System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting data; means for pre-processing the collected data; means for integrating the pre-processed data; means for executing an artificial intelligence model using the integrated data; means for providing insights derived from the artificial intelligence model; and means for customizing a user interface.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In today's business and individual investment environments, it is extremely important to effectively collect and analyze information from a variety of data sources to make optimal decisions. However, many small and medium-sized enterprises, entrepreneurs, and individual investors lack sufficient data analysis capabilities or budgets, making it difficult to obtain appropriate information for market analysis and investment decisions. Therefore, there is a need for methods to overcome these challenges and support more efficient and accurate decision-making. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides a system including the following elements: means for collecting data, means for preprocessing the collected data, means for integrating the preprocessed data, means for running an AI model using the integrated data, means for providing insights obtained from the AI ​​model, and means for customizing a user interface. This allows users, even without specialized data analysis knowledge, to utilize real-time insights obtained from various data sources to quickly and accurately grasp market trends and make optimal business strategies and investment decisions.

[0006] "Means of collecting data" refers to the functions and processes for obtaining the required information from multiple data sources.

[0007] "Means for pre-processing collected data" refers to methods and devices for converting acquired raw data into a predetermined format and preparing it for analysis.

[0008] "Means for integrating preprocessed data" refers to systems and algorithms for linking preprocessed data from different sources to build a coherent dataset.

[0009] "Means for running artificial intelligence models" refers to computing resources and programs for analyzing and predicting the integrated data using machine learning algorithms and deep learning models.

[0010] "Means for providing insights gained from artificial intelligence models" refers to interfaces and communication means for presenting predictions and analysis results generated by AI models in a format that is easy for users to understand.

[0011] "Means for customizing the user interface" refers to the configuration and operation tools that allow users to filter, visualize, and customize the data and analysis results displayed according to their needs. [Brief explanation of the drawings]

[0012] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0013] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0014] First, the terms used in the following description will be explained.

[0015] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0016] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0017] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0018] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0020] [First embodiment]

[0021] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0022] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0023] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0024] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0025] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0026] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0028] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0030] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0031] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0032] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0033] The present invention is a system that collects, preprocesses, and integrates data, analyzes it using artificial intelligence models, and provides insights to users. It also provides an interface that users can customize as needed. The following describes the program processing and specific examples of this system.

[0034] This system is run mainly by the server. The program processing flow is explained in detail below.

[0035] Data collection

[0036] The server collects the necessary information from multiple data sources, such as business data, financial market data, and social media data, via APIs, allowing it to collect the latest information in real time.

[0037] Data Preprocessing

[0038] The collected raw data is not suitable for analysis as it is, so the server performs preprocessing. During this process, the data is cleansed (filling in missing values, removing outliers) and formatted (normalizing text data, scaling numerical data). This generates data that is suitable for analysis.

[0039] Data Integration

[0040] The pre-processed data is then integrated by the server. Data from different data sources is linked based on key attributes (e.g., timestamp or category) to create a consistent dataset. This integration process allows for multi-dimensional insights to be gained from diverse data.

[0041] Running an AI model

[0042] The server uses the integrated data to run AI models, such as machine learning models (regression models, classification models, etc.) trained on past data to make predictions and classifications, and performs cross-validation and hyperparameter tuning to improve the accuracy of the models.

[0043] Generating and delivering insights

[0044] The insights generated from the trained AI model are updated in real time by the server and delivered to the user's device. These insights include market forecasts and business strategy suggestions. The insights are presented in a visually easy-to-understand format, allowing users to understand and use them immediately.

[0045] User Interface Customization

[0046] Users can customize the interface to suit their needs by setting specific filter conditions (e.g., time period, region, category) and selecting the data visualization format (graph, chart, table, etc.) through their terminal. The server generates the customized data accordingly and provides it in real time.

[0047] Specific examples

[0048] Market strategy formulation for small and medium-sized enterprises

[0049] Small and medium-sized business owners (users) use this system for market analysis. The server collects, preprocesses, and integrates business data and market trend data via API. It then trains a market forecasting model based on historical data and predicts market trends in real time. These forecasts are provided to managers in dashboard format, allowing them to plan promotion strategies.

[0050] Investment decision-making by individual investors

[0051] Individual investors (users) use this system to help them decide where to invest. The server obtains real-time stock market data from the financial API, normalizes and scales the data, and then integrates it. It then uses a machine learning model to predict stock prices and displays the results on a dashboard. Investors can use this information to determine the timing of buying and selling specific stocks.

[0052] In this way, the present invention provides real-time data insights tailored to various needs and assists users in their decision-making process.

[0053] The processing flow will be explained below.

[0054] Step 1:

[0055] The server collects the required data from multiple data sources, such as business data, financial market data, social media data, etc., through APIs. The server initiates the data collection process periodically or based on a trigger event.

[0056] Step 2:

[0057] The server preprocesses the collected raw data, applying data cleansing rules to fill in missing values ​​and remove outliers. For text data, it performs normalization (converting to lowercase, removing special characters), and for numerical data, it performs scaling and standardization.

[0058] Step 3:

[0059] The server integrates the pre-processed data, linking data from different data sources based on key attributes (e.g., timestamps or categories) to build a coherent dataset, systematically grouping related data points together.

[0060] Step 4:

[0061] The server trains AI models using the integrated dataset. It trains machine learning and deep learning models based on historical data to build models for prediction and classification. During this process, it performs cross-validation to evaluate the accuracy of the models and tunes hyperparameters as needed.

[0062] Step 5:

[0063] The server analyzes real-time data using trained AI models to generate insights, including market trend predictions and performance assessments, which are then delivered to users in the form of appropriate dashboards and alerts.

[0064] Step 6:

[0065] Users can view information using the provided dashboard. Users can customize the interface by setting filter conditions such as a specific period, region, category, etc. The server generates customized data based on the user's request and provides it in real time.

[0066] Step 7:

[0067] Through the device, users can make decisions based on the generated insights and customized reports. For example, small business owners can decide on promotion strategies based on market trends, and individual investors can decide when to buy or sell based on stock price forecasts.

[0068] Through the above processing steps, the system efficiently executes a series of processes from data collection to analysis, and generation and provision of insights, thereby supporting user decision-making.

[0069] Example 1

[0070] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0071] In today's information-overloaded environment, it is difficult to quickly and accurately collect necessary information from diverse data sources and analyze it to gain useful insights. Furthermore, the collected data is often incomplete and unsuitable for analysis as is. Furthermore, there is a lack of systems that can effectively analyze integrated data and provide it in a customizable format that meets user needs. This creates significant barriers for companies and individuals to make fast and accurate decisions.

[0072] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0073] In this invention, the server includes means for collecting data, means for preprocessing the collected data, and means for integrating the preprocessed data, which allows the server to obtain information from multiple data sources via API, impute missing values, remove outliers, normalize text data, scale numeric data, and link data from different data sources based on key attributes.

[0074] The server further includes means for running an artificial intelligence model using the integrated data, means for providing insights derived from the artificial intelligence model, and means for customizing a user interface that allows for training the machine learning model, cross-validation and hyperparameter tuning, real-time updates of the generated insights, providing them in a visually understandable format, setting specific filter conditions, and selecting data visualization formats.

[0075] "Data collection" is the process of gathering necessary information from multiple sources.

[0076] "API" stands for Application Program Interface, a standardized means of exchanging data between different software applications.

[0077] "Data preprocessing" refers to a series of processes for converting collected raw data into a form suitable for analysis, including imputing missing values, removing outliers, normalizing text data, and scaling numerical data.

[0078] "Data integration" is the process of combining pre-processed data from different data sources into a coherent dataset, which involves combining data based on key attributes (e.g., timestamp or category).

[0079] An "artificial intelligence model" refers to an analytical method that uses algorithms such as machine learning and deep learning to generate insights and predictions from data.

[0080] "Cross-validation" is a statistical technique for evaluating the performance of a model by dividing a dataset into multiple parts.

[0081] "Hyperparameter tuning" is the process of optimizing the hyperparameters of a machine learning model in order to maximize the model's performance.

[0082] "Insights" are useful new information or insights gained from analyzing data that help users make better decisions.

[0083] "User interface" refers to the screens and operating methods that users use to interact with the system, allowing them to easily access information and check analysis results.

[0084] "Customization" refers to users changing system settings and adjusting the way information is displayed to suit their own needs.

[0085] This invention is a system that collects, preprocesses, integrates, and analyzes data using artificial intelligence models, and provides insights to users. It also has an interface that users can customize as needed. The following describes the program processing and specific examples of this system.

[0086] This system is run primarily by a server, which is often built using programming languages ​​such as Python or JavaScript. Below, we will explain the main processes and the specific software and hardware used for them.

[0087] Data collection

[0088] The server collects the necessary information from multiple data sources, such as business data, financial market data, and social media data, via APIs. This can be done using the Python requests library, which allows for the collection of the latest information in real time.

[0089] Data Preprocessing

[0090] The collected raw data is not suitable for analysis as it is, so the server performs preprocessing. During this process, the data is cleansed (filling in missing values, removing outliers) and formatted (normalizing text data, scaling numerical data). Here, it is recommended to use the Python pandas library.

[0091] Data Integration

[0092] The pre-processed data is then integrated by the server. Data from different data sources is linked based on key attributes (e.g. timestamp or category) to create a consistent dataset. This integration process can be performed using the pandas merge method.

[0093] Running an AI model

[0094] Using the combined data, the server runs AI models, such as machine learning models (regression models, classification models, etc.) trained on past data to perform predictions and classifications. Here, the scikit-learn library is used to build the models and perform cross-validation and hyperparameter tuning.

[0095] Generating and delivering insights

[0096] The insights generated from the trained AI model are updated in real time by the server and delivered to the user's device, including market forecasts and business strategy suggestions, and are presented in a visually understandable format using visualization libraries such as Plotly and Matplotlib.

[0097] User Interface Customization

[0098] Users can customize the interface to suit their needs by setting specific filter conditions (e.g., time period, region, category) and selecting the data visualization format (graph, chart, table, etc.) through their terminal. The server generates the customized data accordingly and provides it in real time.

[0099] Specific examples

[0100] Market strategy formulation for small and medium-sized enterprises

[0101] Small and medium-sized business owners (users) use this system for market analysis. The server collects, preprocesses, and integrates business data and market trend data via API. It then trains a market forecasting model based on historical data and predicts market trends in real time. These forecasts are provided to managers in dashboard format, allowing them to plan promotion strategies.

[0102] Investment decision-making by individual investors

[0103] Individual investors (users) use this system to help them decide where to invest. The server obtains real-time stock market data from the financial API, normalizes and scales the data, and then integrates it. It then uses a machine learning model to predict stock prices and displays the results on a dashboard. Investors can use this information to determine the timing of buying and selling specific stocks.

[0104] Prompt Sentence Examples

[0105] "Collect the latest business and market trend data and train predictive models to help small and medium-sized businesses with their market strategies."

[0106] "Use real-time stock price data to predict stock prices for a specific stock for the next week and display the results visually."

[0107] In this way, the present invention provides real-time data insights tailored to various needs and assists users in their decision-making process.

[0108] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0109] Step 1: Data collection

[0110] The server retrieves business, market, and social media data from each data source based on a pre-configured list of APIs. Specifically, the server uses the Python requests library to send HTTP requests to each data source. Each request includes an API key as authentication information. The server uses the API endpoint and authentication information as input and stores the raw data in JSON format in a local database as output.

[0111] Step 2: Data Preprocessing

[0112] The server preprocesses the collected raw data. This involves first converting it into a data frame using the pandas library. Then, it uses the fillna method to impute missing values ​​and statistical methods (e.g., standard deviation and IQR) to remove outliers. Text data is normalized and numerical data is scaled. The raw data frame is used as input, and clean, unified data is obtained as output.

[0113] Step 3: Data Integration

[0114] The server merges the preprocessed data from multiple data sources, using the pandas merge method to combine datasets from different data sources based on key attributes (timestamp or category), using multiple preprocessed data frames as input and producing a merged dataset as output.

[0115] Step 4: Run the AI ​​model

[0116] The server builds and runs machine learning models based on the merged dataset. First, it trains regression and classification models using the scikit-learn library. Then, it evaluates the accuracy of the models and optimizes their hyperparameters using GridSearchCV and RandomizedSearchCV for cross-validation. It uses the merged dataset as input and generates a trained model and its prediction results as output.

[0117] Step 5: Generate and deliver insights

[0118] The server generates useful insights based on the predictions and analysis results obtained from the trained AI model. Specifically, it uses visualization libraries such as Plotly and Matplotlib to display the results in a user-friendly format. It uses the predictions and analysis results as input, generates visualized graphs and charts as output, and provides them to the user's device.

[0119] Step 6: Customizing the User Interface

[0120] Users customize the interface through their devices by setting specific filter conditions (e.g., time period, region, category) and selecting the data visualization format (graph, chart, table, etc.). The server generates the customized data accordingly and serves it in real time. It uses the user settings as input and generates the customized data and visualization information as output.

[0121] Through this series of processing steps, the server collects information from various data sources, preprocesses, integrates, runs AI models, generates insights, and provides the information to users through a customizable interface.

[0122] (Application example 1)

[0123] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0124] Autonomous vehicles require accurate preprocessing and integration of data to collect various sensor data in real time and ensure safe and efficient operation. However, current systems often lack sufficient data imputation, outlier removal, and format standardization, resulting in inaccurate data analysis. Furthermore, there is a lack of means to properly link and analyze sensor data, making it difficult to provide timely insights.

[0125] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0126] In this invention, the server includes means for collecting data from multiple data transmission devices, means for imputing missing values, removing outliers, and standardizing the format of the collected data, means for integrating the preprocessed data into a consistent format, means for running a classification model using the integrated data, means for providing insights gained from the model, and means for customizing an interface based on user requests, thereby enabling real-time anomaly detection and safe route provision.

[0127] A "data transmission device" is a device that collects data from multiple sensors and data collection devices and transmits it to a server.

[0128] "Missing value imputation" is a process of filling in missing data values ​​with average values, estimated values, etc.

[0129] "Outlier removal" is the process of detecting and removing or correcting unusual values ​​in a data set.

[0130] "Format unification" is the process of converting data provided in different formats into a consistent format.

[0131] An "artificial intelligence model" is a mathematical model that uses machine learning algorithms to analyze data and make predictions and classifications.

[0132] "Insight" refers to useful knowledge or information derived from analytical results or analysis obtained from artificial intelligence models.

[0133] "User interface customization" is a function for changing the display content and operation method to meet the user's requirements.

[0134] "Anomaly detection" refers to detecting unusual patterns or values ​​in data.

[0135] A "safe route" is a route along which an autonomous vehicle is predicted to travel safely.

[0136] "Sensor data" refers to real-time information obtained from various sensors (LiDAR, cameras, GPS, etc.) installed in autonomous vehicles.

[0137] "Consistent format" refers to data format expressed in a unified format and scale.

[0138] A "classification model" is a machine learning model for classifying input data into specific categories or classes.

[0139] The present invention is a system that collects, preprocesses, and integrates sensor data from autonomous vehicles in real time, and utilizes artificial intelligence models to determine safe driving routes and detect anomalies. The system operates centrally on a server, and uses the necessary hardware and software to collect, analyze, and provide insights into the data. A specific embodiment of the system is described below.

[0140] Hardware and Software Configuration

[0141] The hardware used in this system includes multiple sensor devices (LiDAR, cameras, GPS, etc.) and a server. The sensor devices are installed in autonomous vehicles and collect data in real time. The server receives the sensor data and performs subsequent data processing and analysis.

[0142] The software used includes Python, Scikit-learn, the Requests library, and Matplotlib. Python is used as the main programming language for this system, and Scikit-learn is used to run the artificial intelligence model (classification model). The Requests library is used for API calls to collect data from sensor devices, and Matplotlib is used for visualization in the user interface.

[0143] Data collection

[0144] The server collects the necessary sensor data from multiple data transmitters in real time. This data collection is done via the API of each sensor device. For example, data is collected from URLs such as "http: / / sensor1.api" and "http: / / sensor2.api."

[0145] Data Preprocessing

[0146] The collected sensor data is not suitable for analysis as is, so the server performs preprocessing on the data. Preprocessing includes filling in missing values, removing outliers, and standardizing the format. Missing values ​​are filled in using the average value or other methods, and outliers are removed using the 3-sigma method. In addition, the data format is standardized by scaling the numerical data, etc.

[0147] Data Integration

[0148] The pre-processed data is then integrated into a consistent format by the server. Data collected from different sources is linked based on time series attributes. This integration process creates a unified data set that can be analyzed.

[0149] Running artificial intelligence models

[0150] The server runs an artificial intelligence model (classification model) using the integrated data. The model analyzes the data using a random forest classifier to identify safe routes and detect anomalies. Model training and prediction includes cross-validation and hyperparameter tuning.

[0151] Providing insights

[0152] Insights gained from the trained AI model are provided to users in real time, such as a safe route index or anomaly detection results, which are displayed in a dashboard format that allows users (fleet managers and engineers) to intuitively understand them.

[0153] User Interface Customization

[0154] Users can customize the interface to suit their needs, for example by setting filter conditions to highlight specific sensor data and selecting visualization formats such as graphs and charts, providing users with fast and accurate information to support real-time decision-making.

[0155] Specific examples

[0156] For example, let's assume that an autonomous vehicle has the following route data. Data such as obstacles, road gradients, and weather conditions is acquired every second via a sensor API and analyzed in real time. This allows the vehicle to detect anomalies that occur during operation and propose safe routes.

[0157] Prompt Sentence Examples

[0158] "Implement a system that analyzes sensor data from an autonomous vehicle to determine safe routes and detect anomalies. Collect each sensor data using an API, and write a prompt that includes preprocessing, data integration, prediction using an AI model, providing insights to the user, and customizing the interface. The AI ​​model used is a random forest classifier. Specifically, include real-time data collection from the sensor API, data preprocessing, and the ability to visualize insights."

[0159] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0160] Step 1:

[0161] Sensor data collection

[0162] The server collects data in real time from multiple data transmitters (sensors). Specifically, it sends an HTTP request to the API of each sensor device (for example, "http: / / sensor1.api" or "http: / / sensor2.api") to obtain sensor data. The input is the API endpoint of each sensor, and the output is the collected raw data.

[0163] Step 2:

[0164] Data Preprocessing

[0165] The server performs preprocessing on the collected raw data. The input is the collected raw data, and missing values ​​are filled in using the average value or other methods, and outliers are removed using the 3-sigma method. The server also scales the numerical data to unify the data format. The output is preprocessed, clean data.

[0166] Step 3:

[0167] Data integration

[0168] The server aggregates the pre-processed data into a consistent format. The input is the pre-processed data, and the different sensor data are linked based on time series attributes. The output is an integrated dataset.

[0169] Step 4:

[0170] Running artificial intelligence models

[0171] The server runs an artificial intelligence model (a random forest classification model) using the integrated data. The input is the integrated dataset, and the model is trained after cross-validation and hyperparameter tuning. The output is predictions for safe routes and anomaly detection.

[0172] Step 5:

[0173] Providing insights

[0174] The server generates insights based on the training and predicted results and provides them to the user. The input is the prediction results from the AI ​​model, and the visual display is a safe route index and anomaly detection index. The output is a visual insight in the form of a dashboard for the user.

[0175] Step 6:

[0176] User Interface Customization

[0177] Users can customize the interface to suit their needs: the input is the customization options set by the user (e.g., filter criteria for specific sensor data), the server generates the corresponding display, and the output is a customized dashboard delivered to the user in real time.

[0178] This enables the server to collect, preprocess, and integrate a series of sensor data, run AI models, provide insights, and customize interfaces to support the safe and efficient operation of autonomous vehicles.

[0179] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0180] The present invention is a system that collects, preprocesses, and integrates data, analyzes it using an artificial intelligence model, and provides the resulting insights to the user. Furthermore, it is equipped with an emotion engine that recognizes the user's emotions, allowing it to customize the information and interface provided based on the user's emotional state. Below, we will explain the program processing and specific examples of this system.

[0181] This system is run mainly by the server. The program processing flow is explained in detail below.

[0182] Data collection

[0183] The server collects the required data from multiple data sources, such as business data, financial market data, social media data, etc., through APIs. The server initiates the data collection process periodically or based on a trigger event.

[0184] Data Preprocessing

[0185] The collected raw data is not suitable for analysis as it is, so the server performs preprocessing. During this process, the data is cleansed (filling in missing values, removing outliers) and formatted (normalizing text data, scaling numerical data). This generates data that is suitable for analysis.

[0186] Data Integration

[0187] The pre-processed data is then integrated by the server. Data from different data sources is linked based on key attributes (e.g., timestamp or category) to create a consistent dataset. This integration process allows for multi-dimensional insights to be gained from diverse data.

[0188] Running an AI model

[0189] The server uses the integrated data to run AI models, such as machine learning models (regression models, classification models, etc.) trained on past data to make predictions and classifications, and performs cross-validation and hyperparameter tuning to improve the accuracy of the models.

[0190] Generating and delivering insights

[0191] The insights generated from the trained AI model are updated in real time by the server and delivered to the user's device. These insights include market forecasts and business strategy suggestions. The insights are presented in a visually easy-to-understand format, allowing users to understand and use them immediately.

[0192] Emotion Engine Operation

[0193] The emotion engine analyzes the user's voice, facial expressions, and input data to recognize their emotional state. The server automatically adapts the information and interface it provides based on this emotional data. For example, if the user is feeling stressed, it will reduce the amount of information displayed or limit the information provided to the most important ones.

[0194] User Interface Customization

[0195] Users can customize the interface to suit their needs by setting specific filter conditions (e.g., time period, region, category) and selecting the data visualization format (graph, chart, table, etc.) through their terminal. The server generates the customized data accordingly and provides it in real time.

[0196] Specific examples

[0197] Market strategy formulation for small and medium-sized enterprises

[0198] Small and medium-sized business owners (users) use this system for market analysis. The server collects, preprocesses, and integrates business and market trend data via API. It then trains a market forecasting model based on historical data to predict market trends in real time. These forecasts are provided to the owner in dashboard format, and if the emotion engine detects stress in the owner, it will simplify the information display to improve usability.

[0199] Investment decision-making by individual investors

[0200] Individual investors (users) use this system to make investment decisions. The server obtains real-time stock market data from a financial API, normalizes and scales the data, and then integrates it. It then uses a machine learning model to predict stock prices and displays the results on a dashboard. The sentiment engine analyzes the investor's emotional state and, if high interest or concern is detected, provides additional information or alerts accordingly.

[0201] As such, the present invention is a system that provides real-time data insights and emotion recognition functions that meet a variety of needs, and provides powerful support for users' decision-making processes.

[0202] The processing flow will be explained below.

[0203] Step 1:

[0204] The server collects the required data from multiple data sources, such as business data, financial market data, social media data, etc., through APIs. The server initiates the data collection process periodically or based on a trigger event.

[0205] Step 2:

[0206] The server preprocesses the collected raw data, applying data cleansing rules to fill in missing values ​​and remove outliers. For text data, it performs normalization (converting to lowercase, removing special characters), and for numerical data, it performs scaling and standardization.

[0207] Step 3:

[0208] The server integrates the pre-processed data, linking data from different data sources based on key attributes (e.g., timestamps or categories) to build a coherent dataset, systematically grouping related data points together.

[0209] Step 4:

[0210] The server trains AI models using the integrated dataset. It trains machine learning and deep learning models based on historical data to build models for prediction and classification. During this process, it performs cross-validation to evaluate the accuracy of the models and tunes hyperparameters as needed.

[0211] Step 5:

[0212] The server analyzes real-time data using trained AI models to generate insights, including market trend predictions and performance assessments, which are then delivered to users in the form of appropriate dashboards and alerts.

[0213] Step 6:

[0214] The emotion engine analyzes the user's voice, facial expressions, and input data to recognize the user's emotional state. For example, it obtains facial expression data from the user's webcam and applies emotion recognition algorithms to determine the user's current emotion (e.g., joy, sadness, anger, etc.). It also analyzes emotions from voice input.

[0215] Step 7:

[0216] The server automatically adapts the information and interface it provides based on the user's emotional data recognized by the emotion engine. For example, if it determines that the user is feeling stressed, it reduces the amount of information displayed and highlights only the important information. If the user is excited, it is set to display detailed data analysis results.

[0217] Step 8:

[0218] Users can view information using the provided dashboard, and customize the interface by setting filter criteria such as specific time periods, regions, and categories.

[0219] Step 9:

[0220] Through the device, users can make decisions based on the generated insights and customized reports. For example, small business owners can decide on promotion strategies based on market trends, and individual investors can decide when to buy or sell based on stock price forecasts.

[0221] Through the above processing steps, this system collects and analyzes data, generates and provides insights, and also provides multidimensional support that includes emotion recognition, thereby efficiently and effectively assisting users in their decision-making process.

[0222] Example 2

[0223] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0224] In conventional information collection and analysis systems, data preprocessing and integration are cumbersome, and advanced expertise is required to obtain highly accurate insights. Furthermore, due to a lack of mechanisms for recognizing the user's emotional state and adapting the information and interface provided, the user interface cannot be fully customized, making it difficult to improve usability. Our goal is to solve these problems and realize an efficient and flexible data analysis system.

[0225] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0226] In this invention, the server includes a means for collecting data, a means for preprocessing the collected data, and a means for integrating the preprocessed data, thereby enabling efficient and highly accurate data analysis and the provision of insights.

[0227] The server further includes means for executing an artificial intelligence model using the integrated data, means for providing insights obtained from the artificial intelligence model, means for recognizing the user's emotional state and adapting the information and interface to be provided based on the emotional state, and means for customizing the user interface, thereby enabling appropriate information to be provided and the interface to be customized according to the user's emotions, thereby improving usability.

[0228] "Means of collecting data" refers to the function of obtaining necessary data from multiple data sources using an interface such as an API.

[0229] "Means for preprocessing collected data" refers to functions for cleansing collected data, filling in missing values, removing outliers, and standardizing data formats (standardization, scaling, etc.).

[0230] A "means for integrating pre-processed data" is a function that combines pre-processed data into a coherent data set based on key attributes (e.g., timestamps).

[0231] "Means for running artificial intelligence models using the integrated data" refers to the ability to use trained machine learning algorithms to analyze the integrated data and perform tasks such as prediction and classification.

[0232] "Means for providing insights obtained from an AI model" refers to a function that provides users with insights obtained from the analysis results of an AI model in a visually easy-to-understand format (graphs, charts, etc.).

[0233] "Means for recognizing the user's emotional state and adapting the information and interface provided based on that" refers to a function that analyzes the user's voice, facial expressions, input data, etc. to identify their emotional state, and changes the way information is displayed and the interface according to that state.

[0234] "Means for customizing the user interface" refers to the ability to select and change the filter conditions and visualization formats (graphs, charts, tables, etc.) of the interface according to the user's needs.

[0235] The following is a detailed description of the mode for carrying out the invention. The invention consists of a system for data collection, pre-processing, integration, analysis by artificial intelligence models, providing insights, recognizing user emotions, and customizing the interface. The system mainly consists of three elements: a server, a terminal, and a user.

[0236] Data collection

[0237] The server retrieves the necessary data from multiple data sources through APIs. Data sources include business data, financial market data, social media data, etc. The server initiates the data collection process based on a regular schedule or specific trigger events. For example, the server accesses a financial API every 10 minutes to retrieve the latest stock price data.

[0238] Data Preprocessing

[0239] The collected raw data is preprocessed by the server. This process involves cleansing the data, filling in missing values, removing outliers, normalizing text data, and scaling numerical data. For example, abnormally high trading volumes are detected and removed from the collected stock price data. Also, all company names are standardized to lowercase.

[0240] Data Integration

[0241] The pre-processed data is then integrated by the server. Data from different data sources is linked based on key attributes (e.g., timestamps) to create a consistent dataset, enabling multi-dimensional insights to be gained. The integrated data is then stored in a relational database.

[0242] Running artificial intelligence models

[0243] The server runs an artificial intelligence model using the integrated data. A machine learning algorithm (e.g., a regression model or a classification model) is used. The server performs cross-validation and hyperparameter tuning to improve the model's accuracy. For example, the server trains a regression model to predict the next day's stock price from the training dataset.

[0244] Generating and delivering insights

[0245] The server analyzes the predictions and classifications generated by the trained AI model and generates these insights in a user-friendly visual format (e.g., graphs or charts). These insights are updated in real time and provided to the user's device. For example, stock price predictions may be generated as line graphs and displayed in real time on the user's device.

[0246] Emotion Engine Operation

[0247] The emotion engine analyzes the user's voice, facial expressions, and input data to recognize the user's emotional state. The server then adapts the information and interface it provides based on this emotional data. For example, if the user is feeling stressed, it reduces the amount of information displayed and focuses on providing only the most important information.

[0248] User Interface Customization

[0249] Users can customize the interface to suit their needs by setting specific filter conditions (e.g., time period, region, category) and selecting the data visualization format (graph, chart, table, etc.) through their terminal. The server generates the customized data accordingly and provides it in real time.

[0250] Specific examples

[0251] Example of market strategy formulation for small and medium-sized enterprises

[0252] Small and medium-sized business owners (users) use this system for market analysis. The server collects, preprocesses, and integrates business and market trend data via API. It then trains a market forecasting model based on historical data to predict market trends in real time. These forecasts are provided to the owner in dashboard format, and if the emotion engine detects stress in the owner, it can simplify the information display to improve usability.

[0253] Examples of investment decisions made by individual investors

[0254] Individual investors (users) use this system to make investment decisions. The server obtains real-time stock market data from financial APIs, normalizes and scales the data, and then integrates it. It then uses a machine learning model to predict stock prices and displays the results on a dashboard. The sentiment engine analyzes the investor's emotional state and, if high interest or concern is detected, provides additional information or alerts accordingly.

[0255] Prompt Sentence Examples

[0256] "Create an AI model to predict upcoming market trends based on an integrated data set for market analysis of small and medium-sized enterprises."

[0257] In this way, the present invention is a system that provides real-time data insights and emotion recognition capabilities to meet various needs and assist users in their decision-making process.

[0258] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0259] Step 1:

[0260] The server collects data from multiple data sources.

[0261] Input: APIs for business data, financial market data, social media data, etc.

[0262] What it does: Every 10 minutes, the server accesses a financial API to retrieve the latest stock price data, including company names, stock prices, and trading volumes.

[0263] Output: raw collected data

[0264] Step 2:

[0265] The server pre-processes the collected raw data.

[0266] Input: raw data collected

[0267] Specific behavior:

[0268] Missing value imputation: The server uses the previous data to impute missing parts.

[0269] Outlier Removal: Statistical methods are used to detect and remove abnormally high trading volumes.

[0270] Text data normalization: The server normalizes all company names to lowercase.

[0271] Scaling of numerical data: Standardization (mean 0, standard deviation 1) is performed.

[0272] Output: Preprocessed data

[0273] Step 3:

[0274] The server aggregates the pre-processed data.

[0275] Input: Preprocessed data

[0276] What it does: The server combines data from different data sources based on key attributes (e.g., timestamps). The combined data is stored in a relational database.

[0277] Output: A consolidated dataset

[0278] Step 4:

[0279] The server runs an artificial intelligence model using the integrated data.

[0280] Input: Integrated dataset

[0281] Specific behavior:

[0282] Analyze using machine learning algorithms (e.g., regression models, classification models).

[0283] Improve the accuracy of the model by performing cross-validation and hyperparameter tuning.

[0284] Output: Prediction results and classification results

[0285] Step 5:

[0286] The server provides insights derived from artificial intelligence models.

[0287] Input: Prediction results and classification results

[0288] Specific operation: The server generates insights in a visually easy-to-understand format (e.g., graphs, charts) and provides them to the user's device in real time.

[0289] Output: Visualized insights (e.g. line graphs and dashboards)

[0290] Step 6:

[0291] The emotion engine recognizes the user's emotional state and adapts information and interfaces accordingly.

[0292] Input: User's voice, facial expressions, input data

[0293] Specific operation: The emotion engine uses the analysis results to reduce the amount of information displayed if the user is feeling stressed, and provides only important information.

[0294] Output: Adapted information and interface

[0295] Step 7:

[0296] The user customizes the interface.

[0297] Input: User filter criteria (e.g., time period, region, category) and visualization format (graph, chart, table, etc.)

[0298] Specific operation: The server generates customized data based on the conditions specified by the user and provides it in real time.

[0299] Output: Customized data and interface

[0300] (Application example 2)

[0301] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0302] Modern manufacturing plants require the management and analysis of complex data, making it important to optimize the work environment by taking into account the emotional state of workers. However, current systems struggle to efficiently integrate and analyze this data and provide appropriate insights in real time. Furthermore, interfaces are rarely adapted based on the emotional state of workers, resulting in problems such as reduced work efficiency and increased worker stress. To address these issues, a system capable of integrating data and providing insights that take into account emotional states is needed.

[0303] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0304] In this invention, the server includes means for collecting data, means for preprocessing the collected data, means for integrating the preprocessed data, means for running an artificial intelligence model using the integrated data, means for providing insights obtained from the artificial intelligence model, means for customizing a user interface, means for recognizing a user's emotional state using an emotion engine, means for adapting information and an interface to be provided based on the user's emotional state, means for collecting and analyzing factory environment data and worker biometric data, and means for providing insights that optimize the work environment and worker conditions. This makes it possible to efficiently analyze data within a factory and provide optimal insights in real time while taking into account the emotional states of workers.

[0305] A "data collection tool" is a process or device for automatically acquiring data from multiple data sources.

[0306] "Data preprocessing means" refers to processes and methods used to prepare collected raw data in a format suitable for analysis. Specifically, this involves filling in missing values, removing outliers, and normalizing the data.

[0307] A "data integration procedure" is a process or method for combining pre-processed data into a single coherent data set.

[0308] An "artificial intelligence model execution means" is a process or device that uses integrated data to execute an AI model using methods such as machine learning or deep learning to make predictions and classifications.

[0309] An "insight providing means" is a process or method for presenting the analysis results and prediction results obtained by an artificial intelligence model in a format that is easy for users to understand.

[0310] A "user interface customization means" is a process or method for tailoring the displayed information or interface to suit the needs and requirements of the user.

[0311] An "emotion engine" is a system or software that analyzes a user's voice, facial expressions, and input data to recognize the user's emotional state.

[0312] "Factory environment data" refers to data related to the environment within a factory, such as temperature, humidity, and noise levels.

[0313] "Worker's biometric data" refers to data that indicates the physical condition of a factory worker, such as their heart rate and stress level.

[0314] The "optimization insight providing means" is a process or method for using analyzed data to provide insights and suggestions necessary for optimizing factory operations and work environments in real time.

[0315] This invention is a system that collects, pre-processes, integrates, and analyzes data in a factory environment, and provides insights in real time. It has the ability to recognize the emotional state of workers using an emotion engine. This system can optimize factory operations and reduce worker stress.

[0316] Overall system overview

[0317] This system mainly consists of a server, multiple data collection devices, an emotion engine, and a user interface. The server collects, preprocesses, and integrates data from within the factory, and analyzes it using an artificial intelligence model. The analysis results are presented visually and easily understood, and the emotion engine grasps the emotional state of workers in real time and suggests appropriate responses.

[0318] Hardware and software used

[0319] Hardware:

[0320] Various sensors in the factory (temperature sensors, humidity sensors, noise level sensors)

[0321] Worker biometric data acquisition devices (heart rate monitors, stress level measuring devices)

[0322] Audio input devices, cameras

[0323] software:

[0324] Python: Data collection and preprocessing

[0325] Pandas: Data Shaping and Processing

[0326] Scikit-learn: Building and running machine learning models

[0327] TensorFlow: Emotion Engine Implementation

[0328] Data collection and preprocessing

[0329] The server collects various environmental and biometric data in real time from sensors in the factory and biometric data acquisition devices for workers. The collected data is centralized and preprocessed using Pandas. Preprocessing involves filling in missing values, removing outliers, and normalizing text data.

[0330] Data integration and AI analysis

[0331] The pre-processed data is integrated into a coherent dataset. AI models built with Scikit-learn are then run to optimize factory operations and identify stressors. An emotion engine powered by TensorFlow analyzes workers' voices, facial expressions, and input data to recognize their emotional state in real time.

[0332] Providing insights and customizing the interface

[0333] Insights gained from the AI ​​model are delivered in real time through a user interface, including suggestions for improving work efficiency and taking breaks. The user interface can be customized to meet the needs of workers and managers, and the information provided and the interface adapt based on their emotional state.

[0334] Specific examples

[0335] For example, in a manufacturing factory, AI can identify bottlenecks on the production line from past data and suggest countermeasures. Also, when workers become stressed, AI can suggest appropriate times to take breaks, reducing the burden on the workers. This improves the efficiency of the entire factory and the happiness of workers.

[0336] Prompt Sentence Examples

[0337] "How can we suggest a break to a stressed worker?"

[0338] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0339] Step 1:

[0340] Data collection

[0341] The server collects data from various sensors in the factory and workers' biometric data acquisition devices. Input data includes temperature, humidity, noise level, heart rate, stress level, audio, and video. The server periodically obtains this data through an API. This data is first stored on the server in raw format.

[0342] Step 2:

[0343] Data Preprocessing

[0344] The server performs preprocessing on the collected raw data. Specifically, it uses Pandas to impute missing values, remove outliers, and normalize text data. By normalizing the input data and removing outliers, a dataset suitable for analysis is generated. The output data is a dataset in a clean and consistent format.

[0345] Step 3:

[0346] Data integration

[0347] The pre-processed data is then integrated into a consistent dataset by the server. Specifically, data from different data sources is matched using timestamps as a key. As a result, a single unified large-scale dataset is generated. This dataset is then used as input for subsequent AI analysis.

[0348] Step 4:

[0349] Running an AI model

[0350] The server uses the integrated dataset to run artificial intelligence models. These include a prediction model using Scikit-learn and an emotion analysis model built with TensorFlow. Specifically, it runs a classification model to identify factors that reduce work efficiency and a regression model to predict worker stress. The input data is the integrated dataset, and the output data is the prediction results and estimated emotional states.

[0351] Step 5:

[0352] Generating and delivering insights

[0353] Based on the analysis results obtained from the AI ​​model, the server generates insights and provides them through a user interface. These insights include measures to improve work efficiency and recommendations for worker breaks. Specifically, the results are displayed visually using graphs and charts. The input data is the output results from the AI ​​model, and the output data is a visually formatted insight report.

[0354] Step 6:

[0355] Emotion Engine Operation

[0356] The server uses an emotion engine to analyze the user's emotional state in real time. Specifically, it runs a TensorFlow model using audio and video data to estimate the level of stress and fatigue. The input data is audio and video data, and the output data is a tagged emotional state.

[0357] Step 7:

[0358] Interface customization

[0359] The server automatically adapts the information and interface it provides based on the user's emotional state. For example, if the user is under stress, it simplifies the information displayed and provides only the most important information. The input data is the output result from the emotion engine, and the output data is the adapted user interface.

[0360] Specific prompt examples

[0361] "How can we suggest a break to a stressed worker?"

[0362] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0363] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0364] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0365] [Second embodiment]

[0366] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0367] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0368] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0369] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0370] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0371] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0372] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0373] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0374] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0375] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0376] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0377] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0378] The present invention is a system that collects, preprocesses, and integrates data, analyzes it using artificial intelligence models, and provides insights to users. It also provides an interface that users can customize as needed. The following describes the program processing and specific examples of this system.

[0379] This system is run mainly by the server. The program processing flow is explained in detail below.

[0380] Data collection

[0381] The server collects the necessary information from multiple data sources, such as business data, financial market data, and social media data, via APIs, allowing it to collect the latest information in real time.

[0382] Data Preprocessing

[0383] The collected raw data is not suitable for analysis as it is, so the server performs preprocessing. During this process, the data is cleansed (filling in missing values, removing outliers) and formatted (normalizing text data, scaling numerical data). This generates data that is suitable for analysis.

[0384] Data Integration

[0385] The pre-processed data is then integrated by the server. Data from different data sources is linked based on key attributes (e.g., timestamp or category) to create a consistent dataset. This integration process allows for multi-dimensional insights to be gained from diverse data.

[0386] Running an AI model

[0387] The server uses the integrated data to run AI models, such as machine learning models (regression models, classification models, etc.) trained on past data to make predictions and classifications, and performs cross-validation and hyperparameter tuning to improve the accuracy of the models.

[0388] Generating and delivering insights

[0389] The insights generated from the trained AI model are updated in real time by the server and delivered to the user's device. These insights include market forecasts and business strategy suggestions. The insights are presented in a visually easy-to-understand format, allowing users to understand and use them immediately.

[0390] User Interface Customization

[0391] Users can customize the interface to suit their needs by setting specific filter conditions (e.g., time period, region, category) and selecting the data visualization format (graph, chart, table, etc.) through their terminal. The server generates the customized data accordingly and provides it in real time.

[0392] Specific examples

[0393] Market strategy formulation for small and medium-sized enterprises

[0394] Small and medium-sized business owners (users) use this system for market analysis. The server collects, preprocesses, and integrates business data and market trend data via API. It then trains a market forecasting model based on historical data and predicts market trends in real time. These forecasts are provided to managers in dashboard format, allowing them to plan promotion strategies.

[0395] Investment decision-making by individual investors

[0396] Individual investors (users) use this system to help them decide where to invest. The server obtains real-time stock market data from the financial API, normalizes and scales the data, and then integrates it. It then uses a machine learning model to predict stock prices and displays the results on a dashboard. Investors can use this information to determine the timing of buying and selling specific stocks.

[0397] In this way, the present invention provides real-time data insights tailored to various needs and assists users in their decision-making process.

[0398] The processing flow will be explained below.

[0399] Step 1:

[0400] The server collects the required data from multiple data sources, such as business data, financial market data, social media data, etc., through APIs. The server initiates the data collection process periodically or based on a trigger event.

[0401] Step 2:

[0402] The server preprocesses the collected raw data, applying data cleansing rules to fill in missing values ​​and remove outliers. For text data, it performs normalization (converting to lowercase, removing special characters), and for numerical data, it performs scaling and standardization.

[0403] Step 3:

[0404] The server integrates the pre-processed data, linking data from different data sources based on key attributes (e.g., timestamps or categories) to build a coherent dataset, systematically grouping related data points together.

[0405] Step 4:

[0406] The server trains AI models using the integrated dataset. It trains machine learning and deep learning models based on historical data to build models for prediction and classification. During this process, it performs cross-validation to evaluate the accuracy of the models and tunes hyperparameters as needed.

[0407] Step 5:

[0408] The server analyzes real-time data using trained AI models to generate insights, including market trend predictions and performance assessments, which are then delivered to users in the form of appropriate dashboards and alerts.

[0409] Step 6:

[0410] Users can view information using the provided dashboard. Users can customize the interface by setting filter conditions such as a specific period, region, category, etc. The server generates customized data based on the user's request and provides it in real time.

[0411] Step 7:

[0412] Through the device, users can make decisions based on the generated insights and customized reports. For example, small business owners can decide on promotion strategies based on market trends, and individual investors can decide when to buy or sell based on stock price forecasts.

[0413] Through the above processing steps, the system efficiently executes a series of processes from data collection to analysis, and generation and provision of insights, thereby supporting user decision-making.

[0414] Example 1

[0415] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0416] In today's information-overloaded environment, it is difficult to quickly and accurately collect necessary information from diverse data sources and analyze it to gain useful insights. Furthermore, the collected data is often incomplete and unsuitable for analysis as is. Furthermore, there is a lack of systems that can effectively analyze integrated data and provide it in a customizable format that meets user needs. This creates significant barriers for companies and individuals to make fast and accurate decisions.

[0417] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0418] In this invention, the server includes means for collecting data, means for preprocessing the collected data, and means for integrating the preprocessed data, which allows the server to obtain information from multiple data sources via API, impute missing values, remove outliers, normalize text data, scale numeric data, and link data from different data sources based on key attributes.

[0419] The server further includes means for running an artificial intelligence model using the integrated data, means for providing insights derived from the artificial intelligence model, and means for customizing a user interface that allows for training the machine learning model, cross-validation and hyperparameter tuning, real-time updates of the generated insights, providing them in a visually understandable format, setting specific filter conditions, and selecting data visualization formats.

[0420] "Data collection" is the process of gathering necessary information from multiple sources.

[0421] "API" stands for Application Program Interface, a standardized means of exchanging data between different software applications.

[0422] "Data preprocessing" refers to a series of processes for converting collected raw data into a form suitable for analysis, including imputing missing values, removing outliers, normalizing text data, and scaling numerical data.

[0423] "Data integration" is the process of combining pre-processed data from different data sources into a coherent dataset, which involves combining data based on key attributes (e.g., timestamp or category).

[0424] An "artificial intelligence model" refers to an analytical method that uses algorithms such as machine learning and deep learning to generate insights and predictions from data.

[0425] "Cross-validation" is a statistical technique for evaluating the performance of a model by dividing a dataset into multiple parts.

[0426] "Hyperparameter tuning" is the process of optimizing the hyperparameters of a machine learning model in order to maximize the model's performance.

[0427] "Insights" are useful new information or insights gained from analyzing data that help users make better decisions.

[0428] "User interface" refers to the screens and operating methods that users use to interact with the system, allowing them to easily access information and check analysis results.

[0429] "Customization" refers to users changing system settings and adjusting the way information is displayed to suit their own needs.

[0430] This invention is a system that collects, preprocesses, integrates, and analyzes data using artificial intelligence models, and provides insights to users. It also has an interface that users can customize as needed. The following describes the program processing and specific examples of this system.

[0431] This system is run primarily by a server, which is often built using programming languages ​​such as Python or JavaScript. Below, we will explain the main processes and the specific software and hardware used for them.

[0432] Data collection

[0433] The server collects the necessary information from multiple data sources, such as business data, financial market data, and social media data, via APIs. This can be done using the Python requests library, which allows for the collection of the latest information in real time.

[0434] Data Preprocessing

[0435] The collected raw data is not suitable for analysis as it is, so the server performs preprocessing. During this process, the data is cleansed (filling in missing values, removing outliers) and formatted (normalizing text data, scaling numerical data). Here, it is recommended to use the Python pandas library.

[0436] Data Integration

[0437] The pre-processed data is then integrated by the server. Data from different data sources is linked based on key attributes (e.g. timestamp or category) to create a consistent dataset. This integration process can be performed using the pandas merge method.

[0438] Running an AI model

[0439] Using the combined data, the server runs AI models, such as machine learning models (regression models, classification models, etc.) trained on past data to perform predictions and classifications. Here, the scikit-learn library is used to build the models and perform cross-validation and hyperparameter tuning.

[0440] Generating and delivering insights

[0441] The insights generated from the trained AI model are updated in real time by the server and delivered to the user's device, including market forecasts and business strategy suggestions, and are presented in a visually understandable format using visualization libraries such as Plotly and Matplotlib.

[0442] User Interface Customization

[0443] Users can customize the interface to suit their needs by setting specific filter conditions (e.g., time period, region, category) and selecting the data visualization format (graph, chart, table, etc.) through their terminal. The server generates the customized data accordingly and provides it in real time.

[0444] Specific examples

[0445] Market strategy formulation for small and medium-sized enterprises

[0446] Small and medium-sized business owners (users) use this system for market analysis. The server collects, preprocesses, and integrates business data and market trend data via API. It then trains a market forecasting model based on historical data and predicts market trends in real time. These forecasts are provided to managers in dashboard format, allowing them to plan promotion strategies.

[0447] Investment decision-making by individual investors

[0448] Individual investors (users) use this system to help them decide where to invest. The server obtains real-time stock market data from the financial API, normalizes and scales the data, and then integrates it. It then uses a machine learning model to predict stock prices and displays the results on a dashboard. Investors can use this information to determine the timing of buying and selling specific stocks.

[0449] Prompt Sentence Examples

[0450] "Collect the latest business and market trend data and train predictive models to help small and medium-sized businesses with their market strategies."

[0451] "Use real-time stock price data to predict stock prices for a specific stock for the next week and display the results visually."

[0452] In this way, the present invention provides real-time data insights tailored to various needs and assists users in their decision-making process.

[0453] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0454] Step 1: Data collection

[0455] The server retrieves business, market, and social media data from each data source based on a pre-configured list of APIs. Specifically, the server uses the Python requests library to send HTTP requests to each data source. Each request includes an API key as authentication information. The server uses the API endpoint and authentication information as input and stores the raw data in JSON format in a local database as output.

[0456] Step 2: Data Preprocessing

[0457] The server preprocesses the collected raw data. This involves first converting it into a data frame using the pandas library. Then, it uses the fillna method to impute missing values ​​and statistical methods (e.g., standard deviation and IQR) to remove outliers. Text data is normalized and numerical data is scaled. The raw data frame is used as input, and clean, unified data is obtained as output.

[0458] Step 3: Data Integration

[0459] The server merges the preprocessed data from multiple data sources, using the pandas merge method to combine datasets from different data sources based on key attributes (timestamp or category), using multiple preprocessed data frames as input and producing a merged dataset as output.

[0460] Step 4: Run the AI ​​model

[0461] The server builds and runs machine learning models based on the merged dataset. First, it trains regression and classification models using the scikit-learn library. Then, it evaluates the accuracy of the models and optimizes their hyperparameters using GridSearchCV and RandomizedSearchCV for cross-validation. It uses the merged dataset as input and generates a trained model and its prediction results as output.

[0462] Step 5: Generate and deliver insights

[0463] The server generates useful insights based on the predictions and analysis results obtained from the trained AI model. Specifically, it uses visualization libraries such as Plotly and Matplotlib to display the results in a user-friendly format. It uses the predictions and analysis results as input, generates visualized graphs and charts as output, and provides them to the user's device.

[0464] Step 6: Customizing the User Interface

[0465] Users customize the interface through their devices by setting specific filter conditions (e.g., time period, region, category) and selecting the data visualization format (graph, chart, table, etc.). The server generates the customized data accordingly and serves it in real time. It uses the user settings as input and generates the customized data and visualization information as output.

[0466] Through this series of processing steps, the server collects information from various data sources, preprocesses, integrates, runs AI models, generates insights, and provides the information to users through a customizable interface.

[0467] (Application example 1)

[0468] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0469] Autonomous vehicles require accurate preprocessing and integration of data to collect various sensor data in real time and ensure safe and efficient operation. However, current systems often lack sufficient data imputation, outlier removal, and format standardization, resulting in inaccurate data analysis. Furthermore, there is a lack of means to properly link and analyze sensor data, making it difficult to provide timely insights.

[0470] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0471] In this invention, the server includes means for collecting data from multiple data transmission devices, means for imputing missing values, removing outliers, and standardizing the format of the collected data, means for integrating the preprocessed data into a consistent format, means for running a classification model using the integrated data, means for providing insights gained from the model, and means for customizing an interface based on user requests, thereby enabling real-time anomaly detection and safe route provision.

[0472] A "data transmission device" is a device that collects data from multiple sensors and data collection devices and transmits it to a server.

[0473] "Missing value imputation" is a process of filling in missing data values ​​with average values, estimated values, etc.

[0474] "Outlier removal" is the process of detecting and removing or correcting unusual values ​​in a data set.

[0475] "Format unification" is the process of converting data provided in different formats into a consistent format.

[0476] An "artificial intelligence model" is a mathematical model that uses machine learning algorithms to analyze data and make predictions and classifications.

[0477] "Insight" refers to useful knowledge or information derived from analytical results or analysis obtained from artificial intelligence models.

[0478] "User interface customization" is a function for changing the display content and operation method to meet the user's requirements.

[0479] "Anomaly detection" refers to detecting unusual patterns or values ​​in data.

[0480] A "safe route" is a route along which an autonomous vehicle is predicted to travel safely.

[0481] "Sensor data" refers to real-time information obtained from various sensors (LiDAR, cameras, GPS, etc.) installed in autonomous vehicles.

[0482] "Consistent format" refers to data format expressed in a unified format and scale.

[0483] A "classification model" is a machine learning model for classifying input data into specific categories or classes.

[0484] The present invention is a system that collects, preprocesses, and integrates sensor data from autonomous vehicles in real time, and utilizes artificial intelligence models to determine safe driving routes and detect anomalies. The system operates centrally on a server, and uses the necessary hardware and software to collect, analyze, and provide insights into the data. A specific embodiment of the system is described below.

[0485] Hardware and Software Configuration

[0486] The hardware used in this system includes multiple sensor devices (LiDAR, cameras, GPS, etc.) and a server. The sensor devices are installed in autonomous vehicles and collect data in real time. The server receives the sensor data and performs subsequent data processing and analysis.

[0487] The software used includes Python, Scikit-learn, the Requests library, and Matplotlib. Python is used as the main programming language for this system, and Scikit-learn is used to run the artificial intelligence model (classification model). The Requests library is used for API calls to collect data from sensor devices, and Matplotlib is used for visualization in the user interface.

[0488] Data collection

[0489] The server collects the necessary sensor data from multiple data transmitters in real time. This data collection is done via the API of each sensor device. For example, data is collected from URLs such as "http: / / sensor1.api" and "http: / / sensor2.api."

[0490] Data Preprocessing

[0491] The collected sensor data is not suitable for analysis as is, so the server performs preprocessing on the data. Preprocessing includes filling in missing values, removing outliers, and standardizing the format. Missing values ​​are filled in using the average value or other methods, and outliers are removed using the 3-sigma method. In addition, the data format is standardized by scaling the numerical data, etc.

[0492] Data Integration

[0493] The pre-processed data is then integrated into a consistent format by the server. Data collected from different sources is linked based on time series attributes. This integration process creates a unified data set that can be analyzed.

[0494] Running artificial intelligence models

[0495] The server runs an artificial intelligence model (classification model) using the integrated data. The model analyzes the data using a random forest classifier to identify safe routes and detect anomalies. Model training and prediction includes cross-validation and hyperparameter tuning.

[0496] Providing insights

[0497] Insights gained from the trained AI model are provided to users in real time, such as a safe route index or anomaly detection results, which are displayed in a dashboard format that allows users (fleet managers and engineers) to intuitively understand them.

[0498] User Interface Customization

[0499] Users can customize the interface to suit their needs, for example by setting filter conditions to highlight specific sensor data and selecting visualization formats such as graphs and charts, providing users with fast and accurate information to support real-time decision-making.

[0500] Specific examples

[0501] For example, let's assume that an autonomous vehicle has the following route data. Data such as obstacles, road gradients, and weather conditions is acquired every second via a sensor API and analyzed in real time. This allows the vehicle to detect anomalies that occur during operation and propose safe routes.

[0502] Prompt Sentence Examples

[0503] "Implement a system that analyzes sensor data from an autonomous vehicle to determine safe routes and detect anomalies. Collect each sensor data using an API, and write a prompt that includes preprocessing, data integration, prediction using an AI model, providing insights to the user, and customizing the interface. The AI ​​model used is a random forest classifier. Specifically, include real-time data collection from the sensor API, data preprocessing, and the ability to visualize insights."

[0504] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0505] Step 1:

[0506] Sensor data collection

[0507] The server collects data in real time from multiple data transmitters (sensors). Specifically, it sends an HTTP request to the API of each sensor device (for example, "http: / / sensor1.api" or "http: / / sensor2.api") to obtain sensor data. The input is the API endpoint of each sensor, and the output is the collected raw data.

[0508] Step 2:

[0509] Data Preprocessing

[0510] The server performs preprocessing on the collected raw data. The input is the collected raw data, and missing values ​​are filled in using the average value or other methods, and outliers are removed using the 3-sigma method. The server also scales the numerical data to unify the data format. The output is preprocessed, clean data.

[0511] Step 3:

[0512] Data integration

[0513] The server aggregates the pre-processed data into a consistent format. The input is the pre-processed data, and the different sensor data are linked based on time series attributes. The output is an integrated dataset.

[0514] Step 4:

[0515] Running artificial intelligence models

[0516] The server runs an artificial intelligence model (a random forest classification model) using the integrated data. The input is the integrated dataset, and the model is trained after cross-validation and hyperparameter tuning. The output is predictions for safe routes and anomaly detection.

[0517] Step 5:

[0518] Providing insights

[0519] The server generates insights based on the training and predicted results and provides them to the user. The input is the prediction results from the AI ​​model, and the visual display is a safe route index and anomaly detection index. The output is a visual insight in the form of a dashboard for the user.

[0520] Step 6:

[0521] User Interface Customization

[0522] Users can customize the interface to suit their needs: the input is the customization options set by the user (e.g., filter criteria for specific sensor data), the server generates the corresponding display, and the output is a customized dashboard delivered to the user in real time.

[0523] This enables the server to collect, preprocess, and integrate a series of sensor data, run AI models, provide insights, and customize interfaces to support the safe and efficient operation of autonomous vehicles.

[0524] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0525] The present invention is a system that collects, preprocesses, and integrates data, analyzes it using an artificial intelligence model, and provides the resulting insights to the user. Furthermore, it is equipped with an emotion engine that recognizes the user's emotions, allowing it to customize the information and interface provided based on the user's emotional state. Below, we will explain the program processing and specific examples of this system.

[0526] This system is run mainly by the server. The program processing flow is explained in detail below.

[0527] Data collection

[0528] The server collects the required data from multiple data sources, such as business data, financial market data, social media data, etc., through APIs. The server initiates the data collection process periodically or based on a trigger event.

[0529] Data Preprocessing

[0530] The collected raw data is not suitable for analysis as it is, so the server performs preprocessing. During this process, the data is cleansed (filling in missing values, removing outliers) and formatted (normalizing text data, scaling numerical data). This generates data that is suitable for analysis.

[0531] Data Integration

[0532] The pre-processed data is then integrated by the server. Data from different data sources is linked based on key attributes (e.g., timestamp or category) to create a consistent dataset. This integration process allows for multi-dimensional insights to be gained from diverse data.

[0533] Running an AI model

[0534] The server uses the integrated data to run AI models, such as machine learning models (regression models, classification models, etc.) trained on past data to make predictions and classifications, and performs cross-validation and hyperparameter tuning to improve the accuracy of the models.

[0535] Generating and delivering insights

[0536] The insights generated from the trained AI model are updated in real time by the server and delivered to the user's device. These insights include market forecasts and business strategy suggestions. The insights are presented in a visually easy-to-understand format, allowing users to understand and use them immediately.

[0537] Emotion Engine Operation

[0538] The emotion engine analyzes the user's voice, facial expressions, and input data to recognize their emotional state. The server automatically adapts the information and interface it provides based on this emotional data. For example, if the user is feeling stressed, it will reduce the amount of information displayed or limit the information provided to the most important ones.

[0539] User Interface Customization

[0540] Users can customize the interface to suit their needs by setting specific filter conditions (e.g., time period, region, category) and selecting the data visualization format (graph, chart, table, etc.) through their terminal. The server generates the customized data accordingly and provides it in real time.

[0541] Specific examples

[0542] Market strategy formulation for small and medium-sized enterprises

[0543] Small and medium-sized business owners (users) use this system for market analysis. The server collects, preprocesses, and integrates business and market trend data via API. It then trains a market forecasting model based on historical data to predict market trends in real time. These forecasts are provided to the owner in dashboard format, and if the emotion engine detects stress in the owner, it will simplify the information display to improve usability.

[0544] Investment decision-making by individual investors

[0545] Individual investors (users) use this system to make investment decisions. The server obtains real-time stock market data from a financial API, normalizes and scales the data, and then integrates it. It then uses a machine learning model to predict stock prices and displays the results on a dashboard. The sentiment engine analyzes the investor's emotional state and, if high interest or concern is detected, provides additional information or alerts accordingly.

[0546] As such, the present invention is a system that provides real-time data insights and emotion recognition functions that meet a variety of needs, and provides powerful support for users' decision-making processes.

[0547] The processing flow will be explained below.

[0548] Step 1:

[0549] The server collects the required data from multiple data sources, such as business data, financial market data, social media data, etc., through APIs. The server initiates the data collection process periodically or based on a trigger event.

[0550] Step 2:

[0551] The server preprocesses the collected raw data, applying data cleansing rules to fill in missing values ​​and remove outliers. For text data, it performs normalization (converting to lowercase, removing special characters), and for numerical data, it performs scaling and standardization.

[0552] Step 3:

[0553] The server integrates the pre-processed data, linking data from different data sources based on key attributes (e.g., timestamps or categories) to build a coherent dataset, systematically grouping related data points together.

[0554] Step 4:

[0555] The server trains AI models using the integrated dataset. It trains machine learning and deep learning models based on historical data to build models for prediction and classification. During this process, it performs cross-validation to evaluate the accuracy of the models and tunes hyperparameters as needed.

[0556] Step 5:

[0557] The server analyzes real-time data using trained AI models to generate insights, including market trend predictions and performance assessments, which are then delivered to users in the form of appropriate dashboards and alerts.

[0558] Step 6:

[0559] The emotion engine analyzes the user's voice, facial expressions, and input data to recognize the user's emotional state. For example, it obtains facial expression data from the user's webcam and applies emotion recognition algorithms to determine the user's current emotion (e.g., joy, sadness, anger, etc.). It also analyzes emotions from voice input.

[0560] Step 7:

[0561] The server automatically adapts the information and interface it provides based on the user's emotional data recognized by the emotion engine. For example, if it determines that the user is feeling stressed, it reduces the amount of information displayed and highlights only the important information. If the user is excited, it is set to display detailed data analysis results.

[0562] Step 8:

[0563] Users can view information using the provided dashboard, and customize the interface by setting filter criteria such as specific time periods, regions, and categories.

[0564] Step 9:

[0565] Through the device, users can make decisions based on the generated insights and customized reports. For example, small business owners can decide on promotion strategies based on market trends, and individual investors can decide when to buy or sell based on stock price forecasts.

[0566] Through the above processing steps, this system collects and analyzes data, generates and provides insights, and also provides multidimensional support that includes emotion recognition, thereby efficiently and effectively assisting users in their decision-making process.

[0567] Example 2

[0568] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0569] In conventional information collection and analysis systems, data preprocessing and integration are cumbersome, and advanced expertise is required to obtain highly accurate insights. Furthermore, due to a lack of mechanisms for recognizing the user's emotional state and adapting the information and interface provided, the user interface cannot be fully customized, making it difficult to improve usability. Our goal is to solve these problems and realize an efficient and flexible data analysis system.

[0570] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0571] In this invention, the server includes a means for collecting data, a means for preprocessing the collected data, and a means for integrating the preprocessed data, thereby enabling efficient and highly accurate data analysis and the provision of insights.

[0572] The server further includes means for executing an artificial intelligence model using the integrated data, means for providing insights obtained from the artificial intelligence model, means for recognizing the user's emotional state and adapting the information and interface to be provided based on the emotional state, and means for customizing the user interface, thereby enabling appropriate information to be provided and the interface to be customized according to the user's emotions, thereby improving usability.

[0573] "Means of collecting data" refers to the function of obtaining necessary data from multiple data sources using an interface such as an API.

[0574] "Means for preprocessing collected data" refers to functions for cleansing collected data, filling in missing values, removing outliers, and standardizing data formats (standardization, scaling, etc.).

[0575] A "means for integrating pre-processed data" is a function that combines pre-processed data into a coherent data set based on key attributes (e.g., timestamps).

[0576] "Means for running artificial intelligence models using the integrated data" refers to the ability to use trained machine learning algorithms to analyze the integrated data and perform tasks such as prediction and classification.

[0577] "Means for providing insights obtained from an AI model" refers to a function that provides users with insights obtained from the analysis results of an AI model in a visually easy-to-understand format (graphs, charts, etc.).

[0578] "Means for recognizing the user's emotional state and adapting the information and interface provided based on that" refers to a function that analyzes the user's voice, facial expressions, input data, etc. to identify their emotional state, and changes the way information is displayed and the interface according to that state.

[0579] "Means for customizing the user interface" refers to the ability to select and change the filter conditions and visualization formats (graphs, charts, tables, etc.) of the interface according to the user's needs.

[0580] The following is a detailed description of the mode for carrying out the invention. The invention consists of a system for data collection, pre-processing, integration, analysis by artificial intelligence models, providing insights, recognizing user emotions, and customizing the interface. The system mainly consists of three elements: a server, a terminal, and a user.

[0581] Data collection

[0582] The server retrieves the necessary data from multiple data sources through APIs. Data sources include business data, financial market data, social media data, etc. The server initiates the data collection process based on a regular schedule or specific trigger events. For example, the server accesses a financial API every 10 minutes to retrieve the latest stock price data.

[0583] Data Preprocessing

[0584] The collected raw data is preprocessed by the server. This process involves cleansing the data, filling in missing values, removing outliers, normalizing text data, and scaling numerical data. For example, abnormally high trading volumes are detected and removed from the collected stock price data. Also, all company names are standardized to lowercase.

[0585] Data Integration

[0586] The pre-processed data is then integrated by the server. Data from different data sources is linked based on key attributes (e.g., timestamps) to create a consistent dataset, enabling multi-dimensional insights to be gained. The integrated data is then stored in a relational database.

[0587] Running artificial intelligence models

[0588] The server runs an artificial intelligence model using the integrated data. A machine learning algorithm (e.g., a regression model or a classification model) is used. The server performs cross-validation and hyperparameter tuning to improve the model's accuracy. For example, the server trains a regression model to predict the next day's stock price from the training dataset.

[0589] Generating and delivering insights

[0590] The server analyzes the predictions and classifications generated by the trained AI model and generates these insights in a user-friendly visual format (e.g., graphs or charts). These insights are updated in real time and provided to the user's device. For example, stock price predictions may be generated as line graphs and displayed in real time on the user's device.

[0591] Emotion Engine Operation

[0592] The emotion engine analyzes the user's voice, facial expressions, and input data to recognize the user's emotional state. The server then adapts the information and interface it provides based on this emotional data. For example, if the user is feeling stressed, it reduces the amount of information displayed and focuses on providing only the most important information.

[0593] User Interface Customization

[0594] Users can customize the interface to suit their needs by setting specific filter conditions (e.g., time period, region, category) and selecting the data visualization format (graph, chart, table, etc.) through their terminal. The server generates the customized data accordingly and provides it in real time.

[0595] Specific examples

[0596] Example of market strategy formulation for small and medium-sized enterprises

[0597] Small and medium-sized business owners (users) use this system for market analysis. The server collects, preprocesses, and integrates business and market trend data via API. It then trains a market forecasting model based on historical data to predict market trends in real time. These forecasts are provided to the owner in dashboard format, and if the emotion engine detects stress in the owner, it can simplify the information display to improve usability.

[0598] Examples of investment decisions made by individual investors

[0599] Individual investors (users) use this system to make investment decisions. The server obtains real-time stock market data from financial APIs, normalizes and scales the data, and then integrates it. It then uses a machine learning model to predict stock prices and displays the results on a dashboard. The sentiment engine analyzes the investor's emotional state and, if high interest or concern is detected, provides additional information or alerts accordingly.

[0600] Prompt Sentence Examples

[0601] "Create an AI model to predict upcoming market trends based on an integrated data set for market analysis of small and medium-sized enterprises."

[0602] In this way, the present invention is a system that provides real-time data insights and emotion recognition capabilities to meet various needs and assist users in their decision-making process.

[0603] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0604] Step 1:

[0605] The server collects data from multiple data sources.

[0606] Input: APIs for business data, financial market data, social media data, etc.

[0607] What it does: Every 10 minutes, the server accesses a financial API to retrieve the latest stock price data, including company names, stock prices, and trading volumes.

[0608] Output: raw collected data

[0609] Step 2:

[0610] The server pre-processes the collected raw data.

[0611] Input: raw data collected

[0612] Specific behavior:

[0613] Missing value imputation: The server uses the previous data to impute missing parts.

[0614] Outlier Removal: Statistical methods are used to detect and remove abnormally high trading volumes.

[0615] Text data normalization: The server normalizes all company names to lowercase.

[0616] Scaling of numerical data: Standardization (mean 0, standard deviation 1) is performed.

[0617] Output: Preprocessed data

[0618] Step 3:

[0619] The server aggregates the pre-processed data.

[0620] Input: Preprocessed data

[0621] What it does: The server combines data from different data sources based on key attributes (e.g., timestamps). The combined data is stored in a relational database.

[0622] Output: A consolidated dataset

[0623] Step 4:

[0624] The server runs an artificial intelligence model using the integrated data.

[0625] Input: Integrated dataset

[0626] Specific behavior:

[0627] Analyze using machine learning algorithms (e.g., regression models, classification models).

[0628] Improve the accuracy of the model by performing cross-validation and hyperparameter tuning.

[0629] Output: Prediction results and classification results

[0630] Step 5:

[0631] The server provides insights derived from artificial intelligence models.

[0632] Input: Prediction results and classification results

[0633] Specific operation: The server generates insights in a visually easy-to-understand format (e.g., graphs, charts) and provides them to the user's device in real time.

[0634] Output: Visualized insights (e.g. line graphs and dashboards)

[0635] Step 6:

[0636] The emotion engine recognizes the user's emotional state and adapts information and interfaces accordingly.

[0637] Input: User's voice, facial expressions, input data

[0638] Specific operation: The emotion engine uses the analysis results to reduce the amount of information displayed if the user is feeling stressed, and provides only important information.

[0639] Output: Adapted information and interface

[0640] Step 7:

[0641] The user customizes the interface.

[0642] Input: User filter criteria (e.g., time period, region, category) and visualization format (graph, chart, table, etc.)

[0643] Specific operation: The server generates customized data based on the conditions specified by the user and provides it in real time.

[0644] Output: Customized data and interface

[0645] (Application example 2)

[0646] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0647] Modern manufacturing plants require the management and analysis of complex data, making it important to optimize the work environment by taking into account the emotional state of workers. However, current systems struggle to efficiently integrate and analyze this data and provide appropriate insights in real time. Furthermore, interfaces are rarely adapted based on the emotional state of workers, resulting in problems such as reduced work efficiency and increased worker stress. To address these issues, a system capable of integrating data and providing insights that take into account emotional states is needed.

[0648] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0649] In this invention, the server includes means for collecting data, means for preprocessing the collected data, means for integrating the preprocessed data, means for running an artificial intelligence model using the integrated data, means for providing insights obtained from the artificial intelligence model, means for customizing a user interface, means for recognizing a user's emotional state using an emotion engine, means for adapting information and an interface to be provided based on the user's emotional state, means for collecting and analyzing factory environment data and worker biometric data, and means for providing insights that optimize the work environment and worker conditions. This makes it possible to efficiently analyze data within a factory and provide optimal insights in real time while taking into account the emotional states of workers.

[0650] A "data collection tool" is a process or device for automatically acquiring data from multiple data sources.

[0651] "Data preprocessing means" refers to processes and methods used to prepare collected raw data in a format suitable for analysis. Specifically, this involves filling in missing values, removing outliers, and normalizing the data.

[0652] A "data integration procedure" is a process or method for combining pre-processed data into a single coherent data set.

[0653] An "artificial intelligence model execution means" is a process or device that uses integrated data to execute an AI model using methods such as machine learning or deep learning to make predictions and classifications.

[0654] An "insight providing means" is a process or method for presenting the analysis results and prediction results obtained by an artificial intelligence model in a format that is easy for users to understand.

[0655] A "user interface customization means" is a process or method for tailoring the displayed information or interface to suit the needs and requirements of the user.

[0656] An "emotion engine" is a system or software that analyzes a user's voice, facial expressions, and input data to recognize the user's emotional state.

[0657] "Factory environment data" refers to data related to the environment within a factory, such as temperature, humidity, and noise levels.

[0658] "Worker's biometric data" refers to data that indicates the physical condition of a factory worker, such as their heart rate and stress level.

[0659] The "optimization insight providing means" is a process or method for using analyzed data to provide insights and suggestions necessary for optimizing factory operations and work environments in real time.

[0660] This invention is a system that collects, pre-processes, integrates, and analyzes data in a factory environment, and provides insights in real time. It has the ability to recognize the emotional state of workers using an emotion engine. This system can optimize factory operations and reduce worker stress.

[0661] Overall system overview

[0662] This system mainly consists of a server, multiple data collection devices, an emotion engine, and a user interface. The server collects, preprocesses, and integrates data from within the factory, and analyzes it using an artificial intelligence model. The analysis results are presented visually and easily understood, and the emotion engine grasps the emotional state of workers in real time and suggests appropriate responses.

[0663] Hardware and software used

[0664] Hardware:

[0665] Various sensors in the factory (temperature sensors, humidity sensors, noise level sensors)

[0666] Worker biometric data acquisition devices (heart rate monitors, stress level measuring devices)

[0667] Audio input devices, cameras

[0668] software:

[0669] Python: Data collection and preprocessing

[0670] Pandas: Data Shaping and Processing

[0671] Scikit-learn: Building and running machine learning models

[0672] TensorFlow: Emotion Engine Implementation

[0673] Data collection and preprocessing

[0674] The server collects various environmental and biometric data in real time from sensors in the factory and biometric data acquisition devices for workers. The collected data is centralized and preprocessed using Pandas. Preprocessing involves filling in missing values, removing outliers, and normalizing text data.

[0675] Data integration and AI analysis

[0676] The pre-processed data is integrated into a coherent dataset. AI models built with Scikit-learn are then run to optimize factory operations and identify stressors. An emotion engine powered by TensorFlow analyzes workers' voices, facial expressions, and input data to recognize their emotional state in real time.

[0677] Providing insights and customizing the interface

[0678] Insights gained from the AI ​​model are delivered in real time through a user interface, including suggestions for improving work efficiency and taking breaks. The user interface can be customized to meet the needs of workers and managers, and the information provided and the interface adapt based on their emotional state.

[0679] Specific examples

[0680] For example, in a manufacturing factory, AI can identify bottlenecks on the production line from past data and suggest countermeasures. Also, when workers become stressed, AI can suggest appropriate times to take breaks, reducing the burden on the workers. This improves the efficiency of the entire factory and the happiness of workers.

[0681] Prompt Sentence Examples

[0682] "How can we suggest a break to a stressed worker?"

[0683] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0684] Step 1:

[0685] Data collection

[0686] The server collects data from various sensors in the factory and workers' biometric data acquisition devices. Input data includes temperature, humidity, noise level, heart rate, stress level, audio, and video. The server periodically obtains this data through an API. This data is first stored on the server in raw format.

[0687] Step 2:

[0688] Data Preprocessing

[0689] The server performs preprocessing on the collected raw data. Specifically, it uses Pandas to impute missing values, remove outliers, and normalize text data. By normalizing the input data and removing outliers, a dataset suitable for analysis is generated. The output data is a dataset in a clean and consistent format.

[0690] Step 3:

[0691] Data integration

[0692] The pre-processed data is then integrated into a consistent dataset by the server. Specifically, data from different data sources is matched using timestamps as a key. As a result, a single unified large-scale dataset is generated. This dataset is then used as input for subsequent AI analysis.

[0693] Step 4:

[0694] Running an AI model

[0695] The server uses the integrated dataset to run artificial intelligence models. These include a prediction model using Scikit-learn and an emotion analysis model built with TensorFlow. Specifically, it runs a classification model to identify factors that reduce work efficiency and a regression model to predict worker stress. The input data is the integrated dataset, and the output data is the prediction results and estimated emotional states.

[0696] Step 5:

[0697] Generating and delivering insights

[0698] Based on the analysis results obtained from the AI ​​model, the server generates insights and provides them through a user interface. These insights include measures to improve work efficiency and recommendations for worker breaks. Specifically, the results are displayed visually using graphs and charts. The input data is the output results from the AI ​​model, and the output data is a visually formatted insight report.

[0699] Step 6:

[0700] Emotion Engine Operation

[0701] The server uses an emotion engine to analyze the user's emotional state in real time. Specifically, it runs a TensorFlow model using audio and video data to estimate the level of stress and fatigue. The input data is audio and video data, and the output data is a tagged emotional state.

[0702] Step 7:

[0703] Interface customization

[0704] The server automatically adapts the information and interface it provides based on the user's emotional state. For example, if the user is under stress, it simplifies the information displayed and provides only the most important information. The input data is the output result from the emotion engine, and the output data is the adapted user interface.

[0705] Specific prompt examples

[0706] "How can we suggest a break to a stressed worker?"

[0707] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0708] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0709] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0710] [Third embodiment]

[0711] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0712] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0713] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0714] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0715] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0716] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0717] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0718] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0719] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0720] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0721] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0722] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0723] The present invention is a system that collects, preprocesses, and integrates data, analyzes it using artificial intelligence models, and provides insights to users. It also provides an interface that users can customize as needed. The following describes the program processing and specific examples of this system.

[0724] This system is run mainly by the server. The program processing flow is explained in detail below.

[0725] Data collection

[0726] The server collects the necessary information from multiple data sources, such as business data, financial market data, and social media data, via APIs, allowing it to collect the latest information in real time.

[0727] Data Preprocessing

[0728] The collected raw data is not suitable for analysis as it is, so the server performs preprocessing. During this process, the data is cleansed (filling in missing values, removing outliers) and formatted (normalizing text data, scaling numerical data). This generates data that is suitable for analysis.

[0729] Data Integration

[0730] The pre-processed data is then integrated by the server. Data from different data sources is linked based on key attributes (e.g., timestamp or category) to create a consistent dataset. This integration process allows for multi-dimensional insights to be gained from diverse data.

[0731] Running an AI model

[0732] The server uses the integrated data to run AI models, such as machine learning models (regression models, classification models, etc.) trained on past data to make predictions and classifications, and performs cross-validation and hyperparameter tuning to improve the accuracy of the models.

[0733] Generating and delivering insights

[0734] The insights generated from the trained AI model are updated in real time by the server and delivered to the user's device. These insights include market forecasts and business strategy suggestions. The insights are presented in a visually easy-to-understand format, allowing users to understand and use them immediately.

[0735] User Interface Customization

[0736] Users can customize the interface to suit their needs by setting specific filter conditions (e.g., time period, region, category) and selecting the data visualization format (graph, chart, table, etc.) through their terminal. The server generates the customized data accordingly and provides it in real time.

[0737] Specific examples

[0738] Market strategy formulation for small and medium-sized enterprises

[0739] Small and medium-sized business owners (users) use this system for market analysis. The server collects, preprocesses, and integrates business data and market trend data via API. It then trains a market forecasting model based on historical data and predicts market trends in real time. These forecasts are provided to managers in dashboard format, allowing them to plan promotion strategies.

[0740] Investment decision-making by individual investors

[0741] Individual investors (users) use this system to help them decide where to invest. The server obtains real-time stock market data from the financial API, normalizes and scales the data, and then integrates it. It then uses a machine learning model to predict stock prices and displays the results on a dashboard. Investors can use this information to determine the timing of buying and selling specific stocks.

[0742] In this way, the present invention provides real-time data insights tailored to various needs and assists users in their decision-making process.

[0743] The processing flow will be explained below.

[0744] Step 1:

[0745] The server collects the required data from multiple data sources, such as business data, financial market data, social media data, etc., through APIs. The server initiates the data collection process periodically or based on a trigger event.

[0746] Step 2:

[0747] The server preprocesses the collected raw data, applying data cleansing rules to fill in missing values ​​and remove outliers. For text data, it performs normalization (converting to lowercase, removing special characters), and for numerical data, it performs scaling and standardization.

[0748] Step 3:

[0749] The server integrates the pre-processed data, linking data from different data sources based on key attributes (e.g., timestamps or categories) to build a coherent dataset, systematically grouping related data points together.

[0750] Step 4:

[0751] The server trains AI models using the integrated dataset. It trains machine learning and deep learning models based on historical data to build models for prediction and classification. During this process, it performs cross-validation to evaluate the accuracy of the models and tunes hyperparameters as needed.

[0752] Step 5:

[0753] The server analyzes real-time data using trained AI models to generate insights, including market trend predictions and performance assessments, which are then delivered to users in the form of appropriate dashboards and alerts.

[0754] Step 6:

[0755] Users can view information using the provided dashboard. Users can customize the interface by setting filter conditions such as a specific period, region, category, etc. The server generates customized data based on the user's request and provides it in real time.

[0756] Step 7:

[0757] Through the device, users can make decisions based on the generated insights and customized reports. For example, small business owners can decide on promotion strategies based on market trends, and individual investors can decide when to buy or sell based on stock price forecasts.

[0758] Through the above processing steps, the system efficiently executes a series of processes from data collection to analysis, and generation and provision of insights, thereby supporting user decision-making.

[0759] Example 1

[0760] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0761] In today's information-overloaded environment, it is difficult to quickly and accurately collect necessary information from diverse data sources and analyze it to gain useful insights. Furthermore, the collected data is often incomplete and unsuitable for analysis as is. Furthermore, there is a lack of systems that can effectively analyze integrated data and provide it in a customizable format that meets user needs. This creates significant barriers for companies and individuals to make fast and accurate decisions.

[0762] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0763] In this invention, the server includes means for collecting data, means for preprocessing the collected data, and means for integrating the preprocessed data, which allows the server to obtain information from multiple data sources via API, impute missing values, remove outliers, normalize text data, scale numeric data, and link data from different data sources based on key attributes.

[0764] The server further includes means for running an artificial intelligence model using the integrated data, means for providing insights derived from the artificial intelligence model, and means for customizing a user interface that allows for training the machine learning model, cross-validation and hyperparameter tuning, real-time updates of the generated insights, providing them in a visually understandable format, setting specific filter conditions, and selecting data visualization formats.

[0765] "Data collection" is the process of gathering necessary information from multiple sources.

[0766] "API" stands for Application Program Interface, a standardized means of exchanging data between different software applications.

[0767] "Data preprocessing" refers to a series of processes for converting collected raw data into a form suitable for analysis, including imputing missing values, removing outliers, normalizing text data, and scaling numerical data.

[0768] "Data integration" is the process of combining pre-processed data from different data sources into a coherent dataset, which involves combining data based on key attributes (e.g., timestamp or category).

[0769] An "artificial intelligence model" refers to an analytical method that uses algorithms such as machine learning and deep learning to generate insights and predictions from data.

[0770] "Cross-validation" is a statistical technique for evaluating the performance of a model by dividing a dataset into multiple parts.

[0771] "Hyperparameter tuning" is the process of optimizing the hyperparameters of a machine learning model in order to maximize the model's performance.

[0772] "Insights" are useful new information or insights gained from analyzing data that help users make better decisions.

[0773] "User interface" refers to the screens and operating methods that users use to interact with the system, allowing them to easily access information and check analysis results.

[0774] "Customization" refers to users changing system settings and adjusting the way information is displayed to suit their own needs.

[0775] This invention is a system that collects, preprocesses, integrates, and analyzes data using artificial intelligence models, and provides insights to users. It also has an interface that users can customize as needed. The following describes the program processing and specific examples of this system.

[0776] This system is run primarily by a server, which is often built using programming languages ​​such as Python or JavaScript. Below, we will explain the main processes and the specific software and hardware used for them.

[0777] Data collection

[0778] The server collects the necessary information from multiple data sources, such as business data, financial market data, and social media data, via APIs. This can be done using the Python requests library, which allows for the collection of the latest information in real time.

[0779] Data Preprocessing

[0780] The collected raw data is not suitable for analysis as it is, so the server performs preprocessing. During this process, the data is cleansed (filling in missing values, removing outliers) and formatted (normalizing text data, scaling numerical data). Here, it is recommended to use the Python pandas library.

[0781] Data Integration

[0782] The pre-processed data is then integrated by the server. Data from different data sources is linked based on key attributes (e.g. timestamp or category) to create a consistent dataset. This integration process can be performed using the pandas merge method.

[0783] Running an AI model

[0784] Using the combined data, the server runs AI models, such as machine learning models (regression models, classification models, etc.) trained on past data to perform predictions and classifications. Here, the scikit-learn library is used to build the models and perform cross-validation and hyperparameter tuning.

[0785] Generating and delivering insights

[0786] The insights generated from the trained AI model are updated in real time by the server and delivered to the user's device, including market forecasts and business strategy suggestions, and are presented in a visually understandable format using visualization libraries such as Plotly and Matplotlib.

[0787] User Interface Customization

[0788] Users can customize the interface to suit their needs by setting specific filter conditions (e.g., time period, region, category) and selecting the data visualization format (graph, chart, table, etc.) through their terminal. The server generates the customized data accordingly and provides it in real time.

[0789] Specific examples

[0790] Market strategy formulation for small and medium-sized enterprises

[0791] Small and medium-sized business owners (users) use this system for market analysis. The server collects, preprocesses, and integrates business data and market trend data via API. It then trains a market forecasting model based on historical data and predicts market trends in real time. These forecasts are provided to managers in dashboard format, allowing them to plan promotion strategies.

[0792] Investment decision-making by individual investors

[0793] Individual investors (users) use this system to help them decide where to invest. The server obtains real-time stock market data from the financial API, normalizes and scales the data, and then integrates it. It then uses a machine learning model to predict stock prices and displays the results on a dashboard. Investors can use this information to determine the timing of buying and selling specific stocks.

[0794] Prompt Sentence Examples

[0795] "Collect the latest business and market trend data and train predictive models to help small and medium-sized businesses with their market strategies."

[0796] "Use real-time stock price data to predict stock prices for a specific stock for the next week and display the results visually."

[0797] In this way, the present invention provides real-time data insights tailored to various needs and assists users in their decision-making process.

[0798] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0799] Step 1: Data collection

[0800] The server retrieves business, market, and social media data from each data source based on a pre-configured list of APIs. Specifically, the server uses the Python requests library to send HTTP requests to each data source. Each request includes an API key as authentication information. The server uses the API endpoint and authentication information as input and stores the raw data in JSON format in a local database as output.

[0801] Step 2: Data Preprocessing

[0802] The server preprocesses the collected raw data. This involves first converting it into a data frame using the pandas library. Then, it uses the fillna method to impute missing values ​​and statistical methods (e.g., standard deviation and IQR) to remove outliers. Text data is normalized and numerical data is scaled. The raw data frame is used as input, and clean, unified data is obtained as output.

[0803] Step 3: Data Integration

[0804] The server merges the preprocessed data from multiple data sources, using the pandas merge method to combine datasets from different data sources based on key attributes (timestamp or category), using multiple preprocessed data frames as input and producing a merged dataset as output.

[0805] Step 4: Run the AI ​​model

[0806] The server builds and runs machine learning models based on the merged dataset. First, it trains regression and classification models using the scikit-learn library. Then, it evaluates the accuracy of the models and optimizes their hyperparameters using GridSearchCV and RandomizedSearchCV for cross-validation. It uses the merged dataset as input and generates a trained model and its prediction results as output.

[0807] Step 5: Generate and deliver insights

[0808] The server generates useful insights based on the predictions and analysis results obtained from the trained AI model. Specifically, it uses visualization libraries such as Plotly and Matplotlib to display the results in a user-friendly format. It uses the predictions and analysis results as input, generates visualized graphs and charts as output, and provides them to the user's device.

[0809] Step 6: Customizing the User Interface

[0810] Users customize the interface through their devices by setting specific filter conditions (e.g., time period, region, category) and selecting the data visualization format (graph, chart, table, etc.). The server generates the customized data accordingly and serves it in real time. It uses the user settings as input and generates the customized data and visualization information as output.

[0811] Through this series of processing steps, the server collects information from various data sources, preprocesses, integrates, runs AI models, generates insights, and provides the information to users through a customizable interface.

[0812] (Application example 1)

[0813] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0814] Autonomous vehicles require accurate preprocessing and integration of data to collect various sensor data in real time and ensure safe and efficient operation. However, current systems often lack sufficient data imputation, outlier removal, and format standardization, resulting in inaccurate data analysis. Furthermore, there is a lack of means to properly link and analyze sensor data, making it difficult to provide timely insights.

[0815] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0816] In this invention, the server includes means for collecting data from multiple data transmission devices, means for imputing missing values, removing outliers, and standardizing the format of the collected data, means for integrating the preprocessed data into a consistent format, means for running a classification model using the integrated data, means for providing insights gained from the model, and means for customizing an interface based on user requests, thereby enabling real-time anomaly detection and safe route provision.

[0817] A "data transmission device" is a device that collects data from multiple sensors and data collection devices and transmits it to a server.

[0818] "Missing value imputation" is a process of filling in missing data values ​​with average values, estimated values, etc.

[0819] "Outlier removal" is the process of detecting and removing or correcting unusual values ​​in a data set.

[0820] "Format unification" is the process of converting data provided in different formats into a consistent format.

[0821] An "artificial intelligence model" is a mathematical model that uses machine learning algorithms to analyze data and make predictions and classifications.

[0822] "Insight" refers to useful knowledge or information derived from analytical results or analysis obtained from artificial intelligence models.

[0823] "User interface customization" is a function for changing the display content and operation method to meet the user's requirements.

[0824] "Anomaly detection" refers to detecting unusual patterns or values ​​in data.

[0825] A "safe route" is a route along which an autonomous vehicle is predicted to travel safely.

[0826] "Sensor data" refers to real-time information obtained from various sensors (LiDAR, cameras, GPS, etc.) installed in autonomous vehicles.

[0827] "Consistent format" refers to data format expressed in a unified format and scale.

[0828] A "classification model" is a machine learning model for classifying input data into specific categories or classes.

[0829] The present invention is a system that collects, preprocesses, and integrates sensor data from autonomous vehicles in real time, and utilizes artificial intelligence models to determine safe driving routes and detect anomalies. The system operates centrally on a server, and uses the necessary hardware and software to collect, analyze, and provide insights into the data. A specific embodiment of the system is described below.

[0830] Hardware and Software Configuration

[0831] The hardware used in this system includes multiple sensor devices (LiDAR, cameras, GPS, etc.) and a server. The sensor devices are installed in autonomous vehicles and collect data in real time. The server receives the sensor data and performs subsequent data processing and analysis.

[0832] The software used includes Python, Scikit-learn, the Requests library, and Matplotlib. Python is used as the main programming language for this system, and Scikit-learn is used to run the artificial intelligence model (classification model). The Requests library is used for API calls to collect data from sensor devices, and Matplotlib is used for visualization in the user interface.

[0833] Data collection

[0834] The server collects the necessary sensor data from multiple data transmitters in real time. This data collection is done via the API of each sensor device. For example, data is collected from URLs such as "http: / / sensor1.api" and "http: / / sensor2.api."

[0835] Data Preprocessing

[0836] The collected sensor data is not suitable for analysis as is, so the server performs preprocessing on the data. Preprocessing includes filling in missing values, removing outliers, and standardizing the format. Missing values ​​are filled in using the average value or other methods, and outliers are removed using the 3-sigma method. In addition, the data format is standardized by scaling the numerical data, etc.

[0837] Data Integration

[0838] The pre-processed data is then integrated into a consistent format by the server. Data collected from different sources is linked based on time series attributes. This integration process creates a unified data set that can be analyzed.

[0839] Running artificial intelligence models

[0840] The server runs an artificial intelligence model (classification model) using the integrated data. The model analyzes the data using a random forest classifier to identify safe routes and detect anomalies. Model training and prediction includes cross-validation and hyperparameter tuning.

[0841] Providing insights

[0842] Insights gained from the trained AI model are provided to users in real time, such as a safe route index or anomaly detection results, which are displayed in a dashboard format that allows users (fleet managers and engineers) to intuitively understand them.

[0843] User Interface Customization

[0844] Users can customize the interface to suit their needs, for example by setting filter conditions to highlight specific sensor data and selecting visualization formats such as graphs and charts, providing users with fast and accurate information to support real-time decision-making.

[0845] Specific examples

[0846] For example, let's assume that an autonomous vehicle has the following route data. Data such as obstacles, road gradients, and weather conditions is acquired every second via a sensor API and analyzed in real time. This allows the vehicle to detect anomalies that occur during operation and propose safe routes.

[0847] Prompt Sentence Examples

[0848] "Implement a system that analyzes sensor data from an autonomous vehicle to determine safe routes and detect anomalies. Collect each sensor data using an API, and write a prompt that includes preprocessing, data integration, prediction using an AI model, providing insights to the user, and customizing the interface. The AI ​​model used is a random forest classifier. Specifically, include real-time data collection from the sensor API, data preprocessing, and the ability to visualize insights."

[0849] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0850] Step 1:

[0851] Sensor data collection

[0852] The server collects data in real time from multiple data transmitters (sensors). Specifically, it sends an HTTP request to the API of each sensor device (for example, "http: / / sensor1.api" or "http: / / sensor2.api") to obtain sensor data. The input is the API endpoint of each sensor, and the output is the collected raw data.

[0853] Step 2:

[0854] Data Preprocessing

[0855] The server performs preprocessing on the collected raw data. The input is the collected raw data, and missing values ​​are filled in using the average value or other methods, and outliers are removed using the 3-sigma method. The server also scales the numerical data to unify the data format. The output is preprocessed, clean data.

[0856] Step 3:

[0857] Data integration

[0858] The server aggregates the pre-processed data into a consistent format. The input is the pre-processed data, and the different sensor data are linked based on time series attributes. The output is an integrated dataset.

[0859] Step 4:

[0860] Running artificial intelligence models

[0861] The server runs an artificial intelligence model (a random forest classification model) using the integrated data. The input is the integrated dataset, and the model is trained after cross-validation and hyperparameter tuning. The output is predictions for safe routes and anomaly detection.

[0862] Step 5:

[0863] Providing insights

[0864] The server generates insights based on the training and predicted results and provides them to the user. The input is the prediction results from the AI ​​model, and the visual display is a safe route index and anomaly detection index. The output is a visual insight in the form of a dashboard for the user.

[0865] Step 6:

[0866] User Interface Customization

[0867] Users can customize the interface to suit their needs: the input is the customization options set by the user (e.g., filter criteria for specific sensor data), the server generates the corresponding display, and the output is a customized dashboard delivered to the user in real time.

[0868] This enables the server to collect, preprocess, and integrate a series of sensor data, run AI models, provide insights, and customize interfaces to support the safe and efficient operation of autonomous vehicles.

[0869] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0870] The present invention is a system that collects, preprocesses, and integrates data, analyzes it using an artificial intelligence model, and provides the resulting insights to the user. Furthermore, it is equipped with an emotion engine that recognizes the user's emotions, allowing it to customize the information and interface provided based on the user's emotional state. Below, we will explain the program processing and specific examples of this system.

[0871] This system is run mainly by the server. The program processing flow is explained in detail below.

[0872] Data collection

[0873] The server collects the required data from multiple data sources, such as business data, financial market data, social media data, etc., through APIs. The server initiates the data collection process periodically or based on a trigger event.

[0874] Data Preprocessing

[0875] The collected raw data is not suitable for analysis as it is, so the server performs preprocessing. During this process, the data is cleansed (filling in missing values, removing outliers) and formatted (normalizing text data, scaling numerical data). This generates data that is suitable for analysis.

[0876] Data Integration

[0877] The pre-processed data is then integrated by the server. Data from different data sources is linked based on key attributes (e.g., timestamp or category) to create a consistent dataset. This integration process allows for multi-dimensional insights to be gained from diverse data.

[0878] Running an AI model

[0879] The server uses the integrated data to run AI models, such as machine learning models (regression models, classification models, etc.) trained on past data to make predictions and classifications, and performs cross-validation and hyperparameter tuning to improve the accuracy of the models.

[0880] Generating and delivering insights

[0881] The insights generated from the trained AI model are updated in real time by the server and delivered to the user's device. These insights include market forecasts and business strategy suggestions. The insights are presented in a visually easy-to-understand format, allowing users to understand and use them immediately.

[0882] Emotion Engine Operation

[0883] The emotion engine analyzes the user's voice, facial expressions, and input data to recognize their emotional state. The server automatically adapts the information and interface it provides based on this emotional data. For example, if the user is feeling stressed, it will reduce the amount of information displayed or limit the information provided to the most important ones.

[0884] User Interface Customization

[0885] Users can customize the interface to suit their needs by setting specific filter conditions (e.g., time period, region, category) and selecting the data visualization format (graph, chart, table, etc.) through their terminal. The server generates the customized data accordingly and provides it in real time.

[0886] Specific examples

[0887] Market strategy formulation for small and medium-sized enterprises

[0888] Small and medium-sized business owners (users) use this system for market analysis. The server collects, preprocesses, and integrates business and market trend data via API. It then trains a market forecasting model based on historical data to predict market trends in real time. These forecasts are provided to the owner in dashboard format, and if the emotion engine detects stress in the owner, it will simplify the information display to improve usability.

[0889] Investment decision-making by individual investors

[0890] Individual investors (users) use this system to make investment decisions. The server obtains real-time stock market data from a financial API, normalizes and scales the data, and then integrates it. It then uses a machine learning model to predict stock prices and displays the results on a dashboard. The sentiment engine analyzes the investor's emotional state and, if high interest or concern is detected, provides additional information or alerts accordingly.

[0891] As such, the present invention is a system that provides real-time data insights and emotion recognition functions that meet a variety of needs, and provides powerful support for users' decision-making processes.

[0892] The processing flow will be explained below.

[0893] Step 1:

[0894] The server collects the required data from multiple data sources, such as business data, financial market data, social media data, etc., through APIs. The server initiates the data collection process periodically or based on a trigger event.

[0895] Step 2:

[0896] The server preprocesses the collected raw data, applying data cleansing rules to fill in missing values ​​and remove outliers. For text data, it performs normalization (converting to lowercase, removing special characters), and for numerical data, it performs scaling and standardization.

[0897] Step 3:

[0898] The server integrates the pre-processed data, linking data from different data sources based on key attributes (e.g., timestamps or categories) to build a coherent dataset, systematically grouping related data points together.

[0899] Step 4:

[0900] The server trains AI models using the integrated dataset. It trains machine learning and deep learning models based on historical data to build models for prediction and classification. During this process, it performs cross-validation to evaluate the accuracy of the models and tunes hyperparameters as needed.

[0901] Step 5:

[0902] The server analyzes real-time data using trained AI models to generate insights, including market trend predictions and performance assessments, which are then delivered to users in the form of appropriate dashboards and alerts.

[0903] Step 6:

[0904] The emotion engine analyzes the user's voice, facial expressions, and input data to recognize the user's emotional state. For example, it obtains facial expression data from the user's webcam and applies emotion recognition algorithms to determine the user's current emotion (e.g., joy, sadness, anger, etc.). It also analyzes emotions from voice input.

[0905] Step 7:

[0906] The server automatically adapts the information and interface it provides based on the user's emotional data recognized by the emotion engine. For example, if it determines that the user is feeling stressed, it reduces the amount of information displayed and highlights only the important information. If the user is excited, it is set to display detailed data analysis results.

[0907] Step 8:

[0908] Users can view information using the provided dashboard, and customize the interface by setting filter criteria such as specific time periods, regions, and categories.

[0909] Step 9:

[0910] Through the device, users can make decisions based on the generated insights and customized reports. For example, small business owners can decide on promotion strategies based on market trends, and individual investors can decide when to buy or sell based on stock price forecasts.

[0911] Through the above processing steps, this system collects and analyzes data, generates and provides insights, and also provides multidimensional support that includes emotion recognition, thereby efficiently and effectively assisting users in their decision-making process.

[0912] Example 2

[0913] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0914] In conventional information collection and analysis systems, data preprocessing and integration are cumbersome, and advanced expertise is required to obtain highly accurate insights. Furthermore, due to a lack of mechanisms for recognizing the user's emotional state and adapting the information and interface provided, the user interface cannot be fully customized, making it difficult to improve usability. Our goal is to solve these problems and realize an efficient and flexible data analysis system.

[0915] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0916] In this invention, the server includes a means for collecting data, a means for preprocessing the collected data, and a means for integrating the preprocessed data, thereby enabling efficient and highly accurate data analysis and the provision of insights.

[0917] The server further includes means for executing an artificial intelligence model using the integrated data, means for providing insights obtained from the artificial intelligence model, means for recognizing the user's emotional state and adapting the information and interface to be provided based on the emotional state, and means for customizing the user interface, thereby enabling appropriate information to be provided and the interface to be customized according to the user's emotions, thereby improving usability.

[0918] "Means of collecting data" refers to the function of obtaining necessary data from multiple data sources using an interface such as an API.

[0919] "Means for preprocessing collected data" refers to functions for cleansing collected data, filling in missing values, removing outliers, and standardizing data formats (standardization, scaling, etc.).

[0920] A "means for integrating pre-processed data" is a function that combines pre-processed data into a coherent data set based on key attributes (e.g., timestamps).

[0921] "Means for running artificial intelligence models using the integrated data" refers to the ability to use trained machine learning algorithms to analyze the integrated data and perform tasks such as prediction and classification.

[0922] "Means for providing insights obtained from an AI model" refers to a function that provides users with insights obtained from the analysis results of an AI model in a visually easy-to-understand format (graphs, charts, etc.).

[0923] "Means for recognizing the user's emotional state and adapting the information and interface provided based on that" refers to a function that analyzes the user's voice, facial expressions, input data, etc. to identify their emotional state, and changes the way information is displayed and the interface according to that state.

[0924] "Means for customizing the user interface" refers to the ability to select and change the filter conditions and visualization formats (graphs, charts, tables, etc.) of the interface according to the user's needs.

[0925] The following is a detailed description of the mode for carrying out the invention. The invention consists of a system for data collection, pre-processing, integration, analysis by artificial intelligence models, providing insights, recognizing user emotions, and customizing the interface. The system mainly consists of three elements: a server, a terminal, and a user.

[0926] Data collection

[0927] The server retrieves the necessary data from multiple data sources through APIs. Data sources include business data, financial market data, social media data, etc. The server initiates the data collection process based on a regular schedule or specific trigger events. For example, the server accesses a financial API every 10 minutes to retrieve the latest stock price data.

[0928] Data Preprocessing

[0929] The collected raw data is preprocessed by the server. This process involves cleansing the data, filling in missing values, removing outliers, normalizing text data, and scaling numerical data. For example, abnormally high trading volumes are detected and removed from the collected stock price data. Also, all company names are standardized to lowercase.

[0930] Data Integration

[0931] The pre-processed data is then integrated by the server. Data from different data sources is linked based on key attributes (e.g., timestamps) to create a consistent dataset, enabling multi-dimensional insights to be gained. The integrated data is then stored in a relational database.

[0932] Running artificial intelligence models

[0933] The server runs an artificial intelligence model using the integrated data. A machine learning algorithm (e.g., a regression model or a classification model) is used. The server performs cross-validation and hyperparameter tuning to improve the model's accuracy. For example, the server trains a regression model to predict the next day's stock price from the training dataset.

[0934] Generating and delivering insights

[0935] The server analyzes the predictions and classifications generated by the trained AI model and generates these insights in a user-friendly visual format (e.g., graphs or charts). These insights are updated in real time and provided to the user's device. For example, stock price predictions may be generated as line graphs and displayed in real time on the user's device.

[0936] Emotion Engine Operation

[0937] The emotion engine analyzes the user's voice, facial expressions, and input data to recognize the user's emotional state. The server then adapts the information and interface it provides based on this emotional data. For example, if the user is feeling stressed, it reduces the amount of information displayed and focuses on providing only the most important information.

[0938] User Interface Customization

[0939] Users can customize the interface to suit their needs by setting specific filter conditions (e.g., time period, region, category) and selecting the data visualization format (graph, chart, table, etc.) through their terminal. The server generates the customized data accordingly and provides it in real time.

[0940] Specific examples

[0941] Example of market strategy formulation for small and medium-sized enterprises

[0942] Small and medium-sized business owners (users) use this system for market analysis. The server collects, preprocesses, and integrates business and market trend data via API. It then trains a market forecasting model based on historical data to predict market trends in real time. These forecasts are provided to the owner in dashboard format, and if the emotion engine detects stress in the owner, it can simplify the information display to improve usability.

[0943] Examples of investment decisions made by individual investors

[0944] Individual investors (users) use this system to make investment decisions. The server obtains real-time stock market data from financial APIs, normalizes and scales the data, and then integrates it. It then uses a machine learning model to predict stock prices and displays the results on a dashboard. The sentiment engine analyzes the investor's emotional state and, if high interest or concern is detected, provides additional information or alerts accordingly.

[0945] Prompt Sentence Examples

[0946] "Create an AI model to predict upcoming market trends based on an integrated data set for market analysis of small and medium-sized enterprises."

[0947] In this way, the present invention is a system that provides real-time data insights and emotion recognition capabilities to meet various needs and assist users in their decision-making process.

[0948] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0949] Step 1:

[0950] The server collects data from multiple data sources.

[0951] Input: APIs for business data, financial market data, social media data, etc.

[0952] What it does: Every 10 minutes, the server accesses a financial API to retrieve the latest stock price data, including company names, stock prices, and trading volumes.

[0953] Output: raw collected data

[0954] Step 2:

[0955] The server pre-processes the collected raw data.

[0956] Input: raw data collected

[0957] Specific behavior:

[0958] Missing value imputation: The server uses the previous data to impute missing parts.

[0959] Outlier Removal: Statistical methods are used to detect and remove abnormally high trading volumes.

[0960] Text data normalization: The server normalizes all company names to lowercase.

[0961] Scaling of numerical data: Standardization (mean 0, standard deviation 1) is performed.

[0962] Output: Preprocessed data

[0963] Step 3:

[0964] The server aggregates the pre-processed data.

[0965] Input: Preprocessed data

[0966] What it does: The server combines data from different data sources based on key attributes (e.g., timestamps). The combined data is stored in a relational database.

[0967] Output: A consolidated dataset

[0968] Step 4:

[0969] The server runs an artificial intelligence model using the integrated data.

[0970] Input: Integrated dataset

[0971] Specific behavior:

[0972] Analyze using machine learning algorithms (e.g., regression models, classification models).

[0973] Improve the accuracy of the model by performing cross-validation and hyperparameter tuning.

[0974] Output: Prediction results and classification results

[0975] Step 5:

[0976] The server provides insights derived from artificial intelligence models.

[0977] Input: Prediction results and classification results

[0978] Specific operation: The server generates insights in a visually easy-to-understand format (e.g., graphs, charts) and provides them to the user's device in real time.

[0979] Output: Visualized insights (e.g. line graphs and dashboards)

[0980] Step 6:

[0981] The emotion engine recognizes the user's emotional state and adapts information and interfaces accordingly.

[0982] Input: User's voice, facial expressions, input data

[0983] Specific operation: The emotion engine uses the analysis results to reduce the amount of information displayed if the user is feeling stressed, and provides only important information.

[0984] Output: Adapted information and interface

[0985] Step 7:

[0986] The user customizes the interface.

[0987] Input: User filter criteria (e.g., time period, region, category) and visualization format (graph, chart, table, etc.)

[0988] Specific operation: The server generates customized data based on the conditions specified by the user and provides it in real time.

[0989] Output: Customized data and interface

[0990] (Application example 2)

[0991] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0992] Modern manufacturing plants require the management and analysis of complex data, making it important to optimize the work environment by taking into account the emotional state of workers. However, current systems struggle to efficiently integrate and analyze this data and provide appropriate insights in real time. Furthermore, interfaces are rarely adapted based on the emotional state of workers, resulting in problems such as reduced work efficiency and increased worker stress. To address these issues, a system capable of integrating data and providing insights that take into account emotional states is needed.

[0993] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0994] In this invention, the server includes means for collecting data, means for preprocessing the collected data, means for integrating the preprocessed data, means for running an artificial intelligence model using the integrated data, means for providing insights obtained from the artificial intelligence model, means for customizing a user interface, means for recognizing a user's emotional state using an emotion engine, means for adapting information and an interface to be provided based on the user's emotional state, means for collecting and analyzing factory environment data and worker biometric data, and means for providing insights that optimize the work environment and worker conditions. This makes it possible to efficiently analyze data within a factory and provide optimal insights in real time while taking into account the emotional states of workers.

[0995] A "data collection tool" is a process or device for automatically acquiring data from multiple data sources.

[0996] "Data preprocessing means" refers to processes and methods used to prepare collected raw data in a format suitable for analysis. Specifically, this involves filling in missing values, removing outliers, and normalizing the data.

[0997] A "data integration procedure" is a process or method for combining pre-processed data into a single coherent data set.

[0998] An "artificial intelligence model execution means" is a process or device that uses integrated data to execute an AI model using methods such as machine learning or deep learning to make predictions and classifications.

[0999] An "insight providing means" is a process or method for presenting the analysis results and prediction results obtained by an artificial intelligence model in a format that is easy for users to understand.

[1000] A "user interface customization means" is a process or method for tailoring the displayed information or interface to suit the needs and requirements of the user.

[1001] An "emotion engine" is a system or software that analyzes a user's voice, facial expressions, and input data to recognize the user's emotional state.

[1002] "Factory environment data" refers to data related to the environment within a factory, such as temperature, humidity, and noise levels.

[1003] "Worker's biometric data" refers to data that indicates the physical condition of a factory worker, such as their heart rate and stress level.

[1004] The "optimization insight providing means" is a process or method for using analyzed data to provide insights and suggestions necessary for optimizing factory operations and work environments in real time.

[1005] This invention is a system that collects, pre-processes, integrates, and analyzes data in a factory environment, and provides insights in real time. It has the ability to recognize the emotional state of workers using an emotion engine. This system can optimize factory operations and reduce worker stress.

[1006] Overall system overview

[1007] This system mainly consists of a server, multiple data collection devices, an emotion engine, and a user interface. The server collects, preprocesses, and integrates data from within the factory, and analyzes it using an artificial intelligence model. The analysis results are presented visually and easily understood, and the emotion engine grasps the emotional state of workers in real time and suggests appropriate responses.

[1008] Hardware and software used

[1009] Hardware:

[1010] Various sensors in the factory (temperature sensors, humidity sensors, noise level sensors)

[1011] Worker biometric data acquisition devices (heart rate monitors, stress level measuring devices)

[1012] Audio input devices, cameras

[1013] software:

[1014] Python: Data collection and preprocessing

[1015] Pandas: Data Shaping and Processing

[1016] Scikit-learn: Building and running machine learning models

[1017] TensorFlow: Emotion Engine Implementation

[1018] Data collection and preprocessing

[1019] The server collects various environmental and biometric data in real time from sensors in the factory and biometric data acquisition devices for workers. The collected data is centralized and preprocessed using Pandas. Preprocessing involves filling in missing values, removing outliers, and normalizing text data.

[1020] Data integration and AI analysis

[1021] The pre-processed data is integrated into a coherent dataset. AI models built with Scikit-learn are then run to optimize factory operations and identify stressors. An emotion engine powered by TensorFlow analyzes workers' voices, facial expressions, and input data to recognize their emotional state in real time.

[1022] Providing insights and customizing the interface

[1023] Insights gained from the AI ​​model are delivered in real time through a user interface, including suggestions for improving work efficiency and taking breaks. The user interface can be customized to meet the needs of workers and managers, and the information provided and the interface adapt based on their emotional state.

[1024] Specific examples

[1025] For example, in a manufacturing factory, AI can identify bottlenecks on the production line from past data and suggest countermeasures. Also, when workers become stressed, AI can suggest appropriate times to take breaks, reducing the burden on the workers. This improves the efficiency of the entire factory and the happiness of workers.

[1026] Prompt Sentence Examples

[1027] "How can we suggest a break to a stressed worker?"

[1028] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1029] Step 1:

[1030] Data collection

[1031] The server collects data from various sensors in the factory and workers' biometric data acquisition devices. Input data includes temperature, humidity, noise level, heart rate, stress level, audio, and video. The server periodically obtains this data through an API. This data is first stored on the server in raw format.

[1032] Step 2:

[1033] Data Preprocessing

[1034] The server performs preprocessing on the collected raw data. Specifically, it uses Pandas to impute missing values, remove outliers, and normalize text data. By normalizing the input data and removing outliers, a dataset suitable for analysis is generated. The output data is a dataset in a clean and consistent format.

[1035] Step 3:

[1036] Data integration

[1037] The pre-processed data is then integrated into a consistent dataset by the server. Specifically, data from different data sources is matched using timestamps as a key. As a result, a single unified large-scale dataset is generated. This dataset is then used as input for subsequent AI analysis.

[1038] Step 4:

[1039] Running an AI model

[1040] The server uses the integrated dataset to run artificial intelligence models. These include a prediction model using Scikit-learn and an emotion analysis model built with TensorFlow. Specifically, it runs a classification model to identify factors that reduce work efficiency and a regression model to predict worker stress. The input data is the integrated dataset, and the output data is the prediction results and estimated emotional states.

[1041] Step 5:

[1042] Generating and delivering insights

[1043] Based on the analysis results obtained from the AI ​​model, the server generates insights and provides them through a user interface. These insights include measures to improve work efficiency and recommendations for worker breaks. Specifically, the results are displayed visually using graphs and charts. The input data is the output results from the AI ​​model, and the output data is a visually formatted insight report.

[1044] Step 6:

[1045] Emotion Engine Operation

[1046] The server uses an emotion engine to analyze the user's emotional state in real time. Specifically, it runs a TensorFlow model using audio and video data to estimate the level of stress and fatigue. The input data is audio and video data, and the output data is a tagged emotional state.

[1047] Step 7:

[1048] Interface customization

[1049] The server automatically adapts the information and interface it provides based on the user's emotional state. For example, if the user is under stress, it simplifies the information displayed and provides only the most important information. The input data is the output result from the emotion engine, and the output data is the adapted user interface.

[1050] Specific prompt examples

[1051] "How can we suggest a break to a stressed worker?"

[1052] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1053] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1054] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1055] [Fourth embodiment]

[1056] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1057] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1058] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1059] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1060] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1061] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1062] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1063] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1064] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1065] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1066] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1067] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1068] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1069] The present invention is a system that collects, preprocesses, and integrates data, analyzes it using artificial intelligence models, and provides insights to users. It also provides an interface that users can customize as needed. The following describes the program processing and specific examples of this system.

[1070] This system is run mainly by the server. The program processing flow is explained in detail below.

[1071] Data collection

[1072] The server collects the necessary information from multiple data sources, such as business data, financial market data, and social media data, via APIs, allowing it to collect the latest information in real time.

[1073] Data Preprocessing

[1074] The collected raw data is not suitable for analysis as it is, so the server performs preprocessing. During this process, the data is cleansed (filling in missing values, removing outliers) and formatted (normalizing text data, scaling numerical data). This generates data that is suitable for analysis.

[1075] Data Integration

[1076] The pre-processed data is then integrated by the server. Data from different data sources is linked based on key attributes (e.g., timestamp or category) to create a consistent dataset. This integration process allows for multi-dimensional insights to be gained from diverse data.

[1077] Running an AI model

[1078] The server uses the integrated data to run AI models, such as machine learning models (regression models, classification models, etc.) trained on past data to make predictions and classifications, and performs cross-validation and hyperparameter tuning to improve the accuracy of the models.

[1079] Generating and delivering insights

[1080] The insights generated from the trained AI model are updated in real time by the server and delivered to the user's device. These insights include market forecasts and business strategy suggestions. The insights are presented in a visually easy-to-understand format, allowing users to understand and use them immediately.

[1081] User Interface Customization

[1082] Users can customize the interface to suit their needs by setting specific filter conditions (e.g., time period, region, category) and selecting the data visualization format (graph, chart, table, etc.) through their terminal. The server generates the customized data accordingly and provides it in real time.

[1083] Specific examples

[1084] Market strategy formulation for small and medium-sized enterprises

[1085] Small and medium-sized business owners (users) use this system for market analysis. The server collects, preprocesses, and integrates business data and market trend data via API. It then trains a market forecasting model based on historical data and predicts market trends in real time. These forecasts are provided to managers in dashboard format, allowing them to plan promotion strategies.

[1086] Investment decision-making by individual investors

[1087] Individual investors (users) use this system to help them decide where to invest. The server obtains real-time stock market data from the financial API, normalizes and scales the data, and then integrates it. It then uses a machine learning model to predict stock prices and displays the results on a dashboard. Investors can use this information to determine the timing of buying and selling specific stocks.

[1088] In this way, the present invention provides real-time data insights tailored to various needs and assists users in their decision-making process.

[1089] The processing flow will be explained below.

[1090] Step 1:

[1091] The server collects the required data from multiple data sources, such as business data, financial market data, social media data, etc., through APIs. The server initiates the data collection process periodically or based on a trigger event.

[1092] Step 2:

[1093] The server preprocesses the collected raw data, applying data cleansing rules to fill in missing values ​​and remove outliers. For text data, it performs normalization (converting to lowercase, removing special characters), and for numerical data, it performs scaling and standardization.

[1094] Step 3:

[1095] The server integrates the pre-processed data, linking data from different data sources based on key attributes (e.g., timestamps or categories) to build a coherent dataset, systematically grouping related data points together.

[1096] Step 4:

[1097] The server trains AI models using the integrated dataset. It trains machine learning and deep learning models based on historical data to build models for prediction and classification. During this process, it performs cross-validation to evaluate the accuracy of the models and tunes hyperparameters as needed.

[1098] Step 5:

[1099] The server analyzes real-time data using trained AI models to generate insights, including market trend predictions and performance assessments, which are then delivered to users in the form of appropriate dashboards and alerts.

[1100] Step 6:

[1101] Users can view information using the provided dashboard. Users can customize the interface by setting filter conditions such as a specific period, region, category, etc. The server generates customized data based on the user's request and provides it in real time.

[1102] Step 7:

[1103] Through the device, users can make decisions based on the generated insights and customized reports. For example, small business owners can decide on promotion strategies based on market trends, and individual investors can decide when to buy or sell based on stock price forecasts.

[1104] Through the above processing steps, the system efficiently executes a series of processes from data collection to analysis, and generation and provision of insights, thereby supporting user decision-making.

[1105] Example 1

[1106] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1107] In today's information-overloaded environment, it is difficult to quickly and accurately collect necessary information from diverse data sources and analyze it to gain useful insights. Furthermore, the collected data is often incomplete and unsuitable for analysis as is. Furthermore, there is a lack of systems that can effectively analyze integrated data and provide it in a customizable format that meets user needs. This creates significant barriers for companies and individuals to make fast and accurate decisions.

[1108] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1109] In this invention, the server includes means for collecting data, means for preprocessing the collected data, and means for integrating the preprocessed data, which allows the server to obtain information from multiple data sources via API, impute missing values, remove outliers, normalize text data, scale numeric data, and link data from different data sources based on key attributes.

[1110] The server further includes means for running an artificial intelligence model using the integrated data, means for providing insights derived from the artificial intelligence model, and means for customizing a user interface that allows for training the machine learning model, cross-validation and hyperparameter tuning, real-time updates of the generated insights, providing them in a visually understandable format, setting specific filter conditions, and selecting data visualization formats.

[1111] "Data collection" is the process of gathering necessary information from multiple sources.

[1112] "API" stands for Application Program Interface, a standardized means of exchanging data between different software applications.

[1113] "Data preprocessing" refers to a series of processes for converting collected raw data into a form suitable for analysis, including imputing missing values, removing outliers, normalizing text data, and scaling numerical data.

[1114] "Data integration" is the process of combining pre-processed data from different data sources into a coherent dataset, which involves combining data based on key attributes (e.g., timestamp or category).

[1115] An "artificial intelligence model" refers to an analytical method that uses algorithms such as machine learning and deep learning to generate insights and predictions from data.

[1116] "Cross-validation" is a statistical technique for evaluating the performance of a model by dividing a dataset into multiple parts.

[1117] "Hyperparameter tuning" is the process of optimizing the hyperparameters of a machine learning model in order to maximize the model's performance.

[1118] "Insights" are useful new information or insights gained from analyzing data that help users make better decisions.

[1119] "User interface" refers to the screens and operating methods that users use to interact with the system, allowing them to easily access information and check analysis results.

[1120] "Customization" refers to users changing system settings and adjusting the way information is displayed to suit their own needs.

[1121] This invention is a system that collects, preprocesses, integrates, and analyzes data using artificial intelligence models, and provides insights to users. It also has an interface that users can customize as needed. The following describes the program processing and specific examples of this system.

[1122] This system is run primarily by a server, which is often built using programming languages ​​such as Python or JavaScript. Below, we will explain the main processes and the specific software and hardware used for them.

[1123] Data collection

[1124] The server collects the necessary information from multiple data sources, such as business data, financial market data, and social media data, via APIs. This can be done using the Python requests library, which allows for the collection of the latest information in real time.

[1125] Data Preprocessing

[1126] The collected raw data is not suitable for analysis as it is, so the server performs preprocessing. During this process, the data is cleansed (filling in missing values, removing outliers) and formatted (normalizing text data, scaling numerical data). Here, it is recommended to use the Python pandas library.

[1127] Data Integration

[1128] The pre-processed data is then integrated by the server. Data from different data sources is linked based on key attributes (e.g. timestamp or category) to create a consistent dataset. This integration process can be performed using the pandas merge method.

[1129] Running an AI model

[1130] Using the combined data, the server runs AI models, such as machine learning models (regression models, classification models, etc.) trained on past data to perform predictions and classifications. Here, the scikit-learn library is used to build the models and perform cross-validation and hyperparameter tuning.

[1131] Generating and delivering insights

[1132] The insights generated from the trained AI model are updated in real time by the server and delivered to the user's device, including market forecasts and business strategy suggestions, and are presented in a visually understandable format using visualization libraries such as Plotly and Matplotlib.

[1133] User Interface Customization

[1134] Users can customize the interface to suit their needs by setting specific filter conditions (e.g., time period, region, category) and selecting the data visualization format (graph, chart, table, etc.) through their terminal. The server generates the customized data accordingly and provides it in real time.

[1135] Specific examples

[1136] Market strategy formulation for small and medium-sized enterprises

[1137] Small and medium-sized business owners (users) use this system for market analysis. The server collects, preprocesses, and integrates business data and market trend data via API. It then trains a market forecasting model based on historical data and predicts market trends in real time. These forecasts are provided to managers in dashboard format, allowing them to plan promotion strategies.

[1138] Investment decision-making by individual investors

[1139] Individual investors (users) use this system to help them decide where to invest. The server obtains real-time stock market data from the financial API, normalizes and scales the data, and then integrates it. It then uses a machine learning model to predict stock prices and displays the results on a dashboard. Investors can use this information to determine the timing of buying and selling specific stocks.

[1140] Prompt Sentence Examples

[1141] "Collect the latest business and market trend data and train predictive models to help small and medium-sized businesses with their market strategies."

[1142] "Use real-time stock price data to predict stock prices for a specific stock for the next week and display the results visually."

[1143] In this way, the present invention provides real-time data insights tailored to various needs and assists users in their decision-making process.

[1144] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1145] Step 1: Data collection

[1146] The server retrieves business, market, and social media data from each data source based on a pre-configured list of APIs. Specifically, the server uses the Python requests library to send HTTP requests to each data source. Each request includes an API key as authentication information. The server uses the API endpoint and authentication information as input and stores the raw data in JSON format in a local database as output.

[1147] Step 2: Data Preprocessing

[1148] The server preprocesses the collected raw data. This involves first converting it into a data frame using the pandas library. Then, it uses the fillna method to impute missing values ​​and statistical methods (e.g., standard deviation and IQR) to remove outliers. Text data is normalized and numerical data is scaled. The raw data frame is used as input, and clean, unified data is obtained as output.

[1149] Step 3: Data Integration

[1150] The server merges the preprocessed data from multiple data sources, using the pandas merge method to combine datasets from different data sources based on key attributes (timestamp or category), using multiple preprocessed data frames as input and producing a merged dataset as output.

[1151] Step 4: Run the AI ​​model

[1152] The server builds and runs machine learning models based on the merged dataset. First, it trains regression and classification models using the scikit-learn library. Then, it evaluates the accuracy of the models and optimizes their hyperparameters using GridSearchCV and RandomizedSearchCV for cross-validation. It uses the merged dataset as input and generates a trained model and its prediction results as output.

[1153] Step 5: Generate and deliver insights

[1154] The server generates useful insights based on the predictions and analysis results obtained from the trained AI model. Specifically, it uses visualization libraries such as Plotly and Matplotlib to display the results in a user-friendly format. It uses the predictions and analysis results as input, generates visualized graphs and charts as output, and provides them to the user's device.

[1155] Step 6: Customizing the User Interface

[1156] Users customize the interface through their devices by setting specific filter conditions (e.g., time period, region, category) and selecting the data visualization format (graph, chart, table, etc.). The server generates the customized data accordingly and serves it in real time. It uses the user settings as input and generates the customized data and visualization information as output.

[1157] Through this series of processing steps, the server collects information from various data sources, preprocesses, integrates, runs AI models, generates insights, and provides the information to users through a customizable interface.

[1158] (Application example 1)

[1159] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1160] Autonomous vehicles require accurate preprocessing and integration of data to collect various sensor data in real time and ensure safe and efficient operation. However, current systems often lack sufficient data imputation, outlier removal, and format standardization, resulting in inaccurate data analysis. Furthermore, there is a lack of means to properly link and analyze sensor data, making it difficult to provide timely insights.

[1161] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1162] In this invention, the server includes means for collecting data from multiple data transmission devices, means for imputing missing values, removing outliers, and standardizing the format of the collected data, means for integrating the preprocessed data into a consistent format, means for running a classification model using the integrated data, means for providing insights gained from the model, and means for customizing an interface based on user requests, thereby enabling real-time anomaly detection and safe route provision.

[1163] A "data transmission device" is a device that collects data from multiple sensors and data collection devices and transmits it to a server.

[1164] "Missing value imputation" is a process of filling in missing data values ​​with average values, estimated values, etc.

[1165] "Outlier removal" is the process of detecting and removing or correcting unusual values ​​in a data set.

[1166] "Format unification" is the process of converting data provided in different formats into a consistent format.

[1167] An "artificial intelligence model" is a mathematical model that uses machine learning algorithms to analyze data and make predictions and classifications.

[1168] "Insight" refers to useful knowledge or information derived from analytical results or analysis obtained from artificial intelligence models.

[1169] "User interface customization" is a function for changing the display content and operation method to meet the user's requirements.

[1170] "Anomaly detection" refers to detecting unusual patterns or values ​​in data.

[1171] A "safe route" is a route along which an autonomous vehicle is predicted to travel safely.

[1172] "Sensor data" refers to real-time information obtained from various sensors (LiDAR, cameras, GPS, etc.) installed in autonomous vehicles.

[1173] "Consistent format" refers to data format expressed in a unified format and scale.

[1174] A "classification model" is a machine learning model for classifying input data into specific categories or classes.

[1175] The present invention is a system that collects, preprocesses, and integrates sensor data from autonomous vehicles in real time, and utilizes artificial intelligence models to determine safe driving routes and detect anomalies. The system operates centrally on a server, and uses the necessary hardware and software to collect, analyze, and provide insights into the data. A specific embodiment of the system is described below.

[1176] Hardware and Software Configuration

[1177] The hardware used in this system includes multiple sensor devices (LiDAR, cameras, GPS, etc.) and a server. The sensor devices are installed in autonomous vehicles and collect data in real time. The server receives the sensor data and performs subsequent data processing and analysis.

[1178] The software used includes Python, Scikit-learn, the Requests library, and Matplotlib. Python is used as the main programming language for this system, and Scikit-learn is used to run the artificial intelligence model (classification model). The Requests library is used for API calls to collect data from sensor devices, and Matplotlib is used for visualization in the user interface.

[1179] Data collection

[1180] The server collects the necessary sensor data from multiple data transmitters in real time. This data collection is done via the API of each sensor device. For example, data is collected from URLs such as "http: / / sensor1.api" and "http: / / sensor2.api."

[1181] Data Preprocessing

[1182] The collected sensor data is not suitable for analysis as is, so the server performs preprocessing on the data. Preprocessing includes filling in missing values, removing outliers, and standardizing the format. Missing values ​​are filled in using the average value or other methods, and outliers are removed using the 3-sigma method. In addition, the data format is standardized by scaling the numerical data, etc.

[1183] Data Integration

[1184] The pre-processed data is then integrated into a consistent format by the server. Data collected from different sources is linked based on time series attributes. This integration process creates a unified data set that can be analyzed.

[1185] Running artificial intelligence models

[1186] The server runs an artificial intelligence model (classification model) using the integrated data. The model analyzes the data using a random forest classifier to identify safe routes and detect anomalies. Model training and prediction includes cross-validation and hyperparameter tuning.

[1187] Providing insights

[1188] Insights gained from the trained AI model are provided to users in real time, such as a safe route index or anomaly detection results, which are displayed in a dashboard format that allows users (fleet managers and engineers) to intuitively understand them.

[1189] User Interface Customization

[1190] Users can customize the interface to suit their needs, for example by setting filter conditions to highlight specific sensor data and selecting visualization formats such as graphs and charts, providing users with fast and accurate information to support real-time decision-making.

[1191] Specific examples

[1192] For example, let's assume that an autonomous vehicle has the following route data. Data such as obstacles, road gradients, and weather conditions is acquired every second via a sensor API and analyzed in real time. This allows the vehicle to detect anomalies that occur during operation and propose safe routes.

[1193] Prompt Sentence Examples

[1194] "Implement a system that analyzes sensor data from an autonomous vehicle to determine safe routes and detect anomalies. Collect each sensor data using an API, and write a prompt that includes preprocessing, data integration, prediction using an AI model, providing insights to the user, and customizing the interface. The AI ​​model used is a random forest classifier. Specifically, include real-time data collection from the sensor API, data preprocessing, and the ability to visualize insights."

[1195] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1196] Step 1:

[1197] Sensor data collection

[1198] The server collects data in real time from multiple data transmitters (sensors). Specifically, it sends an HTTP request to the API of each sensor device (for example, "http: / / sensor1.api" or "http: / / sensor2.api") to obtain sensor data. The input is the API endpoint of each sensor, and the output is the collected raw data.

[1199] Step 2:

[1200] Data Preprocessing

[1201] The server performs preprocessing on the collected raw data. The input is the collected raw data, and missing values ​​are filled in using the average value or other methods, and outliers are removed using the 3-sigma method. The server also scales the numerical data to unify the data format. The output is preprocessed, clean data.

[1202] Step 3:

[1203] Data integration

[1204] The server aggregates the pre-processed data into a consistent format. The input is the pre-processed data, and the different sensor data are linked based on time series attributes. The output is an integrated dataset.

[1205] Step 4:

[1206] Running artificial intelligence models

[1207] The server runs an artificial intelligence model (a random forest classification model) using the integrated data. The input is the integrated dataset, and the model is trained after cross-validation and hyperparameter tuning. The output is predictions for safe routes and anomaly detection.

[1208] Step 5:

[1209] Providing insights

[1210] The server generates insights based on the training and predicted results and provides them to the user. The input is the prediction results from the AI ​​model, and the visual display is a safe route index and anomaly detection index. The output is a visual insight in the form of a dashboard for the user.

[1211] Step 6:

[1212] User Interface Customization

[1213] Users can customize the interface to suit their needs: the input is the customization options set by the user (e.g., filter criteria for specific sensor data), the server generates the corresponding display, and the output is a customized dashboard delivered to the user in real time.

[1214] This enables the server to collect, preprocess, and integrate a series of sensor data, run AI models, provide insights, and customize interfaces to support the safe and efficient operation of autonomous vehicles.

[1215] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1216] The present invention is a system that collects, preprocesses, and integrates data, analyzes it using an artificial intelligence model, and provides the resulting insights to the user. Furthermore, it is equipped with an emotion engine that recognizes the user's emotions, allowing it to customize the information and interface provided based on the user's emotional state. Below, we will explain the program processing and specific examples of this system.

[1217] This system is run mainly by the server. The program processing flow is explained in detail below.

[1218] Data collection

[1219] The server collects the required data from multiple data sources, such as business data, financial market data, social media data, etc., through APIs. The server initiates the data collection process periodically or based on a trigger event.

[1220] Data Preprocessing

[1221] The collected raw data is not suitable for analysis as it is, so the server performs preprocessing. During this process, the data is cleansed (filling in missing values, removing outliers) and formatted (normalizing text data, scaling numerical data). This generates data that is suitable for analysis.

[1222] Data Integration

[1223] The pre-processed data is then integrated by the server. Data from different data sources is linked based on key attributes (e.g., timestamp or category) to create a consistent dataset. This integration process allows for multi-dimensional insights to be gained from diverse data.

[1224] Running an AI model

[1225] The server uses the integrated data to run AI models, such as machine learning models (regression models, classification models, etc.) trained on past data to make predictions and classifications, and performs cross-validation and hyperparameter tuning to improve the accuracy of the models.

[1226] Generating and delivering insights

[1227] The insights generated from the trained AI model are updated in real time by the server and delivered to the user's device. These insights include market forecasts and business strategy suggestions. The insights are presented in a visually easy-to-understand format, allowing users to understand and use them immediately.

[1228] Emotion Engine Operation

[1229] The emotion engine analyzes the user's voice, facial expressions, and input data to recognize their emotional state. The server automatically adapts the information and interface it provides based on this emotional data. For example, if the user is feeling stressed, it will reduce the amount of information displayed or limit the information provided to the most important ones.

[1230] User Interface Customization

[1231] Users can customize the interface to suit their needs by setting specific filter conditions (e.g., time period, region, category) and selecting the data visualization format (graph, chart, table, etc.) through their terminal. The server generates the customized data accordingly and provides it in real time.

[1232] Specific examples

[1233] Market strategy formulation for small and medium-sized enterprises

[1234] Small and medium-sized business owners (users) use this system for market analysis. The server collects, preprocesses, and integrates business and market trend data via API. It then trains a market forecasting model based on historical data to predict market trends in real time. These forecasts are provided to the owner in dashboard format, and if the emotion engine detects stress in the owner, it will simplify the information display to improve usability.

[1235] Investment decision-making by individual investors

[1236] Individual investors (users) use this system to make investment decisions. The server obtains real-time stock market data from a financial API, normalizes and scales the data, and then integrates it. It then uses a machine learning model to predict stock prices and displays the results on a dashboard. The sentiment engine analyzes the investor's emotional state and, if high interest or concern is detected, provides additional information or alerts accordingly.

[1237] As such, the present invention is a system that provides real-time data insights and emotion recognition functions that meet a variety of needs, and provides powerful support for users' decision-making processes.

[1238] The processing flow will be explained below.

[1239] Step 1:

[1240] The server collects the required data from multiple data sources, such as business data, financial market data, social media data, etc., through APIs. The server initiates the data collection process periodically or based on a trigger event.

[1241] Step 2:

[1242] The server preprocesses the collected raw data, applying data cleansing rules to fill in missing values ​​and remove outliers. For text data, it performs normalization (converting to lowercase, removing special characters), and for numerical data, it performs scaling and standardization.

[1243] Step 3:

[1244] The server integrates the pre-processed data, linking data from different data sources based on key attributes (e.g., timestamps or categories) to build a coherent dataset, systematically grouping related data points together.

[1245] Step 4:

[1246] The server trains AI models using the integrated dataset. It trains machine learning and deep learning models based on historical data to build models for prediction and classification. During this process, it performs cross-validation to evaluate the accuracy of the models and tunes hyperparameters as needed.

[1247] Step 5:

[1248] The server analyzes real-time data using trained AI models to generate insights, including market trend predictions and performance assessments, which are then delivered to users in the form of appropriate dashboards and alerts.

[1249] Step 6:

[1250] The emotion engine analyzes the user's voice, facial expressions, and input data to recognize the user's emotional state. For example, it obtains facial expression data from the user's webcam and applies emotion recognition algorithms to determine the user's current emotion (e.g., joy, sadness, anger, etc.). It also analyzes emotions from voice input.

[1251] Step 7:

[1252] The server automatically adapts the information and interface it provides based on the user's emotional data recognized by the emotion engine. For example, if it determines that the user is feeling stressed, it reduces the amount of information displayed and highlights only the important information. If the user is excited, it is set to display detailed data analysis results.

[1253] Step 8:

[1254] Users can view information using the provided dashboard, and customize the interface by setting filter criteria such as specific time periods, regions, and categories.

[1255] Step 9:

[1256] Through the device, users can make decisions based on the generated insights and customized reports. For example, small business owners can decide on promotion strategies based on market trends, and individual investors can decide when to buy or sell based on stock price forecasts.

[1257] Through the above processing steps, this system collects and analyzes data, generates and provides insights, and also provides multidimensional support that includes emotion recognition, thereby efficiently and effectively assisting users in their decision-making process.

[1258] Example 2

[1259] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1260] In conventional information collection and analysis systems, data preprocessing and integration are cumbersome, and advanced expertise is required to obtain highly accurate insights. Furthermore, due to a lack of mechanisms for recognizing the user's emotional state and adapting the information and interface provided, the user interface cannot be fully customized, making it difficult to improve usability. Our goal is to solve these problems and realize an efficient and flexible data analysis system.

[1261] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1262] In this invention, the server includes a means for collecting data, a means for preprocessing the collected data, and a means for integrating the preprocessed data, thereby enabling efficient and highly accurate data analysis and the provision of insights.

[1263] The server further includes means for executing an artificial intelligence model using the integrated data, means for providing insights obtained from the artificial intelligence model, means for recognizing the user's emotional state and adapting the information and interface to be provided based on the emotional state, and means for customizing the user interface, thereby enabling appropriate information to be provided and the interface to be customized according to the user's emotions, thereby improving usability.

[1264] "Means of collecting data" refers to the function of obtaining necessary data from multiple data sources using an interface such as an API.

[1265] "Means for preprocessing collected data" refers to functions for cleansing collected data, filling in missing values, removing outliers, and standardizing data formats (standardization, scaling, etc.).

[1266] A "means for integrating pre-processed data" is a function that combines pre-processed data into a coherent data set based on key attributes (e.g., timestamps).

[1267] "Means for running artificial intelligence models using the integrated data" refers to the ability to use trained machine learning algorithms to analyze the integrated data and perform tasks such as prediction and classification.

[1268] "Means for providing insights obtained from an AI model" refers to a function that provides users with insights obtained from the analysis results of an AI model in a visually easy-to-understand format (graphs, charts, etc.).

[1269] "Means for recognizing the user's emotional state and adapting the information and interface provided based on that" refers to a function that analyzes the user's voice, facial expressions, input data, etc. to identify their emotional state, and changes the way information is displayed and the interface according to that state.

[1270] "Means for customizing the user interface" refers to the ability to select and change the filter conditions and visualization formats (graphs, charts, tables, etc.) of the interface according to the user's needs.

[1271] The following is a detailed description of the mode for carrying out the invention. The invention consists of a system for data collection, pre-processing, integration, analysis by artificial intelligence models, providing insights, recognizing user emotions, and customizing the interface. The system mainly consists of three elements: a server, a terminal, and a user.

[1272] Data collection

[1273] The server retrieves the necessary data from multiple data sources through APIs. Data sources include business data, financial market data, social media data, etc. The server initiates the data collection process based on a regular schedule or specific trigger events. For example, the server accesses a financial API every 10 minutes to retrieve the latest stock price data.

[1274] Data Preprocessing

[1275] The collected raw data is preprocessed by the server. This process involves cleansing the data, filling in missing values, removing outliers, normalizing text data, and scaling numerical data. For example, abnormally high trading volumes are detected and removed from the collected stock price data. Also, all company names are standardized to lowercase.

[1276] Data Integration

[1277] The pre-processed data is then integrated by the server. Data from different data sources is linked based on key attributes (e.g., timestamps) to create a consistent dataset, enabling multi-dimensional insights to be gained. The integrated data is then stored in a relational database.

[1278] Running artificial intelligence models

[1279] The server runs an artificial intelligence model using the integrated data. A machine learning algorithm (e.g., a regression model or a classification model) is used. The server performs cross-validation and hyperparameter tuning to improve the model's accuracy. For example, the server trains a regression model to predict the next day's stock price from the training dataset.

[1280] Generating and delivering insights

[1281] The server analyzes the predictions and classifications generated by the trained AI model and generates these insights in a user-friendly visual format (e.g., graphs or charts). These insights are updated in real time and provided to the user's device. For example, stock price predictions may be generated as line graphs and displayed in real time on the user's device.

[1282] Emotion Engine Operation

[1283] The emotion engine analyzes the user's voice, facial expressions, and input data to recognize the user's emotional state. The server then adapts the information and interface it provides based on this emotional data. For example, if the user is feeling stressed, it reduces the amount of information displayed and focuses on providing only the most important information.

[1284] User Interface Customization

[1285] Users can customize the interface to suit their needs by setting specific filter conditions (e.g., time period, region, category) and selecting the data visualization format (graph, chart, table, etc.) through their terminal. The server generates the customized data accordingly and provides it in real time.

[1286] Specific examples

[1287] Example of market strategy formulation for small and medium-sized enterprises

[1288] Small and medium-sized business owners (users) use this system for market analysis. The server collects, preprocesses, and integrates business and market trend data via API. It then trains a market forecasting model based on historical data to predict market trends in real time. These forecasts are provided to the owner in dashboard format, and if the emotion engine detects stress in the owner, it can simplify the information display to improve usability.

[1289] Examples of investment decisions made by individual investors

[1290] Individual investors (users) use this system to make investment decisions. The server obtains real-time stock market data from financial APIs, normalizes and scales the data, and then integrates it. It then uses a machine learning model to predict stock prices and displays the results on a dashboard. The sentiment engine analyzes the investor's emotional state and, if high interest or concern is detected, provides additional information or alerts accordingly.

[1291] Prompt Sentence Examples

[1292] "Create an AI model to predict upcoming market trends based on an integrated data set for market analysis of small and medium-sized enterprises."

[1293] In this way, the present invention is a system that provides real-time data insights and emotion recognition capabilities to meet various needs and assist users in their decision-making process.

[1294] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1295] Step 1:

[1296] The server collects data from multiple data sources.

[1297] Input: APIs for business data, financial market data, social media data, etc.

[1298] What it does: Every 10 minutes, the server accesses a financial API to retrieve the latest stock price data, including company names, stock prices, and trading volumes.

[1299] Output: raw collected data

[1300] Step 2:

[1301] The server pre-processes the collected raw data.

[1302] Input: raw data collected

[1303] Specific behavior:

[1304] Missing value imputation: The server uses the previous data to impute missing parts.

[1305] Outlier Removal: Statistical methods are used to detect and remove abnormally high trading volumes.

[1306] Text data normalization: The server normalizes all company names to lowercase.

[1307] Scaling of numerical data: Standardization (mean 0, standard deviation 1) is performed.

[1308] Output: Preprocessed data

[1309] Step 3:

[1310] The server aggregates the pre-processed data.

[1311] Input: Preprocessed data

[1312] What it does: The server combines data from different data sources based on key attributes (e.g., timestamps). The combined data is stored in a relational database.

[1313] Output: A consolidated dataset

[1314] Step 4:

[1315] The server runs an artificial intelligence model using the integrated data.

[1316] Input: Integrated dataset

[1317] Specific behavior:

[1318] Analyze using machine learning algorithms (e.g., regression models, classification models).

[1319] Improve the accuracy of the model by performing cross-validation and hyperparameter tuning.

[1320] Output: Prediction results and classification results

[1321] Step 5:

[1322] The server provides insights derived from artificial intelligence models.

[1323] Input: Prediction results and classification results

[1324] Specific operation: The server generates insights in a visually easy-to-understand format (e.g., graphs, charts) and provides them to the user's device in real time.

[1325] Output: Visualized insights (e.g. line graphs and dashboards)

[1326] Step 6:

[1327] The emotion engine recognizes the user's emotional state and adapts information and interfaces accordingly.

[1328] Input: User's voice, facial expressions, input data

[1329] Specific operation: The emotion engine uses the analysis results to reduce the amount of information displayed if the user is feeling stressed, and provides only important information.

[1330] Output: Adapted information and interface

[1331] Step 7:

[1332] The user customizes the interface.

[1333] Input: User filter criteria (e.g., time period, region, category) and visualization format (graph, chart, table, etc.)

[1334] Specific operation: The server generates customized data based on the conditions specified by the user and provides it in real time.

[1335] Output: Customized data and interface

[1336] (Application example 2)

[1337] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1338] Modern manufacturing plants require the management and analysis of complex data, making it important to optimize the work environment by taking into account the emotional state of workers. However, current systems struggle to efficiently integrate and analyze this data and provide appropriate insights in real time. Furthermore, interfaces are rarely adapted based on the emotional state of workers, resulting in problems such as reduced work efficiency and increased worker stress. To address these issues, a system capable of integrating data and providing insights that take into account emotional states is needed.

[1339] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1340] In this invention, the server includes means for collecting data, means for preprocessing the collected data, means for integrating the preprocessed data, means for running an artificial intelligence model using the integrated data, means for providing insights obtained from the artificial intelligence model, means for customizing a user interface, means for recognizing a user's emotional state using an emotion engine, means for adapting information and an interface to be provided based on the user's emotional state, means for collecting and analyzing factory environment data and worker biometric data, and means for providing insights that optimize the work environment and worker conditions. This makes it possible to efficiently analyze data within a factory and provide optimal insights in real time while taking into account the emotional states of workers.

[1341] A "data collection tool" is a process or device for automatically acquiring data from multiple data sources.

[1342] "Data preprocessing means" refers to processes and methods used to prepare collected raw data in a format suitable for analysis. Specifically, this involves filling in missing values, removing outliers, and normalizing the data.

[1343] A "data integration procedure" is a process or method for combining pre-processed data into a single coherent data set.

[1344] An "artificial intelligence model execution means" is a process or device that uses integrated data to execute an AI model using methods such as machine learning or deep learning to make predictions and classifications.

[1345] An "insight providing means" is a process or method for presenting the analysis results and prediction results obtained by an artificial intelligence model in a format that is easy for users to understand.

[1346] A "user interface customization means" is a process or method for tailoring the displayed information or interface to suit the needs and requirements of the user.

[1347] An "emotion engine" is a system or software that analyzes a user's voice, facial expressions, and input data to recognize the user's emotional state.

[1348] "Factory environment data" refers to data related to the environment within a factory, such as temperature, humidity, and noise levels.

[1349] "Worker's biometric data" refers to data that indicates the physical condition of a factory worker, such as their heart rate and stress level.

[1350] The "optimization insight providing means" is a process or method for using analyzed data to provide insights and suggestions necessary for optimizing factory operations and work environments in real time.

[1351] This invention is a system that collects, pre-processes, integrates, and analyzes data in a factory environment, and provides insights in real time. It has the ability to recognize the emotional state of workers using an emotion engine. This system can optimize factory operations and reduce worker stress.

[1352] Overall system overview

[1353] This system mainly consists of a server, multiple data collection devices, an emotion engine, and a user interface. The server collects, preprocesses, and integrates data from within the factory, and analyzes it using an artificial intelligence model. The analysis results are presented visually and easily understood, and the emotion engine grasps the emotional state of workers in real time and suggests appropriate responses.

[1354] Hardware and software used

[1355] Hardware:

[1356] Various sensors in the factory (temperature sensors, humidity sensors, noise level sensors)

[1357] Worker biometric data acquisition devices (heart rate monitors, stress level measuring devices)

[1358] Audio input devices, cameras

[1359] software:

[1360] Python: Data collection and preprocessing

[1361] Pandas: Data Shaping and Processing

[1362] Scikit-learn: Building and running machine learning models

[1363] TensorFlow: Emotion Engine Implementation

[1364] Data collection and preprocessing

[1365] The server collects various environmental and biometric data in real time from sensors in the factory and biometric data acquisition devices for workers. The collected data is centralized and preprocessed using Pandas. Preprocessing involves filling in missing values, removing outliers, and normalizing text data.

[1366] Data integration and AI analysis

[1367] The pre-processed data is integrated into a coherent dataset. AI models built with Scikit-learn are then run to optimize factory operations and identify stressors. An emotion engine powered by TensorFlow analyzes workers' voices, facial expressions, and input data to recognize their emotional state in real time.

[1368] Providing insights and customizing the interface

[1369] Insights gained from the AI ​​model are delivered in real time through a user interface, including suggestions for improving work efficiency and taking breaks. The user interface can be customized to meet the needs of workers and managers, and the information provided and the interface adapt based on their emotional state.

[1370] Specific examples

[1371] For example, in a manufacturing factory, AI can identify bottlenecks on the production line from past data and suggest countermeasures. Also, when workers become stressed, AI can suggest appropriate times to take breaks, reducing the burden on the workers. This improves the efficiency of the entire factory and the happiness of workers.

[1372] Prompt Sentence Examples

[1373] "How can we suggest a break to a stressed worker?"

[1374] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1375] Step 1:

[1376] Data collection

[1377] The server collects data from various sensors in the factory and workers' biometric data acquisition devices. Input data includes temperature, humidity, noise level, heart rate, stress level, audio, and video. The server periodically obtains this data through an API. This data is first stored on the server in raw format.

[1378] Step 2:

[1379] Data Preprocessing

[1380] The server performs preprocessing on the collected raw data. Specifically, it uses Pandas to impute missing values, remove outliers, and normalize text data. By normalizing the input data and removing outliers, a dataset suitable for analysis is generated. The output data is a dataset in a clean and consistent format.

[1381] Step 3:

[1382] Data integration

[1383] The pre-processed data is then integrated into a consistent dataset by the server. Specifically, data from different data sources is matched using timestamps as a key. As a result, a single unified large-scale dataset is generated. This dataset is then used as input for subsequent AI analysis.

[1384] Step 4:

[1385] Running an AI model

[1386] The server uses the integrated dataset to run artificial intelligence models. These include a prediction model using Scikit-learn and an emotion analysis model built with TensorFlow. Specifically, it runs a classification model to identify factors that reduce work efficiency and a regression model to predict worker stress. The input data is the integrated dataset, and the output data is the prediction results and estimated emotional states.

[1387] Step 5:

[1388] Generating and delivering insights

[1389] Based on the analysis results obtained from the AI ​​model, the server generates insights and provides them through a user interface. These insights include measures to improve work efficiency and recommendations for worker breaks. Specifically, the results are displayed visually using graphs and charts. The input data is the output results from the AI ​​model, and the output data is a visually formatted insight report.

[1390] Step 6:

[1391] Emotion Engine Operation

[1392] The server uses an emotion engine to analyze the user's emotional state in real time. Specifically, it runs a TensorFlow model using audio and video data to estimate the level of stress and fatigue. The input data is audio and video data, and the output data is a tagged emotional state.

[1393] Step 7:

[1394] Interface customization

[1395] The server automatically adapts the information and interface it provides based on the user's emotional state. For example, if the user is under stress, it simplifies the information displayed and provides only the most important information. The input data is the output result from the emotion engine, and the output data is the adapted user interface.

[1396] Specific prompt examples

[1397] "How can we suggest a break to a stressed worker?"

[1398] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1399] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1400] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1401] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1402] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1403] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1404] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1405] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1406] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1407] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1408] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1409] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1410] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1411] 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.

[1412] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1413] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1414] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1415] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1416] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1417] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1418] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1419] The following is further disclosed regarding the above embodiment.

[1420] (Claim 1)

[1421] a means of collecting data;

[1422] a means for pre-processing the collected data;

[1423] a means for integrating the preprocessed data;

[1424] means for running an artificial intelligence model using the integrated data;

[1425] a means for providing insights derived from artificial intelligence models; and

[1426] a means for customizing the user interface;

[1427] A system including:

[1428] (Claim 2)

[1429] The system of claim 1 performs missing value imputation, outlier removal, and text data normalization on the collected data.

[1430] (Claim 3)

[1431] A means of integrating data from multiple data sources into a coherent data set;

[1432] a means of linking different data points based on time series attributes;

[1433] 10. The system of claim 1, comprising:

[1434] "Example 1"

[1435] (Claim 1)

[1436] a means of collecting data;

[1437] a means for pre-processing the collected data;

[1438] a means for integrating the preprocessed data;

[1439] means for running an artificial intelligence model using the integrated data;

[1440] a means for providing insights derived from artificial intelligence models; and

[1441] a means for customizing the user interface;

[1442] Data collection involves obtaining information from multiple data sources via API,

[1443] Data preprocessing includes methods for imputing missing values, removing outliers, normalizing text data, and scaling numerical data.

[1444] Data integration involves combining data from different data sources based on key attributes and

[1445] The execution of AI models requires a means to train machine learning models, perform cross-validation and hyperparameter tuning, and

[1446] A means to present the generated insights in a visually understandable format that updates in real time;

[1447] Customizing the interface includes the means to set specific filter criteria and select the data visualization format.

[1448] A system including:

[1449] (Claim 2)

[1450] The system of claim 1 performs missing value imputation, outlier removal, and text data normalization on the collected data.

[1451] (Claim 3)

[1452] A means of integrating data from multiple data sources into a coherent data set;

[1453] a means of linking different data points based on time series attributes;

[1454] 10. The system of claim 1, comprising:

[1455] "Application Example 1"

[1456] (Claim 1)

[1457] means for collecting data from a plurality of data transmission devices;

[1458] A means of completing missing values, removing outliers, and standardizing the format of collected data;

[1459] a means of integrating the preprocessed data into a consistent format;

[1460] means for running a classification model using the integrated data;

[1461] a means of delivering insights gained from the model; and

[1462] a means for customizing the interface based on user requirements;

[1463] A system including:

[1464] (Claim 2)

[1465] 10. The system of claim 1, wherein the collected sensor data is used for real-time anomaly detection and safe route provision.

[1466] (Claim 3)

[1467] a means of linking sensor data based on time series attributes and using artificial intelligence models to make predictions;

[1468] means for visually displaying the obtained insights on a user terminal;

[1469] 10. The system of claim 1, comprising:

[1470] "Example 2: Combining Emotion Engines"

[1471] (Claim 1)

[1472] a means of collecting data;

[1473] a means for pre-processing the collected data;

[1474] a means for integrating the preprocessed data;

[1475] means for running an artificial intelligence model using the integrated data;

[1476] a means for providing insights derived from artificial intelligence models; and

[1477] means for recognizing a user's emotional state and adapting the information and interface provided accordingly;

[1478] a means for customizing the user interface;

[1479] A system including:

[1480] (Claim 2)

[1481] A means for imputing missing values, removing outliers, and normalizing text data from the collected data;

[1482] means for scaling the numerical data;

[1483] 10. The system of claim 1, comprising:

[1484] (Claim 3)

[1485] A means of integrating data from multiple data sources into a coherent data set;

[1486] a means of linking different data points based on time series attributes;

[1487] means for storing the preprocessed data in a relational database;

[1488] 10. The system of claim 1, comprising:

[1489] "Application example 2 when combining emotion engines"

[1490] (Claim 1)

[1491] a means of collecting data;

[1492] a means for pre-processing the collected data;

[1493] a means for integrating the preprocessed data;

[1494] means for running an artificial intelligence model using the integrated data;

[1495] a means for providing insights derived from artificial intelligence models; and

[1496] a means for customizing the user interface;

[1497] means for recognizing an emotional state of a user using an emotion engine;

[1498] means for adapting the information and interface provided based on the user's emotional state;

[1499] A means for collecting and analyzing factory environment data and worker biometric data;

[1500] a means of providing insights to optimize the working environment and worker conditions;

[1501] A system including:

[1502] (Claim 2)

[1503] The system of claim 1 performs missing value imputation, outlier removal, and text data normalization on the collected data.

[1504] (Claim 3)

[1505] A means of integrating data from multiple data sources into a coherent data set;

[1506] a means of linking different data points based on time series attributes;

[1507] A means to provide real-time insights needed to optimize factory operations, and

[1508] 10. The system of claim 1, comprising: [Explanation of symbols]

[1509] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means of collecting data; a means for pre-processing the collected data; a means for integrating the preprocessed data; means for running an artificial intelligence model using the integrated data; a means for providing insights derived from artificial intelligence models; and a means for customizing the user interface; A system including:

2. The system according to claim 1 , wherein the collected data is subjected to missing value imputation, outlier removal, and text data normalization.

3. A means of integrating data from multiple data sources into a coherent data set; a means of linking different data points based on time series attributes; The system of claim 1 , comprising:

Images