System

Abstract

A system is provided.SOLUTION: A system comprising: means for obtaining information from a data source; means for cleaning and standardizing the obtained data; means for analyzing the pre-processed data using a machine learning algorithm; means for visualizing the analysis results; means for transmitting the visualized data to a user interface; and means for displaying the visualized data at the 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 recent years, with the rapid increase and complexity of data, the service industry has been required to analyze data quickly and accurately and provide appropriate insights. However, current methods have difficulty efficiently processing large amounts of data, and there are issues with the accuracy and speed of anomaly detection and predictive analysis in particular. Furthermore, with the combination of labor shortages and rising labor costs, the entire service industry is seeking effective solutions to improve efficiency. The present invention aims to solve these issues, automate data analysis in the service industry, and provide faster and more accurate insights. [Means for solving the problem]

[0005] The present invention provides a system comprising the following means: a means for acquiring information from a data source; a means for cleaning and standardizing the acquired data; a means for analyzing the preprocessed data using a machine learning algorithm; a means for visualizing the analysis results; a means for transmitting the visualized data to a user interface; and a means for displaying the visualized data on the user interface. This system enables rapid and efficient analysis of large amounts of data collected from different data sources and presents the results in an intuitively understandable format. This is expected to resolve issues of labor shortages and labor costs in the service industry and improve business efficiency.

[0006] A "data source" is a system, device, or service that is the origin or starting point for collecting information.

[0007] "Means of obtaining information" refers to the methods and techniques used to access data sources and collect the required data.

[0008] "Data cleaning means" refers to methods and techniques for detecting errors, missing values, outliers, etc. from acquired data and correcting or removing them.

[0009] "Means of data standardization" refers to methods and techniques for converting data provided in different formats or units into a consistent format or unit.

[0010] "Machine learning algorithm" refers to mathematical and statistical methods and techniques for learning and finding patterns from empirical data in order to perform data analysis and predictions.

[0011] "Means of analysis" refers to the methods and techniques used to apply machine learning algorithms to data and extract desired information or insights.

[0012] "Visualization means" refers to methods and techniques for displaying analysis results in a form that is intuitively easy for humans to understand (for example, graphs or charts).

[0013] "User interface" refers to a collection of interactive elements, such as a screen and input devices, that allow a user to interact with a device or system.

[0014] "Means for transmitting visualization data" refers to the method or technology for transmitting the visualized analysis results to the user interface.

[0015] "Displaying means" refers to the methods and techniques for presenting visualization data to a user through a user interface. [Brief explanation of the drawings]

[0016] [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

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] The system according to the present invention automates multiple processes, allowing users to efficiently analyze large amounts of data and quickly gain insights. Specific embodiments of the system are described below.

[0038] 1. Data collection

[0039] The server connects to various data sources (e.g. sensors, APIs, databases) and during this connection process sets the necessary authentication information and connection parameters.

[0040] Example: A server sends an HTTP request to a temperature sensor every 5 minutes to get the latest temperature data, while simultaneously retrieving user posts related to a specific keyword from a social media API.

[0041] 2. Pretreatment

[0042] The server cleans the acquired data, which includes imputing missing values ​​and detecting and correcting outliers. It also standardizes the data, for example, converting data provided in different units into a common unit.

[0043] Example: A server converts temperature data recorded in Fahrenheit to Celsius and formats all data into a uniform timestamp format.

[0044] 3. Data Analysis

[0045] The server then applies machine learning algorithms to the pre-processed data, enabling it to detect anomalies and predict future trends.

[0046] Example: The server creates a regression model based on past temperature data to predict future temperature changes, and if an abnormally high temperature is detected, reports the time and temperature.

[0047] 4. Visualizing the results

[0048] The server visualizes the analysis results in a user-friendly format, which includes generating graphs and charts.

[0049] Example: The server displays predicted temperature changes as a line graph and highlights any anomalies detected.

[0050] 5. User Interface

[0051] The terminal receives the visualization data sent from the server and displays it on the screen, which the user can use to check the results and take necessary actions.

[0052] Example: A temperature forecast graph sent from a server is displayed on a tablet device, allowing the user to consider future measures.

[0053] Through these processes, the system based on the present invention automates the entire process from data collection, pre-processing, analysis, visualization of results, and display of data on a user interface, providing fast and accurate insights.

[0054] The processing flow will be explained below.

[0055] Step 1: Connecting the Data Source

[0056] The server configures connections to data sources (sensors, APIs, databases, etc.), for example specifying endpoint URLs for sensors and setting up credentials for social media APIs.

[0057] Step 2: Getting the data

[0058] The server periodically retrieves information from connected data sources, for example, collecting data from a temperature sensor every five minutes, or calling social media APIs in real time to collect post data.

[0059] Step 3: Cleaning the data

[0060] The server then cleans the acquired data by imputing missing values ​​and detecting and correcting outliers. For example, it imputes missing temperature data with previous and subsequent values, and removes or corrects extremely high or low values.

[0061] Step 4: Standardize the data

[0062] The server standardizes the cleaned data, for example converting temperature data from Fahrenheit to Celsius and aligning all data timestamps to a uniform format.

[0063] Step 5: Feature extraction

[0064] The server extracts the features required for analysis from the data, such as the average temperature, maximum and minimum temperatures, and temperature fluctuation range for each day.

[0065] Step 6: Applying machine learning algorithms

[0066] The server then uses the extracted features to apply machine learning algorithms, such as building a regression model using past temperature data to predict future temperature fluctuations.

[0067] Step 7: Visualize the analysis results

[0068] The server then visualizes the results of the analysis, for example generating a line graph showing the temperature predictions and highlighting any outliers.

[0069] Step 8: Submitting visualization data

[0070] The server transmits the visualized analysis results to a user interface, for example, by transmitting the generated graphs to a terminal.

[0071] Step 9: Receive and display data

[0072] The device receives the visualization data sent from the server and displays it on the screen. For example, a temperature forecast graph is displayed on a tablet device for the user to check.

[0073] Step 10: User review and decision making

[0074] The user can check the analysis results displayed on the device and make necessary decisions, such as adjusting heating and cooling or considering additional measures based on future temperature predictions.

[0075] Example 1

[0076] 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."

[0077] Traditionally, efficiently analyzing large amounts of data collected from various data sources and quickly and accurately gaining insights required a great deal of time and effort. Furthermore, acquiring data from multiple data sources using different protocols and authentication information was complex, and the process of preprocessing, analyzing, visualizing, and providing it to users was not easy. Furthermore, there was a need to automate these processes to detect anomalies and predict future trends.

[0078] 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.

[0079] In this invention, the server includes means for acquiring information from data sources, means for cleaning and standardizing the acquired data, means for analyzing the preprocessed data using a machine learning algorithm, means for visualizing the analysis results, means for transmitting the visualized data to a user interface, and means for displaying the visualized data on the user interface. This allows efficient data collection from multiple data sources using different protocols and authentication information, and enables analysis, anomaly detection, and trend prediction using a machine learning algorithm using the cleaned and standardized data. In addition, by visualizing the analysis results and providing them on the user interface, users can quickly and accurately gain insights.

[0080] A "data source" is a device or system that serves as an input source for providing information.

[0081] "Means of obtaining information" are the methods or processes used to collect data from data sources.

[0082] "Data cleaning methods" are methods or processes for removing unnecessary information from collected data and correcting missing or erroneous values.

[0083] A "data standardization method" is a method or process for converting data in different units or formats into a single common format.

[0084] A "machine learning algorithm" is a mathematical model that analyzes collected and preprocessed data to find patterns and relationships.

[0085] "Means of analysis" refers to the methods or processes used to extract useful information from pre-processed data using machine learning algorithms.

[0086] "Means for visualizing analysis results" refers to methods or tools for displaying information obtained through data analysis in a visual format such as graphs or charts.

[0087] "Means for transmitting visualization data to a user interface" refers to a communication means or protocol that allows a user to view the visualized data through the interface.

[0088] "Means for displaying visualized data in a user interface" refers to a display device or software that allows a user to easily view and manipulate the visualized data.

[0089] "Anomaly detection" is the process of finding and identifying unnatural patterns or values ​​in data.

[0090] "Trend forecasting" is the process of predicting future trends and patterns based on past data.

[0091] The system according to the present invention allows users to efficiently analyze large amounts of data and quickly gain insights. It also allows data collection from multiple data sources using different protocols and authentication information, and uses machine learning algorithms to detect anomalies and predict future trends. Specific embodiments of the system are described below.

[0092] 1. Data collection

[0093] The server connects to various data sources, such as temperature sensors and social media APIs, to collect data. This process involves setting the necessary authentication information and connection parameters. For example, HTTP requests are used to periodically retrieve data from the temperature sensor and retrieve posts related to specific keywords from the social media API. This allows the server to collect temperature data and text data from social media.

[0094] 2. Data Preprocessing

[0095] The server cleans and standardizes the collected data. During this stage, missing values ​​are imputed and outliers are corrected. Data standardization also involves converting data provided in different units into a common format. For example, temperature data recorded in Fahrenheit is converted to Celsius. This preprocessing improves data quality and facilitates subsequent analysis.

[0096] 3. Data Analysis

[0097] The server then applies machine learning algorithms to the preprocessed data to detect anomalies and predict future trends. For example, it creates a regression model based on past temperature data to predict future temperature changes. It also reports abnormally high or low temperatures if they are detected. This analysis is a key step in helping users quickly gain insights.

[0098] 4. Visualizing the results

[0099] The server visualizes the results of the data analysis. Specifically, it displays predicted temperature changes as a line graph and highlights any detected anomalies. This visualization allows users to intuitively understand trends and anomalies in the data.

[0100] 5. User Interface

[0101] The device receives the visualized data sent from the server and displays it on the screen. The user can use this to check the results and take necessary actions. For example, a user can check the temperature forecast graph displayed on the tablet device and make a plan to adjust heating and cooling in the future. Users can also click on anomaly detection results to check detailed information.

[0102] Example prompt

[0103] Below is an example of a prompt sentence to input to the generative AI model.

[0104] Prompt statement:

[0105] Design a system that meets the following criteria:

[0106] 1. A server that collects data from various data sources (e.g., temperature sensors, social media APIs).

[0107] 2. Clean the collected data, complete missing values, and correct outliers.

[0108] 3. Use machine learning algorithms to analyze the collected data and predict future trends.

[0109] 4. Visualize the analysis results and present them in an easy-to-understand format.

[0110] 5. Display the analysis results on a tablet device so that the user can take appropriate action.

[0111] As described above, this system consistently automates data collection, preprocessing, analysis, and visualization of results, and is optimized to enable users to quickly gain insights.

[0112] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0113] Step 1: Collect data

[0114] The server connects to multiple data sources, such as temperature sensors and social media APIs. The inputs are the sensor's IP address, port number, authentication key, and API access token and query parameters. Specifically, the server sends an HTTP request to the temperature sensor every five minutes to retrieve temperature data. At the same time, it retrieves post data related to specified keywords from the social media API. The retrieved data is temperature data (e.g., 25.3°F) and social media post data (e.g., 10 posts related to "global warming").

[0115] Step 2: Preprocessing the data

[0116] The server cleans and standardizes the collected data. Specifically, it uses collected temperature data and social media post data as input. First, the server detects missing values ​​and fills them with the average of the surrounding data. Next, it replaces outliers (e.g., temperature values ​​that deviate significantly) with the median. Finally, it converts temperature data recorded in Fahrenheit to Celsius. As output, it obtains cleaned and standardized data (e.g., temperature data of 22.75°C and standardized text data).

[0117] Step 3: Analyze the data

[0118] The server applies machine learning algorithms to analyze the preprocessed data. The cleaned and standardized temperature data and social media post data are used as inputs. The server uses these data to create a regression model to predict future temperature changes. It also runs an anomaly detection algorithm to identify unusual data points. Specifically, the regression model predicts future temperatures and lists outliers (e.g., temperatures above 30°C). The output is the predicted temperature data (e.g., the predicted temperature for the next day is 25.1°C) and the anomaly detection results.

[0119] Step 4: Visualize the results

[0120] The server uses the predicted temperature data and anomaly detection results as input to visualize the analysis results. Specifically, it generates line graphs and charts based on these data. It displays the line graph showing the temperature change and the anomaly detection results in highlighted form. As output, visualized data (e.g., graphs or charts) is generated.

[0121] Step 5: Display in the user interface

[0122] The terminal receives the visualized data sent from the server and displays it on the screen. The visualized data (graphs and charts) is used as input. The user can view this to check the current situation and take necessary actions. Specifically, the user can view the temperature forecast graph displayed on the tablet terminal and make a plan to adjust heating and cooling. They can also click on anomaly detection results to view detailed information. The output is the visualized data displayed on the user interface.

[0123] (Application example 1)

[0124] 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."

[0125] Conventional factory monitoring systems have difficulty analyzing the diverse data collected from sensors in real time to detect anomalies and perform predictive analysis. They also lack a way to display the analysis results in an intuitive and easy-to-understand way for on-site workers. In particular, there was no way for workers to check real-time data while on the move, which often led to delays in rapid response.

[0126] 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.

[0127] In this invention, the server includes means for acquiring information from a data source, means for cleaning and standardizing the acquired data, means for analyzing the preprocessed data using a machine learning algorithm, means for visualizing the analysis results, means for transmitting the visualized data to a user interface, means for displaying the visualized data on the user interface, and means for displaying real-time data on an augmented reality display, thereby enabling real-time anomaly detection and predictive analysis, allowing workers to intuitively check necessary information even while on the move and enabling prompt action.

[0128] A "data source" is the source from which information is collected, such as from sensors, APIs, or databases.

[0129] "Cleaning" is the process of preparing data by correcting or removing missing or outlier values.

[0130] "Standardization" is the process of converting data provided in different units into a common standard.

[0131] A "machine learning algorithm" is a mathematical technique that uses past data to learn patterns and make predictions or detect anomalies.

[0132] "Analysis" is the process of applying specific algorithms to collected data to obtain desired information.

[0133] "Visualization" refers to displaying the results of data analysis in the form of graphs, charts, etc., making them easy for humans to understand.

[0134] A "user interface" is an operation screen or display device that allows a user to interact with a system.

[0135] An "augmented reality display" is a display device that uses technology to overlay computer-generated information on the real world.

[0136] The system that realizes this application example analyzes various data obtained from sensors in a factory environment in real time and displays the results on an augmented reality display. This system uses the following hardware and software.

[0137] The server uses Python and APIs to collect data from sensors, such as temperature, humidity, and machine operating status data, using REST APIs and MQTT protocols.

[0138] Next, the server performs data preprocessing. It uses NumPy and Pandas to clean the collected data and to impute and correct missing or outlier values. It also standardizes data provided in different units to unify them. For example, it converts temperature data from Fahrenheit to Celsius.

[0139] Once the preprocessing is complete, the data is analyzed using machine learning algorithms. The server uses Scikit-Learn and Tensorflow (registered trademark) to detect anomalies and predict trends. For example, it applies a regression model created using past data to predict future temperature changes. If an abnormally high temperature is detected, the information is analyzed in real time.

[0140] The analysis results are visualized and sent to a user interface. The server generates graphs using Matplotlib or Plotly and highlights any anomalies detected. For example, predicted temperature changes are displayed as a line graph, and anomalies are highlighted with a red marker.

[0141] Finally, the visualized data is displayed in real time on an augmented reality display, where smart glasses or other devices use Unity or Vuforia to overlay the analysis results, allowing factory workers to intuitively view the information on the move.

[0142] As a concrete example, if the following prompt sentence is input into a generative AI model, a program for the entire system can be generated.

[0143] Create a Python program to collect data from sensors in a factory and perform anomaly detection and trend prediction. Clean the data and convert its units using the Pandas library, then use Scikit-Learn to detect anomalies and TensorFlow to predict trends. Visualize the results using Matplotlib and display them in real time on smart glasses.

[0144] In this way, the present invention automates complex data processing within a factory and intuitively displays the analysis results in real time, thereby improving work efficiency and enabling rapid response.

[0145] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0146] Step 1:

[0147] The server collects data from various sensors installed in the factory (such as temperature, humidity, and machine operation status). The server periodically obtains information from these sensors using REST API and MQTT protocol and stores it in a database. It receives raw data from the sensors as input and generates data in a standard format as output.

[0148] Step 2:

[0149] The server cleans and standardizes the collected data. It uses NumPy and Pandas to detect, impute, and correct missing and outlier values. It also converts data recorded in different units into a common unit. It receives raw sensor data as input and obtains cleaned and standardized data as output.

[0150] Step 3:

[0151] The server applies machine learning algorithms to the cleaned and standardized data to detect anomalies and predict trends. It uses Scikit-Learn to create an anomaly detection model and TensorFlow to predict future trends. It receives preprocessed data as input and generates analysis results, including anomalies and predictions, as output.

[0152] Step 4:

[0153] The server visualizes the analysis results. It uses Matplotlib or Plotly to display predicted data fluctuations and anomaly detection results in graphs and charts. It receives analyzed data as input and generates visualized data (graphs and charts) as output.

[0154] Step 5:

[0155] The server transmits the visualized data to the user interface, transmits the visualized data in real time in a format accessible to the user, and receives the visualized data as input and generates data that is transmitted to the user interface as output.

[0156] Step 6:

[0157] The terminal (smart glasses, smartphone, etc.) receives the visualization data sent from the server and displays it on the augmented reality display. Unity or Vuforia is used to overlay it on the physical environment in the factory. It receives the visualization data from the server as input and generates the augmented reality data that is displayed on the display as output.

[0158] The above processing steps enable factory workers to check data in real time and take prompt action if an abnormality is detected.

[0159] 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.

[0160] The system based on the present invention automates the entire process from data acquisition to analysis and visualization of the results, and further combines it with an emotion engine that recognizes the user's emotions to provide more appropriate and personalized insights to the user. Specific embodiments of the system are described below.

[0161] 1. Data collection

[0162] The server connects to multiple data sources (e.g., sensors, APIs, databases) to collect information, setting any necessary authentication and connection parameters along the way.

[0163] Example: A server sends an HTTP request to a temperature sensor every 5 minutes to collect the latest temperature data, while simultaneously connecting to a social media API to collect user posts related to specific keywords.

[0164] 2. Pretreatment

[0165] The server cleans and standardizes the collected data, including imputing missing data and correcting outliers.

[0166] Example: The server fills in missing temperature data with previous or next values, converts data expressed in Fahrenheit to Celsius, and formats all data into a uniform timestamp format.

[0167] 3. Data Analysis

[0168] The server then applies machine learning algorithms to the pre-processed data, enabling it to detect anomalies and predict future trends.

[0169] Example: The server builds a regression model based on past temperature data to predict future temperature fluctuations, and if an abnormally high temperature is detected, reports the time and temperature.

[0170] 4. Visualizing the results

[0171] The server visualizes the analysis results in a user-friendly format, which includes generating graphs and charts.

[0172] Example: The server displays the predicted temperature change as a line graph, highlighting outliers.

[0173] 5. User Interface

[0174] The terminal receives the visualization data sent from the server and displays it on the screen, which the user can use to check the results and take necessary actions.

[0175] Example: A temperature forecast graph sent from a server is displayed on a tablet device, allowing the user to consider future measures.

[0176] 6. Incorporating an Emotional Engine

[0177] The server recognizes the user's emotions using an emotion engine, which analyzes voice and facial expression data to estimate the user's current emotional state.

[0178] Example: When a user speaks into the device, the voice data is sent to the server, and the emotion engine analyzes and recognizes the user's emotions (e.g., joy, sadness, surprise).

[0179] 7. Emotion-Based Data Adjustment

[0180] The server adjusts the analysis results and visualization data based on the user's perceived emotions, for example, providing a simpler and easier-to-understand visualization if the user is feeling stressed.

[0181] Example: If the server detects that the user is tired, it displays a simple summary on the screen instead of a complex graph.

[0182] Through these steps, the system based on the present invention can highly automate the entire process, from data collection to pre-processing, analysis, result visualization and emotion recognition, and provide personalized insights to users.

[0183] The processing flow will be explained below.

[0184] Step 1: Connecting the Data Source

[0185] The server configures the connection to the data source (e.g., temperature sensor, social media API, database) by specifying the sensor's endpoint URL and setting up API credentials.

[0186] Step 2: Getting the data

[0187] The server periodically retrieves information from connected data sources, for example, collecting data from a temperature sensor every five minutes, or calling social media APIs in real time to collect post data.

[0188] Step 3: Cleaning the data

[0189] The server then cleans the acquired data, which includes imputing missing values ​​and detecting and correcting outliers by filling in missing temperature data with previous and subsequent values ​​and removing or adjusting extremely high or low values.

[0190] Step 4: Standardize the data

[0191] The server standardizes the cleaned data, for example converting temperature data from Fahrenheit to Celsius and aligning all data timestamps to a uniform format.

[0192] Step 5: Feature extraction

[0193] The server extracts the features required for analysis from the data, such as the average temperature, maximum and minimum temperatures, and temperature fluctuation range for each day.

[0194] Step 6: Applying machine learning algorithms

[0195] The server then uses the extracted features to apply machine learning algorithms, such as building a regression model using past temperature data to predict future temperature fluctuations.

[0196] Step 7: Visualize the analysis results

[0197] The server visualizes the analysis results, generating a line graph showing the predicted temperature results and highlighting outliers.

[0198] Step 8: Incorporating the Emotion Engine

[0199] The server recognizes the user's emotions using an emotion engine, which analyzes voice and facial expression data to estimate the user's current emotional state.

[0200] Step 9: Adjust data based on sentiment

[0201] The server adjusts the analysis results and visualization data based on the user's perceived emotions, for example, providing a simpler and easier-to-understand visualization if the user is feeling stressed.

[0202] Step 10: Send visualization data

[0203] The server transmits the visualized analysis results to a user interface, for example, by transmitting the generated graphs to a terminal.

[0204] Step 11: Receiving and displaying data

[0205] The device receives the visualization data sent from the server and displays it on the screen. Specifically, a temperature forecast graph is displayed on the tablet device for the user to check.

[0206] Step 12: User review and decision making

[0207] The user can check the analysis results displayed on the device and make the necessary decisions, such as adjusting heating and cooling or considering additional measures based on future temperature predictions.

[0208] Example 2

[0209] 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."

[0210] In conventional data analysis systems, the processes from data collection to analysis and visualization are not automated, which means that they require a great deal of time and effort. Furthermore, they lack the ability to recognize user emotions and adjust data accordingly, making it difficult to provide information in an optimal format to users.

[0211] 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.

[0212] In this invention, the server includes means for acquiring information from data sources, means for cleaning and standardizing the acquired data, means for analyzing the pre-processed data using machine learning algorithms, means for visualizing the analysis results, means for transmitting the visualized data to a user interface, means for analyzing the voice data and facial expression data to estimate the emotional state of the user, and means for adjusting the analysis results and the visualized data based on the emotional state, thereby providing personalized insights to the user and automating the entire process.

[0213] "Data source" refers to a device or system that provides data, including sensors, APIs, databases, and other diverse sources.

[0214] "Cleaning" refers to the process of removing noise and outliers from data and filling in missing data.

[0215] "Standardization" refers to the process of converting data expressed in different formats into a unified format, including, for example, unifying different units of measurement or timestamp formats.

[0216] A "machine learning algorithm" is a set of mathematical models for data analysis and prediction, which can automatically detect patterns and trends.

[0217] "Analysis" refers to the process of applying statistical and mathematical methods to collected and pre-processed data to derive useful insights and predictive results.

[0218] "Visualization" refers to the process of presenting analytical results in a form that is easy for users to understand, including the generation of graphs and charts.

[0219] "User interface" refers to the interface through which a user and a system communicate with each other. This includes devices such as computers, smartphones, and tablets.

[0220] "Emotion engine" refers to technology that analyzes data such as voice and facial expressions to recognize the user's emotional state, making it possible to grasp the user's psychological state.

[0221] "Personalized insights" refers to information and suggestions that are optimized based on the individual characteristics and status of each user, enabling more appropriate and personalized services to be provided.

[0222] "Automation" refers to the state in which a series of operations or processes are carried out automatically without human intervention, resulting in efficient and error-free processing.

[0223] The system according to the present invention automates the entire process from data acquisition to analysis, visualization, and user emotion recognition, providing highly personalized insights. Specific embodiments of this system are described below.

[0224] 1. Data collection

[0225] The server connects to multiple data sources and collects the required data. For example, the server uses HTTP requests and SQL queries to retrieve data from sensors, APIs, databases, and other sources.

[0226] Example: A server sends an HTTP request every 5 minutes to collect the latest temperature data from a temperature sensor. It also connects to a social media API to retrieve user posts related to the keyword "climate change."

[0227] 2. Data Preprocessing

[0228] The server cleans and standardizes the collected data, a process that involves filling in missing data, correcting outliers, and standardizing the data format.

[0229] Example: The server fills in missing temperature data with previous or next values, converts data expressed in Fahrenheit to Celsius, and formats all data into a uniform timestamp format.

[0230] 3. Data Analysis

[0231] The server then applies machine learning algorithms to the pre-processed data, enabling it to detect anomalies and predict future trends.

[0232] Example: The server builds a regression model based on historical temperature data to predict temperature fluctuations over the next week, and reports any abnormally high temperatures recorded during a particular time period.

[0233] 4. Visualizing the results

[0234] The server visualizes the analysis results in a user-friendly format, which includes generating graphs and charts.

[0235] Example: The server displays a line graph of predicted temperature changes, highlighting outliers in red, and providing tooltips with detailed information about each data point.

[0236] 5. User Interface

[0237] The terminal receives the visualization data sent from the server and displays it on the screen, which the user can use to check the results and take necessary actions.

[0238] Example: A tablet device displays a temperature forecast graph sent from a server in a web browser. The user can view detailed information by touching a data point on the screen.

[0239] 6. Incorporating an Emotional Engine

[0240] The server recognizes the user's emotions using an emotion engine, which analyzes voice data and facial expression image data to estimate the user's current emotional state.

[0241] Example: When a user says "It's cold today," the voice data is sent to the server, where the speech recognition engine converts the speech into text data. The emotion engine then recognizes the user's emotional state as "I feel cold."

[0242] 7. Emotion-Based Data Adjustment

[0243] The server adjusts the analysis results and visualization data based on the user's perceived emotions, for example, providing a simpler and easier-to-understand visualization if the user is feeling stressed.

[0244] Example: If the server detects that the user is tired, it will remove complex graphs and display only the most important information in bulleted form, and it will also optimize the use of colors and font sizes.

[0245] As a result, the system automates the entire process for users, from data collection to analysis and visualization, and by incorporating emotion recognition, it is possible to provide personalized insights.

[0246] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0247] Step 1:

[0248] Data collection

[0249] The server retrieves information from multiple data sources. Specifically, the server sends HTTP requests to pre-configured URLs to collect data from APIs and also sends SQL queries to databases to retrieve information. The input is data from sensors, APIs, databases, etc., and the output is the collected raw data.

[0250] What it does: The server sends an HTTP request every 5 minutes to get the latest temperature data from the temperature sensor, and also sends a request containing the keyword "climate change" to social media APIs to gather related information.

[0251] Step 2:

[0252] Data Preprocessing

[0253] The server cleans and standardizes the collected data. This step takes raw data as input and produces processed data as output. It also fills gaps in the data, corrects outliers, and converts data represented in different formats into a unified format.

[0254] What happens: The server fills in missing temperature data with the previous or next value, converts Fahrenheit temperature data to Celsius, and unifies the timestamp format.

[0255] Step 3:

[0256] Data analysis

[0257] The server applies machine learning algorithms to the preprocessed data. The input is the preprocessed data, and the output is the analysis results. This step detects anomalies and predicts future trends.

[0258] Specific operation: The server uses the preprocessed temperature data to build a regression model and predict temperature fluctuations over the next week. Furthermore, if an abnormally high temperature is recorded, the server outputs the time and temperature as abnormal data.

[0259] Step 4:

[0260] Visualizing the results

[0261] The server outputs the analysis results in a visually understandable format. The input is the analysis results, and the output is visualized data (graphs and charts).

[0262] What it does: The server visualizes future temperature fluctuation data as a line graph, highlighting outliers in red, and providing detailed information about each data point as a tooltip.

[0263] Step 5:

[0264] Send and display to the user interface

[0265] The terminal receives the visualization data sent from the server and displays it on the screen. The input is the visualization data sent from the server, and the output is a display in a format that can be confirmed by the user.

[0266] Specific operation: The tablet device displays the temperature forecast graph sent from the server on a web browser. The user can check detailed information by touching a data point on the graph.

[0267] Step 6:

[0268] Incorporating an emotion engine

[0269] The server uses an emotion engine to recognize the user's emotions. The input is voice data or facial expression data from the user, and the output is the user's emotional state.

[0270] How it works: When a user says "It's cold today," the voice data is sent to the server, where the speech recognition engine converts the speech into text. The emotion engine then determines the user's emotional state as "feeling cold."

[0271] Step 7:

[0272] Emotion-based data adjustment

[0273] The server adjusts the analysis results and visualization data based on the recognized user emotion. The input is the user's emotional state, and the output is the adjusted analysis results and visualization data.

[0274] What it does: When the server detects that the user is tired, it will not display complex graphs, but will instead display only the most important information in bulleted form, and will optimize color usage and font size.

[0275] Through these steps, the system of the present invention realizes a highly automated data analysis and visualization process, and further provides personalized insights that take into account the user's emotions.

[0276] (Application example 2)

[0277] 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."

[0278] Conventional data analysis systems have been effective to a certain extent by displaying the analysis results of collected data, but this alone has the problem of not being able to respond flexibly based on the user's emotions. In particular, in the security field, where situations that cause users to feel anxious or stress often occur, there is a need for systems that not only visualize data but also reflect the user's emotional state and provide appropriate actions.

[0279] 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.

[0280] In this invention, the server includes means for acquiring information from a data source, means for cleaning and standardizing the acquired data, means for analyzing the preprocessed data using a machine learning algorithm, means for visualizing the analysis results, means for transmitting the visualized data to a user terminal, means for displaying the visualized data on the user terminal, means for recognizing a user's emotion, and means for adjusting the analysis results and the visualized data based on the recognized emotion. This allows the system to sense when the user is emotionally stressed or anxious and provide optimal visualizations and warnings according to the emotion.

[0281] A "data source" is an information source that provides information from multiple sensors, APIs, databases, etc.

[0282] "Acquisition" is the act of gathering the necessary information from a data source.

[0283] "Cleaning" is the process of removing missing values ​​and outliers from collected data and arranging the data.

[0284] "Standardization" is the process of standardizing data formats to ensure consistency when analyzing and visualizing them.

[0285] "Preprocessing" is a series of operations to prepare data for analysis.

[0286] A "machine learning algorithm" is a computational method that mimics human learning abilities to find patterns and rules in data.

[0287] "Analysis" is the act of analyzing information based on collected data to gain useful knowledge and insights.

[0288] "Visualization" refers to the presentation of analytical results in a visual format such as a graph or chart.

[0289] A "user terminal" is a device that a user can directly operate (e.g., a smartphone, tablet, or PC).

[0290] "Send" is the act of transferring data from the server to the user terminal.

[0291] "Display" refers to the act of presenting information on the screen of a user terminal.

[0292] "Emotion recognition" is the process of determining a user's emotional state by analyzing voice and facial expression data.

[0293] "Adjustment" refers to changing the content or format of analysis results or visualization data based on recognized emotions.

[0294] The system based on this invention automates the entire process from data acquisition to analysis, visualization of results, and adjustment based on user emotions, providing high flexibility and adaptability for use in the security field. The specific configuration and functions of this system are described below.

[0295] The system mainly includes the following elements: a server, multiple data sources (sensors, APIs, databases), and user devices (smartphones, tablets, PCs).

[0296] First, the server periodically retrieves data from sensors and APIs using HTTP requests. To collect this data, the server needs to set authentication information and connection parameters. For example, temperature data from a temperature sensor is retrieved every five minutes, along with image data from a security camera.

[0297] The acquired data is then cleaned and standardized. Cleaning involves imputing missing values ​​and correcting outliers. For example, missing temperature data is imputed with previous or next values, and a standardization process is performed to convert the represented data into a unified format.

[0298] The cleaned and standardized data is then analyzed using machine learning algorithms. This analysis detects anomalies and predicts future trends. For example, if an abnormally high temperature is detected, the time and temperature are reported. The server performs this analysis using libraries such as Python and TensorFlow.

[0299] The results of the analysis are visualized and presented in a user-friendly format, often using libraries such as Matplotlib or D3.js, and are displayed as graphs or charts with outliers highlighted.

[0300] These visualized data are sent to the user's terminal and displayed on the screen. The user can check it and take necessary actions. The user interface is sometimes provided on a web browser, and the data can be checked in real time.

[0301] The emotion engine is built into the server and recognizes the user's emotions. It analyzes voice and facial expression data to estimate the user's current emotional state. What the user says to the device is sent to the server and analyzed by the emotion engine. This engine uses NLP libraries and generative AI models.

[0302] Based on the perceived emotion, the analysis results and visualization data are adjusted. For example, if the server detects that the user is feeling stressed, it will provide a more concise and easy-to-understand visualization, allowing the user to process information more efficiently.

[0303] As a specific example, if a user performs high activity (clicking or typing) on ​​a computer for more than 10 minutes continuously, a warning is issued immediately if it is recognized that the user is feeling stressed. In this case, an example of a prompt sentence to the generative AI model is as follows: "The user's frequency of operation is higher than usual. Determine whether the user is feeling stressed and recommend appropriate action."

[0304] By realizing such a system, it will be possible to provide highly flexible security services that take into consideration the feelings of users in the security field.

[0305] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0306] Step 1:

[0307] The user performs a specific operation using the device.

[0308] Input: Data on user operations and behavior on a computer or smartphone.

[0309] Specific actions: The user operates the web browser and performs a specific action (click, keyboard input, etc.).

[0310] Step 2:

[0311] The server retrieves the information from the data source.

[0312] Input: Raw data from multiple sensors, APIs and databases.

[0313] Output: Acquired sensor data and API responses.

[0314] What happens: The server retrieves temperature sensor and security camera data using HTTP requests.

[0315] Step 3:

[0316] The server cleans and standardizes the data it retrieves.

[0317] Input: The raw data obtained.

[0318] Output: Cleaned and standardized data.

[0319] Specific operation: The server complements missing temperature data with previous and next values ​​and standardizes the representation format, for example, converting temperature data from Fahrenheit to Celsius.

[0320] Step 4:

[0321] The server analyzes the preprocessed data using machine learning algorithms.

[0322] Input: Cleaned and standardized data.

[0323] Output: Anomaly detection results and trend predictions.

[0324] What it does: The server runs anomaly detection algorithms using Python and TensorFlow to detect high temperatures and abnormal behavior.

[0325] Step 5:

[0326] The server visualizes the analysis results.

[0327] Input: Analysis results.

[0328] Output: Visualized data in the form of graphs and charts.

[0329] What it does: The server uses Matplotlib and D3.js to convert the data into line and bar graphs.

[0330] Step 6:

[0331] The server transmits the visualized data to the user terminal.

[0332] Input: Visualization data.

[0333] Output: Visualization data sent to the user device.

[0334] Specific operation: The server sends data to the user terminal in real time using HTTP responses or WebSockets.

[0335] Step 7:

[0336] The user terminal displays the visualization data.

[0337] Input: Visualization data sent from the server.

[0338] Output: Graphs and charts displayed on the screen.

[0339] Specific operation: The user's device displays the visualized data on a web browser, and the user checks it.

[0340] Step 8:

[0341] The server recognizes the user's emotions.

[0342] Input: User's voice and facial expression data.

[0343] Output: The user's emotional state (e.g., happy, sad, surprised, stressed).

[0344] Specific operation: The server uses NLP libraries and generative AI models to analyze the user's emotions from voice and facial expression data.

[0345] Step 9:

[0346] The server adjusts the analysis results and visualization data based on the emotions it recognizes.

[0347] Input: The user's emotional state.

[0348] Output: Adjusted visualization data and warning messages.

[0349] Specific operation: Based on the results of the emotion engine, the server converts the visualized data into a concise format and generates appropriate warning messages.

[0350] Step 10:

[0351] The user reviews the adjusted data and takes any necessary action.

[0352] Input: Adjusted visualization data and warning messages.

[0353] Output: User's corrective action.

[0354] Specific actions: The user views the data on the device and, if necessary, contacts the system administrator or strengthens security measures.

[0355] 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.

[0356] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0357] 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.

[0358] [Second embodiment]

[0359] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0360] 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.

[0361] 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).

[0362] 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.

[0363] 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.

[0364] 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).

[0365] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0366] 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.

[0367] 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.

[0368] 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.

[0369] 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.

[0370] 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."

[0371] The system according to the present invention automates multiple processes, allowing users to efficiently analyze large amounts of data and quickly gain insights. Specific embodiments of the system are described below.

[0372] 1. Data collection

[0373] The server connects to various data sources (e.g. sensors, APIs, databases) and during this connection process sets the necessary authentication information and connection parameters.

[0374] Example: A server sends an HTTP request to a temperature sensor every 5 minutes to get the latest temperature data, while simultaneously retrieving user posts related to a specific keyword from a social media API.

[0375] 2. Pretreatment

[0376] The server cleans the acquired data, which includes imputing missing values ​​and detecting and correcting outliers. It also standardizes the data, for example, converting data provided in different units into a common unit.

[0377] Example: A server converts temperature data recorded in Fahrenheit to Celsius and formats all data into a uniform timestamp format.

[0378] 3. Data Analysis

[0379] The server then applies machine learning algorithms to the pre-processed data, enabling it to detect anomalies and predict future trends.

[0380] Example: The server creates a regression model based on past temperature data to predict future temperature changes, and if an abnormally high temperature is detected, reports the time and temperature.

[0381] 4. Visualizing the results

[0382] The server visualizes the analysis results in a user-friendly format, which includes generating graphs and charts.

[0383] Example: The server displays predicted temperature changes as a line graph and highlights any anomalies detected.

[0384] 5. User Interface

[0385] The terminal receives the visualization data sent from the server and displays it on the screen, which the user can use to check the results and take necessary actions.

[0386] Example: A temperature forecast graph sent from a server is displayed on a tablet device, allowing the user to consider future measures.

[0387] Through these processes, the system based on the present invention automates the entire process from data collection, pre-processing, analysis, visualization of results, and display of data on a user interface, providing fast and accurate insights.

[0388] The processing flow will be explained below.

[0389] Step 1: Connecting the Data Source

[0390] The server configures connections to data sources (sensors, APIs, databases, etc.), for example specifying endpoint URLs for sensors and setting up credentials for social media APIs.

[0391] Step 2: Getting the data

[0392] The server periodically retrieves information from connected data sources, for example, collecting data from a temperature sensor every five minutes, or calling social media APIs in real time to collect post data.

[0393] Step 3: Cleaning the data

[0394] The server then cleans the acquired data by imputing missing values ​​and detecting and correcting outliers. For example, it imputes missing temperature data with previous and subsequent values, and removes or corrects extremely high or low values.

[0395] Step 4: Standardize the data

[0396] The server standardizes the cleaned data, for example converting temperature data from Fahrenheit to Celsius and aligning all data timestamps to a uniform format.

[0397] Step 5: Feature extraction

[0398] The server extracts the features required for analysis from the data, such as the average temperature, maximum and minimum temperatures, and temperature fluctuation range for each day.

[0399] Step 6: Applying machine learning algorithms

[0400] The server then uses the extracted features to apply machine learning algorithms, such as building a regression model using past temperature data to predict future temperature fluctuations.

[0401] Step 7: Visualize the analysis results

[0402] The server then visualizes the results of the analysis, for example generating a line graph showing the temperature predictions and highlighting any outliers.

[0403] Step 8: Submitting visualization data

[0404] The server transmits the visualized analysis results to a user interface, for example, by transmitting the generated graphs to a terminal.

[0405] Step 9: Receive and display data

[0406] The device receives the visualization data sent from the server and displays it on the screen. For example, a temperature forecast graph is displayed on a tablet device for the user to check.

[0407] Step 10: User review and decision making

[0408] The user can check the analysis results displayed on the device and make necessary decisions, such as adjusting heating and cooling or considering additional measures based on future temperature predictions.

[0409] Example 1

[0410] 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."

[0411] Traditionally, efficiently analyzing large amounts of data collected from various data sources and quickly and accurately gaining insights required a great deal of time and effort. Furthermore, acquiring data from multiple data sources using different protocols and authentication information was complex, and the process of preprocessing, analyzing, visualizing, and providing it to users was not easy. Furthermore, there was a need to automate these processes to detect anomalies and predict future trends.

[0412] 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.

[0413] In this invention, the server includes means for acquiring information from data sources, means for cleaning and standardizing the acquired data, means for analyzing the preprocessed data using a machine learning algorithm, means for visualizing the analysis results, means for transmitting the visualized data to a user interface, and means for displaying the visualized data on the user interface. This allows efficient data collection from multiple data sources using different protocols and authentication information, and enables analysis, anomaly detection, and trend prediction using a machine learning algorithm using the cleaned and standardized data. In addition, by visualizing the analysis results and providing them on the user interface, users can quickly and accurately gain insights.

[0414] A "data source" is a device or system that serves as an input source for providing information.

[0415] "Means of obtaining information" are the methods or processes used to collect data from data sources.

[0416] "Data cleaning methods" are methods or processes for removing unnecessary information from collected data and correcting missing or erroneous values.

[0417] A "data standardization method" is a method or process for converting data in different units or formats into a single common format.

[0418] A "machine learning algorithm" is a mathematical model that analyzes collected and preprocessed data to find patterns and relationships.

[0419] "Means of analysis" refers to the methods or processes used to extract useful information from pre-processed data using machine learning algorithms.

[0420] "Means for visualizing analysis results" refers to methods or tools for displaying information obtained through data analysis in a visual format such as graphs or charts.

[0421] "Means for transmitting visualization data to a user interface" refers to communication means or protocols that allow a user to view the visualized data through the interface.

[0422] "Means for displaying visualized data in a user interface" refers to a display device or software that allows a user to easily view and manipulate the visualized data.

[0423] "Anomaly detection" is the process of finding and identifying unnatural patterns or values ​​in data.

[0424] "Trend forecasting" is the process of predicting future trends and patterns based on past data.

[0425] The system according to the present invention allows users to efficiently analyze large amounts of data and quickly gain insights. It also allows data collection from multiple data sources using different protocols and authentication information, and uses machine learning algorithms to detect anomalies and predict future trends. Specific embodiments of the system are described below.

[0426] 1. Data collection

[0427] The server connects to various data sources, such as temperature sensors and social media APIs, to collect data. This process involves setting the necessary authentication information and connection parameters. For example, HTTP requests are used to periodically retrieve data from the temperature sensor and retrieve posts related to specific keywords from the social media API. This allows the server to collect temperature data and text data from social media.

[0428] 2. Data Preprocessing

[0429] The server cleans and standardizes the collected data. During this stage, missing values ​​are imputed and outliers are corrected. Data standardization also involves converting data provided in different units into a common format. For example, temperature data recorded in Fahrenheit is converted to Celsius. This preprocessing improves data quality and facilitates subsequent analysis.

[0430] 3. Data Analysis

[0431] The server then applies machine learning algorithms to the preprocessed data to detect anomalies and predict future trends. For example, it creates a regression model based on past temperature data to predict future temperature changes. It also reports abnormally high or low temperatures if they are detected. This analysis is a key step in helping users quickly gain insights.

[0432] 4. Visualizing the results

[0433] The server visualizes the results of the data analysis. Specifically, it displays predicted temperature changes as a line graph and highlights any detected anomalies. This visualization allows users to intuitively understand trends and anomalies in the data.

[0434] 5. User Interface

[0435] The device receives the visualized data sent from the server and displays it on the screen. The user can use this to check the results and take necessary actions. For example, a user can check the temperature forecast graph displayed on the tablet device and make a plan to adjust heating and cooling in the future. Users can also click on anomaly detection results to check detailed information.

[0436] Example prompt

[0437] Below is an example of a prompt sentence to input to the generative AI model.

[0438] Prompt statement:

[0439] Design a system that meets the following criteria:

[0440] 1. A server that collects data from various data sources (e.g., temperature sensors, social media APIs).

[0441] 2. Clean the collected data, complete missing values, and correct outliers.

[0442] 3. Use machine learning algorithms to analyze the collected data and predict future trends.

[0443] 4. Visualize the analysis results and present them in an easy-to-understand format.

[0444] 5. Display the analysis results on a tablet device so that the user can take appropriate action.

[0445] As described above, this system consistently automates data collection, preprocessing, analysis, and visualization of results, and is optimized to enable users to quickly gain insights.

[0446] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0447] Step 1: Collect data

[0448] The server connects to multiple data sources, such as temperature sensors and social media APIs. The inputs are the sensor's IP address, port number, authentication key, and API access token and query parameters. Specifically, the server sends an HTTP request to the temperature sensor every five minutes to retrieve temperature data. At the same time, it retrieves post data related to specified keywords from the social media API. The retrieved data is temperature data (e.g., 25.3°F) and social media post data (e.g., 10 posts related to "global warming").

[0449] Step 2: Preprocessing the data

[0450] The server cleans and standardizes the collected data. Specifically, it uses collected temperature data and social media post data as input. First, the server detects missing values ​​and fills them with the average of the surrounding data. Next, it replaces outliers (e.g., temperature values ​​that deviate significantly) with the median. Finally, it converts temperature data recorded in Fahrenheit to Celsius. As output, it obtains cleaned and standardized data (e.g., temperature data of 22.75°C and standardized text data).

[0451] Step 3: Analyze the data

[0452] The server applies machine learning algorithms to analyze the preprocessed data. The cleaned and standardized temperature data and social media post data are used as inputs. The server uses these data to create a regression model to predict future temperature changes. It also runs an anomaly detection algorithm to identify unusual data points. Specifically, the regression model predicts future temperatures and lists outliers (e.g., temperatures above 30°C). The output is the predicted temperature data (e.g., the predicted temperature for the next day is 25.1°C) and the anomaly detection results.

[0453] Step 4: Visualize the results

[0454] The server uses the predicted temperature data and anomaly detection results as input to visualize the analysis results. Specifically, it generates line graphs and charts based on these data. It displays the line graph showing the temperature change and the anomaly detection results in highlighted form. As output, visualized data (e.g., graphs or charts) is generated.

[0455] Step 5: Display in the user interface

[0456] The terminal receives the visualized data sent from the server and displays it on the screen. The visualized data (graphs and charts) is used as input. The user can view this to check the current situation and take necessary actions. Specifically, the user can view the temperature forecast graph displayed on the tablet terminal and make a plan to adjust heating and cooling. They can also click on anomaly detection results to view detailed information. The output is the visualized data displayed on the user interface.

[0457] (Application example 1)

[0458] 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."

[0459] Conventional factory monitoring systems have difficulty analyzing the diverse data collected from sensors in real time to detect anomalies and perform predictive analysis. They also lack a way to display the analysis results in an intuitive and easy-to-understand way for on-site workers. In particular, there was no way for workers to check real-time data while on the move, which often led to delays in rapid response.

[0460] 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.

[0461] In this invention, the server includes means for acquiring information from a data source, means for cleaning and standardizing the acquired data, means for analyzing the preprocessed data using a machine learning algorithm, means for visualizing the analysis results, means for transmitting the visualized data to a user interface, means for displaying the visualized data on the user interface, and means for displaying real-time data on an augmented reality display, thereby enabling real-time anomaly detection and predictive analysis, allowing workers to intuitively check necessary information even while on the move and enabling prompt action.

[0462] A "data source" is the source from which information is collected, such as from sensors, APIs, or databases.

[0463] "Cleaning" is the process of preparing data by correcting or removing missing or outlier values.

[0464] "Standardization" is the process of converting data provided in different units into a common standard.

[0465] A "machine learning algorithm" is a mathematical technique that uses past data to learn patterns and make predictions or detect anomalies.

[0466] "Analysis" is the process of applying specific algorithms to collected data to obtain desired information.

[0467] "Visualization" refers to displaying the results of data analysis in the form of graphs, charts, etc., making them easy for humans to understand.

[0468] A "user interface" is an operation screen or display device that allows a user to interact with a system.

[0469] An "augmented reality display" is a display device that uses technology to overlay computer-generated information on the real world.

[0470] The system that realizes this application example analyzes various data obtained from sensors in a factory environment in real time and displays the results on an augmented reality display. This system uses the following hardware and software.

[0471] The server uses Python and APIs to collect data from sensors, such as temperature, humidity, and machine operating status data, using REST APIs and MQTT protocols.

[0472] Next, the server performs data preprocessing. It uses NumPy and Pandas to clean the collected data and to impute and correct missing or outlier values. It also standardizes data provided in different units to unify them. For example, it converts temperature data from Fahrenheit to Celsius.

[0473] Once preprocessed, the data is analyzed using machine learning algorithms. The server uses Scikit-Learn and TensorFlow to detect anomalies and predict trends. For example, it applies a regression model created using past data to predict future temperature changes. If an abnormally high temperature is detected, the information is analyzed in real time.

[0474] The analysis results are visualized and sent to a user interface. The server generates graphs using Matplotlib or Plotly and highlights any anomalies detected. For example, predicted temperature changes are displayed as a line graph, and anomalies are highlighted with a red marker.

[0475] Finally, the visualized data is displayed in real time on an augmented reality display, where smart glasses or other devices use Unity or Vuforia to overlay the analysis results, allowing factory workers to intuitively view the information on the move.

[0476] As a concrete example, if the following prompt sentence is input into a generative AI model, a program for the entire system can be generated.

[0477] Create a Python program to collect data from sensors in a factory and perform anomaly detection and trend prediction. Clean the data and convert its units using the Pandas library, then use Scikit-Learn to detect anomalies and TensorFlow to predict trends. Visualize the results using Matplotlib and display them in real time on smart glasses.

[0478] In this way, the present invention automates complex data processing within a factory and intuitively displays the analysis results in real time, thereby improving work efficiency and enabling rapid response.

[0479] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0480] Step 1:

[0481] The server collects data from various sensors installed in the factory (such as temperature, humidity, and machine operation status). The server periodically obtains information from these sensors using REST API and MQTT protocol and stores it in a database. It receives raw data from the sensors as input and generates data in a standard format as output.

[0482] Step 2:

[0483] The server cleans and standardizes the collected data. It uses NumPy and Pandas to detect, impute, and correct missing and outlier values. It also converts data recorded in different units into a common unit. It receives raw sensor data as input and obtains cleaned and standardized data as output.

[0484] Step 3:

[0485] The server applies machine learning algorithms to the cleaned and standardized data to detect anomalies and predict trends. It uses Scikit-Learn to create an anomaly detection model and TensorFlow to predict future trends. It receives preprocessed data as input and generates analysis results, including anomalies and predictions, as output.

[0486] Step 4:

[0487] The server visualizes the analysis results. It uses Matplotlib or Plotly to display predicted data fluctuations and anomaly detection results in graphs and charts. It receives analyzed data as input and generates visualized data (graphs and charts) as output.

[0488] Step 5:

[0489] The server transmits the visualized data to the user interface, transmits the visualized data in real time in a format accessible to the user, and receives the visualized data as input and generates data that is transmitted to the user interface as output.

[0490] Step 6:

[0491] The terminal (smart glasses, smartphone, etc.) receives the visualization data sent from the server and displays it on the augmented reality display. Unity or Vuforia is used to overlay it on the physical environment in the factory. It receives the visualization data from the server as input and generates the augmented reality data that is displayed on the display as output.

[0492] The above processing steps enable factory workers to check data in real time and take prompt action if an abnormality is detected.

[0493] 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.

[0494] The system based on the present invention automates the entire process from data acquisition to analysis and visualization of the results, and further combines it with an emotion engine that recognizes the user's emotions to provide more appropriate and personalized insights to the user. Specific embodiments of the system are described below.

[0495] 1. Data collection

[0496] The server connects to multiple data sources (e.g., sensors, APIs, databases) to collect information, setting any necessary authentication and connection parameters along the way.

[0497] Example: A server sends an HTTP request to a temperature sensor every 5 minutes to collect the latest temperature data, while simultaneously connecting to a social media API to collect user posts related to specific keywords.

[0498] 2. Pretreatment

[0499] The server cleans and standardizes the collected data, including imputing missing data and correcting outliers.

[0500] Example: The server fills in missing temperature data with previous or next values, converts data expressed in Fahrenheit to Celsius, and formats all data into a uniform timestamp format.

[0501] 3. Data Analysis

[0502] The server then applies machine learning algorithms to the pre-processed data, enabling it to detect anomalies and predict future trends.

[0503] Example: The server builds a regression model based on past temperature data to predict future temperature fluctuations, and if an abnormally high temperature is detected, reports the time and temperature.

[0504] 4. Visualizing the results

[0505] The server visualizes the analysis results in a user-friendly format, which includes generating graphs and charts.

[0506] Example: The server displays the predicted temperature change as a line graph, highlighting outliers.

[0507] 5. User Interface

[0508] The terminal receives the visualization data sent from the server and displays it on the screen, which the user can use to check the results and take necessary actions.

[0509] Example: A temperature forecast graph sent from a server is displayed on a tablet device, allowing the user to consider future measures.

[0510] 6. Incorporating an Emotional Engine

[0511] The server recognizes the user's emotions using an emotion engine, which analyzes voice and facial expression data to estimate the user's current emotional state.

[0512] Example: When a user speaks into the device, the voice data is sent to the server, and the emotion engine analyzes and recognizes the user's emotions (e.g., joy, sadness, surprise).

[0513] 7. Emotion-Based Data Adjustment

[0514] The server adjusts the analysis results and visualization data based on the user's perceived emotions, for example, providing a simpler and easier-to-understand visualization if the user is feeling stressed.

[0515] Example: If the server detects that the user is tired, it displays a simple summary on the screen instead of a complex graph.

[0516] Through these steps, the system based on the present invention can highly automate the entire process, from data collection to pre-processing, analysis, result visualization and emotion recognition, and provide personalized insights to users.

[0517] The processing flow will be explained below.

[0518] Step 1: Connecting the Data Source

[0519] The server configures the connection to the data source (e.g., temperature sensor, social media API, database) by specifying the sensor's endpoint URL and setting up API credentials.

[0520] Step 2: Getting the data

[0521] The server periodically retrieves information from connected data sources, for example, collecting data from a temperature sensor every five minutes, or calling social media APIs in real time to collect post data.

[0522] Step 3: Cleaning the data

[0523] The server then cleans the acquired data, which includes imputing missing values ​​and detecting and correcting outliers by filling in missing temperature data with previous and subsequent values ​​and removing or adjusting extremely high or low values.

[0524] Step 4: Standardize the data

[0525] The server standardizes the cleaned data, for example converting temperature data from Fahrenheit to Celsius and aligning all data timestamps to a uniform format.

[0526] Step 5: Feature extraction

[0527] The server extracts the features required for analysis from the data, such as the average temperature, maximum and minimum temperatures, and temperature fluctuation range for each day.

[0528] Step 6: Applying machine learning algorithms

[0529] The server then uses the extracted features to apply machine learning algorithms, such as building a regression model using past temperature data to predict future temperature fluctuations.

[0530] Step 7: Visualize the analysis results

[0531] The server visualizes the analysis results, generating a line graph showing the predicted temperature results and highlighting outliers.

[0532] Step 8: Incorporating the Emotion Engine

[0533] The server recognizes the user's emotions using an emotion engine, which analyzes voice and facial expression data to estimate the user's current emotional state.

[0534] Step 9: Adjust data based on sentiment

[0535] The server adjusts the analysis results and visualization data based on the user's perceived emotions, for example, providing a simpler and easier-to-understand visualization if the user is feeling stressed.

[0536] Step 10: Send visualization data

[0537] The server transmits the visualized analysis results to a user interface, for example, by transmitting the generated graphs to a terminal.

[0538] Step 11: Receiving and displaying data

[0539] The device receives the visualization data sent from the server and displays it on the screen. Specifically, a temperature forecast graph is displayed on the tablet device for the user to check.

[0540] Step 12: User review and decision making

[0541] The user can check the analysis results displayed on the device and make the necessary decisions, such as adjusting heating and cooling or considering additional measures based on future temperature predictions.

[0542] Example 2

[0543] 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."

[0544] In conventional data analysis systems, the processes from data collection to analysis and visualization are not automated, which means that they require a great deal of time and effort. Furthermore, they lack the ability to recognize user emotions and adjust data accordingly, making it difficult to provide information in an optimal format to users.

[0545] 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.

[0546] In this invention, the server includes means for acquiring information from data sources, means for cleaning and standardizing the acquired data, means for analyzing the pre-processed data using machine learning algorithms, means for visualizing the analysis results, means for transmitting the visualized data to a user interface, means for analyzing the voice data and facial expression data to estimate the emotional state of the user, and means for adjusting the analysis results and the visualized data based on the emotional state, thereby providing personalized insights to the user and automating the entire process.

[0547] "Data source" refers to a device or system that provides data, including sensors, APIs, databases, and other diverse sources.

[0548] "Cleaning" refers to the process of removing noise and outliers from data and filling in missing data.

[0549] "Standardization" refers to the process of converting data expressed in different formats into a unified format, including, for example, unifying different units of measurement or timestamp formats.

[0550] A "machine learning algorithm" is a set of mathematical models for data analysis and prediction, which can automatically detect patterns and trends.

[0551] "Analysis" refers to the process of applying statistical and mathematical methods to collected and pre-processed data to derive useful insights and predictive results.

[0552] "Visualization" refers to the process of presenting analytical results in a form that is easy for users to understand, including the generation of graphs and charts.

[0553] "User interface" refers to the interface through which a user and a system communicate with each other. This includes devices such as computers, smartphones, and tablets.

[0554] "Emotion engine" refers to technology that analyzes data such as voice and facial expressions to recognize the user's emotional state, making it possible to grasp the user's psychological state.

[0555] "Personalized insights" refers to information and suggestions that are optimized based on the individual characteristics and status of each user, enabling more appropriate and personalized services to be provided.

[0556] "Automation" refers to the state in which a series of operations or processes are carried out automatically without human intervention, resulting in efficient and error-free processing.

[0557] The system according to the present invention automates the entire process from data acquisition to analysis, visualization, and user emotion recognition, providing highly personalized insights. Specific embodiments of this system are described below.

[0558] 1. Data collection

[0559] The server connects to multiple data sources and collects the required data. For example, the server uses HTTP requests and SQL queries to retrieve data from sensors, APIs, databases, and other sources.

[0560] Example: A server sends an HTTP request every 5 minutes to collect the latest temperature data from a temperature sensor. It also connects to a social media API to retrieve user posts related to the keyword "climate change."

[0561] 2. Data Preprocessing

[0562] The server cleans and standardizes the collected data, a process that involves filling in missing data, correcting outliers, and standardizing the data format.

[0563] Example: The server fills in missing temperature data with previous or next values, converts data expressed in Fahrenheit to Celsius, and formats all data into a uniform timestamp format.

[0564] 3. Data Analysis

[0565] The server then applies machine learning algorithms to the pre-processed data, enabling it to detect anomalies and predict future trends.

[0566] Example: The server builds a regression model based on historical temperature data to predict temperature fluctuations over the next week, and reports any abnormally high temperatures recorded during a particular time period.

[0567] 4. Visualizing the results

[0568] The server visualizes the analysis results in a user-friendly format, which includes generating graphs and charts.

[0569] Example: The server displays a line graph of predicted temperature changes, highlighting outliers in red, and providing tooltips with detailed information about each data point.

[0570] 5. User Interface

[0571] The terminal receives the visualization data sent from the server and displays it on the screen, which the user can use to check the results and take necessary actions.

[0572] Example: A tablet device displays a temperature forecast graph sent from a server in a web browser. The user can view detailed information by touching a data point on the screen.

[0573] 6. Incorporating an Emotional Engine

[0574] The server recognizes the user's emotions using an emotion engine, which analyzes voice data and facial expression image data to estimate the user's current emotional state.

[0575] Example: When a user says "It's cold today," the voice data is sent to the server, where the speech recognition engine converts the speech into text data. The emotion engine then recognizes the user's emotional state as "I feel cold."

[0576] 7. Emotion-Based Data Adjustment

[0577] The server adjusts the analysis results and visualization data based on the user's perceived emotions, for example, providing a simpler and easier-to-understand visualization if the user is feeling stressed.

[0578] Example: If the server detects that the user is tired, it will remove complex graphs and display only the most important information in bulleted form, and it will also optimize the use of colors and font sizes.

[0579] As a result, the system automates the entire process for users, from data collection to analysis and visualization, and by incorporating emotion recognition, it is possible to provide personalized insights.

[0580] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0581] Step 1:

[0582] Data collection

[0583] The server retrieves information from multiple data sources. Specifically, the server sends HTTP requests to pre-configured URLs to collect data from APIs and also sends SQL queries to databases to retrieve information. The input is data from sensors, APIs, databases, etc., and the output is the collected raw data.

[0584] What it does: The server sends an HTTP request every 5 minutes to get the latest temperature data from the temperature sensor, and also sends a request containing the keyword "climate change" to social media APIs to gather related information.

[0585] Step 2:

[0586] Data Preprocessing

[0587] The server cleans and standardizes the collected data. This step takes raw data as input and produces processed data as output. It also fills gaps in the data, corrects outliers, and converts data represented in different formats into a unified format.

[0588] What happens: The server fills in missing temperature data with the previous or next value, converts Fahrenheit temperature data to Celsius, and unifies the timestamp format.

[0589] Step 3:

[0590] Data analysis

[0591] The server applies machine learning algorithms to the preprocessed data. The input is the preprocessed data, and the output is the analysis results. This step detects anomalies and predicts future trends.

[0592] Specific operation: The server uses the preprocessed temperature data to build a regression model and predict temperature fluctuations over the next week. Furthermore, if an abnormally high temperature is recorded, the server outputs the time and temperature as abnormal data.

[0593] Step 4:

[0594] Visualizing the results

[0595] The server outputs the analysis results in a visually understandable format. The input is the analysis results, and the output is visualized data (graphs and charts).

[0596] What it does: The server visualizes future temperature fluctuation data as a line graph, highlighting outliers in red, and providing detailed information about each data point as a tooltip.

[0597] Step 5:

[0598] Send and display to the user interface

[0599] The terminal receives the visualization data sent from the server and displays it on the screen. The input is the visualization data sent from the server, and the output is a display in a format that can be confirmed by the user.

[0600] Specific operation: The tablet device displays the temperature forecast graph sent from the server on a web browser. The user can check detailed information by touching a data point on the graph.

[0601] Step 6:

[0602] Incorporating an emotion engine

[0603] The server uses an emotion engine to recognize the user's emotions. The input is voice data or facial expression data from the user, and the output is the user's emotional state.

[0604] How it works: When a user says "It's cold today," the voice data is sent to the server, where the speech recognition engine converts the speech into text. The emotion engine then determines the user's emotional state as "feeling cold."

[0605] Step 7:

[0606] Emotion-based data adjustment

[0607] The server adjusts the analysis results and visualization data based on the recognized user emotion. The input is the user's emotional state, and the output is the adjusted analysis results and visualization data.

[0608] What it does: When the server detects that the user is tired, it will not display complex graphs, but will instead display only the most important information in bulleted form, and will optimize color usage and font size.

[0609] Through these steps, the system of the present invention realizes a highly automated data analysis and visualization process, and further provides personalized insights that take into account the user's emotions.

[0610] (Application example 2)

[0611] 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."

[0612] Conventional data analysis systems have been effective to a certain extent by displaying the analysis results of collected data, but this alone has the problem of not being able to respond flexibly based on the user's emotions. In particular, in the security field, where situations that cause users to feel anxious or stress often occur, there is a need for systems that not only visualize data but also reflect the user's emotional state and provide appropriate actions.

[0613] 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.

[0614] In this invention, the server includes means for acquiring information from a data source, means for cleaning and standardizing the acquired data, means for analyzing the preprocessed data using a machine learning algorithm, means for visualizing the analysis results, means for transmitting the visualized data to a user terminal, means for displaying the visualized data on the user terminal, means for recognizing a user's emotion, and means for adjusting the analysis results and the visualized data based on the recognized emotion. This allows the system to sense when the user is emotionally stressed or anxious and provide optimal visualizations and warnings according to the emotion.

[0615] A "data source" is an information source that provides information from multiple sensors, APIs, databases, etc.

[0616] "Acquisition" is the act of gathering the necessary information from a data source.

[0617] "Cleaning" is the process of removing missing values ​​and outliers from collected data and arranging the data.

[0618] "Standardization" is the process of standardizing data formats to ensure consistency when analyzing and visualizing them.

[0619] "Preprocessing" is a series of operations to prepare data for analysis.

[0620] A "machine learning algorithm" is a computational method that mimics human learning abilities to find patterns and rules in data.

[0621] "Analysis" is the act of analyzing information based on collected data to gain useful knowledge and insights.

[0622] "Visualization" refers to the presentation of analytical results in a visual format such as a graph or chart.

[0623] A "user terminal" is a device that a user can directly operate (e.g., a smartphone, tablet, or PC).

[0624] "Send" is the act of transferring data from the server to the user terminal.

[0625] "Display" refers to the act of presenting information on the screen of a user terminal.

[0626] "Emotion recognition" is the process of determining a user's emotional state by analyzing voice and facial expression data.

[0627] "Adjustment" refers to changing the content or format of analysis results or visualization data based on recognized emotions.

[0628] The system based on this invention automates the entire process from data acquisition to analysis, visualization of results, and adjustment based on user emotions, providing high flexibility and adaptability for use in the security field. The specific configuration and functions of this system are described below.

[0629] The system mainly includes the following elements: a server, multiple data sources (sensors, APIs, databases), and user devices (smartphones, tablets, PCs).

[0630] First, the server periodically retrieves data from sensors and APIs using HTTP requests. To collect this data, the server needs to set authentication information and connection parameters. For example, temperature data from a temperature sensor is retrieved every five minutes, along with image data from a security camera.

[0631] The acquired data is then cleaned and standardized. Cleaning involves imputing missing values ​​and correcting outliers. For example, missing temperature data is imputed with previous or next values, and a standardization process is performed to convert the represented data into a unified format.

[0632] The cleaned and standardized data is then analyzed using machine learning algorithms. This analysis detects anomalies and predicts future trends. For example, if an abnormally high temperature is detected, the time and temperature are reported. The server performs this analysis using libraries such as Python and TensorFlow.

[0633] The results of the analysis are visualized and presented in a user-friendly format, often using libraries such as Matplotlib or D3.js, and are displayed as graphs or charts with outliers highlighted.

[0634] These visualized data are sent to the user's terminal and displayed on the screen. The user can check it and take necessary actions. The user interface is sometimes provided on a web browser, and the data can be checked in real time.

[0635] The emotion engine is built into the server and recognizes the user's emotions. It analyzes voice and facial expression data to estimate the user's current emotional state. What the user says to the device is sent to the server and analyzed by the emotion engine. This engine uses NLP libraries and generative AI models.

[0636] Based on the perceived emotion, the analysis results and visualization data are adjusted. For example, if the server detects that the user is feeling stressed, it will provide a more concise and easy-to-understand visualization, allowing the user to process information more efficiently.

[0637] As a specific example, if a user performs high activity (clicking or typing) on ​​a computer for more than 10 minutes continuously, a warning is issued immediately if it is recognized that the user is feeling stressed. In this case, an example of a prompt sentence to the generative AI model is as follows: "The user's frequency of operation is higher than usual. Determine whether the user is feeling stressed and recommend appropriate action."

[0638] By realizing such a system, it will be possible to provide highly flexible security services that take into consideration the feelings of users in the security field.

[0639] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0640] Step 1:

[0641] The user performs a specific operation using the device.

[0642] Input: Data on user operations and behavior on a computer or smartphone.

[0643] Specific actions: The user operates the web browser and performs a specific action (click, keyboard input, etc.).

[0644] Step 2:

[0645] The server retrieves the information from the data source.

[0646] Input: Raw data from multiple sensors, APIs and databases.

[0647] Output: Acquired sensor data and API responses.

[0648] What happens: The server retrieves temperature sensor and security camera data using HTTP requests.

[0649] Step 3:

[0650] The server cleans and standardizes the data it retrieves.

[0651] Input: The raw data obtained.

[0652] Output: Cleaned and standardized data.

[0653] Specific operation: The server complements missing temperature data with previous and next values ​​and standardizes the representation format, for example, converting temperature data from Fahrenheit to Celsius.

[0654] Step 4:

[0655] The server analyzes the preprocessed data using machine learning algorithms.

[0656] Input: Cleaned and standardized data.

[0657] Output: Anomaly detection results and trend predictions.

[0658] What it does: The server runs anomaly detection algorithms using Python and TensorFlow to detect high temperatures and abnormal behavior.

[0659] Step 5:

[0660] The server visualizes the analysis results.

[0661] Input: Analysis results.

[0662] Output: Visualized data in the form of graphs and charts.

[0663] What it does: The server uses Matplotlib and D3.js to convert the data into line and bar graphs.

[0664] Step 6:

[0665] The server transmits the visualized data to the user terminal.

[0666] Input: Visualization data.

[0667] Output: Visualization data sent to the user device.

[0668] Specific operation: The server sends data to the user terminal in real time using HTTP responses or WebSockets.

[0669] Step 7:

[0670] The user terminal displays the visualization data.

[0671] Input: Visualization data sent from the server.

[0672] Output: Graphs and charts displayed on the screen.

[0673] Specific operation: The user's device displays the visualized data on a web browser, and the user checks it.

[0674] Step 8:

[0675] The server recognizes the user's emotions.

[0676] Input: User's voice and facial expression data.

[0677] Output: The user's emotional state (e.g., happy, sad, surprised, stressed).

[0678] Specific operation: The server uses NLP libraries and generative AI models to analyze the user's emotions from voice and facial expression data.

[0679] Step 9:

[0680] The server adjusts the analysis results and visualization data based on the emotions it recognizes.

[0681] Input: The user's emotional state.

[0682] Output: Adjusted visualization data and warning messages.

[0683] Specific operation: Based on the results of the emotion engine, the server converts the visualized data into a concise format and generates appropriate warning messages.

[0684] Step 10:

[0685] The user reviews the adjusted data and takes any necessary action.

[0686] Input: Adjusted visualization data and warning messages.

[0687] Output: User's corrective action.

[0688] Specific actions: The user views the data on the device and, if necessary, contacts the system administrator or strengthens security measures.

[0689] 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.

[0690] 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.

[0691] 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.

[0692] [Third embodiment]

[0693] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0694] 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.

[0695] 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).

[0696] 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.

[0697] 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.

[0698] 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).

[0699] 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.

[0700] 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.

[0701] 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.

[0702] 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.

[0703] 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.

[0704] 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."

[0705] The system according to the present invention automates multiple processes, allowing users to efficiently analyze large amounts of data and quickly gain insights. Specific embodiments of the system are described below.

[0706] 1. Data collection

[0707] The server connects to various data sources (e.g. sensors, APIs, databases) and during this connection process sets the necessary authentication information and connection parameters.

[0708] Example: A server sends an HTTP request to a temperature sensor every 5 minutes to get the latest temperature data, while simultaneously retrieving user posts related to a specific keyword from a social media API.

[0709] 2. Pretreatment

[0710] The server cleans the acquired data, which includes imputing missing values ​​and detecting and correcting outliers. It also standardizes the data, for example, converting data provided in different units into a common unit.

[0711] Example: A server converts temperature data recorded in Fahrenheit to Celsius and formats all data into a uniform timestamp format.

[0712] 3. Data Analysis

[0713] The server then applies machine learning algorithms to the pre-processed data, enabling it to detect anomalies and predict future trends.

[0714] Example: The server creates a regression model based on past temperature data to predict future temperature changes, and if an abnormally high temperature is detected, reports the time and temperature.

[0715] 4. Visualizing the results

[0716] The server visualizes the analysis results in a user-friendly format, which includes generating graphs and charts.

[0717] Example: The server displays predicted temperature changes as a line graph and highlights any anomalies detected.

[0718] 5. User Interface

[0719] The terminal receives the visualization data sent from the server and displays it on the screen, which the user can use to check the results and take necessary actions.

[0720] Example: A temperature forecast graph sent from a server is displayed on a tablet device, allowing the user to consider future measures.

[0721] Through these processes, the system based on the present invention automates the entire process from data collection, pre-processing, analysis, visualization of results, and display of data on a user interface, providing fast and accurate insights.

[0722] The processing flow will be explained below.

[0723] Step 1: Connecting the Data Source

[0724] The server configures connections to data sources (sensors, APIs, databases, etc.), for example specifying endpoint URLs for sensors and setting up credentials for social media APIs.

[0725] Step 2: Getting the data

[0726] The server periodically retrieves information from connected data sources, for example, collecting data from a temperature sensor every five minutes, or calling social media APIs in real time to collect post data.

[0727] Step 3: Cleaning the data

[0728] The server then cleans the acquired data by imputing missing values ​​and detecting and correcting outliers. For example, it imputes missing temperature data with previous and subsequent values, and removes or corrects extremely high or low values.

[0729] Step 4: Standardize the data

[0730] The server standardizes the cleaned data, for example converting temperature data from Fahrenheit to Celsius and aligning all data timestamps to a uniform format.

[0731] Step 5: Feature extraction

[0732] The server extracts the features required for analysis from the data, such as the average temperature, maximum and minimum temperatures, and temperature fluctuation range for each day.

[0733] Step 6: Applying machine learning algorithms

[0734] The server then uses the extracted features to apply machine learning algorithms, such as building a regression model using past temperature data to predict future temperature fluctuations.

[0735] Step 7: Visualize the analysis results

[0736] The server then visualizes the results of the analysis, for example generating a line graph showing the temperature predictions and highlighting any outliers.

[0737] Step 8: Submitting visualization data

[0738] The server transmits the visualized analysis results to a user interface, for example, by transmitting the generated graphs to a terminal.

[0739] Step 9: Receive and display data

[0740] The device receives the visualization data sent from the server and displays it on the screen. For example, a temperature forecast graph is displayed on a tablet device for the user to check.

[0741] Step 10: User review and decision making

[0742] The user can check the analysis results displayed on the device and make necessary decisions, such as adjusting heating and cooling or considering additional measures based on future temperature predictions.

[0743] Example 1

[0744] 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."

[0745] Traditionally, efficiently analyzing large amounts of data collected from various data sources and quickly and accurately gaining insights required a great deal of time and effort. Furthermore, acquiring data from multiple data sources using different protocols and authentication information was complex, and the process of preprocessing, analyzing, visualizing, and providing it to users was not easy. Furthermore, there was a need to automate these processes to detect anomalies and predict future trends.

[0746] 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.

[0747] In this invention, the server includes means for acquiring information from data sources, means for cleaning and standardizing the acquired data, means for analyzing the preprocessed data using a machine learning algorithm, means for visualizing the analysis results, means for transmitting the visualized data to a user interface, and means for displaying the visualized data on the user interface. This allows efficient data collection from multiple data sources using different protocols and authentication information, and enables analysis, anomaly detection, and trend prediction using a machine learning algorithm using the cleaned and standardized data. In addition, by visualizing the analysis results and providing them on the user interface, users can quickly and accurately gain insights.

[0748] A "data source" is a device or system that serves as an input source for providing information.

[0749] "Means of obtaining information" are the methods or processes used to collect data from data sources.

[0750] "Data cleaning methods" are methods or processes for removing unnecessary information from collected data and correcting missing or erroneous values.

[0751] A "data standardization method" is a method or process for converting data in different units or formats into a single common format.

[0752] A "machine learning algorithm" is a mathematical model that analyzes collected and preprocessed data to find patterns and relationships.

[0753] "Means of analysis" refers to the methods or processes used to extract useful information from pre-processed data using machine learning algorithms.

[0754] "Means for visualizing analysis results" refers to methods or tools for displaying information obtained through data analysis in a visual format such as graphs or charts.

[0755] "Means for transmitting visualization data to a user interface" refers to a communication means or protocol that allows a user to view the visualized data through the interface.

[0756] "Means for displaying visualized data in a user interface" refers to a display device or software that allows a user to easily view and manipulate the visualized data.

[0757] "Anomaly detection" is the process of finding and identifying unnatural patterns or values ​​in data.

[0758] "Trend forecasting" is the process of predicting future trends and patterns based on past data.

[0759] The system according to the present invention allows users to efficiently analyze large amounts of data and quickly gain insights. It also allows data collection from multiple data sources using different protocols and authentication information, and uses machine learning algorithms to detect anomalies and predict future trends. Specific embodiments of the system are described below.

[0760] 1. Data collection

[0761] The server connects to various data sources, such as temperature sensors and social media APIs, to collect data. This process involves setting the necessary authentication information and connection parameters. For example, HTTP requests are used to periodically retrieve data from the temperature sensor and retrieve posts related to specific keywords from the social media API. This allows the server to collect temperature data and text data from social media.

[0762] 2. Data Preprocessing

[0763] The server cleans and standardizes the collected data. During this stage, missing values ​​are imputed and outliers are corrected. Data standardization also involves converting data provided in different units into a common format. For example, temperature data recorded in Fahrenheit is converted to Celsius. This preprocessing improves data quality and facilitates subsequent analysis.

[0764] 3. Data Analysis

[0765] The server then applies machine learning algorithms to the preprocessed data to detect anomalies and predict future trends. For example, it creates a regression model based on past temperature data to predict future temperature changes. It also reports abnormally high or low temperatures if they are detected. This analysis is a key step in helping users quickly gain insights.

[0766] 4. Visualizing the results

[0767] The server visualizes the results of the data analysis. Specifically, it displays predicted temperature changes as a line graph and highlights any detected anomalies. This visualization allows users to intuitively understand trends and anomalies in the data.

[0768] 5. User Interface

[0769] The device receives the visualized data sent from the server and displays it on the screen. The user can use this to check the results and take necessary actions. For example, a user can check the temperature forecast graph displayed on the tablet device and make a plan to adjust heating and cooling in the future. Users can also click on anomaly detection results to check detailed information.

[0770] Example prompt

[0771] Below is an example of a prompt sentence to input to the generative AI model.

[0772] Prompt statement:

[0773] Design a system that meets the following criteria:

[0774] 1. A server that collects data from various data sources (e.g., temperature sensors, social media APIs).

[0775] 2. Clean the collected data, complete missing values, and correct outliers.

[0776] 3. Use machine learning algorithms to analyze the collected data and predict future trends.

[0777] 4. Visualize the analysis results and present them in an easy-to-understand format.

[0778] 5. Display the analysis results on a tablet device so that the user can take appropriate action.

[0779] As described above, this system consistently automates data collection, preprocessing, analysis, and visualization of results, and is optimized to enable users to quickly gain insights.

[0780] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0781] Step 1: Collect data

[0782] The server connects to multiple data sources, such as temperature sensors and social media APIs. The inputs are the sensor's IP address, port number, authentication key, and API access token and query parameters. Specifically, the server sends an HTTP request to the temperature sensor every five minutes to retrieve temperature data. At the same time, it retrieves post data related to specified keywords from the social media API. The retrieved data is temperature data (e.g., 25.3°F) and social media post data (e.g., 10 posts related to "global warming").

[0783] Step 2: Preprocessing the data

[0784] The server cleans and standardizes the collected data. Specifically, it uses collected temperature data and social media post data as input. First, the server detects missing values ​​and fills them with the average of the surrounding data. Next, it replaces outliers (e.g., temperature values ​​that deviate significantly) with the median. Finally, it converts temperature data recorded in Fahrenheit to Celsius. As output, it obtains cleaned and standardized data (e.g., temperature data of 22.75°C and standardized text data).

[0785] Step 3: Analyze the data

[0786] The server applies machine learning algorithms to analyze the preprocessed data. The cleaned and standardized temperature data and social media post data are used as inputs. The server uses these data to create a regression model to predict future temperature changes. It also runs an anomaly detection algorithm to identify unusual data points. Specifically, the regression model predicts future temperatures and lists outliers (e.g., temperatures above 30°C). The output is the predicted temperature data (e.g., the predicted temperature for the next day is 25.1°C) and the anomaly detection results.

[0787] Step 4: Visualize the results

[0788] The server uses the predicted temperature data and anomaly detection results as input to visualize the analysis results. Specifically, it generates line graphs and charts based on these data. It displays the line graph showing the temperature change and the anomaly detection results in highlighted form. As output, visualized data (e.g., graphs or charts) is generated.

[0789] Step 5: Display in the user interface

[0790] The terminal receives the visualized data sent from the server and displays it on the screen. The visualized data (graphs and charts) is used as input. The user can view this to check the current situation and take necessary actions. Specifically, the user can view the temperature forecast graph displayed on the tablet terminal and make a plan to adjust heating and cooling. They can also click on anomaly detection results to view detailed information. The output is the visualized data displayed on the user interface.

[0791] (Application example 1)

[0792] 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."

[0793] Conventional factory monitoring systems have difficulty analyzing the diverse data collected from sensors in real time to detect anomalies and perform predictive analysis. They also lack a way to display the analysis results in an intuitive and easy-to-understand way for on-site workers. In particular, there was no way for workers to check real-time data while on the move, which often led to delays in rapid response.

[0794] 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.

[0795] In this invention, the server includes means for acquiring information from a data source, means for cleaning and standardizing the acquired data, means for analyzing the preprocessed data using a machine learning algorithm, means for visualizing the analysis results, means for transmitting the visualized data to a user interface, means for displaying the visualized data on the user interface, and means for displaying real-time data on an augmented reality display, thereby enabling real-time anomaly detection and predictive analysis, allowing workers to intuitively check necessary information even while on the move and enabling prompt action.

[0796] A "data source" is the source from which information is collected, such as from sensors, APIs, or databases.

[0797] "Cleaning" is the process of preparing data by correcting or removing missing or outlier values.

[0798] "Standardization" is the process of converting data provided in different units into a common standard.

[0799] A "machine learning algorithm" is a mathematical technique that uses past data to learn patterns and make predictions or detect anomalies.

[0800] "Analysis" is the process of applying specific algorithms to collected data to obtain desired information.

[0801] "Visualization" refers to displaying the results of data analysis in the form of graphs, charts, etc., making them easy for humans to understand.

[0802] A "user interface" is an operation screen or display device that allows a user to interact with a system.

[0803] An "augmented reality display" is a display device that uses technology to overlay computer-generated information on the real world.

[0804] The system that realizes this application example analyzes various data obtained from sensors in a factory environment in real time and displays the results on an augmented reality display. This system uses the following hardware and software.

[0805] The server uses Python and APIs to collect data from sensors, such as temperature, humidity, and machine operating status data, using REST APIs and MQTT protocols.

[0806] Next, the server performs data preprocessing. It uses NumPy and Pandas to clean the collected data and to impute and correct missing or outlier values. It also standardizes data provided in different units to unify them. For example, it converts temperature data from Fahrenheit to Celsius.

[0807] Once preprocessed, the data is analyzed using machine learning algorithms. The server uses Scikit-Learn and TensorFlow to detect anomalies and predict trends. For example, it applies a regression model created using past data to predict future temperature changes. If an abnormally high temperature is detected, the information is analyzed in real time.

[0808] The analysis results are visualized and sent to a user interface. The server generates graphs using Matplotlib or Plotly and highlights any anomalies detected. For example, predicted temperature changes are displayed as a line graph, and anomalies are highlighted with a red marker.

[0809] Finally, the visualized data is displayed in real time on an augmented reality display, where smart glasses or other devices use Unity or Vuforia to overlay the analysis results, allowing factory workers to intuitively view the information on the move.

[0810] As a concrete example, if the following prompt sentence is input into a generative AI model, a program for the entire system can be generated.

[0811] Create a Python program to collect data from sensors in a factory and perform anomaly detection and trend prediction. Clean the data and convert its units using the Pandas library, then use Scikit-Learn to detect anomalies and TensorFlow to predict trends. Visualize the results using Matplotlib and display them in real time on smart glasses.

[0812] In this way, the present invention automates complex data processing within a factory and intuitively displays the analysis results in real time, thereby improving work efficiency and enabling rapid response.

[0813] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0814] Step 1:

[0815] The server collects data from various sensors installed in the factory (such as temperature, humidity, and machine operation status). The server periodically obtains information from these sensors using REST API and MQTT protocol and stores it in a database. It receives raw data from the sensors as input and generates data in a standard format as output.

[0816] Step 2:

[0817] The server cleans and standardizes the collected data. It uses NumPy and Pandas to detect, impute, and correct missing and outlier values. It also converts data recorded in different units into a common unit. It receives raw sensor data as input and obtains cleaned and standardized data as output.

[0818] Step 3:

[0819] The server applies machine learning algorithms to the cleaned and standardized data to detect anomalies and predict trends. It uses Scikit-Learn to create an anomaly detection model and TensorFlow to predict future trends. It receives preprocessed data as input and generates analysis results, including anomalies and predictions, as output.

[0820] Step 4:

[0821] The server visualizes the analysis results. It uses Matplotlib or Plotly to display predicted data fluctuations and anomaly detection results in graphs and charts. It receives analyzed data as input and generates visualized data (graphs and charts) as output.

[0822] Step 5:

[0823] The server transmits the visualized data to the user interface, transmits the visualized data in real time in a format accessible to the user, and receives the visualized data as input and generates data that is transmitted to the user interface as output.

[0824] Step 6:

[0825] The terminal (smart glasses, smartphone, etc.) receives the visualization data sent from the server and displays it on the augmented reality display. Unity or Vuforia is used to overlay it on the physical environment in the factory. It receives the visualization data from the server as input and generates the augmented reality data that is displayed on the display as output.

[0826] The above processing steps allow factory workers to check data in real time and respond quickly if an abnormality is detected.

[0827] 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.

[0828] The system based on the present invention automates the entire process from data acquisition to analysis and visualization of the results, and further combines it with an emotion engine that recognizes the user's emotions to provide more appropriate and personalized insights to the user. Specific embodiments of the system are described below.

[0829] 1. Data collection

[0830] The server connects to multiple data sources (e.g., sensors, APIs, databases) to collect information, setting any necessary authentication and connection parameters along the way.

[0831] Example: A server sends an HTTP request to a temperature sensor every 5 minutes to collect the latest temperature data, while simultaneously connecting to a social media API to collect user posts related to specific keywords.

[0832] 2. Pretreatment

[0833] The server cleans and standardizes the collected data, including imputing missing data and correcting outliers.

[0834] Example: The server fills in missing temperature data with previous or next values, converts data expressed in Fahrenheit to Celsius, and formats all data into a uniform timestamp format.

[0835] 3. Data Analysis

[0836] The server then applies machine learning algorithms to the pre-processed data, enabling it to detect anomalies and predict future trends.

[0837] Example: The server builds a regression model based on past temperature data to predict future temperature fluctuations, and if an abnormally high temperature is detected, reports the time and temperature.

[0838] 4. Visualizing the results

[0839] The server visualizes the analysis results in a user-friendly format, which includes generating graphs and charts.

[0840] Example: The server displays the predicted temperature change as a line graph, highlighting outliers.

[0841] 5. User Interface

[0842] The terminal receives the visualization data sent from the server and displays it on the screen, which the user can use to check the results and take necessary actions.

[0843] Example: A temperature forecast graph sent from a server is displayed on a tablet device, allowing the user to consider future measures.

[0844] 6. Incorporating an Emotional Engine

[0845] The server recognizes the user's emotions using an emotion engine, which analyzes voice and facial expression data to estimate the user's current emotional state.

[0846] Example: When a user speaks into the device, the voice data is sent to the server, and the emotion engine analyzes and recognizes the user's emotions (e.g., joy, sadness, surprise).

[0847] 7. Emotion-Based Data Adjustment

[0848] The server adjusts the analysis results and visualization data based on the user's perceived emotions, for example, providing a simpler and easier-to-understand visualization if the user is feeling stressed.

[0849] Example: If the server detects that the user is tired, it displays a simple summary on the screen instead of a complex graph.

[0850] Through these steps, the system based on the present invention can highly automate the entire process, from data collection to pre-processing, analysis, result visualization and emotion recognition, and provide personalized insights to users.

[0851] The processing flow will be explained below.

[0852] Step 1: Connecting the Data Source

[0853] The server configures the connection to the data source (e.g., temperature sensor, social media API, database) by specifying the sensor's endpoint URL and setting up API credentials.

[0854] Step 2: Getting the data

[0855] The server periodically retrieves information from connected data sources, for example, collecting data from a temperature sensor every five minutes, or calling social media APIs in real time to collect post data.

[0856] Step 3: Cleaning the data

[0857] The server then cleans the acquired data, which includes filling in missing values ​​and detecting and correcting outliers by filling in missing temperature data with previous and subsequent values ​​and removing or adjusting extremely high or low values.

[0858] Step 4: Standardize the data

[0859] The server standardizes the cleaned data, for example converting temperature data from Fahrenheit to Celsius and aligning all data timestamps to a uniform format.

[0860] Step 5: Feature extraction

[0861] The server extracts the features required for analysis from the data, such as the average temperature, maximum and minimum temperatures, and temperature fluctuation range for each day.

[0862] Step 6: Applying machine learning algorithms

[0863] The server then uses the extracted features to apply machine learning algorithms, such as building a regression model using past temperature data to predict future temperature fluctuations.

[0864] Step 7: Visualize the analysis results

[0865] The server visualizes the analysis results, generating a line graph showing the predicted temperature results and highlighting outliers.

[0866] Step 8: Incorporating the Emotion Engine

[0867] The server recognizes the user's emotions using an emotion engine, which analyzes voice and facial expression data to estimate the user's current emotional state.

[0868] Step 9: Adjust data based on sentiment

[0869] The server adjusts the analysis results and visualization data based on the user's perceived emotions, for example, providing a simpler and easier-to-understand visualization if the user is feeling stressed.

[0870] Step 10: Send visualization data

[0871] The server transmits the visualized analysis results to a user interface, for example, by transmitting the generated graphs to a terminal.

[0872] Step 11: Receiving and displaying data

[0873] The device receives the visualization data sent from the server and displays it on the screen. Specifically, a temperature forecast graph is displayed on the tablet device for the user to check.

[0874] Step 12: User review and decision making

[0875] The user can check the analysis results displayed on the device and make the necessary decisions, such as adjusting heating and cooling or considering additional measures based on future temperature predictions.

[0876] Example 2

[0877] 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."

[0878] In conventional data analysis systems, the processes from data collection to analysis and visualization are not automated, which means that they require a great deal of time and effort. Furthermore, they lack the ability to recognize user emotions and adjust data accordingly, making it difficult to provide information in an optimal format to users.

[0879] 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.

[0880] In this invention, the server includes means for acquiring information from data sources, means for cleaning and standardizing the acquired data, means for analyzing the pre-processed data using machine learning algorithms, means for visualizing the analysis results, means for transmitting the visualized data to a user interface, means for analyzing the voice data and facial expression data to estimate the emotional state of the user, and means for adjusting the analysis results and the visualized data based on the emotional state, thereby providing personalized insights to the user and automating the entire process.

[0881] "Data source" refers to a device or system that provides data, including sensors, APIs, databases, and other diverse sources.

[0882] "Cleaning" refers to the process of removing noise and outliers from data and filling in missing data.

[0883] "Standardization" refers to the process of converting data expressed in different formats into a unified format, including, for example, unifying different units of measurement or timestamp formats.

[0884] "Machine learning algorithms" refer to a set of mathematical models for data analysis and prediction, which can automatically detect patterns and trends.

[0885] "Analysis" refers to the process of applying statistical and mathematical methods to collected and pre-processed data to derive useful insights and predictive results.

[0886] "Visualization" refers to the process of presenting analytical results in a form that is easy for users to understand, including the generation of graphs and charts.

[0887] "User interface" refers to the interface through which a user and a system communicate with each other. This includes devices such as computers, smartphones, and tablets.

[0888] "Emotion engine" refers to technology that analyzes data such as voice and facial expressions to recognize the user's emotional state, making it possible to grasp the user's psychological state.

[0889] "Personalized insights" refers to information and suggestions that are optimized based on the individual characteristics and status of each user, enabling more appropriate and personalized services to be provided.

[0890] "Automation" refers to the state in which a series of operations or processes are carried out automatically without human intervention, resulting in efficient and error-free processing.

[0891] The system according to the present invention automates the entire process from data acquisition to analysis, visualization, and user emotion recognition, providing highly personalized insights. Specific embodiments of this system are described below.

[0892] 1. Data collection

[0893] The server connects to multiple data sources and collects the required data. For example, the server uses HTTP requests and SQL queries to retrieve data from sensors, APIs, databases, and other sources.

[0894] Example: A server sends an HTTP request every 5 minutes to collect the latest temperature data from a temperature sensor. It also connects to a social media API to retrieve user posts related to the keyword "climate change."

[0895] 2. Data Preprocessing

[0896] The server cleans and standardizes the collected data, a process that involves filling in missing data, correcting outliers, and standardizing the data format.

[0897] Example: The server fills in missing temperature data with previous or next values, converts data expressed in Fahrenheit to Celsius, and formats all data into a uniform timestamp format.

[0898] 3. Data Analysis

[0899] The server then applies machine learning algorithms to the pre-processed data, enabling it to detect anomalies and predict future trends.

[0900] Example: The server builds a regression model based on historical temperature data to predict temperature fluctuations over the next week, and reports any abnormally high temperatures recorded during a particular time period.

[0901] 4. Visualizing the results

[0902] The server visualizes the analysis results in a user-friendly format, which includes generating graphs and charts.

[0903] Example: The server displays a line graph of predicted temperature changes, highlighting outliers in red, and providing tooltips with detailed information about each data point.

[0904] 5. User Interface

[0905] The terminal receives the visualization data sent from the server and displays it on the screen, which the user can use to check the results and take necessary actions.

[0906] Example: A tablet device displays a temperature forecast graph sent from a server in a web browser. The user can view detailed information by touching a data point on the screen.

[0907] 6. Incorporating an Emotional Engine

[0908] The server recognizes the user's emotions using an emotion engine, which analyzes voice data and facial expression image data to estimate the user's current emotional state.

[0909] Example: When a user says "It's cold today," the voice data is sent to the server, where the speech recognition engine converts the speech into text data. The emotion engine then recognizes the user's emotional state as "I feel cold."

[0910] 7. Emotion-Based Data Adjustment

[0911] The server adjusts the analysis results and visualization data based on the user's perceived emotions, for example, providing a simpler and easier-to-understand visualization if the user is feeling stressed.

[0912] Example: If the server detects that the user is tired, it will remove complex graphs and display only the most important information in bullet points, and it will also optimize the use of colors and font sizes.

[0913] As a result, the system automates the entire process for users, from data collection to analysis and visualization, and by incorporating emotion recognition, it is possible to provide personalized insights.

[0914] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0915] Step 1:

[0916] Data collection

[0917] The server retrieves information from multiple data sources. Specifically, the server sends HTTP requests to pre-configured URLs to collect data from APIs and also sends SQL queries to databases to retrieve information. The input is data from sensors, APIs, databases, etc., and the output is the collected raw data.

[0918] What it does: The server sends an HTTP request every 5 minutes to get the latest temperature data from the temperature sensor, and also sends a request containing the keyword "climate change" to social media APIs to gather related information.

[0919] Step 2:

[0920] Data Preprocessing

[0921] The server cleans and standardizes the collected data. This step takes raw data as input and produces processed data as output. It also fills gaps in the data, corrects outliers, and converts data represented in different formats into a unified format.

[0922] What happens: The server fills in missing temperature data with the previous or next value, converts Fahrenheit temperature data to Celsius, and unifies the timestamp format.

[0923] Step 3:

[0924] Data analysis

[0925] The server applies machine learning algorithms to the preprocessed data. The input is the preprocessed data, and the output is the analysis results. This step detects anomalies and predicts future trends.

[0926] Specific operation: The server uses the preprocessed temperature data to build a regression model and predict temperature fluctuations over the next week. Furthermore, if an abnormally high temperature is recorded, the server outputs the time and temperature as abnormal data.

[0927] Step 4:

[0928] Visualizing the results

[0929] The server outputs the analysis results in a visually understandable format. The input is the analysis results, and the output is visualized data (graphs and charts).

[0930] What it does: The server visualizes future temperature fluctuation data as a line graph, highlighting outliers in red, and providing detailed information about each data point as a tooltip.

[0931] Step 5:

[0932] Send and display to the user interface

[0933] The terminal receives the visualization data sent from the server and displays it on the screen. The input is the visualization data sent from the server, and the output is a display in a format that can be confirmed by the user.

[0934] Specific operation: The tablet device displays the temperature forecast graph sent from the server on a web browser. The user can check detailed information by touching a data point on the graph.

[0935] Step 6:

[0936] Incorporating an emotion engine

[0937] The server uses an emotion engine to recognize the user's emotions. The input is voice data or facial expression data from the user, and the output is the user's emotional state.

[0938] How it works: When a user says "It's cold today," the voice data is sent to the server, where the speech recognition engine converts the speech into text. The emotion engine then determines the user's emotional state as "feeling cold."

[0939] Step 7:

[0940] Emotion-based data adjustment

[0941] The server adjusts the analysis results and visualization data based on the recognized user emotion. The input is the user's emotional state, and the output is the adjusted analysis results and visualization data.

[0942] What it does: When the server detects that the user is tired, it will not display complex graphs, but will instead display only the most important information in bulleted form, and will optimize color usage and font size.

[0943] Through these steps, the system of the present invention realizes a highly automated data analysis and visualization process, and further provides personalized insights that take into account the user's emotions.

[0944] (Application example 2)

[0945] 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."

[0946] Conventional data analysis systems have been effective to a certain extent by displaying the analysis results of collected data, but this alone has the problem of not being able to respond flexibly based on the user's emotions. In particular, in the security field, where situations that cause users to feel anxious or stress often occur, there is a need for systems that not only visualize data but also reflect the user's emotional state and provide appropriate actions.

[0947] 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.

[0948] In this invention, the server includes means for acquiring information from a data source, means for cleaning and standardizing the acquired data, means for analyzing the preprocessed data using a machine learning algorithm, means for visualizing the analysis results, means for transmitting the visualized data to a user terminal, means for displaying the visualized data on the user terminal, means for recognizing a user's emotion, and means for adjusting the analysis results and the visualized data based on the recognized emotion. This allows the system to sense when the user is emotionally stressed or anxious and provide optimal visualizations and warnings according to the emotion.

[0949] A "data source" is an information source that provides information from multiple sensors, APIs, databases, etc.

[0950] "Acquisition" is the act of gathering the necessary information from a data source.

[0951] "Cleaning" is the process of removing missing values ​​and outliers from collected data and arranging the data.

[0952] "Standardization" is the process of standardizing data formats to ensure consistency when analyzing and visualizing them.

[0953] "Preprocessing" is a series of operations to prepare data for analysis.

[0954] A "machine learning algorithm" is a computational method that mimics human learning abilities to find patterns and rules in data.

[0955] "Analysis" is the act of analyzing information based on collected data to gain useful knowledge and insights.

[0956] "Visualization" refers to the presentation of analytical results in a visual format such as a graph or chart.

[0957] A "user terminal" is a device that a user can directly operate (e.g., a smartphone, tablet, or PC).

[0958] "Send" is the act of transferring data from the server to the user terminal.

[0959] "Display" refers to the act of presenting information on the screen of a user terminal.

[0960] "Emotion recognition" is the process of determining a user's emotional state by analyzing voice and facial expression data.

[0961] "Adjustment" refers to changing the content or format of analysis results or visualization data based on recognized emotions.

[0962] The system based on this invention automates the entire process from data acquisition to analysis, visualization of results, and adjustment based on user emotions, providing high flexibility and adaptability for use in the security field. The specific configuration and functions of this system are described below.

[0963] The system mainly includes the following elements: a server, multiple data sources (sensors, APIs, databases), and user devices (smartphones, tablets, PCs).

[0964] First, the server periodically retrieves data from sensors and APIs using HTTP requests. To collect this data, the server needs to set authentication information and connection parameters. For example, temperature data from a temperature sensor is retrieved every five minutes, along with image data from a security camera.

[0965] The acquired data is then cleaned and standardized. Cleaning involves imputing missing values ​​and correcting outliers. For example, missing temperature data is imputed with previous or next values, and a standardization process is performed to convert the represented data into a unified format.

[0966] The cleaned and standardized data is then analyzed using machine learning algorithms. This analysis detects anomalies and predicts future trends. For example, if an abnormally high temperature is detected, the time and temperature are reported. The server performs this analysis using libraries such as Python and TensorFlow.

[0967] The results of the analysis are visualized and presented in a user-friendly format, often using libraries such as Matplotlib or D3.js, and are displayed as graphs or charts with outliers highlighted.

[0968] These visualized data are sent to the user's terminal and displayed on the screen. The user can check it and take necessary actions. The user interface is sometimes provided on a web browser, and the data can be checked in real time.

[0969] The emotion engine is built into the server and recognizes the user's emotions. It analyzes voice and facial expression data to estimate the user's current emotional state. What the user says to the device is sent to the server and analyzed by the emotion engine. This engine uses NLP libraries and generative AI models.

[0970] Based on the perceived emotion, the analysis results and visualization data are adjusted. For example, if the server detects that the user is feeling stressed, it will provide a more concise and easy-to-understand visualization, allowing the user to process information more efficiently.

[0971] As a specific example, if a user performs high activity (clicking or typing) on ​​a computer for more than 10 minutes continuously, a warning is issued immediately if it is recognized that the user is feeling stressed. In this case, an example of a prompt sentence to the generative AI model is as follows: "The user's frequency of operation is higher than usual. Determine whether the user is feeling stressed and recommend appropriate action."

[0972] By realizing such a system, it will be possible to provide highly flexible security services that take into consideration the feelings of users in the security field.

[0973] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0974] Step 1:

[0975] The user performs a specific operation using the device.

[0976] Input: Data on user operations and behavior on a computer or smartphone.

[0977] Specific actions: The user operates the web browser and performs a specific action (click, keyboard input, etc.).

[0978] Step 2:

[0979] The server retrieves the information from the data source.

[0980] Input: Raw data from multiple sensors, APIs and databases.

[0981] Output: Acquired sensor data and API responses.

[0982] What happens: The server retrieves temperature sensor and security camera data using HTTP requests.

[0983] Step 3:

[0984] The server cleans and standardizes the data it retrieves.

[0985] Input: The raw data obtained.

[0986] Output: Cleaned and standardized data.

[0987] Specific operation: The server complements missing temperature data with previous and next values ​​and standardizes the representation format, for example, converting temperature data from Fahrenheit to Celsius.

[0988] Step 4:

[0989] The server analyzes the preprocessed data using machine learning algorithms.

[0990] Input: Cleaned and standardized data.

[0991] Output: Anomaly detection results and trend predictions.

[0992] What it does: The server runs anomaly detection algorithms using Python and TensorFlow to detect high temperatures and abnormal behavior.

[0993] Step 5:

[0994] The server visualizes the analysis results.

[0995] Input: Analysis results.

[0996] Output: Visualized data in the form of graphs and charts.

[0997] What it does: The server uses Matplotlib and D3.js to convert the data into line and bar graphs.

[0998] Step 6:

[0999] The server transmits the visualized data to the user terminal.

[1000] Input: Visualization data.

[1001] Output: Visualization data sent to the user device.

[1002] Specific operation: The server sends data to the user terminal in real time using HTTP responses or WebSockets.

[1003] Step 7:

[1004] The user terminal displays the visualization data.

[1005] Input: Visualization data sent from the server.

[1006] Output: Graphs and charts displayed on the screen.

[1007] Specific operation: The user's device displays the visualized data on a web browser, and the user checks it.

[1008] Step 8:

[1009] The server recognizes the user's emotions.

[1010] Input: User's voice and facial expression data.

[1011] Output: The user's emotional state (e.g., happy, sad, surprised, stressed).

[1012] Specific operation: The server uses NLP libraries and generative AI models to analyze the user's emotions from voice and facial expression data.

[1013] Step 9:

[1014] The server adjusts the analysis results and visualization data based on the emotions it recognizes.

[1015] Input: The user's emotional state.

[1016] Output: Adjusted visualization data and warning messages.

[1017] Specific operation: Based on the results of the emotion engine, the server converts the visualized data into a concise format and generates appropriate warning messages.

[1018] Step 10:

[1019] The user reviews the adjusted data and takes any necessary action.

[1020] Input: Adjusted visualization data and warning messages.

[1021] Output: User's corrective action.

[1022] Specific actions: The user views the data on the device and, if necessary, contacts the system administrator or strengthens security measures.

[1023] 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.

[1024] 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.

[1025] 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.

[1026] [Fourth embodiment]

[1027] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1028] 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.

[1029] 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).

[1030] 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.

[1031] 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.

[1032] 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).

[1033] 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.

[1034] 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.

[1035] 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.

[1036] 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.

[1037] 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.

[1038] 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.

[1039] 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."

[1040] The system according to the present invention automates multiple processes, allowing users to efficiently analyze large amounts of data and quickly gain insights. Specific embodiments of the system are described below.

[1041] 1. Data collection

[1042] The server connects to various data sources (e.g. sensors, APIs, databases) and during this connection process sets the necessary authentication information and connection parameters.

[1043] Example: A server sends an HTTP request to a temperature sensor every 5 minutes to get the latest temperature data, while simultaneously retrieving user posts related to a specific keyword from a social media API.

[1044] 2. Pretreatment

[1045] The server cleans the acquired data, which includes imputing missing values ​​and detecting and correcting outliers. It also standardizes the data, for example, converting data provided in different units into a common unit.

[1046] Example: A server converts temperature data recorded in Fahrenheit to Celsius and formats all data into a uniform timestamp format.

[1047] 3. Data Analysis

[1048] The server then applies machine learning algorithms to the pre-processed data, enabling it to detect anomalies and predict future trends.

[1049] Example: The server creates a regression model based on past temperature data to predict future temperature changes, and if an abnormally high temperature is detected, reports the time and temperature.

[1050] 4. Visualizing the results

[1051] The server visualizes the analysis results in a user-friendly format, which includes generating graphs and charts.

[1052] Example: The server displays predicted temperature changes as a line graph and highlights any anomalies detected.

[1053] 5. User Interface

[1054] The terminal receives the visualization data sent from the server and displays it on the screen, which the user can use to check the results and take necessary actions.

[1055] Example: A temperature forecast graph sent from a server is displayed on a tablet device, allowing the user to consider future measures.

[1056] Through these processes, the system based on the present invention automates the entire process from data collection, pre-processing, analysis, visualization of results, and display of data on a user interface, providing fast and accurate insights.

[1057] The processing flow will be explained below.

[1058] Step 1: Connecting the Data Source

[1059] The server configures connections to data sources (sensors, APIs, databases, etc.), for example specifying endpoint URLs for sensors and setting up credentials for social media APIs.

[1060] Step 2: Getting the data

[1061] The server periodically retrieves information from connected data sources, for example, collecting data from a temperature sensor every five minutes, or calling social media APIs in real time to collect post data.

[1062] Step 3: Cleaning the data

[1063] The server then cleans the acquired data by imputing missing values ​​and detecting and correcting outliers. For example, it imputes missing temperature data with previous and subsequent values, and removes or corrects extremely high or low values.

[1064] Step 4: Standardize the data

[1065] The server standardizes the cleaned data, for example converting temperature data from Fahrenheit to Celsius and aligning all data timestamps to a uniform format.

[1066] Step 5: Feature extraction

[1067] The server extracts the features required for analysis from the data, such as the average temperature, maximum and minimum temperatures, and temperature fluctuation range for each day.

[1068] Step 6: Applying machine learning algorithms

[1069] The server then uses the extracted features to apply machine learning algorithms, such as building a regression model using past temperature data to predict future temperature fluctuations.

[1070] Step 7: Visualize the analysis results

[1071] The server then visualizes the results of the analysis, for example generating a line graph showing the temperature predictions and highlighting any outliers.

[1072] Step 8: Submitting visualization data

[1073] The server transmits the visualized analysis results to a user interface, for example, by transmitting the generated graphs to a terminal.

[1074] Step 9: Receive and display data

[1075] The device receives the visualization data sent from the server and displays it on the screen. For example, a temperature forecast graph is displayed on a tablet device for the user to check.

[1076] Step 10: User review and decision making

[1077] The user can check the analysis results displayed on the device and make necessary decisions, such as adjusting heating and cooling or considering additional measures based on future temperature predictions.

[1078] Example 1

[1079] 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."

[1080] Traditionally, efficiently analyzing large amounts of data collected from various data sources and quickly and accurately gaining insights required a great deal of time and effort. Furthermore, acquiring data from multiple data sources using different protocols and authentication information was complex, and the process of preprocessing, analyzing, visualizing, and providing it to users was not easy. Furthermore, there was a need to automate these processes to detect anomalies and predict future trends.

[1081] 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.

[1082] In this invention, the server includes means for acquiring information from data sources, means for cleaning and standardizing the acquired data, means for analyzing the preprocessed data using a machine learning algorithm, means for visualizing the analysis results, means for transmitting the visualized data to a user interface, and means for displaying the visualized data on the user interface. This allows efficient data collection from multiple data sources using different protocols and authentication information, and enables analysis, anomaly detection, and trend prediction using a machine learning algorithm using the cleaned and standardized data. In addition, by visualizing the analysis results and providing them on the user interface, users can quickly and accurately gain insights.

[1083] A "data source" is a device or system that serves as an input source for providing information.

[1084] "Means of obtaining information" are the methods or processes used to collect data from data sources.

[1085] "Data cleaning methods" are methods or processes for removing unnecessary information from collected data and correcting missing or erroneous values.

[1086] A "data standardization method" is a method or process for converting data in different units or formats into a single common format.

[1087] A "machine learning algorithm" is a mathematical model that analyzes collected and preprocessed data to find patterns and relationships.

[1088] "Means of analysis" refers to the methods or processes used to extract useful information from pre-processed data using machine learning algorithms.

[1089] "Means for visualizing analysis results" refers to methods or tools for displaying information obtained through data analysis in a visual format such as graphs or charts.

[1090] "Means for transmitting visualization data to a user interface" refers to a communication means or protocol that allows a user to view the visualized data through the interface.

[1091] "Means for displaying visualized data in a user interface" refers to a display device or software that allows a user to easily view and manipulate the visualized data.

[1092] "Anomaly detection" is the process of finding and identifying unnatural patterns or values ​​in data.

[1093] "Trend forecasting" is the process of predicting future trends and patterns based on past data.

[1094] The system according to the present invention allows users to efficiently analyze large amounts of data and quickly gain insights. It also allows data collection from multiple data sources using different protocols and authentication information, and uses machine learning algorithms to detect anomalies and predict future trends. Specific embodiments of the system are described below.

[1095] 1. Data collection

[1096] The server connects to various data sources, such as temperature sensors and social media APIs, to collect data. This process involves setting the necessary authentication information and connection parameters. For example, HTTP requests are used to periodically retrieve data from the temperature sensor and retrieve posts related to specific keywords from the social media API. This allows the server to collect temperature data and text data from social media.

[1097] 2. Data Preprocessing

[1098] The server cleans and standardizes the collected data. During this stage, missing values ​​are imputed and outliers are corrected. Data standardization also involves converting data provided in different units into a common format. For example, temperature data recorded in Fahrenheit is converted to Celsius. This preprocessing improves data quality and facilitates subsequent analysis.

[1099] 3. Data Analysis

[1100] The server then applies machine learning algorithms to the preprocessed data to detect anomalies and predict future trends. For example, it creates a regression model based on past temperature data to predict future temperature changes. It also reports abnormally high or low temperatures if they are detected. This analysis is a key step in helping users quickly gain insights.

[1101] 4. Visualizing the results

[1102] The server visualizes the results of the data analysis. Specifically, it displays predicted temperature changes as a line graph and highlights any detected anomalies. This visualization allows users to intuitively understand trends and anomalies in the data.

[1103] 5. User Interface

[1104] The device receives the visualized data sent from the server and displays it on the screen. The user can use this to check the results and take necessary actions. For example, a user can check the temperature forecast graph displayed on the tablet device and make a plan to adjust heating and cooling in the future. Users can also click on anomaly detection results to check detailed information.

[1105] Example prompt

[1106] Below is an example of a prompt sentence to input to the generative AI model.

[1107] Prompt statement:

[1108] Design a system that meets the following criteria:

[1109] 1. A server that collects data from various data sources (e.g., temperature sensors, social media APIs).

[1110] 2. Clean the collected data, complete missing values, and correct outliers.

[1111] 3. Use machine learning algorithms to analyze the collected data and predict future trends.

[1112] 4. Visualize the analysis results and present them in an easy-to-understand format.

[1113] 5. Display the analysis results on a tablet device so that the user can take appropriate action.

[1114] As described above, this system consistently automates data collection, preprocessing, analysis, and visualization of results, and is optimized to enable users to quickly gain insights.

[1115] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1116] Step 1: Collect data

[1117] The server connects to multiple data sources, such as temperature sensors and social media APIs. The inputs are the sensor's IP address, port number, authentication key, and API access token and query parameters. Specifically, the server sends an HTTP request to the temperature sensor every five minutes to retrieve temperature data. At the same time, it retrieves post data related to specified keywords from the social media API. The retrieved data is temperature data (e.g., 25.3°F) and social media post data (e.g., 10 posts related to "global warming").

[1118] Step 2: Preprocessing the data

[1119] The server cleans and standardizes the collected data. Specifically, it uses collected temperature data and social media post data as input. First, the server detects missing values ​​and fills them with the average of the surrounding data. Next, it replaces outliers (e.g., temperature values ​​that deviate significantly) with the median. Finally, it converts temperature data recorded in Fahrenheit to Celsius. As output, it obtains cleaned and standardized data (e.g., temperature data of 22.75°C and standardized text data).

[1120] Step 3: Analyze the data

[1121] The server applies machine learning algorithms to analyze the preprocessed data. The cleaned and standardized temperature data and social media post data are used as inputs. The server uses these data to create a regression model to predict future temperature changes. It also runs an anomaly detection algorithm to identify unusual data points. Specifically, the regression model predicts future temperatures and lists outliers (e.g., temperatures above 30°C). The output is the predicted temperature data (e.g., the predicted temperature for the next day is 25.1°C) and the anomaly detection results.

[1122] Step 4: Visualize the results

[1123] The server uses the predicted temperature data and anomaly detection results as input to visualize the analysis results. Specifically, it generates line graphs and charts based on these data. It displays the line graph showing the temperature change and the anomaly detection results in highlighted form. As output, visualized data (e.g., graphs or charts) is generated.

[1124] Step 5: Display in the user interface

[1125] The terminal receives the visualized data sent from the server and displays it on the screen. The visualized data (graphs and charts) is used as input. The user can view this to check the current situation and take necessary actions. Specifically, the user can view the temperature forecast graph displayed on the tablet terminal and make a plan to adjust heating and cooling. They can also click on anomaly detection results to view detailed information. The output is the visualized data displayed on the user interface.

[1126] (Application example 1)

[1127] 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."

[1128] Conventional factory monitoring systems have difficulty analyzing the diverse data collected from sensors in real time to detect anomalies and perform predictive analysis. They also lack a way to display the analysis results in an intuitive and easy-to-understand way for on-site workers. In particular, there was no way for workers to check real-time data while on the move, which often led to delays in rapid response.

[1129] 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.

[1130] In this invention, the server includes means for acquiring information from a data source, means for cleaning and standardizing the acquired data, means for analyzing the preprocessed data using a machine learning algorithm, means for visualizing the analysis results, means for transmitting the visualized data to a user interface, means for displaying the visualized data on the user interface, and means for displaying real-time data on an augmented reality display, thereby enabling real-time anomaly detection and predictive analysis, allowing workers to intuitively check necessary information even while on the move and enabling prompt action.

[1131] A "data source" is the source from which information is collected, such as from sensors, APIs, or databases.

[1132] "Cleaning" is the process of preparing data by correcting or removing missing or outlier values.

[1133] "Standardization" is the process of converting data provided in different units into a common standard.

[1134] A "machine learning algorithm" is a mathematical technique that uses past data to learn patterns and make predictions or detect anomalies.

[1135] "Analysis" is the process of applying specific algorithms to collected data to obtain desired information.

[1136] "Visualization" refers to displaying the results of data analysis in the form of graphs, charts, etc., making them easy for humans to understand.

[1137] A "user interface" is an operation screen or display device that allows a user to interact with a system.

[1138] An "augmented reality display" is a display device that uses technology to overlay computer-generated information on the real world.

[1139] The system that realizes this application example analyzes various data obtained from sensors in a factory environment in real time and displays the results on an augmented reality display. This system uses the following hardware and software.

[1140] The server uses Python and APIs to collect data from sensors, such as temperature, humidity, and machine operating status data, using REST APIs and MQTT protocols.

[1141] Next, the server performs data preprocessing. It uses NumPy and Pandas to clean the collected data and to impute and correct missing or outlier values. It also standardizes data provided in different units to unify them. For example, it converts temperature data from Fahrenheit to Celsius.

[1142] Once preprocessed, the data is analyzed using machine learning algorithms. The server uses Scikit-Learn and TensorFlow to detect anomalies and predict trends. For example, it applies a regression model created using past data to predict future temperature changes. If an abnormally high temperature is detected, the information is analyzed in real time.

[1143] The analysis results are visualized and sent to a user interface. The server generates graphs using Matplotlib or Plotly and highlights any anomalies detected. For example, predicted temperature changes are displayed as a line graph, and anomalies are highlighted with a red marker.

[1144] Finally, the visualized data is displayed in real time on an augmented reality display, where smart glasses or other devices use Unity or Vuforia to overlay the analysis results, allowing factory workers to intuitively view the information on the move.

[1145] As a concrete example, if the following prompt sentence is input into a generative AI model, a program for the entire system can be generated.

[1146] Create a Python program to collect data from sensors in a factory and perform anomaly detection and trend prediction. Clean the data and convert its units using the Pandas library, then use Scikit-Learn to detect anomalies and TensorFlow to predict trends. Visualize the results using Matplotlib and display them in real time on smart glasses.

[1147] In this way, the present invention automates complex data processing within a factory and intuitively displays the analysis results in real time, thereby improving work efficiency and enabling rapid response.

[1148] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1149] Step 1:

[1150] The server collects data from various sensors installed in the factory (such as temperature, humidity, and machine operation status). The server periodically obtains information from these sensors using REST API and MQTT protocol and stores it in a database. It receives raw data from the sensors as input and generates data in a standard format as output.

[1151] Step 2:

[1152] The server cleans and standardizes the collected data. It uses NumPy and Pandas to detect, impute, and correct missing and outlier values. It also converts data recorded in different units into a common unit. It receives raw sensor data as input and obtains cleaned and standardized data as output.

[1153] Step 3:

[1154] The server applies machine learning algorithms to the cleaned and standardized data to detect anomalies and predict trends. It uses Scikit-Learn to create an anomaly detection model and TensorFlow to predict future trends. It receives preprocessed data as input and generates analysis results, including anomalies and predictions, as output.

[1155] Step 4:

[1156] The server visualizes the analysis results. It uses Matplotlib or Plotly to display predicted data fluctuations and anomaly detection results in graphs and charts. It receives analyzed data as input and generates visualized data (graphs and charts) as output.

[1157] Step 5:

[1158] The server transmits the visualized data to the user interface, transmits the visualized data in real time in a format accessible to the user, and receives the visualized data as input and generates data that is transmitted to the user interface as output.

[1159] Step 6:

[1160] The terminal (smart glasses, smartphone, etc.) receives the visualization data sent from the server and displays it on the augmented reality display. Unity or Vuforia is used to overlay it on the physical environment in the factory. It receives the visualization data from the server as input and generates the augmented reality data that is displayed on the display as output.

[1161] The above processing steps allow factory workers to check data in real time and respond quickly if an abnormality is detected.

[1162] 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.

[1163] The system based on the present invention automates the entire process from data acquisition to analysis and visualization of the results, and further combines it with an emotion engine that recognizes the user's emotions to provide more appropriate and personalized insights to the user. Specific embodiments of the system are described below.

[1164] 1. Data collection

[1165] The server connects to multiple data sources (e.g., sensors, APIs, databases) to collect information, setting any necessary authentication and connection parameters along the way.

[1166] Example: A server sends an HTTP request to a temperature sensor every 5 minutes to collect the latest temperature data, while simultaneously connecting to a social media API to collect user posts related to specific keywords.

[1167] 2. Pretreatment

[1168] The server cleans and standardizes the collected data, including imputing missing data and correcting outliers.

[1169] Example: The server fills in missing temperature data with previous or next values, converts data expressed in Fahrenheit to Celsius, and formats all data into a uniform timestamp format.

[1170] 3. Data Analysis

[1171] The server then applies machine learning algorithms to the pre-processed data, enabling it to detect anomalies and predict future trends.

[1172] Example: The server builds a regression model based on past temperature data to predict future temperature fluctuations, and if an abnormally high temperature is detected, reports the time and temperature.

[1173] 4. Visualizing the results

[1174] The server visualizes the analysis results in a user-friendly format, which includes generating graphs and charts.

[1175] Example: The server displays the predicted temperature change as a line graph, highlighting outliers.

[1176] 5. User Interface

[1177] The terminal receives the visualization data sent from the server and displays it on the screen, which the user can use to check the results and take necessary actions.

[1178] Example: A temperature forecast graph sent from a server is displayed on a tablet device, allowing the user to consider future measures.

[1179] 6. Incorporating an Emotional Engine

[1180] The server recognizes the user's emotions using an emotion engine, which analyzes voice and facial expression data to estimate the user's current emotional state.

[1181] Example: When a user speaks into the device, the voice data is sent to the server, and the emotion engine analyzes and recognizes the user's emotions (e.g., joy, sadness, surprise).

[1182] 7. Emotion-Based Data Adjustment

[1183] The server adjusts the analysis results and visualization data based on the user's perceived emotions, for example, providing a simpler and easier-to-understand visualization if the user is feeling stressed.

[1184] Example: If the server detects that the user is tired, it displays a simple summary on the screen instead of a complex graph.

[1185] Through these steps, the system based on the present invention can highly automate the entire process, from data collection to pre-processing, analysis, result visualization and emotion recognition, and provide personalized insights to users.

[1186] The processing flow will be explained below.

[1187] Step 1: Connecting the Data Source

[1188] The server configures the connection to the data source (e.g., temperature sensor, social media API, database) by specifying the sensor's endpoint URL and setting up API credentials.

[1189] Step 2: Getting the data

[1190] The server periodically retrieves information from connected data sources, for example, collecting data from a temperature sensor every five minutes, or calling social media APIs in real time to collect post data.

[1191] Step 3: Cleaning the data

[1192] The server then cleans the acquired data, which includes filling in missing values ​​and detecting and correcting outliers by filling in missing temperature data with previous and subsequent values ​​and removing or adjusting extremely high or low values.

[1193] Step 4: Standardize the data

[1194] The server standardizes the cleaned data, for example converting temperature data from Fahrenheit to Celsius and aligning all data timestamps to a uniform format.

[1195] Step 5: Feature extraction

[1196] The server extracts the features required for analysis from the data, such as the average temperature, maximum and minimum temperatures, and temperature fluctuation range for each day.

[1197] Step 6: Applying machine learning algorithms

[1198] The server then uses the extracted features to apply machine learning algorithms, such as building a regression model using past temperature data to predict future temperature fluctuations.

[1199] Step 7: Visualize the analysis results

[1200] The server visualizes the analysis results, generating a line graph showing the predicted temperature results and highlighting outliers.

[1201] Step 8: Incorporating the Emotion Engine

[1202] The server recognizes the user's emotions using an emotion engine, which analyzes voice and facial expression data to estimate the user's current emotional state.

[1203] Step 9: Adjust data based on sentiment

[1204] The server adjusts the analysis results and visualization data based on the user's perceived emotions, for example, providing a simpler and easier-to-understand visualization if the user is feeling stressed.

[1205] Step 10: Send visualization data

[1206] The server transmits the visualized analysis results to a user interface, for example, by transmitting the generated graphs to a terminal.

[1207] Step 11: Receiving and displaying data

[1208] The device receives the visualization data sent from the server and displays it on the screen. Specifically, a temperature forecast graph is displayed on the tablet device for the user to check.

[1209] Step 12: User review and decision making

[1210] The user can check the analysis results displayed on the device and make the necessary decisions, such as adjusting heating and cooling or considering additional measures based on future temperature predictions.

[1211] Example 2

[1212] 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."

[1213] In conventional data analysis systems, the processes from data collection to analysis and visualization are not automated, which means that they require a great deal of time and effort. Furthermore, they lack the ability to recognize user emotions and adjust data accordingly, making it difficult to provide information in an optimal format to users.

[1214] 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.

[1215] In this invention, the server includes means for acquiring information from data sources, means for cleaning and standardizing the acquired data, means for analyzing the pre-processed data using machine learning algorithms, means for visualizing the analysis results, means for transmitting the visualized data to a user interface, means for analyzing the voice data and facial expression data to estimate the emotional state of the user, and means for adjusting the analysis results and the visualized data based on the emotional state, thereby providing personalized insights to the user and automating the entire process.

[1216] "Data source" refers to a device or system that provides data, including sensors, APIs, databases, and other diverse sources.

[1217] "Cleaning" refers to the process of removing noise and outliers from data and filling in missing data.

[1218] "Standardization" refers to the process of converting data expressed in different formats into a unified format, including, for example, unifying different units of measurement or timestamp formats.

[1219] "Machine learning algorithms" refer to a set of mathematical models for data analysis and prediction, which can automatically detect patterns and trends.

[1220] "Analysis" refers to the process of applying statistical and mathematical methods to collected and pre-processed data to derive useful insights and predictive results.

[1221] "Visualization" refers to the process of presenting analytical results in a form that is easy for users to understand, including the generation of graphs and charts.

[1222] "User interface" refers to the interface through which a user and a system communicate with each other. This includes devices such as computers, smartphones, and tablets.

[1223] "Emotion engine" refers to technology that analyzes data such as voice and facial expressions to recognize the user's emotional state, making it possible to grasp the user's psychological state.

[1224] "Personalized insights" refers to information and suggestions that are optimized based on the individual characteristics and status of each user, enabling more appropriate and personalized services to be provided.

[1225] "Automation" refers to the state in which a series of operations or processes are carried out automatically without human intervention, resulting in efficient and error-free processing.

[1226] The system according to the present invention automates the entire process from data acquisition to analysis, visualization, and user emotion recognition, providing highly personalized insights. Specific embodiments of this system are described below.

[1227] 1. Data collection

[1228] The server connects to multiple data sources and collects the required data. For example, the server uses HTTP requests and SQL queries to retrieve data from sensors, APIs, databases, and other sources.

[1229] Example: A server sends an HTTP request every 5 minutes to collect the latest temperature data from a temperature sensor. It also connects to a social media API to retrieve user posts related to the keyword "climate change."

[1230] 2. Data Preprocessing

[1231] The server cleans and standardizes the collected data, a process that involves filling in missing data, correcting outliers, and standardizing the data format.

[1232] Example: The server fills in missing temperature data with previous or next values, converts data expressed in Fahrenheit to Celsius, and formats all data into a uniform timestamp format.

[1233] 3. Data Analysis

[1234] The server then applies machine learning algorithms to the pre-processed data, enabling it to detect anomalies and predict future trends.

[1235] Example: The server builds a regression model based on historical temperature data to predict temperature fluctuations over the next week, and reports any abnormally high temperatures recorded during a particular time period.

[1236] 4. Visualizing the results

[1237] The server visualizes the analysis results in a user-friendly format, which includes generating graphs and charts.

[1238] Example: The server displays a line graph of predicted temperature changes, highlighting outliers in red, and providing tooltips with detailed information about each data point.

[1239] 5. User Interface

[1240] The terminal receives the visualization data sent from the server and displays it on the screen, which the user can use to check the results and take necessary actions.

[1241] Example: A tablet device displays a temperature forecast graph sent from a server in a web browser. The user can view detailed information by touching a data point on the screen.

[1242] 6. Incorporating an Emotional Engine

[1243] The server recognizes the user's emotions using an emotion engine, which analyzes voice data and facial expression image data to estimate the user's current emotional state.

[1244] Example: When a user says "It's cold today," the voice data is sent to the server, where the speech recognition engine converts the speech into text data. The emotion engine then recognizes the user's emotional state as "I feel cold."

[1245] 7. Emotion-Based Data Adjustment

[1246] The server adjusts the analysis results and visualization data based on the user's perceived emotions, for example, providing a simpler and easier-to-understand visualization if the user is feeling stressed.

[1247] Example: If the server detects that the user is tired, it will remove complex graphs and display only the most important information in bullet points, and it will also optimize the use of colors and font sizes.

[1248] As a result, the system automates the entire process for users, from data collection to analysis and visualization, and by incorporating emotion recognition, it is possible to provide personalized insights.

[1249] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1250] Step 1:

[1251] Data collection

[1252] The server retrieves information from multiple data sources. Specifically, the server sends HTTP requests to pre-configured URLs to collect data from APIs and also sends SQL queries to databases to retrieve information. The input is data from sensors, APIs, databases, etc., and the output is the collected raw data.

[1253] What it does: The server sends an HTTP request every 5 minutes to get the latest temperature data from the temperature sensor, and also sends a request containing the keyword "climate change" to social media APIs to gather related information.

[1254] Step 2:

[1255] Data Preprocessing

[1256] The server cleans and standardizes the collected data. This step takes raw data as input and produces processed data as output. It also fills gaps in the data, corrects outliers, and converts data represented in different formats into a unified format.

[1257] What happens: The server fills in missing temperature data with the previous or next value, converts Fahrenheit temperature data to Celsius, and unifies the timestamp format.

[1258] Step 3:

[1259] Data analysis

[1260] The server applies machine learning algorithms to the preprocessed data. The input is the preprocessed data, and the output is the analysis results. This step detects anomalies and predicts future trends.

[1261] Specific operation: The server uses the preprocessed temperature data to build a regression model and predict temperature fluctuations over the next week. Furthermore, if an abnormally high temperature is recorded, the server outputs the time and temperature as abnormal data.

[1262] Step 4:

[1263] Visualizing the results

[1264] The server outputs the analysis results in a visually understandable format. The input is the analysis results, and the output is visualized data (graphs and charts).

[1265] What it does: The server visualizes future temperature fluctuation data as a line graph, highlighting outliers in red, and providing detailed information about each data point as a tooltip.

[1266] Step 5:

[1267] Send and display to the user interface

[1268] The terminal receives the visualization data sent from the server and displays it on the screen. The input is the visualization data sent from the server, and the output is a display in a format that can be confirmed by the user.

[1269] Specific operation: The tablet device displays the temperature forecast graph sent from the server on a web browser. The user can check detailed information by touching a data point on the graph.

[1270] Step 6:

[1271] Incorporating an emotion engine

[1272] The server uses an emotion engine to recognize the user's emotions. The input is voice data or facial expression data from the user, and the output is the user's emotional state.

[1273] How it works: When a user says "It's cold today," the voice data is sent to the server, where the speech recognition engine converts the speech into text. The emotion engine then determines the user's emotional state as "feeling cold."

[1274] Step 7:

[1275] Emotion-based data adjustment

[1276] The server adjusts the analysis results and visualization data based on the recognized user emotion. The input is the user's emotional state, and the output is the adjusted analysis results and visualization data.

[1277] What it does: When the server detects that the user is tired, it will not display complex graphs, but will instead display only the most important information in bulleted form, and will optimize color usage and font size.

[1278] Through these steps, the system of the present invention realizes a highly automated data analysis and visualization process, and further provides personalized insights that take into account the user's emotions.

[1279] (Application example 2)

[1280] 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."

[1281] Conventional data analysis systems have been effective to a certain extent by displaying the analysis results of collected data, but this alone has the problem of not being able to respond flexibly based on the user's emotions. In particular, in the security field, where situations that cause users to feel anxious or stress often occur, there is a need for systems that not only visualize data but also reflect the user's emotional state and provide appropriate actions.

[1282] 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.

[1283] In this invention, the server includes means for acquiring information from a data source, means for cleaning and standardizing the acquired data, means for analyzing the preprocessed data using a machine learning algorithm, means for visualizing the analysis results, means for transmitting the visualized data to a user terminal, means for displaying the visualized data on the user terminal, means for recognizing a user's emotion, and means for adjusting the analysis results and the visualized data based on the recognized emotion. This allows the system to sense when the user is emotionally stressed or anxious and provide optimal visualizations and warnings according to the emotion.

[1284] A "data source" is an information source that provides information from multiple sensors, APIs, databases, etc.

[1285] "Acquisition" is the act of gathering the necessary information from a data source.

[1286] "Cleaning" is the process of removing missing values ​​and outliers from collected data and arranging the data.

[1287] "Standardization" is the process of standardizing data formats to ensure consistency when analyzing and visualizing them.

[1288] "Preprocessing" is a series of operations to prepare data for analysis.

[1289] A "machine learning algorithm" is a computational method that mimics human learning abilities to find patterns and rules in data.

[1290] "Analysis" is the act of analyzing information based on collected data to gain useful knowledge and insights.

[1291] "Visualization" refers to the presentation of analytical results in a visual format such as a graph or chart.

[1292] A "user terminal" is a device that a user can directly operate (e.g., a smartphone, tablet, or PC).

[1293] "Send" is the act of transferring data from the server to the user terminal.

[1294] "Display" refers to the act of presenting information on the screen of a user terminal.

[1295] "Emotion recognition" is the process of determining a user's emotional state by analyzing voice and facial expression data.

[1296] "Adjustment" refers to changing the content or format of analysis results or visualization data based on recognized emotions.

[1297] The system based on this invention automates the entire process from data acquisition to analysis, visualization of results, and adjustment based on user emotions, providing high flexibility and adaptability for use in the security field. The specific configuration and functions of this system are described below.

[1298] The system mainly includes the following elements: a server, multiple data sources (sensors, APIs, databases), and user devices (smartphones, tablets, PCs).

[1299] First, the server periodically retrieves data from sensors and APIs using HTTP requests. To collect this data, the server needs to set authentication information and connection parameters. For example, temperature data from a temperature sensor is retrieved every five minutes, along with image data from a security camera.

[1300] The acquired data is then cleaned and standardized. Cleaning involves imputing missing values ​​and correcting outliers. For example, missing temperature data is imputed with previous or next values, and a standardization process is performed to convert the represented data into a unified format.

[1301] The cleaned and standardized data is then analyzed using machine learning algorithms. This analysis detects anomalies and predicts future trends. For example, if an abnormally high temperature is detected, the time and temperature are reported. The server performs this analysis using libraries such as Python and TensorFlow.

[1302] The results of the analysis are visualized and presented in a user-friendly format, often using libraries such as Matplotlib or D3.js, and are displayed as graphs or charts with outliers highlighted.

[1303] These visualized data are sent to the user's terminal and displayed on the screen. The user can check it and take necessary actions. The user interface is sometimes provided on a web browser, and the data can be checked in real time.

[1304] The emotion engine is built into the server and recognizes the user's emotions. It analyzes voice and facial expression data to estimate the user's current emotional state. What the user says to the device is sent to the server and analyzed by the emotion engine. This engine uses NLP libraries and generative AI models.

[1305] Based on the perceived emotion, the analysis results and visualization data are adjusted. For example, if the server detects that the user is feeling stressed, it will provide a more concise and easy-to-understand visualization, allowing the user to process information more efficiently.

[1306] As a specific example, if a user performs high activity (clicking or typing) on ​​a computer for more than 10 minutes continuously, a warning is issued immediately if it is recognized that the user is feeling stressed. In this case, an example of a prompt sentence to the generative AI model is as follows: "The user's frequency of operation is higher than usual. Determine whether the user is feeling stressed and recommend appropriate action."

[1307] By realizing such a system, it will be possible to provide highly flexible security services that take into consideration the feelings of users in the security field.

[1308] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1309] Step 1:

[1310] The user performs a specific operation using the device.

[1311] Input: Data on user operations and behavior on a computer or smartphone.

[1312] Specific actions: The user operates the web browser and performs a specific action (click, keyboard input, etc.).

[1313] Step 2:

[1314] The server retrieves the information from the data source.

[1315] Input: Raw data from multiple sensors, APIs and databases.

[1316] Output: Acquired sensor data and API responses.

[1317] What happens: The server retrieves temperature sensor and security camera data using HTTP requests.

[1318] Step 3:

[1319] The server cleans and standardizes the data it retrieves.

[1320] Input: The raw data obtained.

[1321] Output: Cleaned and standardized data.

[1322] Specific operation: The server complements missing temperature data with previous and next values ​​and standardizes the representation format, for example, converting temperature data from Fahrenheit to Celsius.

[1323] Step 4:

[1324] The server analyzes the preprocessed data using machine learning algorithms.

[1325] Input: Cleaned and standardized data.

[1326] Output: Anomaly detection results and trend predictions.

[1327] What it does: The server runs anomaly detection algorithms using Python and TensorFlow to detect high temperatures and abnormal behavior.

[1328] Step 5:

[1329] The server visualizes the analysis results.

[1330] Input: Analysis results.

[1331] Output: Visualized data in the form of graphs and charts.

[1332] What it does: The server uses Matplotlib and D3.js to convert the data into line and bar graphs.

[1333] Step 6:

[1334] The server transmits the visualized data to the user terminal.

[1335] Input: Visualization data.

[1336] Output: Visualization data sent to the user device.

[1337] Specific operation: The server sends data to the user terminal in real time using HTTP responses or WebSockets.

[1338] Step 7:

[1339] The user terminal displays the visualization data.

[1340] Input: Visualization data sent from the server.

[1341] Output: Graphs and charts displayed on the screen.

[1342] Specific operation: The user's device displays the visualized data on a web browser, and the user checks it.

[1343] Step 8:

[1344] The server recognizes the user's emotions.

[1345] Input: User's voice and facial expression data.

[1346] Output: The user's emotional state (e.g., happy, sad, surprised, stressed).

[1347] Specific operation: The server uses NLP libraries and generative AI models to analyze the user's emotions from voice and facial expression data.

[1348] Step 9:

[1349] The server adjusts the analysis results and visualization data based on the emotions it recognizes.

[1350] Input: The user's emotional state.

[1351] Output: Adjusted visualization data and warning messages.

[1352] Specific operation: Based on the results of the emotion engine, the server converts the visualized data into a concise format and generates appropriate warning messages.

[1353] Step 10:

[1354] The user reviews the adjusted data and takes any necessary action.

[1355] Input: Adjusted visualization data and warning messages.

[1356] Output: User's corrective action.

[1357] Specific actions: The user views the data on the device and, if necessary, contacts the system administrator or strengthens security measures.

[1358] 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.

[1359] 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.

[1360] 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.

[1361] 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.

[1362] FIG. 9 illustrates 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 behaviors 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.

[1363] 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.

[1364] 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).

[1365] 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.

[1366] 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."

[1367] 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.

[1368] 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).

[1369] 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.

[1370] 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.

[1371] 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.

[1372] 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.

[1373] 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.

[1374] 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.

[1375] 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.

[1376] 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.

[1377] 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.

[1378] 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.

[1379] The following is further disclosed regarding the above embodiment.

[1380] (Claim 1)

[1381] a means for obtaining information from a data source; and

[1382] a means of cleaning and standardizing the data obtained;

[1383] means for analyzing the preprocessed data using a machine learning algorithm;

[1384] A means of visualizing the analysis results;

[1385] means for transmitting the visualized data to a user interface;

[1386] a means for displaying the visualization data in a user interface;

[1387] A system including:

[1388] (Claim 2)

[1389] 10. The system of claim 1, wherein the system collects information from a variety of data sources.

[1390] (Claim 3)

[1391] 10. The system of claim 1, wherein machine learning algorithms are used to perform anomaly detection and predictive analysis.

[1392] "Example 1"

[1393] (Claim 1)

[1394] a means for obtaining information from a data source; and

[1395] a means of cleaning and standardizing the data obtained;

[1396] means for analyzing the preprocessed data using a machine learning algorithm;

[1397] A means of visualizing the analysis results;

[1398] means for transmitting the visualized data to a user interface;

[1399] a means for displaying the visualization data in a user interface;

[1400] A system including:

[1401] (Claim 2)

[1402] 10. The system of claim 1, wherein the system collects information from multiple data sources using different protocols and authentication information.

[1403] (Claim 3)

[1404] The system of claim 1, wherein machine learning algorithms are used to detect anomalies and predict future trends.

[1405] "Application Example 1"

[1406] (Claim 1)

[1407] a means for obtaining information from a data source; and

[1408] a means of cleaning and standardizing the data obtained;

[1409] means for analyzing the preprocessed data using a machine learning algorithm;

[1410] A means of visualizing the analysis results;

[1411] means for transmitting the visualized data to a user interface;

[1412] a means for displaying the visualization data in a user interface;

[1413] means for displaying real-time data on an augmented reality display;

[1414] A system including:

[1415] (Claim 2)

[1416] 10. The system of claim 1, wherein the system collects information from a variety of data sources.

[1417] (Claim 3)

[1418] 10. The system of claim 1, wherein machine learning algorithms are used to perform anomaly detection and predictive analysis.

[1419] "Example 2: Combining Emotion Engines"

[1420] (Claim 1)

[1421] a means for obtaining information from a data source; and

[1422] a means of cleaning and standardizing the data obtained;

[1423] means for analyzing the preprocessed data using a machine learning algorithm;

[1424] A means of visualizing the analysis results;

[1425] means for transmitting the visualized data to a user interface;

[1426] a means for displaying the visualization data in a user interface;

[1427] means for estimating a user's emotional state by analyzing voice data and facial expression data;

[1428] a means for adjusting analysis results and visualization data based on emotional state;

[1429] A system including:

[1430] (Claim 2)

[1431] 10. The system of claim 1, wherein the system collects information from a variety of data sources.

[1432] (Claim 3)

[1433] 10. The system of claim 1, wherein machine learning algorithms are used to perform anomaly detection and predictive analysis.

[1434] "Application example 2 when combining emotion engines"

[1435] (Claim 1)

[1436] a means for obtaining information from a data source; and

[1437] a means of cleaning and standardizing the data obtained;

[1438] means for analyzing the preprocessed data using a machine learning algorithm;

[1439] A means of visualizing the analysis results;

[1440] means for transmitting the visualized data to a user terminal;

[1441] means for displaying the visualization data on a user terminal;

[1442] a means for recognizing a user's emotion;

[1443] a means for adjusting analysis results and visualization data based on the recognized emotions; and

[1444] A system including:

[1445] (Claim 2)

[1446] 10. The system of claim 1, wherein the system collects information from a variety of data sources.

[1447] (Claim 3)

[1448] 10. The system of claim 1, wherein machine learning algorithms are used to perform anomaly detection and predictive analysis. [Explanation of symbols]

[1449] 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 for obtaining information from a data source; and a means of cleaning and standardizing the data obtained; means for analyzing the preprocessed data using a machine learning algorithm; A means of visualizing the analysis results; means for transmitting the visualized data to a user interface; a means for displaying the visualization data in a user interface; A system including:

2. The system of claim 1 , wherein the system collects information from a variety of data sources.

3. The system of claim 1 , wherein machine learning algorithms are used to perform anomaly detection and predictive analysis.

Images