[0356] In today's business environment, there is a need for systems that support operations efficiently and flexibly based on industry-specific information. However, existing systems struggle to provide real-time support that takes into account the emotional state of users. This challenge makes it difficult to improve operational efficiency and maximize user satisfaction.

[0357] 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.

[0358] In this invention, the server includes means for collecting industry-specific information, means for organizing the information and performing data cleanup, and means for training a learning algorithm using the organized information. This enables highly accurate business support that leverages industry-specific knowledge. Furthermore, flexible business responses based on the user's emotional state are realized, leading to improved business efficiency and increased user satisfaction.

[0359] "Industry-specific information" refers to data and knowledge specific to a particular industry or field, and includes specialized information necessary for business support.

[0360] "Data cleansing" is the process of preparing raw data, a procedure to remove inaccurate data and ensure consistency and accuracy.

[0361] A "learning algorithm" refers to a computational process that uses data to find patterns and rules, enabling problem-solving and prediction.

[0362] "User-specific customization" refers to the process of optimizing the system to meet the unique needs and requirements of each user, ensuring they achieve the best possible performance.

[0363] "Evaluation" refers to the feedback and opinions that users provide to the system, and includes information that helps improve the system.

[0364] "Emotional state" refers to the user's psychological and emotional state, and is a factor considered by the system to provide the user with the best possible support.

[0365] The following describes embodiments for carrying out the invention.

[0366] This system is implemented through collaboration between the server, terminals, and users. The server has a database for collecting and maintaining industry-specific information. The server receives information from partner specialized organizations and performs data cleansing to generate accurate and consistent data. Then, existing machine learning platforms and libraries (e.g., TensorFlow and PyTorch) are utilized to train learning algorithms using this refined data.

[0367] The device features an emotion engine that recognizes the user's emotional state in real time during work. This engine utilizes hardware sensors such as cameras and microphones to analyze the user's facial expressions and voice. This allows the system to understand in real time whether the user is stressed or satisfied. The user's emotions and work data interact to improve the quality of work support.

[0368] As a concrete example, in the manufacturing industry, the terminal can monitor efficiency and quality while equipment is running, and immediately suggest corrective actions if an anomaly is detected. Furthermore, by adjusting the interface according to the user's emotional state, it's possible to reduce stress. The terminal sends this information to a server, which then uses it to improve its algorithms.

[0369] Examples of specific prompt messages include the following:

[0370] "Monitor the efficiency of manufacturing equipment and propose corrective measures if any abnormalities occur."

[0371] "Analyze the user's stress level using an emotion engine and adjust the interface accordingly."

[0372] Based on these prompts, the generated AI model can provide users with personalized work support, thereby improving work efficiency and user satisfaction.

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

[0374] Step 1:

[0375] The server collects industry-specific information from partner specialized organizations. This information input consists of cases and data sets related to a specific industry. The server stores this in a database and makes the information available for use as needed.

[0376] Step 2:

[0377] The server cleans and preprocesses the collected industry-specific information. Inputs include raw and unorganized data, and the output generates consistent and accurate data. This process includes removing incorrect data, imputing missing values, and standardizing the format.

[0378] Step 3:

[0379] The server trains learning algorithms using pre-processed data. The input is cleaned data, and the output includes generative AI models based on pattern detection and prediction. This process involves using a machine learning platform to build an optimal model by adjusting the algorithm's parameters.

[0380] Step 4:

[0381] The server customizes the trained model according to the user's needs. The input is the generated AI model, and the output is the customized model that meets the user's business requirements. Specifically, it considers industry-specific use cases and fine-tunes the model and enhances the algorithms.

[0382] Step 5:

[0383] The server distributes customized models to the terminals. The input is the adjusted AI model, and the output is the terminal environment that received it. This enables business support functions on the terminals.

[0384] Step 6:

[0385] The terminal processes user work data sequentially and provides work support. Input data includes real-time collected work metrics and the user's emotional state. Output provides the user with improvement suggestions and feedback to improve work efficiency.

[0386] Step 7:

[0387] Users submit feedback based on the work results provided by the AI. This feedback is input to a server, which then prompts continuous improvement of the model and is used as retraining data. This feedback loop allows the AI ​​system to continuously evolve.

[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] Modern households require support to efficiently handle various tasks, but conventional technologies have struggled to provide dynamic support that takes user emotions into account. Furthermore, addressing individual household needs often requires massive data processing and model updates, making them impractical. To solve this problem, a system is needed that can grasp the user's emotional state in real time and provide task support accordingly.

[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 means for acquiring business information, means for preparing and purifying the information before processing, and means for training an automated learning model using the prepared information. This enables the analysis of the user's emotional state, business support based on that analysis, and further evolution of the entire system through continuous feedback.

[0393] "Means for acquiring business information" refers to methods and technologies for collecting business-related information, which effectively gather the data required by the system.

[0394] "Preprocessing" refers to the process of preparing acquired information before processing it, correcting inconsistencies to improve accuracy, and converting it to the required format.

[0395] "Purification" refers to the process of removing defects and unnecessary parts from data, and is a method for improving the transparency and accuracy of information.

[0396] "Methods for training automated learning models" refer to methods of using large amounts of data to train machine learning algorithms and build foundational computational models for making predictions and decisions.

[0397] "Means of providing to the device" refers to the process of delivering a model created or improved by the system to a specific device or terminal, making it directly available to the user.

[0398] "Means for processing business information and providing business support" refers to technologies or functions that analyze information according to the user's needs and perform various processes to assist in the optimal execution of business operations.

[0399] "Analyzing emotional state" refers to the process of monitoring a user's facial expressions, tone of voice, and behavioral patterns to evaluate their emotional state and psychological characteristics.

[0400] "Means of collecting feedback" refers to methods of systematically gathering opinions and usage-based responses from users, which are then used to improve the system.

[0401] This invention is a system that analyzes user emotions in real time and provides business support. The server acquires business information and performs preprocessing and purification. For example, it corrects inconsistencies in the information and converts it to the required format. This ensures that the automated learning model is accurately trained. The server also refines this trained model and distributes it to devices. In this process, it is possible to provide the model directly to specific devices or terminals.

[0402] The terminal uses software such as OpenCV and TensorFlow to run models within the device and analyze the user's emotional state. This allows for real-time capture of the user's facial expressions and tone of voice, and an assessment of their emotional state. Based on the evaluation results, the system can provide work support tailored to the user's needs, thereby improving work efficiency. Furthermore, the feedback is compiled and used to improve the system.

[0403] As a concrete example, considering a busy morning at home, the device can individually sense the tension in the user's mood and suggest things like playing music or assisting with breakfast preparation. To support such user interactions, a feedback function based on emotional data will drive the overall evolution of the system.

[0404] Example of a prompt:

[0405] "What kind of robot support would be ideal for the whole family getting ready to leave in the morning?"

[0406] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0407] Step 1:

[0408] The server retrieves business information. This information includes user activity logs and past feedback, providing data that offers hints for improving business efficiency. The server receives data uploaded from the user's device as input and organizes it. The organized data is then passed as output to the preprocessing step.

[0409] Step 2:

[0410] The server preprocesses and cleans the received data. This process uses normalization and filtering techniques to correct inconsistent data and remove noise. The input is the data sorted in step 1, and the output is the data converted into a format acceptable to the model.

[0411] Step 3:

[0412] The server trains an automated learning model using pre-processed data. By feeding the data into a specific learning algorithm and allowing it to learn patterns and trends, it generates a trained model as output. This improves the overall accuracy of the system.

[0413] Step 4:

[0414] The server provides the trained model to the terminal. This process transfers the trained model to the user's device, enabling real-time business support. The input is the trained model, and the output is the model in a format executable on the terminal.

[0415] Step 5:

[0416] The device uses a model to analyze emotional states. It captures the user's facial expressions and voice via the device's built-in camera and microphone, and analyzes them using the model. The input is real-time emotional data, and the output is an analysis result indicating the user's emotional state.

[0417] Step 6:

[0418] The terminal provides business support based on the analysis results. It offers appropriate suggestions and assistance according to the user's emotional state, streamlining the business process. For example, if the user is experiencing excessive stress, the system will suggest playing relaxing music.

[0419] Step 7:

[0420] Users provide feedback on the business support services offered, and the terminal collects this feedback. The input is user feedback, which is sent to the server and used for future model updates. The output is feedback data, which is used to better adjust the server's AI model.

[0421] 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.

[0422] 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.

[0423] 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.

[0424] [Third Embodiment]

[0425] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0426] 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.

[0427] 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).

[0428] 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.

[0429] 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.

[0430] 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).

[0431] 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.

[0432] 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.

[0433] 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.

[0434] 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.

[0435] 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.

[0436] 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".

[0437] This invention is an industry-specific AI dispatch system that leverages specialized industry knowledge to support the operational efficiency of companies. This system operates based on the cooperation of three parties: a server, terminals, and users.

[0438] First, the server receives industry-specific data from partner specialized organizations. This includes industry best practices and process management information, which are stored in a database. The server securely receives business data from users and integrates that data with the know-how.

[0439] The server preprocesses and cleanses the received data, removing noise and incomplete information to optimize the dataset for training machine learning models. Next, the server uses machine learning algorithms to create a trained AI model, which then possesses expertise in a specific industry.

[0440] Once the AI ​​model is trained, it is customized according to the user's specific needs. The server then distributes this customized model to the customer's terminal. On the terminal, the AI ​​agent runs, processing data related to the user's work in real time and supporting business improvement. As a concrete example, in manufacturing, the AI ​​agent can monitor the status of equipment and provide advance warnings of signs of failure.

[0441] Subsequently, the user provides feedback based on the AI ​​system's performance. This feedback is sent to the server and used to improve the AI ​​model. The server continuously optimizes the model and redistributes the new version to the terminal. As a result, the system continues to evolve according to the user's work environment, leading to continuously improved business results.

[0442] In this way, the system of the present invention achieves sustainable operational efficiency for companies through AI agents with specialized industry knowledge.

[0443] The following describes the processing flow.

[0444] Step 1:

[0445] The server receives industry-specific data from partner specialist organizations and stores it in a database. This includes industry best practices and relevant information.

[0446] Step 2:

[0447] Users upload company-specific business data to the server. This data is encrypted and transmitted via a secure protocol.

[0448] Step 3:

[0449] The server cleanses the received data, removing inaccurate data and noise. At this stage, the data format is also standardized, making it suitable for machine learning.

[0450] Step 4:

[0451] The server uses organized data to train a machine learning model. This model is designed to learn industry-specific knowledge and expertise.

[0452] Step 5:

[0453] The trained model is customized according to the user's business needs. The server then transfers this customized model to the terminal.

[0454] Step 6:

[0455] The AI ​​agent installed on the device processes business data in real time and provides users with insights for business improvement. For example, in a manufacturing plant, it monitors the status of equipment and detects anomalies.

[0456] Step 7:

[0457] Users provide feedback to the server regarding the AI ​​agent's behavior. This feedback is used to improve the model.

[0458] Step 8:

[0459] The server updates the AI ​​model based on user feedback and newly acquired data. This updated model is then distributed back to the terminals, ensuring continuous system optimization.

[0460] (Example 1)

[0461] 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."

[0462] In modern business environments, there is a growing demand to improve efficiency by leveraging specific expertise and know-how. However, existing systems have limited the effectiveness of productivity improvements and support due to insufficient detailed data processing and advanced business support tailored to specific tasks. Solving this problem is crucial.

[0463] 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.

[0464] In this invention, the server includes means for collecting business-domain specific information, means for preprocessing the information and performing data improvement, and means for training a generated AI model using the improved information. This enables accurate information provision and real-time business support using a business-specific AI model.

[0465] "Business-specific information" refers to data that includes specialized knowledge and know-how related to a particular business.

[0466] "Preprocessing" refers to the process of preparing raw data into a format suitable for analysis and model training.

[0467] "Data refinement" refers to the process of removing noise and incomplete information from a dataset to make it suitable for analysis.

[0468] A "generative AI model" refers to an artificial intelligence program designed to learn from data and perform predictions and classifications for specific tasks.

[0469] "Teaching" refers to the process by which a model learns specific patterns or rules using machine learning algorithms.

[0470] "Adjusting" refers to the process of changing the parameters and settings of a model to suit specific needs and requirements.

[0471] "Device" refers to equipment that includes hardware or software environments for running AI models and providing business support.

[0472] "Real-time" refers to data processing and analysis that provides results immediately, without any time delay.

[0473] "Opinions" refer to feedback and evaluations provided by users, and are information that can be used to improve the system or model.

[0474] "Insights" refer to new knowledge and understanding gained through data analysis and AI models, which support business decision-making.

[0475] This invention is an AI-powered dispatch system specialized for specific business areas, designed to streamline corporate operations by leveraging specialized knowledge. The system consists of a server, terminals, and users, and each component works in coordination with the others.

[0476] The server first collects business-specific information from partner specialized organizations and stores it in a database. This information includes industry best practices and process management information, and a dataset is formed based on this to analyze business operations. Next, the server receives business data from users and securely retrieves it through encrypted communication using the SSL / TLS protocol. The collected data is preprocessed and data improvement is performed. In this process, the dataset is cleaned up from noise and missing values ​​using libraries such as Pandas, and prepared in a format suitable for training machine learning models.

[0477] The server uses machine learning frameworks such as TensorFlow and PyTorch to train generative AI models. These models learn expertise in the business domain and are tailored to specific business needs. The tailored AI models are distributed to user terminals, where AI agents run. On the terminals, business data is processed in real time to support business improvement. For example, in manufacturing, a terminal processes sensor data from equipment and predicts signs of failure.

[0478] Users provide feedback based on the AI ​​system's performance. This feedback is sent to the server and used to improve the AI ​​model. The server optimizes the model based on this feedback and redistributes it to the terminal as a new version. This allows the system to continuously evolve and always provide support that is compatible with the latest business environment.

[0479] A concrete example of a prompt might be: "Create an AI model that proposes the optimal delivery routes to reduce fuel consumption for the logistics industry. Real-time route optimization considering traffic and weather data is required."

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

[0481] Step 1:

[0482] The server collects domain-specific information from partner specialized organizations. It receives industry data digitally via APIs and data feeds as input. This received data is stored in the server's database. The output is a dataset of organized and stored industry information.

[0483] Step 2:

[0484] The server receives business data from users. As input, it receives encrypted business-related data sent via a REST API. The server adds this data to a database, forming an integrated dataset as output.

[0485] Step 3:

[0486] The server performs preprocessing and data refinement. It receives an integrated dataset as input and uses the Pandas library to denoise and impute missing values. This improves data quality, resulting in clean data suitable for training machine learning models as output.

[0487] Step 4:

[0488] The server trains the generated AI model. It feeds a clean dataset as input to a machine learning algorithm (e.g., TensorFlow) to train the model. The output is a trained AI model with knowledge specific to a particular business domain.

[0489] Step 5:

[0490] The server adjusts the trained model and distributes it to the terminal. As input, it adjusts the model considering user requests and prompts to generate a customized model. The server then sends this customized model to the terminal. The output is a customized AI model that meets the user's specific needs.

[0491] Step 6:

[0492] The terminal processes business data in real time. It supplies various types of data generated from business activities (e.g., sensor data) to the model as input. The terminal uses an AI agent to process the data and provides the user with predictions and optimized suggestions as output.

[0493] Step 7:

[0494] Users provide feedback on the AI ​​system's results. As input, they send opinions and evaluations to the server that reflect the system's output and their experience. The server receives this feedback and, as output, obtains information necessary for improving the model. Based on this feedback, the model is then optimized.

[0495] (Application Example 1)

[0496] 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."

[0497] Detecting equipment malfunctions and providing real-time administrator notifications in factory and other workplace settings is inefficient with conventional technologies, making timely responses difficult. In particular, the decline in productivity caused by equipment failures and reduced operational efficiency is a major problem, and effective measures to prevent this are needed.

[0498] 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.

[0499] In this invention, the server includes means for acquiring industry-specific data, means for pre-processing and cleansing the data, and means for detecting equipment abnormalities and notifying the administrator. This makes it possible to improve work efficiency at the factory floor and prevent equipment failures.

[0500] "Industry-specific materials" are collections of data containing know-how and best practices specific to a particular industrial sector.

[0501] "Preprocessing" is the process of removing and organizing noise and missing information in order to improve the accuracy of the data.

[0502] "Data cleansing" is the process of correcting outliers and invalid data to ensure data quality.

[0503] A "machine learning model" is a mathematical model that uses algorithms to learn patterns and rules from data.

[0504] "Training" in machine learning is the process of optimizing a model using data.

[0505] "Customization" refers to the process of adjusting a product or service to meet specific needs or requirements.

[0506] An "information processing device" is an electronic device used for inputting, processing, and outputting data.

[0507] "Real-time" refers to information being processed and provided to the user immediately the moment it is generated.

[0508] "Work support" refers to activities that provide information and advice to improve the efficiency and accuracy of work.

[0509] "Feedback" refers to the backflow of opinions and information based on the output and usage of a system.

[0510] Anomaly detection is a technology that identifies malfunctions in equipment or systems that deviate from their normal state.

[0511] "Administrator notification" refers to the act of promptly informing the person in charge when important information arises.

[0512] In the system that implements this application, a server plays a central role. The server first retrieves industry-specific data from partner specialized organizations. This includes best practices and technical information that are updated in real time using an edge computing framework. The retrieved data is preprocessed and cleansed and organized into a high-quality dataset. This process removes noise and imputes missing values.

[0513] Next, the server trains a machine learning model using the pre-processed data. This primarily uses Python's Scikit-learn library to build models using algorithms such as random forests and neural networks. This trained model is then customized to meet the customer's specific needs.

[0514] Customized models are distributed to information processing devices, enabling terminals to provide real-time support for on-site work. The terminals use data acquired from equipment within the factory to detect anomalies and generate insights into the equipment. This information is notified to administrators in real time to support rapid response. Furthermore, feedback is sent to the server based on the information received by the terminals, allowing the system to continuously improve.

[0515] As a concrete example, on a manufacturing line, AI can identify the reason for a machine malfunction and prompt the manager with "Which part of the manufacturing line is currently malfunctioning?", allowing for immediate countermeasures to be suggested. At this time, the manager will be shown a prompt message such as "What equipment status should be monitored most closely on this manufacturing line right now?" This enables the AI ​​to quickly analyze the situation on site and propose the optimal solution.

[0516] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0517] Step 1:

[0518] The server retrieves industry-specific data from partner specialized organizations. As input, it receives data periodically downloaded from the specialized organizations' APIs and databases. As output, the collected data is stored in a local database. This operation uses HTTP requests to retrieve the latest information.

[0519] Step 2:

[0520] The server preprocesses and cleanses the acquired data. Raw data stored in a local database is used as input. Data processing uses the Python Pandas library to impute missing values ​​and remove noise. The output is a high-quality dataset. This process ensures that only valid data proceeds to the next step.

[0521] Step 3:

[0522] The server trains a machine learning model using pre-processed data. The input is a normalized dataset. The server uses Scikit-learn to build and train random forest or neural network models. The output is a trained model optimized for a specific industry. Through this process, the model learns patterns from the data and gains predictive power.

[0523] Step 4:

[0524] The server customizes the trained model to meet customer needs and distributes it to the information processing unit. It receives customer requirements and model parameters as input. Data processing is performed by tuning the model's hyperparameters. The customized model is installed on the information processing unit as output. This process makes the optimized model available for field use.

[0525] Step 5:

[0526] The terminal provides real-time work support on-site. Input consists of data from on-site equipment and sensors. The terminal uses a model to detect anomalies and performs analysis using a generated AI model. The output is the notification of necessary information to the administrator. This operation uses prompt messages to provide suggestions and warnings to the administrator.

[0527] Step 6:

[0528] The server collects user feedback and updates the training model. Inputs include terminal usage data and administrator evaluations. Data calculations retrain the model based on the new data. The output is an improved model. This process enhances the overall accuracy and efficiency of the system.

[0529] 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.

[0530] This invention aims to provide more effective business support by combining an industry-specific AI dispatch system with an emotion engine that recognizes user emotions. This system is based on servers, terminals, and users, and aims to improve operational efficiency through their coordination.

[0531] First, the server collects industry-specific data and know-how from partner specialized organizations and stores it in a database. Then, users upload company-specific business data to the server via a secure protocol. The server cleanses the received data, converts it to a unified format, and uses it to train machine learning models.

[0532] The emotion engine allows the device to analyze the user's emotional state in real time. This enables the system to collect feedback data based on the user's emotions. This data is used to adjust parameters to reduce the user's stress level, among other things.

[0533] The server creates a trained AI model and customizes it to meet the user's business needs. This customized model is then distributed to the terminal and provides business support to the user as an AI agent. As a specific example, in manufacturing, the AI ​​agent continuously monitors the efficiency and quality of equipment and suggests improvements when anomalies are detected. It also adjusts the interface to match the user's emotional state.

[0534] Users provide feedback based on the AI ​​system's performance and operational efficiency. Emotional data obtained through the emotion engine complements this feedback and helps in updating the AI ​​model on the server. This feedback allows the server to continuously improve and retrain the AI ​​model, redistributing the new model to terminals and evolving the entire system.

[0535] Throughout this entire system, the present invention, which incorporates emotion recognition, enables support that balances user job satisfaction and efficiency, thereby contributing to improved productivity for companies.

[0536] The following describes the processing flow.

[0537] Step 1:

[0538] The server receives industry-specific data and know-how from partner specialized organizations and stores it in a database. This information includes the latest industry trends and best practices.

[0539] Step 2:

[0540] Users collect company-specific business data and send it to the server via a secure protocol. This data includes production data, sales data, customer inquiry information, and more.

[0541] Step 3:

[0542] The server cleanses the received data, removing noise and inaccurate information to improve data quality. This process converts the data into a unified format.

[0543] Step 4:

[0544] The server uses the cleansed data to train a machine learning model. This model learns industry-specific expertise and builds a foundation for trend prediction and optimization.

[0545] Step 5:

[0546] By utilizing an emotion engine, the device analyzes the user's emotional state in real time. Based on this analysis, the user's stress level can be determined.

[0547] Step 6:

[0548] The trained AI models are customized based on the user's specific business needs and distributed from the server to the terminal. This allows the AI ​​agent to provide support tailored to the company's workflow.

[0549] Step 7:

[0550] The AI ​​agent on the terminal monitors business processes and provides insights for business improvement in a way that is sensitive to the user's emotions. For example, in a manufacturing environment, it provides real-time alerts regarding equipment inefficiency and quality issues.

[0551] Step 8:

[0552] Users send feedback to the server based on the AI ​​agent's performance and interactions. This feedback includes user sentiment data, which is a crucial element for improving the model.

[0553] Step 9:

[0554] The server updates the AI ​​model using feedback and new data. It then retrains the updated model and redistributes the optimized version to the terminals, supporting continuous improvement of operations.

[0555] (Example 2)

[0556] 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."

[0557] In today's business environment, there is a need for systems that support operations efficiently and flexibly based on industry-specific information. However, existing systems struggle to provide real-time support that takes into account the emotional state of users. This challenge makes it difficult to improve operational efficiency and maximize user satisfaction.

[0558] 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.

[0559] In this invention, the server includes means for collecting industry-specific information, means for organizing the information and performing data cleanup, and means for training a learning algorithm using the organized information. This enables highly accurate business support that leverages industry-specific knowledge. Furthermore, flexible business responses based on the user's emotional state are realized, leading to improved business efficiency and increased user satisfaction.

[0560] "Industry-specific information" refers to data and knowledge specific to a particular industry or field, and includes specialized information necessary for business support.

[0561] "Data cleansing" is the process of preparing raw data, a procedure to remove inaccurate data and ensure consistency and accuracy.

[0562] A "learning algorithm" refers to a computational process that uses data to find patterns and rules, enabling problem-solving and prediction.

[0563] "User-specific customization" refers to the process of optimizing the system to meet the unique needs and requirements of each user, ensuring they achieve the best possible performance.

[0564] "Evaluation" refers to the feedback and opinions that users provide to the system, and includes information that helps improve the system.

[0565] "Emotional state" refers to the user's psychological and emotional state, and is a factor considered by the system to provide the user with the best possible support.

[0566] The following describes embodiments for carrying out the invention.

[0567] This system is implemented through collaboration between the server, terminals, and users. The server has a database for collecting and maintaining industry-specific information. The server receives information from partner specialized organizations and performs data cleansing to generate accurate and consistent data. Then, existing machine learning platforms and libraries (e.g., TensorFlow and PyTorch) are utilized to train learning algorithms using this refined data.

[0568] The device features an emotion engine that recognizes the user's emotional state in real time during work. This engine utilizes hardware sensors such as cameras and microphones to analyze the user's facial expressions and voice. This allows the system to understand in real time whether the user is stressed or satisfied. The user's emotions and work data interact to improve the quality of work support.

[0569] As a concrete example, in the manufacturing industry, the terminal can monitor efficiency and quality while equipment is running, and immediately suggest corrective actions if an anomaly is detected. Furthermore, by adjusting the interface according to the user's emotional state, it's possible to reduce stress. The terminal sends this information to a server, which then uses it to improve its algorithms.

[0570] Examples of specific prompt messages include the following:

[0571] "Monitor the efficiency of manufacturing equipment and propose corrective measures if any abnormalities occur."

[0572] "Analyze the user's stress level using an emotion engine and adjust the interface accordingly."

[0573] Based on these prompts, the generated AI model can provide users with personalized work support, thereby improving work efficiency and user satisfaction.

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

[0575] Step 1:

[0576] The server collects industry-specific information from partner specialized organizations. This information input consists of cases and data sets related to a specific industry. The server stores this in a database and makes the information available for use as needed.

[0577] Step 2:

[0578] The server cleans and preprocesses the collected industry-specific information. Inputs include raw and unorganized data, and the output generates consistent and accurate data. This process includes removing incorrect data, imputing missing values, and standardizing the format.

[0579] Step 3:

[0580] The server trains learning algorithms using pre-processed data. The input is cleaned data, and the output includes generative AI models based on pattern detection and prediction. This process involves using a machine learning platform to build an optimal model by adjusting the algorithm's parameters.

[0581] Step 4:

[0582] The server customizes the trained model according to the user's needs. The input is the generated AI model, and the output is the customized model that meets the user's business requirements. Specifically, it considers industry-specific use cases and fine-tunes the model and enhances the algorithms.

[0583] Step 5:

[0584] The server distributes customized models to the terminals. The input is the adjusted AI model, and the output is the terminal environment that received it. This enables business support functions on the terminals.

[0585] Step 6:

[0586] The terminal processes user work data sequentially and provides work support. Input data includes real-time collected work metrics and the user's emotional state. Output provides the user with improvement suggestions and feedback to improve work efficiency.

[0587] Step 7:

[0588] Users submit feedback based on the work results provided by the AI. This feedback is input to a server, which then prompts continuous improvement of the model and is used as retraining data. This feedback loop allows the AI ​​system to continuously evolve.

[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] Modern households require support to efficiently handle various tasks, but conventional technologies have struggled to provide dynamic support that takes user emotions into account. Furthermore, addressing individual household needs often requires massive data processing and model updates, making them impractical. To solve this problem, a system is needed that can grasp the user's emotional state in real time and provide task support accordingly.

[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 means for acquiring business information, means for preparing and purifying the information before processing, and means for training an automated learning model using the prepared information. This enables the analysis of the user's emotional state, business support based on that analysis, and further evolution of the entire system through continuous feedback.

[0594] "Means for acquiring business information" refers to methods and technologies for collecting business-related information, which effectively gather the data required by the system.

[0595] "Preprocessing" refers to the process of preparing acquired information before processing it, correcting inconsistencies to improve accuracy, and converting it to the required format.

[0596] "Purification" refers to the process of removing defects and unnecessary parts from data, and is a method for improving the transparency and accuracy of information.

[0597] "Methods for training automated learning models" refer to methods of using large amounts of data to train machine learning algorithms and build foundational computational models for making predictions and decisions.

[0598] "Means of providing to the device" refers to the process of delivering a model created or improved by the system to a specific device or terminal, making it directly available to the user.

[0599] "Means for processing business information and providing business support" refers to technologies or functions that analyze information according to the user's needs and perform various processes to assist in the optimal execution of business operations.

[0600] "Analyzing emotional state" refers to the process of monitoring a user's facial expressions, tone of voice, and behavioral patterns to evaluate their emotional state and psychological characteristics.

[0601] "Means of collecting feedback" refers to methods of systematically gathering opinions and usage-based responses from users, which are then used to improve the system.

[0602] This invention is a system that analyzes user emotions in real time and provides business support. The server acquires business information and performs preprocessing and purification. For example, it corrects inconsistencies in the information and converts it to the required format. This ensures that the automated learning model is accurately trained. The server also refines this trained model and distributes it to devices. In this process, it is possible to provide the model directly to specific devices or terminals.

[0603] The terminal uses software such as OpenCV and TensorFlow to run models within the device and analyze the user's emotional state. This allows for real-time capture of the user's facial expressions and tone of voice, and an assessment of their emotional state. Based on the evaluation results, the system can provide work support tailored to the user's needs, thereby improving work efficiency. Furthermore, the feedback is compiled and used to improve the system.

[0604] As a concrete example, considering a busy morning at home, the device can individually sense the tension in the user's mood and suggest things like playing music or assisting with breakfast preparation. To support such user interactions, a feedback function based on emotional data will drive the overall evolution of the system.

[0605] Example of a prompt:

[0606] "What kind of robot support would be ideal for the whole family getting ready to leave in the morning?"

[0607] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0608] Step 1:

[0609] The server retrieves business information. This information includes user activity logs and past feedback, providing data that offers hints for improving business efficiency. The server receives data uploaded from the user's device as input and organizes it. The organized data is then passed as output to the preprocessing step.

[0610] Step 2:

[0611] The server preprocesses and cleans the received data. This process uses normalization and filtering techniques to correct inconsistent data and remove noise. The input is the data sorted in step 1, and the output is the data converted into a format acceptable to the model.

[0612] Step 3:

[0613] The server trains an automated learning model using pre-processed data. By feeding the data into a specific learning algorithm and allowing it to learn patterns and trends, it generates a trained model as output. This improves the overall accuracy of the system.

[0614] Step 4:

[0615] The server provides the trained model to the terminal. This process transfers the trained model to the user's device, enabling real-time business support. The input is the trained model, and the output is the model in a format executable on the terminal.

[0616] Step 5:

[0617] The device uses a model to analyze emotional states. It captures the user's facial expressions and voice via the device's built-in camera and microphone, and analyzes them using the model. The input is real-time emotional data, and the output is an analysis result indicating the user's emotional state.

[0618] Step 6:

[0619] The terminal provides business support based on the analysis results. It offers appropriate suggestions and assistance according to the user's emotional state, streamlining the business process. For example, if the user is experiencing excessive stress, the system will suggest playing relaxing music.

[0620] Step 7:

[0621] Users provide feedback on the business support services offered, and the terminal collects this feedback. The input is user feedback, which is sent to the server and used for future model updates. The output is feedback data, which is used to better adjust the server's AI model.

[0622] 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.

[0623] 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.

[0624] 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.

[0625] [Fourth Embodiment]

[0626] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0627] 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.

[0628] 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).

[0629] 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.

[0630] 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.

[0631] 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).

[0632] 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.

[0633] 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.

[0634] 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.

[0635] 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.

[0636] 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.

[0637] 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.

[0638] 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".

[0639] This invention is an industry-specific AI dispatch system that leverages specialized industry knowledge to support the operational efficiency of companies. This system operates based on the cooperation of three parties: a server, terminals, and users.

[0640] First, the server receives industry-specific data from partner specialized organizations. This includes industry best practices and process management information, which are stored in a database. The server securely receives business data from users and integrates that data with the know-how.

[0641] The server preprocesses and cleanses the received data, removing noise and incomplete information to optimize the dataset for training machine learning models. Next, the server uses machine learning algorithms to create a trained AI model, which then possesses expertise in a specific industry.

[0642] Once the AI ​​model is trained, it is customized according to the user's specific needs. The server then distributes this customized model to the customer's terminal. On the terminal, the AI ​​agent runs, processing data related to the user's work in real time and supporting business improvement. As a concrete example, in manufacturing, the AI ​​agent can monitor the status of equipment and provide advance warnings of signs of failure.

[0643] Subsequently, the user provides feedback based on the AI ​​system's performance. This feedback is sent to the server and used to improve the AI ​​model. The server continuously optimizes the model and redistributes the new version to the terminal. As a result, the system continues to evolve according to the user's work environment, leading to continuously improved business results.

[0644] In this way, the system of the present invention achieves sustainable operational efficiency for companies through AI agents with specialized industry knowledge.

[0645] The following describes the processing flow.

[0646] Step 1:

[0647] The server receives industry-specific data from partner specialist organizations and stores it in a database. This includes industry best practices and relevant information.

[0648] Step 2:

[0649] Users upload company-specific business data to the server. This data is encrypted and transmitted via a secure protocol.

[0650] Step 3:

[0651] The server cleanses the received data, removing inaccurate data and noise. At this stage, the data format is also standardized, making it suitable for machine learning.

[0652] Step 4:

[0653] The server uses organized data to train a machine learning model. This model is designed to learn industry-specific knowledge and expertise.

[0654] Step 5:

[0655] The trained model is customized according to the user's business needs. The server then transfers this customized model to the terminal.

[0656] Step 6:

[0657] The AI ​​agent installed on the device processes business data in real time and provides users with insights for business improvement. For example, in a manufacturing plant, it monitors the status of equipment and detects anomalies.

[0658] Step 7:

[0659] Users provide feedback to the server regarding the AI ​​agent's behavior. This feedback is used to improve the model.

[0660] Step 8:

[0661] The server updates the AI ​​model based on user feedback and newly acquired data. This updated model is then distributed back to the terminals, ensuring continuous system optimization.

[0662] (Example 1)

[0663] 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".

[0664] In modern business environments, there is a growing demand to improve efficiency by leveraging specific expertise and know-how. However, existing systems have limited the effectiveness of productivity improvements and support due to insufficient detailed data processing and advanced business support tailored to specific tasks. Solving this problem is crucial.

[0665] 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.

[0666] In this invention, the server includes means for collecting business-domain specific information, means for preprocessing the information and performing data improvement, and means for training a generated AI model using the improved information. This enables accurate information provision and real-time business support using a business-specific AI model.

[0667] "Business-specific information" refers to data that includes specialized knowledge and know-how related to a particular business.

[0668] "Preprocessing" refers to the process of preparing raw data into a format suitable for analysis and model training.

[0669] "Data refinement" refers to the process of removing noise and incomplete information from a dataset to make it suitable for analysis.

[0670] A "generative AI model" refers to an artificial intelligence program designed to learn from data and perform predictions and classifications for specific tasks.

[0671] "Teaching" refers to the process by which a model learns specific patterns or rules using machine learning algorithms.

[0672] "Adjusting" refers to the process of changing the parameters and settings of a model to suit specific needs and requirements.

[0673] "Device" refers to equipment that includes hardware or software environments for running AI models and providing business support.

[0674] "Real-time" refers to data processing and analysis that provides results immediately, without any time delay.

[0675] "Opinions" refer to feedback and evaluations provided by users, and are information that can be used to improve the system or model.

[0676] "Insights" refer to new knowledge and understanding gained through data analysis and AI models, which support business decision-making.

[0677] This invention is an AI-powered dispatch system specialized for specific business areas, designed to streamline corporate operations by leveraging specialized knowledge. The system consists of a server, terminals, and users, and each component works in coordination with the others.

[0678] The server first collects business-specific information from partner specialized organizations and stores it in a database. This information includes industry best practices and process management information, and a dataset is formed based on this to analyze business operations. Next, the server receives business data from users and securely retrieves it through encrypted communication using the SSL / TLS protocol. The collected data is preprocessed and data improvement is performed. In this process, the dataset is cleaned up from noise and missing values ​​using libraries such as Pandas, and prepared in a format suitable for training machine learning models.

[0679] The server uses machine learning frameworks such as TensorFlow and PyTorch to train generative AI models. These models learn expertise in the business domain and are tailored to specific business needs. The tailored AI models are distributed to user terminals, where AI agents run. On the terminals, business data is processed in real time to support business improvement. For example, in manufacturing, a terminal processes sensor data from equipment and predicts signs of failure.

[0680] Users provide feedback based on the AI ​​system's performance. This feedback is sent to the server and used to improve the AI ​​model. The server optimizes the model based on this feedback and redistributes it to the terminal as a new version. This allows the system to continuously evolve and always provide support that is compatible with the latest business environment.

[0681] A concrete example of a prompt might be: "Create an AI model that proposes the optimal delivery routes to reduce fuel consumption for the logistics industry. Real-time route optimization considering traffic and weather data is required."

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

[0683] Step 1:

[0684] The server collects domain-specific information from partner specialized organizations. It receives industry data digitally via APIs and data feeds as input. This received data is stored in the server's database. The output is a dataset of organized and stored industry information.

[0685] Step 2:

[0686] The server receives business data from users. As input, it receives encrypted business-related data sent via a REST API. The server adds this data to a database, forming an integrated dataset as output.

[0687] Step 3:

[0688] The server performs preprocessing and data refinement. It receives an integrated dataset as input and uses the Pandas library to denoise and impute missing values. This improves data quality, resulting in clean data suitable for training machine learning models as output.

[0689] Step 4:

[0690] The server trains the generated AI model. It feeds a clean dataset as input to a machine learning algorithm (e.g., TensorFlow) to train the model. The output is a trained AI model with knowledge specific to a particular business domain.

[0691] Step 5:

[0692] The server adjusts the trained model and distributes it to the terminal. As input, it adjusts the model considering user requests and prompts to generate a customized model. The server then sends this customized model to the terminal. The output is a customized AI model that meets the user's specific needs.

[0693] Step 6:

[0694] The terminal processes business data in real time. It supplies various types of data generated from business activities (e.g., sensor data) to the model as input. The terminal uses an AI agent to process the data and provides the user with predictions and optimized suggestions as output.

[0695] Step 7:

[0696] Users provide feedback on the AI ​​system's results. As input, they send opinions and evaluations to the server that reflect the system's output and their experience. The server receives this feedback and, as output, obtains information necessary for improving the model. Based on this feedback, the model is then optimized.

[0697] (Application Example 1)

[0698] 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".

[0699] Detecting equipment malfunctions and providing real-time administrator notifications in factory and other workplace settings is inefficient with conventional technologies, making timely responses difficult. In particular, the decline in productivity caused by equipment failures and reduced operational efficiency is a major problem, and effective measures to prevent this are needed.

[0700] 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.

[0701] In this invention, the server includes means for acquiring industry-specific data, means for pre-processing and cleansing the data, and means for detecting equipment abnormalities and notifying the administrator. This makes it possible to improve work efficiency at the factory floor and prevent equipment failures.

[0702] "Industry-specific materials" are collections of data containing know-how and best practices specific to a particular industrial sector.

[0703] "Preprocessing" is the process of removing and organizing noise and missing information in order to improve the accuracy of the data.

[0704] "Data cleansing" is the process of correcting outliers and invalid data to ensure data quality.

[0705] A "machine learning model" is a mathematical model that uses algorithms to learn patterns and rules from data.

[0706] "Training" in machine learning is the process of optimizing a model using data.

[0707] "Customization" refers to the process of adjusting a product or service to meet specific needs or requirements.

[0708] An "information processing device" is an electronic device used for inputting, processing, and outputting data.

[0709] "Real-time" refers to information being processed and provided to the user immediately the moment it is generated.

[0710] "Work support" refers to activities that provide information and advice to improve the efficiency and accuracy of work.

[0711] "Feedback" refers to the backflow of opinions and information based on the output and usage of a system.

[0712] Anomaly detection is a technology that identifies malfunctions in equipment or systems that deviate from their normal state.

[0713] "Administrator notification" refers to the act of promptly informing the person in charge when important information arises.

[0714] In the system that implements this application, a server plays a central role. The server first retrieves industry-specific data from partner specialized organizations. This includes best practices and technical information that are updated in real time using an edge computing framework. The retrieved data is preprocessed and cleansed and organized into a high-quality dataset. This process removes noise and imputes missing values.

[0715] Next, the server trains a machine learning model using the pre-processed data. This primarily uses Python's Scikit-learn library to build models using algorithms such as random forests and neural networks. This trained model is then customized to meet the customer's specific needs.

[0716] Customized models are distributed to information processing devices, enabling terminals to provide real-time support for on-site work. The terminals use data acquired from equipment within the factory to detect anomalies and generate insights into the equipment. This information is notified to administrators in real time to support rapid response. Furthermore, feedback is sent to the server based on the information received by the terminals, allowing the system to continuously improve.

[0717] As a concrete example, on a manufacturing line, AI can identify the reason for a machine malfunction and prompt the manager with "Which part of the manufacturing line is currently malfunctioning?", allowing for immediate countermeasures to be suggested. At this time, the manager will be shown a prompt message such as "What equipment status should be monitored most closely on this manufacturing line right now?" This enables the AI ​​to quickly analyze the situation on site and propose the optimal solution.

[0718] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0719] Step 1:

[0720] The server retrieves industry-specific data from partner specialized organizations. As input, it receives data periodically downloaded from the specialized organizations' APIs and databases. As output, the collected data is stored in a local database. This operation uses HTTP requests to retrieve the latest information.

[0721] Step 2:

[0722] The server preprocesses and cleanses the acquired data. Raw data stored in a local database is used as input. Data processing uses the Python Pandas library to impute missing values ​​and remove noise. The output is a high-quality dataset. This process ensures that only valid data proceeds to the next step.

[0723] Step 3:

[0724] The server trains a machine learning model using pre-processed data. The input is a normalized dataset. The server uses Scikit-learn to build and train random forest or neural network models. The output is a trained model optimized for a specific industry. Through this process, the model learns patterns from the data and gains predictive power.

[0725] Step 4:

[0726] The server customizes the trained model to meet customer needs and distributes it to the information processing unit. It receives customer requirements and model parameters as input. Data processing is performed by tuning the model's hyperparameters. The customized model is installed on the information processing unit as output. This process makes the optimized model available for field use.

[0727] Step 5:

[0728] The terminal provides real-time work support on-site. Input consists of data from on-site equipment and sensors. The terminal uses a model to detect anomalies and performs analysis using a generated AI model. The output is the notification of necessary information to the administrator. This operation uses prompt messages to provide suggestions and warnings to the administrator.

[0729] Step 6:

[0730] The server collects user feedback and updates the training model. Inputs include terminal usage data and administrator evaluations. Data calculations retrain the model based on the new data. The output is an improved model. This process enhances the overall accuracy and efficiency of the system.

[0731] 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.

[0732] This invention aims to provide more effective business support by combining an industry-specific AI dispatch system with an emotion engine that recognizes user emotions. This system is based on servers, terminals, and users, and aims to improve operational efficiency through their coordination.

[0733] First, the server collects industry-specific data and know-how from partner specialized organizations and stores it in a database. Then, users upload company-specific business data to the server via a secure protocol. The server cleanses the received data, converts it to a unified format, and uses it to train machine learning models.

[0734] The emotion engine allows the device to analyze the user's emotional state in real time. This enables the system to collect feedback data based on the user's emotions. This data is used to adjust parameters to reduce the user's stress level, among other things.

[0735] The server creates a trained AI model and customizes it to meet the user's business needs. This customized model is then distributed to the terminal and provides business support to the user as an AI agent. As a specific example, in manufacturing, the AI ​​agent continuously monitors the efficiency and quality of equipment and suggests improvements when anomalies are detected. It also adjusts the interface to match the user's emotional state.

[0736] Users provide feedback based on the AI ​​system's performance and operational efficiency. Emotional data obtained through the emotion engine complements this feedback and helps in updating the AI ​​model on the server. This feedback allows the server to continuously improve and retrain the AI ​​model, redistributing the new model to terminals and evolving the entire system.

[0737] Throughout this entire system, the present invention, which incorporates emotion recognition, enables support that balances user job satisfaction and efficiency, thereby contributing to improved productivity for companies.

[0738] The following describes the processing flow.

[0739] Step 1:

[0740] The server receives industry-specific data and know-how from partner specialized organizations and stores it in a database. This information includes the latest industry trends and best practices.

[0741] Step 2:

[0742] Users collect company-specific business data and send it to the server via a secure protocol. This data includes production data, sales data, customer inquiry information, and more.

[0743] Step 3:

[0744] The server cleanses the received data, removing noise and inaccurate information to improve data quality. This process converts the data into a unified format.

[0745] Step 4:

[0746] The server uses the cleansed data to train a machine learning model. This model learns industry-specific expertise and builds a foundation for trend prediction and optimization.

[0747] Step 5:

[0748] By utilizing an emotion engine, the device analyzes the user's emotional state in real time. Based on this analysis, the user's stress level can be determined.

[0749] Step 6:

[0750] The trained AI models are customized based on the user's specific business needs and distributed from the server to the terminal. This allows the AI ​​agent to provide support tailored to the company's workflow.

[0751] Step 7:

[0752] The AI ​​agent on the terminal monitors business processes and provides insights for business improvement in a way that is sensitive to the user's emotions. For example, in a manufacturing environment, it provides real-time alerts regarding equipment inefficiency and quality issues.

[0753] Step 8:

[0754] Users send feedback to the server based on the AI ​​agent's performance and interactions. This feedback includes user sentiment data, which is a crucial element for improving the model.

[0755] Step 9:

[0756] The server updates the AI ​​model using feedback and new data. It then retrains the updated model and redistributes the optimized version to the terminals, supporting continuous improvement of operations.

[0757] (Example 2)

[0758] 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".

[0759] In today's business environment, there is a need for systems that support operations efficiently and flexibly based on industry-specific information. However, existing systems struggle to provide real-time support that takes into account the emotional state of users. This challenge makes it difficult to improve operational efficiency and maximize user satisfaction.

[0760] 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.

[0761] In this invention, the server includes means for collecting industry-specific information, means for organizing the information and performing data cleanup, and means for training a learning algorithm using the organized information. This enables highly accurate business support that leverages industry-specific knowledge. Furthermore, flexible business responses based on the user's emotional state are realized, leading to improved business efficiency and increased user satisfaction.

[0762] "Industry-specific information" refers to data and knowledge specific to a particular industry or field, and includes specialized information necessary for business support.

[0763] "Data cleansing" is the process of preparing raw data, a procedure to remove inaccurate data and ensure consistency and accuracy.

[0764] A "learning algorithm" refers to a computational process that uses data to find patterns and rules, enabling problem-solving and prediction.

[0765] "User-specific customization" refers to the process of optimizing the system to meet the unique needs and requirements of each user, ensuring they achieve the best possible performance.

[0766] "Evaluation" refers to the feedback and opinions that users provide to the system, and includes information that helps improve the system.

[0767] "Emotional state" refers to the user's psychological and emotional state, and is a factor considered by the system to provide the user with the best possible support.

[0768] The following describes embodiments for carrying out the invention.

[0769] This system is implemented through collaboration between the server, terminals, and users. The server has a database for collecting and maintaining industry-specific information. The server receives information from partner specialized organizations and performs data cleansing to generate accurate and consistent data. Then, existing machine learning platforms and libraries (e.g., TensorFlow and PyTorch) are utilized to train learning algorithms using this refined data.

[0770] The device features an emotion engine that recognizes the user's emotional state in real time during work. This engine utilizes hardware sensors such as cameras and microphones to analyze the user's facial expressions and voice. This allows the system to understand in real time whether the user is stressed or satisfied. The user's emotions and work data interact to improve the quality of work support.

[0771] As a concrete example, in the manufacturing industry, the terminal can monitor efficiency and quality while equipment is running, and immediately suggest corrective actions if an anomaly is detected. Furthermore, by adjusting the interface according to the user's emotional state, it's possible to reduce stress. The terminal sends this information to a server, which then uses it to improve its algorithms.

[0772] Examples of specific prompt messages include the following:

[0773] "Monitor the efficiency of manufacturing equipment and propose corrective measures if any abnormalities occur."

[0774] "Analyze the user's stress level using an emotion engine and adjust the interface accordingly."

[0775] Based on these prompts, the generated AI model can provide users with personalized work support, thereby improving work efficiency and user satisfaction.

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

[0777] Step 1:

[0778] The server collects industry-specific information from partner specialized organizations. This information input consists of cases and data sets related to a specific industry. The server stores this in a database and makes the information available for use as needed.

[0779] Step 2:

[0780] The server cleans and preprocesses the collected industry-specific information. Inputs include raw and unorganized data, and the output generates consistent and accurate data. This process includes removing incorrect data, imputing missing values, and standardizing the format.

[0781] Step 3:

[0782] The server trains learning algorithms using pre-processed data. The input is cleaned data, and the output includes generative AI models based on pattern detection and prediction. This process involves using a machine learning platform to build an optimal model by adjusting the algorithm's parameters.

[0783] Step 4:

[0784] The server customizes the trained model according to the user's needs. The input is the generated AI model, and the output is the customized model that meets the user's business requirements. Specifically, it considers industry-specific use cases and fine-tunes the model and enhances the algorithms.

[0785] Step 5:

[0786] The server distributes customized models to the terminals. The input is the adjusted AI model, and the output is the terminal environment that received it. This enables business support functions on the terminals.

[0787] Step 6:

[0788] The terminal processes user work data sequentially and provides work support. Input data includes real-time collected work metrics and the user's emotional state. Output provides the user with improvement suggestions and feedback to improve work efficiency.

[0789] Step 7:

[0790] Users submit feedback based on the work results provided by the AI. This feedback is input to a server, which then prompts continuous improvement of the model and is used as retraining data. This feedback loop allows the AI ​​system to continuously evolve.

[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] Modern households require support to efficiently handle various tasks, but conventional technologies have struggled to provide dynamic support that takes user emotions into account. Furthermore, addressing individual household needs often requires massive data processing and model updates, making them impractical. To solve this problem, a system is needed that can grasp the user's emotional state in real time and provide task support accordingly.

[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 means for acquiring business information, means for preparing and purifying the information before processing, and means for training an automated learning model using the prepared information. This enables the analysis of the user's emotional state, business support based on that analysis, and further evolution of the entire system through continuous feedback.

[0796] "Means for acquiring business information" refers to methods and technologies for collecting business-related information, which effectively gather the data required by the system.

[0797] "Preprocessing" refers to the process of preparing acquired information before processing it, correcting inconsistencies to improve accuracy, and converting it to the required format.

[0798] "Purification" refers to the process of removing defects and unnecessary parts from data, and is a method for improving the transparency and accuracy of information.

[0799] "Methods for training automated learning models" refer to methods of using large amounts of data to train machine learning algorithms and build foundational computational models for making predictions and decisions.

[0800] "Means of providing to the device" refers to the process of delivering a model created or improved by the system to a specific device or terminal, making it directly available to the user.

[0801] "Means for processing business information and providing business support" refers to technologies or functions that analyze information according to the user's needs and perform various processes to assist in the optimal execution of business operations.

[0802] "Analyzing emotional state" refers to the process of monitoring a user's facial expressions, tone of voice, and behavioral patterns to evaluate their emotional state and psychological characteristics.

[0803] "Means of collecting feedback" refers to methods of systematically gathering opinions and usage-based responses from users, which are then used to improve the system.

[0804] This invention is a system that analyzes user emotions in real time and provides business support. The server acquires business information and performs preprocessing and purification. For example, it corrects inconsistencies in the information and converts it to the required format. This ensures that the automated learning model is accurately trained. The server also refines this trained model and distributes it to devices. In this process, it is possible to provide the model directly to specific devices or terminals.

[0805] The terminal uses software such as OpenCV and TensorFlow to run models within the device and analyze the user's emotional state. This allows for real-time capture of the user's facial expressions and tone of voice, and an assessment of their emotional state. Based on the evaluation results, the system can provide work support tailored to the user's needs, thereby improving work efficiency. Furthermore, the feedback is compiled and used to improve the system.

[0806] As a concrete example, considering a busy morning at home, the device can individually sense the tension in the user's mood and suggest things like playing music or assisting with breakfast preparation. To support such user interactions, a feedback function based on emotional data will drive the overall evolution of the system.

[0807] Example of a prompt:

[0808] "What kind of robot support would be ideal for the whole family getting ready to leave in the morning?"

[0809] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0810] Step 1:

[0811] The server retrieves business information. This information includes user activity logs and past feedback, providing data that offers hints for improving business efficiency. The server receives data uploaded from the user's device as input and organizes it. The organized data is then passed as output to the preprocessing step.

[0812] Step 2:

[0813] The server preprocesses and cleans the received data. This process uses normalization and filtering techniques to correct inconsistent data and remove noise. The input is the data sorted in step 1, and the output is the data converted into a format acceptable to the model.

[0814] Step 3:

[0815] The server trains an automated learning model using pre-processed data. By feeding the data into a specific learning algorithm and allowing it to learn patterns and trends, it generates a trained model as output. This improves the overall accuracy of the system.

[0816] Step 4:

[0817] The server provides the trained model to the terminal. This process transfers the trained model to the user's device, enabling real-time business support. The input is the trained model, and the output is the model in a format executable on the terminal.

[0818] Step 5:

[0819] The device uses a model to analyze emotional states. It captures the user's facial expressions and voice via the device's built-in camera and microphone, and analyzes them using the model. The input is real-time emotional data, and the output is an analysis result indicating the user's emotional state.

[0820] Step 6:

[0821] The terminal provides business support based on the analysis results. It offers appropriate suggestions and assistance according to the user's emotional state, streamlining the business process. For example, if the user is experiencing excessive stress, the system will suggest playing relaxing music.

[0822] Step 7:

[0823] Users provide feedback on the business support services offered, and the terminal collects this feedback. The input is user feedback, which is sent to the server and used for future model updates. The output is feedback data, which is used to better adjust the server's AI model.

[0824] 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.

[0825] 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.

[0826] 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.

[0827] 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.

[0828] 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.

[0829] 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.

[0830] 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.

[0831] 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.

[0832] 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."

[0833] 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.

[0834] 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.

[0835] 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.

[0836] 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.

[0837] 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.

[0838] 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.

[0839] 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.

[0840] 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.

[0841] 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.

[0842] 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.

[0843] 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.

[0844] 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.

[0845] The following is further disclosed regarding the embodiments described above.

[0846] (Claim 1)

[0847] Methods for collecting industry-specific data,

[0848] A means for preprocessing and cleansing the aforementioned data,

[0849] A means for training a machine learning model using the aforementioned preprocessed data,

[0850] Means for customizing the aforementioned trained model for the customer,

[0851] A means for distributing the customized model to the terminal,

[0852] A means of processing business data in real time on a terminal and providing business support,

[0853] A means of collecting user feedback and updating the training model,

[0854] A system that includes this.

[0855] (Claim 2)

[0856] The system described in claim 1, which receives industry-specific data and know-how from partner specialized organizations.

[0857] (Claim 3)

[0858] The system according to claim 1, which provides users with insights for business improvement through a model installed on a terminal.

[0859] "Example 1"

[0860] (Claim 1)

[0861] Means of collecting information specific to a particular business area,

[0862] A means for preprocessing the aforementioned information and performing data improvement,

[0863] A means for training a generative AI model using the improved information,

[0864] Means for adjusting the aforementioned pre-trained model for use by the user,

[0865] Means for distributing the adjusted model to the device,

[0866] A means of processing business information immediately using a device and providing business support,

[0867] A means of collecting feedback from users and updating the educational model,

[0868] A system that includes this.

[0869] (Claim 2)

[0870] The system according to claim 1, which receives business-area-specific information and technical knowledge from affiliated specialized organizations.

[0871] (Claim 3)

[0872] The system according to claim 1, which provides users with insights for business improvement through a model installed on the device.

[0873] "Application Example 1"

[0874] (Claim 1)

[0875] Methods for obtaining industry-specific materials,

[0876] A means for preprocessing and cleansing the aforementioned materials,

[0877] A means for training a machine learning model using the aforementioned preprocessed data,

[0878] Means for customizing the aforementioned trained model for the customer,

[0879] Means for distributing the customized model to an information processing device,

[0880] A means of processing work data in real time using an information processing device and providing work support,

[0881] A means of collecting feedback from the device and updating the training model,

[0882] A means of detecting equipment abnormalities and notifying the administrator,

[0883] A system that includes this.

[0884] (Claim 2)

[0885] The system described in claim 1, which receives industry-specific materials and know-how from affiliated specialized organizations.

[0886] (Claim 3)

[0887] The system according to claim 1, which provides insights for work improvement through a model installed on the device.

[0888] "Example 2 of combining an emotion engine"

[0889] (Claim 1)

[0890] Means of collecting industry-specific information,

[0891] A means for organizing the aforementioned information and performing data cleaning,

[0892] A means for training a learning algorithm using the prepared information,

[0893] A means for adjusting the aforementioned trained algorithm for the user,

[0894] Means for transmitting the adjusted algorithm to a terminal,

[0895] A means of processing business information sequentially on a terminal and providing business support,

[0896] A means of collecting user feedback and improving the learning algorithm,

[0897] A means of recognizing the emotional state of users in real time and adapting business support based on that information,

[0898] A system that includes this.

[0899] (Claim 2)

[0900] The system according to claim 1, which receives industry-specific information and knowledge from collaborating specialized organizations.

[0901] (Claim 3)

[0902] The system according to claim 1, which provides users with insights for business improvement through an algorithm installed on a terminal.

[0903] "Application example 2 when combining with an emotional engine"

[0904] (Claim 1)

[0905] Means of obtaining business information,

[0906] The means of preparing the aforementioned information before processing and carrying out purification,

[0907] A means for training an automated learning model using the prepared information,

[0908] Means for improving the aforementioned trained model for use by users,

[0909] Means for providing the improved model to the apparatus,

[0910] A means of processing business information in real time within the device and providing business support,

[0911] A means of analyzing the emotional state of users and collecting emotion-based feedback,

[0912] A means of updating the model based on the aforementioned feedback and evolving the entire system,

[0913] A system that includes this.

[0914] (Claim 2)

[0915] The system according to claim 1, which receives industry-specific information and technical expertise from specialized institutions.

[0916] (Claim 3)

[0917] The system according to claim 1, which provides users with insights for business improvement through a model implemented in the device. [Explanation of symbols]

[0918] 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. Methods for collecting industry-specific data, A means for preprocessing and cleansing the aforementioned data, A means for training a machine learning model using the aforementioned preprocessed data, Means for customizing the aforementioned trained model for the customer, A means for distributing the customized model to the terminal, A means of processing business data in real time on a terminal and providing business support, A means of collecting user feedback and updating the training model, A system that includes this.

2. The system described in claim 1, which receives industry-specific data and know-how from partner specialized organizations.

3. The system according to claim 1, which provides users with insights for business improvement through a model installed on a terminal.

Images